Emerging Trends and Applications in Cognitive Computing Pradeep Kumar Mallick

Emerging Trends and Applications in Cognitive
Computing Pradeep Kumar Mallick download
https://textbookfull.com/product/emerging-trends-and-
applications-in-cognitive-computing-pradeep-kumar-mallick/
Download more ebook from https://textbookfull.com

We believe these products will be a great fit for you. Click
the link to download now, or visit textbookfull.com
to discover even more!
Cognitive Computing in Human Cognition Perspectives and
Applications Pradeep Kumar Mallick
https://textbookfull.com/product/cognitive-computing-in-human-
cognition-perspectives-and-applications-pradeep-kumar-mallick/
Electronic Systems and Intelligent Computing
Proceedings of ESIC 2020 Pradeep Kumar Mallick
https://textbookfull.com/product/electronic-systems-and-
intelligent-computing-proceedings-of-esic-2020-pradeep-kumar-
mallick/
Applications in Ubiquitous Computing Raman Kumar
https://textbookfull.com/product/applications-in-ubiquitous-
computing-raman-kumar/
Evolving Technologies for Computing Communication and
Smart World Proceedings of ETCCS 2020 Pradeep Kumar
Singh
https://textbookfull.com/product/evolving-technologies-for-
computing-communication-and-smart-world-proceedings-of-
etccs-2020-pradeep-kumar-singh/

Cognitive Computing for Big Data Systems Over IoT
Frameworks Tools and Applications 1st Edition Arun
Kumar Sangaiah
https://textbookfull.com/product/cognitive-computing-for-big-
data-systems-over-iot-frameworks-tools-and-applications-1st-
edition-arun-kumar-sangaiah/
Futuristic Trends in Network and Communication
Technologies: First International Conference, FTNCT
2018, Solan, India, February 9–10, 2018, Revised
Selected Papers Pradeep Kumar Singh
https://textbookfull.com/product/futuristic-trends-in-network-
and-communication-technologies-first-international-conference-
ftnct-2018-solan-india-february-9-10-2018-revised-selected-
papers-pradeep-kumar-singh/
Blockchain, big data and machine learning: trends and
applications First Edition Kumar
https://textbookfull.com/product/blockchain-big-data-and-machine-
learning-trends-and-applications-first-edition-kumar/
Emerging trends in applications and infrastructures for
computational biology, bioinformatics, and systems
biology : systems and applications 1st Edition Arabnia
https://textbookfull.com/product/emerging-trends-in-applications-
and-infrastructures-for-computational-biology-bioinformatics-and-
systems-biology-systems-and-applications-1st-edition-arabnia/
Adaptive Agricultural Practices: Building Resilience in
a Changing Climate Pradeep Kumar Dubey
https://textbookfull.com/product/adaptive-agricultural-practices-
building-resilience-in-a-changing-climate-pradeep-kumar-dubey/

Emerging Trends and
Applications in Cognitive
Computing
Pradeep Kumar Mallick
St. Peter’s University, India
Samarjeet Borah
Sikkim Manipal University, India
A volume in the Advances in
Computational Intelligence and
Robotics (ACIR) Book Series

Published in the United States of America by
IGI Global
Engineering Science Reference (an imprint of IGI Global)
701 E. Chocolate Avenue
Hershey PA, USA 17033
Tel: 717-533-8845
Fax: 717-533-8661
E-mail: cust@igi-global.com
Web site: http://www.igi-global.com
Copyright © 2019 by IGI Global. All rights reserved. No part of this publication may be
reproduced, stored or distributed in any form or by any means, electronic or mechanical, including
photocopying, without written permission from the publisher.
Product or company names used in this set are for identification purposes only. Inclusion of the
names of the products or companies does not indicate a claim of ownership by IGI Global of the
trademark or registered trademark.
Library of Congress Cataloging-in-Publication Data
British Cataloguing in Publication Data
A Cataloguing in Publication record for this book is available from the British Library.
All work contributed to this book is new, previously-unpublished material.
The views expressed in this book are those of the authors, but not necessarily of the publisher.
For electronic access to this publication, please contact: eresources@igi-global.com.
Names: Mallick, Pradeep Kumar, 1984- editor. | Borah, Samarjeet, editor.
Title: Emerging trends and applications in cognitive computing / Pradeep
Kumar Mallick and Samarjeet Borah, editors.
Description: Hershey, PA : Engineering Science Reference, [2019]
Identifiers: LCCN 2017055229| ISBN 9781522557937 (h/c) | ISBN 9781522557944
(eISBN)
Subjects: LCSH: Artificial intelligence--Handbooks, manuals, etc. |
Computational intelligence--Handbooks, manuals, etc. | Biomedical
engineering--Data processing--Handbooks, manuals, etc. | Neural
computers--Handbooks, manuals, etc. | Cognitive science--Handbooks,
manuals, etc.
Classification: LCC TA347.A78 H36 2019 | DDC 006.3--dc23 LC record available at https://lccn.
loc.gov/2017055229
This book is published in the IGI Global book series Advances in Computational Intelligence and
Robotics (ACIR) (ISSN: 2327-0411; eISSN: 2327-042X)

Advances in Computational
Intelligence and Robotics
(ACIR) Book Series
Editor-in-Chief: Ivan Giannoccaro, University of Salento, Italy
Mission
ISSN:2327-0411
EISSN:2327-042X
While intelligence is traditionally a term applied to humans and human cognition,
technology has progressed in such a way to allow for the development of intelligent
systems able to simulate many human traits. With this new era of simulated and
artificial intelligence, much research is needed in order to continue to advance
the field and also to evaluate the ethical and societal concerns of the existence of
artificial life and machine learning.
The Advances in Computational Intelligence and Robotics (ACIR) Book
Series encourages scholarly discourse on all topics pertaining to evolutionary
computing,artificiallife,computationalintelligence,machinelearning,androbotics.
ACIR presents the latest research being conducted on diverse topics in intelligence
technologies with the goal of advancing knowledge and applications in this rapidly
evolving field.
• Computational Logic
• Pattern Recognition
• Intelligent control
• Evolutionary computing
• Automated Reasoning
• Machine Learning
• Agent technologies
• Computational Intelligence
• Cyborgs
• Adaptive and Complex Systems
Coverage
IGI Global is currently accepting
manuscripts for publication within this
series.Tosubmitaproposalforavolumein
this series, please contact our Acquisition
EditorsatAcquisitions@igi-global.comor
visit:http://www.igi-global.com/publish/.
The Advances in Computational Intelligence and Robotics (ACIR) Book Series (ISSN 2327-0411) is published by
IGI Global, 701 E. Chocolate Avenue, Hershey, PA 17033-1240, USA, www.igi-global.com. This series is composed of
titles available for purchase individually; each title is edited to be contextually exclusive from any other title within the
series. For pricing and ordering information please visit http://www.igi-global.com/book-series/advances-computational-
intelligence-robotics/73674. Postmaster: Send all address changes to above address. ©© 2019 IGI Global. All rights,
including translation in other languages reserved by the publisher. No part of this series may be reproduced or used in any
form or by any means – graphics, electronic, or mechanical, including photocopying, recording, taping, or information and
retrieval systems – without written permission from the publisher, except for non commercial, educational use, including
classroom teaching purposes. The views expressed in this series are those of the authors, but not necessarily of IGI Global.

701 East Chocolate Avenue, Hershey, PA 17033, USA
Tel: 717-533-8845 x100 • Fax: 717-533-8661
E-Mail: cust@igi-global.com • www.igi-global.com
Nature-Inspired Algorithms for Big Data Frameworks
Hema Banati (Dyal Singh College, India) Shikha Mehta (Jaypee Institute of Information
Technology, India) and Parmeet Kaur (Jaypee Institute of Information Technology, India)
EngineeringScienceReference•©2019•412pp•H/C(ISBN:9781522558521)•US$225.00
Novel Design and Applications of Robotics Technologies
Dan Zhang (York University, Canada) and Bin Wei (York University, Canada)
Optoelectronics in Machine Vision-Based Theories and Applications
Moises Rivas-Lopez (Universidad Autónoma de Baja California, Mexico) Oleg Sergiyenko
(Universidad Autónoma de Baja California, Mexico) Wendy Flores-Fuentes (Universidad
Autónoma de Baja California, Mexico) and Julio Cesar Rodríguez-Quiñonez (Universidad
Autónoma de Baja California, Mexico)
Handbook of Research on Predictive Modeling and Optimization Methods in Science...
Dookie Kim (Kunsan National University, South Korea) Sanjiban Sekhar Roy (VIT
University, India) Tim Länsivaara (Tampere University of Technology, Finland) Ravinesh
Deo (University of Southern Queensland, Australia) and Pijush Samui (National Institute
of Technology Patna, India)
Handbook of Research on Investigations in Artificial Life Research and Development
Maki Habib (The American University in Cairo, Egypt)
Critical Developments and Applications of Swarm Intelligence
Yuhui Shi (Southern University of Science and Technology, China)
For an entire list of titles in this series, please visit:
https://www.igi-global.com/book-series/advances-computational-intelligence-robotics/73674
Titles in this Series
For a list of additional titles in this series, please visit:
https://www.igi-global.com/book-series/advances-computational-intelligence-robotics/73674

Table of Contents
Foreword..............................................................................................................xii
Preface.
................................................................................................................xiii
Chapter 1
Design of Cognitive Healthcare System for Coronary Cardiac Disease .
Detection.................................................................................................................1
Mihir Narayan Mohanty, Siksha ‘O’ Anusandhan University, India
Chapter 2
A Cognitive Information Retrieval Using POP Inference Engine Approaches....35
Parul Kalra, Amity University, India
Deepti Mehrotra, Amity University, India
Abdul Wahid, Maulana Azad National Urdu University, India
Chapter 3
Assessing Animal Emotion and Behavior Using Mobile Sensors and
Affective Computing.............................................................................................49
Heath Yates, Kansas State University, USA
Brent Chamberlain, Utah State University, USA
William Baldwin, Biosecurity Research Institute, USA
William Hsu, Kansas State University, USA
Dana Vanlandingham, Biosecurity Research Institute, USA
Chapter 4
Neuro-Fuzzy Models and Applications................................................................78
Sushruta Mishra, KIIT University, India
Soumya Sahoo, C. V. Raman College of Engineering, India
Brojo Kishore Mishra, C. V. Raman College of Engineering, India
Chapter 5
Human Health Risk Assessment via Amalgamation of Probability and Fuzzy
Numbers................................................................................................................99
Palash Dutta, Dibrugarh University, India

Chapter 6
Green Computing: A Step Towards Eco-Friendly Computing...........................124
Sunil Kumar Mohapatra, College of Engineering and Technology, India
Priyadarshini Nayak, Central Institute of Plastic Engineering and
Technology, India
Sukant Kishoro Bisoy, C. V. Raman College of Engineering, India
Chapter 7
Software Quality Measurement: State of the Art.
...............................................150
Dalila Amara, SMART Lab, Université de Tunis, Institut Supérieur de
Gestion, Tunis, Tunisie
Latifa Ben Arfa Rabai, SMART Lab, Université de Tunis, Institut
Supérieur de Gestion, Tunis, Tunisie & College of Business,
University of Buraimi, Al Buraimi, Oman
Chapter 8
A Study on Risk Management in Financial Market............................................182
Smruti Rekha Das, SOA University, India
Kuhoo, College of Engineering and Technology, India
Debahuti Mishra, SOA University, India
Pradeep Kumar Mallick, Gurukula Kangri Vishwavidyalaya, India
Chapter 9
Clustering Techniques: A Review on Some Clustering Algorithms..................198
Harendra Kumar, Gurukula Kangri Vishwavidyalaya, India
Chapter 10
Addressing Security Issues and Standards in Internet of Things.
.......................224
Brojo Mishra, C. V. Raman College of Engineering, India
Compilation of References............................................................................... 258
About the Contributors.................................................................................... 295
Index................................................................................................................... 299

Detailed Table of Contents
Foreword..............................................................................................................xii
Preface.
................................................................................................................xiii
Chapter 1
Design of Cognitive Healthcare System for Coronary Cardiac Disease .
Detection.................................................................................................................1
Mihir Narayan Mohanty, Siksha ‘O’ Anusandhan University, India
This chapter focuses on clinical decision system (CDS) uses in healthcare units.
In this chapter, cognitive approaches are taken using soft computing techniques
to design clinical decision systems (CDS) for modern healthcare units. Cognitive
computing-based approach is considered. It focuses on cardiac disease detection
exclusively by considering its surrounding factors. Fuzzy logic is utilized as one
part. The other part includes diabetic detection using deep neural network (DNN) for
the automatic identification of the disease. The experiment was done with the Pima
Indian dataset. The classification result has been presented in the result section. The
decision system in the healthcare unit is a suitable example of a multi-agent system.
Chapter 2
A Cognitive Information Retrieval Using POP Inference Engine Approaches....35
Parul Kalra, Amity University, India
Deepti Mehrotra, Amity University, India
Abdul Wahid, Maulana Azad National Urdu University, India
The focus of this chapter is to design a cognitive information retrieval (CIR)
framework using inference engine (IE). IE permits one to analyze the central
concepts of information retrieval: information, information needs, and relevance.
The aim is to propose an inference engine in which adequate user preferences are
considered. As the cognitive inference engine (CIE) approach is involved, the
complex inquiries are required to return more important outcomes as opposed to
customary database questions which get irrelevant and unsolicited responses or
results. The chapter highlights the framework of a cognitive rule-based engine in

which preference queries are dealt with while keeping in mind the intention of the
user, their performance, and optimization.
Chapter 3
Assessing Animal Emotion and Behavior Using Mobile Sensors and
Affective Computing.............................................................................................49
Heath Yates, Kansas State University, USA
Brent Chamberlain, Utah State University, USA
William Baldwin, Biosecurity Research Institute, USA
William Hsu, Kansas State University, USA
Dana Vanlandingham, Biosecurity Research Institute, USA
Affectivecomputingisaveryactiveandyoungfield.Itisdrivenbyseveralpromising
areas that could benefit from affective intelligence such as virtual reality, smart
surveillance, perceptual interfaces, and health. This chapter suggests new design for
the detection of animal affect and emotion under an affective computing framework
via mobile sensors and machine learning. The authors review existing literature and
suggest new use cases by conceptual reevaluation of existing work done in affective
computing and animal sensors.
Chapter 4
Neuro-Fuzzy Models and Applications................................................................78
Brojo Kishore Mishra, C. V. Raman College of Engineering, India
The modern techniques of artificial intelligence have found application in almost all
the fields of human knowledge. Among them, two important techniques of artificial
intelligence, fuzzy systems (FS) and artificial neural networks (ANNs), have found
many applications in various fields such as production, control systems, diagnostic,
supervision, etc. They evolved and improved throughout the years to adapt arising
needs and technological advancements. However, a great emphasis is given in the
engineering field. The techniques of artificial intelligence based on fuzzy logic and
neural networks are frequently applied together for solving engineering problems
where the classic techniques do not supply an easy and accurate solution. Separately,
each one of these techniques possesses advantages and disadvantages that, when
mixed together, provide better results than the ones achieved with the use of each
isolated technique. As ANNs and fuzzy systems have often been applied together,
the concept of a fusion between them started to take shape. Neuro-fuzzy systems
were born which utilize the advantages of both techniques. Such systems show two
distinctwaysofbehavior.Inafirstphase,calledlearningphase,itbehaveslikeneural
networks that learn internal parameters off-line. Later, in the execution phase, it
behaves like a fuzzy logic system. A neuro-fuzzy system is a fuzzy system that uses a

learningalgorithmderivedfromorinspiredbyneuralnetworktheorytodetermineits
parameters(fuzzysetsandfuzzyrules)byprocessingdatasamples.Neuralnetworks
and fuzzy systems can be combined to join its advantages and to cure its individual
illness. Neural networks introduce its computational characteristics of learning in
the fuzzy systems and receive from them the interpretation and clarity of systems
representation. Thus, the disadvantages of the fuzzy systems are compensated by
the capacities of the neural networks. These techniques are complementary, which
justifies its use together. This chapter deals with an analysis of neuro-fuzzy systems.
Benefits of these systems are studied with its limitations too. Comparative analyses
of various categories of neuro-fuzzy systems are discussed in detail. Apart from
these, real-time applications of such systems are also presented.
Chapter 5
Human Health Risk Assessment via Amalgamation of Probability and Fuzzy
Numbers................................................................................................................99
Palash Dutta, Dibrugarh University, India
Thischapterpresentsanapproachtocombineprobabilitydistributionswithimprecise
(fuzzynumbers)parameters(meanandstandarddeviation)aswellasfuzzynumbers
(FNs) of various types and shapes within the same framework. The amalgamation of
probability distribution and fuzzy numbers are done by generating three algorithms.
Human health risk assessment is performed through the proposed algorithms. It is
found that the chapter provides an exertion to perform human health risk assessment
in a specific manner that has more efficacies because of its capacity to exemplify
uncertainties of risk assessment model in its own fashion. It affords assistance to
scientists, environmentalists, and experts to perform human health risk assessment
providing better efficiency to the output.
Chapter 6
Green Computing: A Step Towards Eco-Friendly Computing...........................124
Sunil Kumar Mohapatra, College of Engineering and Technology, India
Priyadarshini Nayak, Central Institute of Plastic Engineering and
Technology, India
Sukant Kishoro Bisoy, C. V. Raman College of Engineering, India
With the increase in the number of computers, the amount of energy consumed by
themisonasignificantrise,whichinturnisincreasingcarboncontentinatmosphere.
Withtherealizationofthisproblem,measuresarebeingtakentominimizethepower
usage of computers. The solution is green computing. It is the efficient utilization
of computing resources while minimizing environmental impact and ensuring
both economic and social benefits. Green computing is a balanced and sustainable
approachtowardsachievingahealthierandsaferenvironmentwithoutcompromising
the technological needs of the current and future generations. This chapter studies

the architectural aspects, the scope, and the applications of green computing. The
emphasis of this study is on current trends in green computing, challenges in the
field of green computing, and the future trends of green computing.
Chapter 7
Software Quality Measurement: State of the Art.
...............................................150
Dalila Amara, SMART Lab, Université de Tunis, Institut Supérieur de
Gestion, Tunis, Tunisie
Latifa Ben Arfa Rabai, SMART Lab, Université de Tunis, Institut
Supérieur de Gestion, Tunis, Tunisie & College of Business,
University of Buraimi, Al Buraimi, Oman
Software measurement helps to quantify the quality and the effectiveness of
software to find areas of improvement and to provide information needed to make
appropriate decisions. In the recent studies, software metrics are widely used for
quality assessment. These metrics are divided into two categories: syntactic and
semantic. A literature review shows that syntactic ones are widely discussed and are
generally used to measure software internal attributes like complexity. It also shows
a lack of studies that focus on measuring external attributes like using internal ones.
This chapter presents a thorough analysis of most quality measurement concepts.
Moreover,itmakesacomparativestudyofobject-orientedsyntacticmetricstoidentify
their effectiveness for quality assessment and in which phase of the development
process these metrics may be used. As reliability is an external attribute, it cannot
be measured directly. In this chapter, the authors discuss how reliability can be
measured using its correlation with syntactic metrics.
Chapter 8
A Study on Risk Management in Financial Market............................................182
Smruti Rekha Das, SOA University, India
Kuhoo, College of Engineering and Technology, India
Debahuti Mishra, SOA University, India
Pradeep Kumar Mallick, Gurukula Kangri Vishwavidyalaya, India
The basic aim of risk management is to recognize, assess, and prioritize risk in order
to assure that the uncertainty should not deviate from the intended purpose of the
businessgoals.Riskcantakeplacefromvarioussources,whichincludesuncertainty
in financial markets, recessions, inflation, interest rates, currency fluctuations, etc.
Various methods used for this management of risk are faced with various decisions
such as the market price, historical data, statistical methodologies, etc. For stock
prices, the information derives from the historical data where the next price depends
only upon the current price and some of the outside factors. Financial market is very
risky to invest money, but the proper prediction with handling the risk will benefit
a lot. Various types of risk in the financial market and the appropriate solutions to
overcome the risk are analyzed in this study.

Chapter 9
Clustering Techniques: A Review on Some Clustering Algorithms..................198
Harendra Kumar, Gurukula Kangri Vishwavidyalaya, India
Clustering is a process of grouping a set of data points in such a way that data
points in the same group (called cluster) are more similar to each other than to data
points lying in other groups (clusters). Clustering is a main task of exploratory data
mining, and it has been widely used in many areas such as pattern recognition, image
analysis,machinelearning,bioinformatics,informationretrieval,andsoon.Clusters
are always identified by similarity measures. These similarity measures include
intensity, distance, and connectivity. Based on the applications of the data, different
similarity measures may be chosen. The purpose of this chapter is to produce an
overview of much (certainly not all) of clustering algorithms. The chapter covers
valuablesurveys,thetypesofclusters,andmethodsusedforconstructingtheclusters.
Chapter 10
Addressing Security Issues and Standards in Internet of Things.
.......................224
Brojo Mishra, C. V. Raman College of Engineering, India
In the IoTs era, the short-range mobile transceivers will be implanted in a variety of
daily requirements. In this chapter, a detail survey in several security and privacy
concerns related to internet of things (IoTs) by defining some open challenges are
discussed. The privacy and security implications of such an evolution should be
carefully considered to the promising technology. The protection of data and privacy
of users has been identified as one of the key challenges in the IoT. In this chapter,
theauthorspresentinternetofthingswitharchitectureanddesigngoals.Theysurvey
security and privacy concerns at different layers in IoTs. In addition, they identify
several open issues related to the security and privacy that need to be addressed by
research community to make a secure and trusted platform for the delivery of future
internet of things. The authors also discuss applications of IoTs in real life. A novel
approach based on cognitive IoT is presented, and a detailed study is undertaken.
In the future, research on the IoTs will remain a hot issue.
Compilation of References............................................................................... 258
About the Contributors.................................................................................... 295
Index................................................................................................................... 299

Foreword
Cognitive Informatics (CI) is a burgeoning interdisciplinary domain comprising of
thecognitiveandinformationsciencesthatfocusesonhumaninformationprocessing,
mechanismsandprocesseswithinthecontextofcomputingandcomputerapplications.
The main goal is to research and develop technologies to facilitate and extend
the information management capacity of individuals through the development and
application of novel concepts in human-system integration to address cognitive
bottlenecks (e.g., limitations in attention, memory, learning, comprehension,
visualization abilities, and decision making). Such mitigations may include
applications and technologies informed by research in psychology/behavioural
science, neuroscience, artificial intelligence, or linguistics.
As initiated by Dr. Pradeep Kumar Mallick and Dr. Samarjeet Borah, Handbook
of Research on Emerging Trends and Applications in Cognitive Computing
presents new approaches and methods for solving real-world problems. It offers,
in particular, exploratory research that describes novel approaches in the fields of
CognitiveInformatics,CognitiveComputing,ComputationalIntelligence,Advanced
Computing,HybridIntelligentModelsandApplications.Newalgorithmsandmethods
inavarietyoffieldsarealsopresented,togetherwithsolution-basedapproaches.The
topics addressed include various theoretical aspects and applications of Computer
Science, Artificial Intelligence, Cybernetics, Automation Control Theory and
Software Engineering.
People are working on these with enthusiasm, tenacity, and dedication to develop
newmethodsofanalysisandprovidenewsolutionstokeepupwiththeever-changing
cognitive informatics. This book is a good step in Cognitive Computing direction.
Gyoo-Soo Chae
Baekseok University, South Korea
xii

Preface
EmergingTrendsandApplicationsinCognitiveComputingisacollectionofresearch
findings of various authors working in the domain.
The first chapter of this volume discusses a design of cognitive healthcare system
for coronary cardiac diseases detection. It is basically a Cognitive Information
Retrieval (CIR) framework using Inference Engine (IE). It explains a framework
of a cognitive rule-based engine in which preference queries are dealt with keeping
in mind the intention of the user, their performance and optimization. Next chapter
is cognitive radio network spectrum (“white spaces”) holes sensing, assignment
methods and access in dual technologies. As per the authors prime challenge for
optional radio frameworks is to have the capacity to robustly detect when they are
inside such a frequencies hole. We review existing literature and suggest new use
cases by conceptual reevaluation of existing work done in affective computing and
animal sensors. A study on neuro-fuzzy models and applications is presented by
Mishraetal.intheirchapter.Benefitsofthesesystemsarestudiedwithitslimitations
too. They are presenting a comparative analyses of various categories of Neuro-
Fuzzy systems are discussed in detail. The evaluation of health risk is the procedure
to assess the character and chance of hostile human health consequences those are
affected by radiation or other harmful compounds in polluted ecological medium,
at the present or in the upcoming days. Palash Dutta discusses the aspects in the
chapter human health risk assessment via amalgamation of probability and fuzzy
numbers. The nest presents a pattern mining algorithm - FTISPAM using hybrid
genetic algorithm. The next chapter studies the architectural aspects, the scope and
applications of green computing. A work on software quality management presents
a thorough analysis of most quality measurement concepts. Authors also discuss
how reliability can be measured using its correlation with syntactic metrics. The
basic aim of risk management is to recognize, assess and prioritize risk, in order to
assure that the uncertainty should not deviate the intended purpose of the business
goals. A study on risk management in financial market is presented by Das et al. The
next chapter provides an overview of much of clustering algorithms. The chapter
is covering the little much valuable survey, the types of clusters, methods used for
xiii

Preface
constructing the clusters. Mishra et al. are addressing security issues and standards
in Internet of Things.
This volume represents a global forum for research on cognitive computing.
It includes mostly the current works and research findings from various research
labs, universities and institutions and may lead to development of market demanded
products. The works reports substantive results on a wide range of learning methods
applied to a variety of learning problems. It provides solid support via empirical
studies, theoretical analysis, or comparison to psychological phenomena. The
volume includes works to show how to apply learning methods to solve important
applications problems as well as how machine learning research is conducted.
The volume editors are very thankful to all the authors, contributors, reviewers
and the publisher for making this effort a successful one.
Pradeep Kr. Mallick
St. Peter’s University, India
Samarjeet Borah
Sikkim Manipal University, India
xiv

Copyright © 2019, IGI Global. Copying or distributing in print or electronic forms without written permission of IGI Global is prohibited.
Chapter 1
1
DOI: 10.4018/978-1-5225-5793-7.ch001
ABSTRACT
This chapter focuses on clinical decision system (CDS) uses in healthcare units.
In this chapter, cognitive approaches are taken using soft computing techniques
to design clinical decision systems (CDS) for modern healthcare units. Cognitive
computing-based approach is considered. It focuses on cardiac disease detection
exclusivelybyconsideringitssurroundingfactors.Fuzzylogicisutilizedasonepart.
The other part includes diabetic detection using deep neural network (DNN) for
the automatic identification of the disease. The experiment was done with the Pima
Indian dataset. The classification result has been presented in the result section. The
decision system in the healthcare unit is a suitable example of a multi-agent system.
INTRODUCTION
Human being has always been a curious creature, constantly aiming at increasing
his knowledge about the world he lives in. Towards achieving new knowledge,
the typical process of learning consists thus of following steps: (1) collecting a
large amount of observations, (2) extracting relevant information, (3) designing a
general model that best explains past and future observations. Machine learning
found applications in many fields such as genetics, search engines, natural language
processing, computational finance or stock market analysis and computer vision. In
Design of Cognitive Healthcare
System for Coronary
Cardiac Disease Detection
Mihir Narayan Mohanty
Siksha ‘O’ Anusandhan University, India

2
Design of Cognitive Healthcare System for Coronary Cardiac Disease Detection
thecaseofmedicalapplications,theinterestforlearning-basedmethodsseemsmore
recent. Nevertheless, this trend is increasing, and more works containing machine
learning as keyword are published each year.
In spite of their effective usefulness, it is not popular clinically that remains a
concern to researchers as well as medical practitioners. The objective is to changes
in clinical effectiveness related to patient care. The design of the evaluated CDSs
reliesoneitherrandomizedcontrolledclinicaltrials(RCTs)orlaboratoryexperiments
to determine the performance of the physicians or systems under controlled
environment. Lack of elaborate surveys on methodologies that indicates reasons for
not using CDSs by clinicians and their practice patterns. It requires the involvement
ofothermedicalprofessionalsandcomputerapplications.Thesearecomputerbased
patientrecords(CPRs),hospitalinformationsystems(HISs),ancillarycaresystems,
physician order entry (POE), etc. (Devi, Ramani & Pandian, 2014; Singh, Mohanty
& Choudhury, 2013; Mohanty, 2016). Such research seems useful in solving issues
related to acceptance or use of CDSs and their relative relevance.
Cognitive informatics (CI) is an area related to cognitive and information
sciences.Thefocusisonprocessingofhumaninformation,computingandcomputer
applicationsmechanismsaswellasprocesses(Al-Sakran,2015).InthistheCIfocuses
on understanding of activities and work processes related to human cognition that
include the interventional solutions concerned to finding solutions to engineering,
computer applications and information technology for better human activities. In
the framework of biomedical informatics, CI helps in describing, understanding,
and predicting the clinical work activities and its nature that benefits the patients,
clinicians as well as lay public. It assists in engineering development and finding
computing solutions to boost clinical practice such as efficient decision-support
system, patient involvement by providing a tool for timely medication schedule. It
also helps public health interventions by providing a suitable mobile application to
determine the spread of an epidemic (Ozcift & Gulten, 2011; Chi, Street & Katz,
2010; Su, 2008).
Many attempts have been made to design automatic machines in the field
of intelligent and cognitive field. These cognitive machines must know their
environments involving similar machines as well as human beings. The machines
mayvaryfromself-evidencedpracticalreasonslikecomputermaintenanceexpenses
to wearable computing in health care which have the cognitive capabilities parallel
to the human brain. The aim of this work is to describe the challenges concerned
to this new design paradigm which may take into account the systemic problems
as well as the design issues. It also includes the teaching of undergraduates in the
field of electrical and computer engineering, researchers, etc. Most studies use an
experimental or RCT in order to assess system capabilities in a varying clinical
environmentforbetterpatientcare(Silvermanetal.,2015).Someoftheseresearches

3
are in the field of CDS whereas none follow a naturalistic design as far as the routine
clinical settings concerned to real patients are considered. The studies mainly focus
on physicians but not on other clinicians. Further, evaluation of CDS studies is
insulated from evaluations of the informatics applications.
Cognitive Technology
Artificial intelligence (AI) technique supports to many technological developments
in current scenario of digital world. The technique of cognitive computing has
the major role to apply reason in numerous data and by interacting with man and
machines. At a decision-making layer, technologies such as machine learning, and
deep learning are helping systems interpret information and arrive at effective,
informed decisions (Zhang et al., 2018; Liu et al., 2017; Jan et al., 2017).
In healthcare, cognitive applications are helping doctors screen and diagnose
patients faster, while allowing companies to broaden their reach across large and
dispersed populations.
Machine Learning
Machine learning systems are capable of learning over time without needing to
be explicitly programmed. These have capabilities and techniques are helping
applications identify patterns in large amounts of information, classify information,
make predictions and detect anomalies. These techniques help organizations build
systems that can process large amounts of data while applying human-like thinking
to information, classify and correlate disparate pieces of information, make more
informed decisions and trigger actions in downstream activities.
Deep Learning
Deep learning methods are based on learning representations of data. As a branch of
machine learning, deep learning attempts to model high level abstractions in data.
It applies multiple layers of processing units where each successive layer uses the
output of the previous layer as input. Each layer corresponds to different layers of
abstraction, forming a hierarchy of concepts. Deep learning solutions help create
applicationsthatcanbetrainedbothinasupervisedandunsupervisedways.Numerous
techniques such as neural networks are under development in the field of deep
learning and are expected to be part of current scenario (Craven & Shavlik, 1997)

4
Neural Networks
Neural networks are among the most used deep learning methods to create learning
and reasoning systems. The application of back propagation, as part of neural
networks, helps to generate continuous improvement in deep learning algorithms
and train multi-layered deep learning systems to enhance their knowledge bases.
Neural networks are helping us solve complex problems that typically took skills
acquired over many years of learning and human experience. These capabilities are
expected to help organizations to analyze audio, video and images as well as any
human expert would, only at exponentially faster speeds and at much greater levels
of depth and quantity (Al Rahhal et al., 2016; Haykin, 1999; Mohapatra, Palo &
Mohanty, 2017).
Cognitive computing represents the state-of-the-art in the management of
knowledge and computer-human interaction, integrating a number of advanced
disciplines such as artificial intelligence, signal processing, natural language
processing,machinelearning,speechandvisionanalysis,andcapacitiesfordialogue
and descriptive narrative. The aim of cognitive computing is the development of
systemsthatemulatehumanbehavior,learnforthemselvesthroughexampleandcan
be deployed in human working environments (Tupe & Kulkarni, 2015; Elayathingal
&Sethuramalinga,2014).TheCIisrelatedtomultidisciplinarystudyofcognitiveand
informationsciences.Itinvestigatesthemechanismsofhumaninformationprocessing
and their engineering applications in the field of computing. The community aims
to find technology-based solutions to reduce the workload of a decision maker,
increases the throughput and production quality. The computer-based MIS (medical
information systems) requires an understanding of computer technology as well as
emphasizes on complex behavioral and social processes.
Cognitive science is basically a science research of the fundamental aspects
relating to cognition. It involves memory, attention, early language acquisition
including applied research. In this context the applied cognitive research helps
efficient human–computer interaction (HCI) that benefits the society in many ways
including educational research.
In last few decades, have witnessed a few practical and experiential knowledge
on the design and implementation that require sensible and intuitive interfaces. It
considers a thorough understanding of work direction and consults the potential
clinicians to implement in advance.
However, there is a limit to experiential knowledge that can produce the robust
generalizationsincludingasounddesignaswellasimplementationprinciples.Hence,
a demand for the common theoretical foundation is essential. The cognitive systems
are characterized by two principles that are interdependent: (a) architectural theories

5
that have the potential with respect to every aspects of cognition using unified theory
(b) To distinguish different knowledge domains for effectiveness of a given domain.
Functionally,anycognitivesystemisbasedonthecapabilitiesitisabletoperform
suchas:(a)focusedattentioncorrespondingtothechosenvisualcharacteristics(b)the
procedureinwhichitconstrainstheperformanceofhumancognitivesuchasmemory
limitations (c) The development occurs in its life span. Concerning to the life span
problem, a few literature has been focused on cognitive aging as well as its aspects.
These are: memory, attention, vision, and change in motor skill as aging functions
(Rogers, 2002). It provides potential inputs to informatics related to development
of e-health care facilities for seniors, or to patients suffering from chronic health
hazards like heart disease, diabetes and arthritis. The field of usability engineering
with respect to cognitive task analysis assists to assess cognition corresponding to
complex medical environment and computer information systems.
Some features of cognitive systems are adaptiveness, Interactive, Contextual
and stateful. The application domains of CI are Multi agent networks, Networks
for computational intelligence, Distributed cognitive robots, sensors, and remote
control systems (Yan et al., 2008; Nahar et al., 2013). In similar manner models
like ANN, FNN, and DNN are able to learn features by means of non-linear data
transformations and learn the feature hierarchies. Use of unsupervised training
removes over-fitting issues.
Medical Cognition
Advances in technologies related to health information and computing during last
two decades brings about many permeate, useful diverse facets in the field of clinical
technology. The rapid developments of internet, handheld devices, and wireless
technologies can afford new opportunities that support, enhances, and extends user
experiences for interactions as well as communications. It is assisted by computer
literatehealthcareindividualsforbetterhealthcare.However,theadvancesinhealth
care domain are slow due to lack of exposure to information technology for use in
theirworkingenvironment.Further,thetechnologiesarehinderedbysocial,cultural,
and cognitive issues (Lokanath, Narayan & Srikanta, 2016; AlSharqi et al., 2014;
Sarangi, Mohanty & Pattanayak, 2016). There is still a need to adapt the technology
in many different diversified levels both in individual and institution category.
Absence of such steps may lead to workflow disruptions hence user dissatisfaction.
Theknowledgerepresentation,typeofsearchwithnaturalnessprovesthesuccess
of cognitive computing applications. In healthcare, bio-medical signal and image
analysisaswellasprocessingistoincreasetheportabilityofscreeninganddiagnosis
(Biswal et al., 2016; Biswal et al., 2016). For instance, specialized screening for

6
conditionssuchasdiabeticretinopathytraditionallywaslimitedinavailabilitydueto
the need for specialized equipment and numerous specialists – thus precluding many
patients from being screened preventatively. However, the ability of deep learning
systems and neural networks, which learn from previous human diagnosed images,
is helping create systems of intelligence that can analyze medical images, predict
the risk and existence of such conditions, and recommend either immediate human
intervention or offer a reassurance of normality. This would help providers reach
larger at-risk populations, many of whom would probably not screen themselves
unless the problem was severe (Das, Turkoglu & Sengur, 2009; Ordonez, 2006;
Ram & Mohanty, 2017; Hannan et al., 2010).
The pneumonia diagnosis and its severity remains complex due to many
interacting factors, thus FCM has been used for decision support. It is suitable for
such problems, although, it requires experience and accumulated expert knowledge.
It is simple, implementable and requires less time (Sikchi, Sikchi & Ali, 2013;
Osowki & Linh, 2001; Pal et al., 2012; Sarangi, Mohanty & Patnaik, 2017). The
authors have developed a FCM method
forexpertsystemthatcandiagnosisinfectiousdiseases,theirtypeandtheseverity
related to cardiac arrest (Sarangi, Mohanty & Patnaik, 2017, 2016; Rahman et al.,
2015; Forkan, Khalil & Tari, 2013). The FCM algorithm has been put as our future
work based on inputs from clinical data using data mining approaches.
METHODOLOGY
Proposed Multi-Agent System
Patient Agent
Communication gadgets such as a mobile or a personal computer is used to inform
the medical authority for hospital registration in case the patient is suffering from
a disease. Figure 1 shows the structure of the proposed multi-agent system.
Hospital Registration
A server is used to store the patient parameter during hospital registration and
forward these information to a doctor i.e. doctor1 agent who recommends for
pathological tests.

7
Doctor 1
The doctor 1 agent functions as an OPD of the concerned hospital. With the help
of fuzzy IF-THEN rules, this agent suggests for any pathological tests desired of
the patient.
Diagnostic Centre Agent
This agent analyses and predicts the disease of the affected person based on the
information received from the patient. A two way data flow i.e. both transmitting
and receiving is accomplished by this agent.
Doctor 2 or Specialist Agent
This agent communicates using either SMS or e-mail with the concerned doctor
and notifies him/her about the abnormality observed in a patient so that the desired
prescriptionisprovided.Ultimately,theprescriptionbasedonthediseaseisgenerated
andisdeliveredtotheconcernedpatient.Incaseanyfurtherinvestigationisdesiredby
the doctor regarding the patient’s medical history or evaluation of patient parameters
in a continuous basis, it will made available to the doctor from the server. It helps
the doctor for future monitoring of the patient condition.
Figure 1. Patient consultancy multi-agent structure with a fuzzy system

8
Server Agent
It provides the desired disease information to all other agents. It communicates
with the diagnostic center by sending and receiving patient report. These reports
serve as inputs to the physician. The server agent takes the decision on data flow
management as and when required for providing efficient healthcare facilities to
the patient using disease information and making the data available for the doctor.
The flow of data in the diagnostic agent is shown in Figure 2. As shown in this
Figure, the diagnostic center receives information on the patient symptoms. Further
analyze and prediction of the disease is made based on the received data in the
diagnostic center. By implementing Fuzzy inference system an attempt has been
made in this work to detect heart disease.
An agent based consultancy system has been given in Figure 3 concerning to
the patient. Here, both the symptoms and the parameters of the disease is uploaded
by the patient into the server using the method of hospital registration. The data
uploaded are then passed to the server which communicates with the diagnostic
center for testing the symptoms. If the diagnostic parameters are in the normal range
then remedial steps has to be taken.
Figure 2. Diagnostic centre structure
Figure 3. Information centre

9
In case of any abnormalities, the diagnostic center informs the specialist or
Doctor 2 for further course of action. The fuzzy IF-THEN rules have been used
here to provide the desired information to the corresponding doctor. The doctor
then verifies the medical reports by sending a request for the same to the server for
further investigation of prescription.
The diagnostic agent problem can be formulated as below:
Using the FIS for the adaptive cardiac disease detection, we have used these
following parameters.
• The range of BP is 90 to 190(in mm Hg)
• The range of Serum Cholesterol is 120-560 (Mg/dl)
• FBS 60-140 (Mg/dl)
• ECG ST-T wave abnormality
These above mentioned inputs have been chosen due to the following.
• When BP is normal the heart function can be considered normal. With rise
in BP, the abnormally in heart occurs which indicates there is a chance of
cardiac disease. Hence, it tends to be an important parameter for heart disease
detection.
• The blood circulation path narrows due to the deposition of TG. This is due to
the presence of excess Cholesterol in blood. Ultimately the circulatory path
gradually narrows and can cause heart disease in a patient.
• Sugar happens to be a silent killer. It increases the fatality in a patient with
heart attacks in case the level is beyond the normal value.
• ECG signal happens to be the best predictor of heart ailment. It is indicated by
studying the ST-T wave. Any abnormality in this wave indicates the potential
heart disease even though the other symptoms mentioned earlier are normal.
In this work, our goal is to consider the experience of the physician in order
to store those in a set of fuzzy tables. The inference engine is used to develop a
computer program which can at its own find out whether a patient is affected with
some specified symptoms with certainty from the listed suspected diseases. A crisp
percentage value is assigned to this certainty for each suspected disease. The four
parametersareconsideredforthediagnosisusingFuzzyinferencesystemisfuzzified.

10
Electrocardiogram
For the fuzzification of electrocardiogram three fuzzy sets has been considered
such as normal, ST-T abnormal and hypertrophy. The MFs of both normal and
hypertrophy fuzzy sets have been considered trapezoidal whereas the MF of ST-T
abnormal has been triangular.
Blood Pressure
Out of systolic and diastolic blood pressure parameters we have considered Systolic
blood pressure in our study and different input variables has been divided into three
fuzzysetswhicharelow,normalandhigh.Themembershipfunctionsforlow,normal
and high has been taken as trapezoidal, triangular and trapezoidal respectively.
Fasting Blood Sugar
The fasting blood sugar is also one of the important factors for abnormality detection
and therefore we have also considered in our investigation. We have defined the
range of blood sugar value into three, i.e., low, normal and high which has the range
below 70, 70–135, 130 and above respectively.
Cholesterol
Medical experts have the opinion that cholesterol has silent effect on the cardiac
malfunctioningandcanmakeitworseveryrapidly.Thetotalcholesterolacombination
of high density lipoprotein (HDL), low density lipoprotein (LDL) and triglyceride
plays a significant role to predict the cardiac diseases. Therefore the total cholesterol
has been considered for the investigation. Here three fuzzy sets namely less risk,
borderline high and high MF has been assigned to the range of values less than
200, 190–245, 240and above respectively. The MFs are taken here as trapezoidal,
triangular and trapezoidal respectively.
Defuzzification
The process of conversion of fuzzy variables obtained as output from the fuzzy logic
rules into real values is known as defuzzification. The value gives the information
about the system and helps to take any action. In Sugeno model, there are two types
of defuzzification methods, i.e., weighted average (WA) and weighted sum (WS).
In this work, we have used the weighted average method for defuzzification.

11
Fuzzy Inference
Apatientbeforehisdiagnosisundergoesathoroughexamination.Asetofsymptoms
let S be obtained. The strength of the measurable symptoms can be expressed in
terms of numerical values whereas the non-measurable values are expressed in
terms of high, medium or low.
Let:
s f



 = = be the fuzzy value for a feature f from the input symptoms.
rij
= jth
relevant feature of the ith
disease.
P r v
ij ij
,



 = certainty of presence of the ith
disease when the relevant feature rij
has
a fuzzy valuev .
δij
= diagnosis decision of the ith
disease based on the relevant feature rij
.
ki
= total number of relevant features for the ith
disease.
wij
= weight of the rij
feature in diagnosing the ith
disease.
σi
= overall diagnosis decision for the ith
disease.
The rij
feature has its own effect upon the diagnosis decision which can be
obtained from the profile table P r v
ij ij
,



 of the disease. For the feature rij
as s rij




out of all the symptoms space the fuzzy value v can be obtained. The effect δij
can
get one of the fuzzy sets Yes, May Be, and No. It can be described as follows:
δij
= Pij
[rij
, s rij



 ] (1)
By adding all the effects of all ki
relevant parameters, the overall diagnosis
decision for the ith
disease would be obtained as follows:
σ δ
i ij ij
j
j k
ij
j
j k
w w
i i
=


























=
=
=
=
∑ ∑
1 1
/ (2)
The weight factor wij
used in the above equation plays a major role in decision
making. The physician can adjust this value depending upon the importance of a
particularsymptomwhilediagnosingforaparticulardisease.Theproperadjustment
of the weights reduces the human error in disease prediction. But if all the symptoms

12
carry equal importance during diagnosis then the weight factor is taken as 1. So the
equation (5.5) is further simplified to
σ δ
i
i
ij
j
j k
k
i
=
=
=
∑
1
1
(3)
The crisp values are obtained by specifying the certainty of presence for every
disease in the set D . This fuzzy set will be as shown in Figure 3.
The center of area method has been chosen for defuzzification.
Let: ci
represents the centroid of the overall diagnosis decision fuzzy set, cy
is
the centroid for the Yes fuzzy set and qi
denotes the certainty of presence of the
considereddiseasedi
inpercent.Thenthedecisioncrispvalueforaparticulardisease
di
can be computed as shown below.
If the results were yes for all the related features of di
, then the decision is
considered to be 100%.
qi
= (ci
/ cy
) x 100% (4)
Algorithm
10 inputs: Gender, Age, Chest Pain, Blood Pressure, Cholesterol, Blood Sugar,
ECG, Heart Beat, Exercise.
1. Output: The heart condition in terms of the linguistic terms.
2. Each chosen input has a set of fuzzy variables
3. Each fuzzy Variable is having its own MF.
4. The MF is computed for every fuzzy variable
Based upon the Mf the rule strength of the fuzzy variable is calculated.
Heart condition is estimated based on the selected output maximum used as the
final result.
Proposed Method Using ANFIS
This part of work proposes an ANFIS model to detect and diagnosis of heart related
problems. The model uses the internet so as to provide better healthcare facilities.
The system comprises of a number of agents who communicates among themselves
via internet as shown in Figure 4.

13
This Figure provides different blocks to represent different agents including the
communication paths using solid lines. The patient acts as a user agent with an user
id who communicates his/her health parameters or symptoms and the pathological
data to a server using a PC or mobile SMS. All these data are uploaded into the
server by the patient which is subsequently collected by the diagnostic agent. The
uploaded patient data is also stored in the server database for future reference. The
analysis of the data is done by the diagnostic agent using the ANFIS technique
so as to diagnosis and detect the disease. In case the patient condition is normal,
the patient is informed about his status via an email with some precautionary
instructions. Similarly, an alert e-mail is sent to the concerned physician in case
some abnormality is found in the report for further consultation. The system also
provides the facilities of checking the medical history of the using his/her database
stored in the server at any time.
Two vital symptoms such as the ECG and BP have been used in this work for
diagnosis and detection of the cardiovascular diseases. These symptoms act as the
inputstoourproposedANFISmodel.Theoutputorresultisthediseaseidentification.
ANFIS Structure
The ANFIS model used in this work has six layers of feed forward ANN and is
followed by fuzzy first order Sugeno model. It is a simpler model and is very less
dependent on expert knowhow. The model does not need the defuzzification hence
is suitable for objective non-linear fuzzy modeling. There are a total of two fuzzy
IF-THEN rules, two inputs such as BP, ECG and one output have been used for the
heart disease detection. These rules are:
Rule 1: IF BP is X1
AND abnormality of ECG is Y1
THEN
f bp ea r bp s ea t
1 1 1 1
,
( ) = ( )+ ( )+

Figure 4. Proposed intelligent health care system

14
Rule 2: IF BP is X2
AND abnormality of ECG is Y2
THEN
f bp ea r bp s ea t
2 2 2 2
,
( )= ( )+ ( ) +

Where Xi
and Yi
, i = 1 2
, represent the fuzzy sets with respect to the inputs
BP and ECG respectively. f bp ea i
i
, , ,
( ) = 1 2 signify the outputs as a linear
combination of the corresponding input variables within the fuzzy region that is
specifiedbyeitherrule-1orrule-2.Theparameters ri
and si
arethedesignparameters
of rule i and are estimated during the process of learning.
A detail function of the ANFIS model and its layers is explained below:
Layer 1 (Input Layer): It is a layer without any sort of computations. The inputs
such as BP and ECG data are given to the input nodes. The variables from the
input layer moves to the hidden layers.
Layer 2 (Fuzzification Layer): It has a number of adaptive nodes. Each node
generates the respective membership grades with respect to the input variable.
The outputs of the hidden nodes Oi
1
( ) are represented as
O w µ
i i Xi
2
= = (bp ), i = 1 2
, (5)
O w
i i
2
= = µ ea i
Yi−
( ) =
2
3 4
, , (6)
The membership functions are either continuous or piecewise differentiable
functions. The or piecewise differentiable functions are in the form of generalized
bell shaped, Gaussian, and triangular. Using a Gaussian function the output of the
node (Oi
2
) is estimated as
µXi
(bp )= =
−
−














e i
bp ci
i
1
2
2
1 2
σ
, , (7)
µ ea e i
Y
ea c
i
i
i
−
( )= =
−
−














2
2
1
2
3 4
σ
, , (8)
where ci
and σi
represent the centers and the width of the Gaussian function
respectively. These parameters characterize the fuzzy sets that describe each input
variable.

Other documents randomly have
different content

He was. He had a full. Three aces and a pair of kings. No wonder
he had been willing to back his luck. I don't know what his feelings
were when he found that I could show still more.
Fours. I think that takes it.
It did.
As I scooped the plunder, Silvester rose.
Show four whenever you like--eh, Townsend?
His tone was disagreeable, and meant to be.
I wish I could.
I should say that your wish was gratified. It occurs to me that
this is distinctly a game at which the soberest wins.
We looked at him. He looked back at us. He was evidently in a
state of mind in which he was disposed to pick a quarrel with us,
either separately or altogether. The thing to do was not to gratify his
whim. He treated Archie to a peculiarly impertinent stare. That was
an odd mistake of yours. I'm drunk, but I'm not drunk enough for
that, and I never could be. He gave Pendarvon a turn--You didn't
choose your cards badly. But it's only a question of courage. Take my
tip, next time you make it fours. He lurched away from the table.
I'm off. You're welcome to what you've got--cut it up between you.
He staggered from the room. Archie rose, intending, as host, to
see him off the premises. Pendarvon caught him by the arm.
Let the beggar see himself out. If we have luck he may break his
neck as he goes downstairs. He's made a bid for it. It seemed that
he had. We could hear him stumble down two or three steps at a
time. We listened. There was the sound of another stumble.
Pendarvon laughed. Bid number two.

Directly afterwards we heard him fidgeting with the handle of the
front door. Archie grew restless.
He'll raise the dead if he goes on like that much longer. Let me
go down, and let him out.
We heard the door open, and immediately afterwards shut with a
bang.
He's let himself out. I fancy a little more rapidly than he
intended. I'll bet an even pony that he's gone face foremost into the
street. Let's hope it. Pendarvon picked up a pack of cards. It's my
deal. What are we going to do?
Getting up, Archie helped himself to another soda and whiskey.
Who'll have some? We both of us did. Let's play unlimited. I'm
sick of this. Pendarvon raised his glass.
Here's to you, Archie; you're a gambler.
I thank the stars I am. Have you any objection, Reggie?
I shrugged my shoulders, perceiving that remonstrance would be
thrown away.
I'm at your service.
Then we'll play unlimited.
And we did.
It was a warmish little game. There is something about unlimited
poker which appeals to one. The spirit of the gamble gets into one's
veins like the breath of the battle into the nostrils of the soldier. One
feels that it is a game for men, and that the manhood which is in
one has a chance to score. Archie evidently meant going for the
gloves. He never bet less than a hundred, and a thousand--in pencil

on a scrap of paper--was as nothing to him. If we wanted to be in
that game we too had to treat thousands as if they had been
sovereigns. At the beginning the luck went round to him--possibly
because it took some little time to make his methods ours. He
bluffed outrageously. With a pair one was not disposed, at the
commencement, to pay a thousand to see his cards. The result was
that he scooped pool after pool. When he had made it plain that, if
we wanted him to show, we should have to pay, we began to pay.
And luck began!
The ante was fixed at a tenner. I was ante. The other two had
come in. Making good, I drew three to a pair of sevens, without
improving my hand. Pendarvon opened with a hundred, Archie
promptly making it five. I had not had a sight--I had had no cards--
for the last five hands. This time, the devil entering into me, I made
up my mind that I would find out what sort of game Archie was
playing, and have a view if it broke me. I saw his five hundred.
Pendarvon saw it too. Then Archie turned up a pair of knaves. I
yielded without showing, and to my surprise, Pendarvon did as I had
done. A pair of knaves seemed hardly worth fifteen hundred pounds.
It looked like easy earning.
The same thing went on time after time. Archie could not be
induced to see a man while he could keep on raising. The very next
hand, when we had both come in, Archie started with a five hundred
bet. So Pendarvon and I let him have the entries. And we had a
twenty pound pot.
We had gone right round and come back again to pairs, when
Pendarvon announced that he could open. He made it a hundred to
enter. Archie and I went in--though, so far as I was concerned, I had
an empty hand. Pendarvon took two, Archie stood pat, and I drew
five, finding myself in possession of a pair of aces. Pendarvon
started with five hundred pounds; we seemed to be getting
incapable of thinking of anything under. Archie raised him nine

thousand five hundred pounds, tabling his IOU for a round ten
thousand. I retired; a pair of aces was not quite good enough for
that. If I was to be broken, I might just as well be broken for
something better. Pendarvon looked at Archie as if he would have
liked to have seen right into him.
Have you the Bank of England at your back?
What are you going to raise me? inquired Archie.
Nothing. I go. The courage is yours. I opened with a pair of
jacks.
Pendarvon showed them. I doubt if he had anything more. I
doubt if Archie had as much. But, still, ten thousand. The average
man is not inclined to go as far as that upon a pair of jacks. I could
see that Pendarvon felt that he had been bluffed. It put his back up.
He meant to be even with Archie--and he was.
Let me clearly understand what unlimited poker means. Does it
mean that I'm at liberty to put half a sheet of notepaper on the table
and say I raise a million?
Archie fired up at the innuendo Pendarvon's words seemed to
convey.
What do you mean by half a sheet of notepaper? Do you suggest
that my IOU is nothing but half a sheet of notepaper?
Not a bit of it. Why should I? My dear Archie, don't get warm.
Only we are none of us millionaires. I know I'm not. Ten thousand
pounds is a considerable sum to me. We, all of us, are playing on
the nod. Before you go any further suppose we name a date by
which all paper must be redeemed.
I'm willing.

Suppose we say that it must be redeemed within a week?
I'm willing again.
I also acquiesced. I saw the force of what he said, and I saw the
pull which it would give him over Archie. Where Archie was likely to
find such a sum as ten thousand pounds within a week was more
than I knew, and, unless I greatly erred, more than he knew either.
Pendarvon is a man of substance. His stannary dues alone are
supposed to average thirty or forty thousand pounds a year, and if it
came to a question of ready-money not improbably he could buy up
Archie lock, stock, and barrel, and scarcely feel that he had made a
purchase.
Archie must have been possessed by the very spirit of mischief.
He entirely refused to be out-crowed on his own dunghill--even
though he knew his rival to be the larger and the stronger bird.
Almost immediately afterwards Pendarvon started the betting with a
thousand pounds. Archie retorted by raising him fourteen thousand,
laying on the table his IOU for fifteen thousand pounds. I went. I
had two pairs, but the atmosphere promised to grow too hot for me.
Pendarvon laughed.
I'll see your raise.
He placed his own IOU on Archie's.
Three kings.
Archie faced them. Pendarvon laughed again. He threw his cards
away.
Too good!
He had supposed that Archie was bluffing--and had paid for his
supposition.

The game fluctuated. Pendarvon had Archie once or twice upon
the hip, paring down his winnings. At last we came to what proved
to be the last, and hardest-fought-for pool of the sitting. It was a
pot. We had gone right through the hands. In the second round
Archie opened when it came to two pairs or better. He made it a
hundred to go in. I went in, though I had only queens. I kept the
pair and an ace, and took two--two more queens. Pendarvon and
Archie both stood pat. I perceived that the scent of a big battle was
coming into the air--when I saw my four queens, and made sure
that they were four queens, it did me good to smell it coming.
Archie began, for him, very modestly--with a five hundred bet. I
turned it into a thousand, which Pendarvon doubled. Then we went
at it, hammer and tongs. As I raised Archie, and Pendarvon every
time raised me, it made it impossible for Archie to even the bets,
and force a display. At last it grew too hot even for him. I reckoned
that I had thirty thousand in the pool. Pendarvon had made it
another four thousand for Archie to come in. Although he was
beginning to look as if he was not altogether enjoying himself, in he
came. I raised him. Pendarvon raised me. The betting went on. I
had IOU's for sixty thousand in the pool. The fates alone knew
where the cash was to come from if I lost--unless it came from Sir
Haselton Jardine, against which possibility the odds seemed pretty
strong. Pendarvon raised me five thousand more. Archie realised at
last that he could not see us unless we chose to let him--and that
we did not mean to let him. He threw down his cards with a curse--it
being a bad habit of his to use strong language when, if he only
knew it, milder words would serve him at least equally well. One can
damn so effectively with a softly-uttered blessing.
When Archie went I saw Pendarvon.
Fours, he said.
I felt a shudder go all down my back.

Four what?
Tens.
Queens.
As I faced them, in its holy of holies my heart sang a loud Te
Deum. Pendarvon stood up, still laughing.
That's enough for me.
When I heard the peculiar something that was ringing in his
laughter, knowing the man as I did, I knew that Mr. Pendarvon
would watch for me and wait. His turn would come.
I'm hanged! cried Archie, if I haven't thrown my money clean
away!
He certainly had--that is, if his IOU's represented money, which
his best friend might be excused for doubting.

DAMON AND PYTHIAS: A MODERN
INSTANCE.
West Kensington.
Dear Mr. Townsend,--Will you come and dine with me one
evening next week? I am always free.
I want to ask your advice on a small personal concern. You know
the world so much better than I do.
Truly yours,
Helen Carruth.
The next morning, when I woke from dreams of poker, this was
the first letter which I opened. It was nicely written, in a small,
round hand, as clear as copperplate--somehow it did not strike me
as being the writing of a woman who did not know the world. Mrs.
Carruth seemed friendly. With a background of intentions, as usual?
What was the small personal concern? An excuse?--only that and
nothing more? I wondered.
I had to go down to Cockington by the afternoon train--to Dora,
and to Haselton Jardine. I should probably stay there till Tuesday or
Wednesday--it depended. I might make it Thursday with Mrs.
Carruth--if anything turned up at the last moment I could always
send an excuse. Something about the woman attracted me. A tête-

à-tête might prove amusing. There and then I scribbled an
acceptance--appointing Thursday.
I was conscious of the possession of a head--the adventures of
the night had left the flavour of brandy behind. We had made up
accounts before we parted. There had been diversions! I had a nice
little pocketful of money. Pendarvon owed me seventeen thousand
odd, Archie owed him over four thousand, and me over thirty-five
thousand. As I surveyed Archie's heap of IOU's I felt that I had
better make early inquiries into the prices current of waste paper.
Pendarvon's seventeen thousand I would get within the week, or
mention it.
No need to trouble myself about Pendarvon. While I still was
fingering his paper, Burton brought me an envelope on which I
recognised his handwriting.
Mr. Pendarvon's servant waits for an answer, sir?
The envelope contained a cheque and note.
ARLINGTON STREET.
Friday.
Dear Townsend,--Enclosed find a cheque for £17,450. Short
reckonings make long friends. Please give IOU's to bearer.
Yours,
C. P.
I packed up his IOU in an envelope, with a word of thanks, and
handed them to Burton. Pendarvon was the sort of man one liked to

play with--when one won. He might not prove so pleasant an
opponent when one lost, and owed one's losings, and was pressed
for cash. Asking for no grace, he gave none. Archie would have to
find that four thousand in a week.
Poor dear old Archie!
What was I to do? I had as much chance of getting thirty-five
thousand pounds out of him as out of the first beggar I might meet
in the street. Well, I could afford to be magnanimous. I was like
unto him that expecteth nothing. I might let him off--if his beggarly,
but proud, Scotch blood would suffer it. It might be worth my while
to put him under an obligation.
He came in just as I had finished dressing--looking as if he had
been spending the time since I had seen him last in trying to find
that five and thirty thousand pounds. His eyes were bloodshot. His
face was white and drawn. He was a vivid illustration of the night it
must have been. Vouchsafing no greeting, sitting down without a
word, leaning on the handle of his stick, he stared at nothing with
his bloodshot eyes.
I opened the ball.
Are you coming down with me to Torquay by the three o'clock?
Silence. I suppose you haven't forgotten your engagement with
Jardine?
I can't keep it. For a sufficient reason.
What's that? Feel seedy? The run down will do you good. You'll
feel as fit as a fiddler by the time you get to Cockington.
That's not the reason.
What is it then? I suppose you're not going to throw them over--
they'll want your gun.

The reason I'm not going is because I have not sufficient money
with which to pay the fare.
I stared. I had not supposed the thing was so bad as that. Yet it
was characteristic. In one of his moods he was just the man to play
for his boots, and not miss them till he wanted to put them on.
I suppose you're joking.
By way of reply he relinquished his stick, stood up, and solemnly
turned out his pockets one by one. He held some coins out towards
me in his hand.
Six-and-ninepence. That represents my cash in hand. Of course,
there is always the pawnshop.
Stuff. You can always borrow.
I am glad to hear it. From whom? Give me the gentleman's
name. He is not known to me, I'll swear. I must be unknown to him,
or he would never lend.
Can't you do anything on a bit of stiff?
I repeat--give me the gentleman's name.
If it comes to that, I'll lend you a hundred or so to go on with
myself, as you very well know.
I owe you five and thirty thousand pounds already.
Look here, Archie, I don't want to make myself disagreeable, as
you believe, but when you like you can be about as much of an idiot
as they make them. Your proceedings last night would have been
more appropriate at a symposium in the county asylum. As to what
you say you owe me, we'll postpone the settling day, with your
permission, to when your ship comes home.

The arrangement was that all paper was to be taken up within a
week.
Rubbish. You and I know what those sort of arrangements are
worth.
Are you suggesting that I'm a thief?
I'm doing nothing of the sort. I'm asserting that you're a fool.
Reggie!
Archie?
He glared at me so that, for a moment, I thought that he was
going to give further proof of the truth of my words upon the spot.
But he changed his mind. He dropped on to a chair with a sort of
gasp.
What you say is correct enough. I have no right to cavil. I thank
you for the word. He sat silent. Then he added, But it's not only
you I owe, I owe Pendarvon.
If you take my advice, you'll pay Pendarvon.
It's not advice I want; it's money. I owe the man, in round
numbers, four thousand five hundred pounds. I don't know where to
turn to raise four hundred.
My dear Archie, you must excuse my saying, that's your affair.
You would punt--although he gave you warning. The man lost
heavily himself. This morning he's sent me round a cheque to
settle.
He has, has he? He is an honest man. My God! what it is to have
money!

That's nonsense. If you were made of money you would not be
justified in playing as you played last night.
That's right. Give it me. I deserve it all. I wonder what my father
will think when he finds out, once more, what sort of son I am.
He'll think of the days of his own youth. When they are
confronted with similar revelations, all our fathers do.
I doubt it. I don't think my father was ever such as I am.
Certainly, he never bound himself to commit murder within a month.
I suppose that you have not forgotten that the Honour of the Club is
in my keeping.
I had not. I had very clearly understood that it was that fact
which had caused him to make the spectacle of himself which he
had done. I stood contemplating the fire, twisting Mrs. Carruth's
note between my fingers. He repeated his own words bitterly--The
Honour of the Club.
It's a pretty club.
My faith it is!
Your only bantling.
Don't say that. It's Pendarvon's. You know it is. It's the biggest
part of the debt I owe him. When I think of it, I feel like killing him.
Why don't you?
It's against the rules. You stood by the rules, and so will I.
Who are you going to kill?
For one thing, I shall kill my father. It will be as good as his
death-blow when he hears of the sort of thing I am.

That sort of murder won't come within the scope of the
definition. If it did, possibly seven men out of ten would be entitled
to the diploma of the club. Archie, I'll make you a proposition. I'll
give you the money to pay Pendarvon, and I'll cry quits for what you
owe me, if you'll agree, since you must kill some one, to kill any
person I may nominate.
Reggie!--what devil's game are you up to now?
At present, none. At this moment I have not the faintest reason
to wish myself rid of any living creature. But before the end of the
month the situation may be altered. Is it a deal?
He hesitated; rose, and began to walk about the room. I watched
him as he did so. I noticed how he clasped and unclasped his hands.
He turned to me.
I agree.
I sat down, then and there, and wrote him an open cheque for
five thousand pounds.
The balance will enable you to rub along for a time. If you take
my tip, you'll let Pendarvon have his coin at once--before leaving
town.
He took the cheque. Scanning the figures, he began to fold it up
with nervous fingers. A smile--of a kind--wrinkled his lips.
What things we may become! If ever there was blood money,
this is it. And I'm a Beaupré. And do you know, Townsend, that for
ever so long I've been dreaming dreams. He looked up at me, with
a sudden flashing of his eyes. Dreams of Dora Jardine.
I turned again to the fire--smiling in my turn.
You told me so before.

But I never told you what sort of dreams I had been dreaming. I
never told you how she fills all my veins till, in all the world, I see
nothing, think of nothing else, but her. I never told you how she is
with me by day and by night, sleeping and waking; that, wherever I
am, and whatever I do, I am always repeating to myself her name. I
never told you that the dreams which I have dreamed of her have
driven me mad. I never told you that.
With all due respect to you, I should hardly have believed you if
you had.
Why? Because I am the thing I am? There's the pity of it! I have
been so conscious of my unworthiness, so conscious that I never
could be worthy, that, constrained by some madness which I verily
believe is in my blood, I have become more unworthy still. He came
closer to me. His voice dropped to a sort of breathless whisper. And
yet, Reggie, do you know, I believe that, in spite of all, she cares for
me.
I think not.
He became, all at once, almost ferocious.
You think not! What right have you to think? How can you tell
what grounds I may have for my belief?
I turned to him. I had purposely kept my back towards him while
he had been indulging in his hysterical ravings. Now I was surprised
and amused to see what a change his hysterics had produced. His
cheeks were flushed. His eyes were flaming. He seemed to have
increased in stature. He seemed to have lost all traces of the hang-
dog air with which he had entered the room.
I ought, Archie, to have stopped you. If I remember rightly I did
stop you on a previous occasion. I have, I assure you, good cause
for thinking that your belief is an erroneous one; that cause is, that I
have reason to believe that she cares for me.

For you--Reggie!
I will be frank with you. With her father's express approval I am
going down to Cockington to-day in the character of Miss Jardine's
suitor.
You!--My God!
Very shortly I hope to receive your congratulations on the
confessedly undeserved good fortune which has dowered me with
such a wife.
But--the man was trembling so that he could scarcely speak--
you're--you're a murderer.
I am as you will shortly be. Let us hope that my man is not
listening to these plain truths. What then?
He began fumbling in his waistcoat pocket.
I won't have your money. You can't buy me body and soul--no,
not altogether. She shall know what manner of man you are.
He threw my cheque from him on to the floor.
I see. Having led me into crime, you are going to tell of me. Is
that sort of conduct in accordance with the Beaupré code of honour?
Are you sure that you are not proposing to play Judas merely
because I have conquered where you have failed?
No! No! I won't tell! I won't tell! You know I won't! But--that you
should be going to marry Dora Jardine!
He sank in a heap on to a chair, looking once more as pitiable an
object as one would care to see.
Come, Archie, pull yourself together. Have a drink, and play the
man. Pick up the cheque, run down with me to Cockington, and wish

me luck upon the road. Surely your own experience has taught you
that love's transferable. So long as one has an object it does not
much matter what it is, or whether it's in the singular or plural.
Between ourselves, I believe that Miss Whortleberry, the American
millionairess, is with the Jardines. You marry her--and her millions--I
promise you I won't tell.
My words did not seem to brighten him up to any considerable
extent. He sat staring with wide open eyes, almost like a man who
had been stricken with paralysis.

THE PROMISE.
But he went with me to Cockington. More, he picked up the
cheque, and cashed it, and let Pendarvon have his money before he
went. He struck me as not being very far from drunk when we
started. Having commenced to drink, he kept at it like a fish. He was
in deliriously high spirits by the time we reached our journey's end. I
began to suspect that there was literal truth in what he had said;
that there was a strain of madness in his blood; and that,
consciously or otherwise, he was in actual training for a madhouse.
The more I considered it, the less his conduct for some time past
smacked to me of sanity.
It was past nine when we reached Jardine's. At the door they told
us that dinner had been kept waiting for our arrival. It was ready to
be served as soon as we appeared. Making a quick change, I hurried
down into the drawing-room. As I entered Dora Jardine advanced to
meet me.
We expected papa by the same train by which you came, but he
is detained in town. I have just had a telegram from him to say so.
He says that he hopes to be here for the shoot, so perhaps he will
come down by the mail--it gets here in the middle of the night, just
before four. I bowed. She added, in a lower tone of voice, Isn't it
odd how some people have too much to do, and others have too
little?
I am afraid, Miss Jardine, that such inequality is characteristic;
while, if you are referring particularly to me, I assure you that very
shortly I hope to be overwhelmed beneath the pressure of
innumerable engagements.

She turned to the others. I knew them all. There was her aunt,
Mrs. Crashaw, fat, not fair, and more than forty, a childless widow,
who was understood to be rich. Lady Mary Porteous, the Marquis of
Bodmin's sister, who was not so young as she had been. And there
was Miss Whortleberry, the daughter of Asa Whortleberry, late of
Chicago, and the present possessor of all his millions. Miss
Whortleberry was one of those young women who seem to be
America's most peculiar and special product. To look at she was a
graceful, slender little thing, with big eyes and a face that was
almost angelic in its innocence. An unsuspecting stranger might have
been excused for taking it for granted that in the frame of a delicate
girl there was the simple spirit of a child. A more prolonged
inspection would, however, have revealed to him the fact that her
costume was, to say the least of it, more suggestive of Paris than
Arcadia. But it was when she opened her mouth that she gave
herself away. Her voice, quite apart from its nasal twang, always
reminded me, in some queer way, of Lancashire streets; it was hard
and metallic. Her conceit was simply monumental. You could not talk
to her for half an hour without discovering that there was only one
heaven for her, and that was the heaven of dollars, and that, in her
own estimation at any rate, she was its uncrowned queen.
She was lolling back in a corner of a sofa as I advanced to her.
She vouchsafed me the tips of her fingers.
Ah, it's you.
That was all the greeting she condescended to bestow.
There were four men. George Innes--Lord George Innes--who, on
the strength of being one of the finest shots in England, is in hot
request wherever there are birds about. I believe Innes is one of the
cleanest living men I know. He is not rich, but, I take it, he lives
within his income. He is fond of a modest gamble, but he won't play
for big stakes, and he will only sit down where there's ready-money.
His manner is a trifle suggestive of a poker down his back, but if I

had been run in a different mould I could have fraternised with
Innes. The man to me rings true--he is a man. He dislikes me--it is
perhaps, just as well for him that he should.
Then there was Tommy Verulam, an ass, if ever there was one. I
suppose he was there because of his father. I don't know what other
recommendation he has. Then there was Denton, the man who
writes. Personally, I have no taste for men who write. They may be
all right in print, but generally they are nothing out of it, and the
worst of it is, they are apt to think they are. And Silcox, M.P. I am
told that he is very popular in his party, as being the only man in the
Radical gang who is a fool, and knows it.
Presently Archie appeared. He was flushed. I thought he looked
uncommonly well. He is a handsome beggar in his way. Dora
received him with a something in her air which made his flush mount
higher. I guessed how she set all his pulses tingling. Even Miss
Whortleberry extended to him a welcome which, for her, was quite
affectionate--he was a son of the Duke of Glenlivet.
Dora went in with Innes, as being the biggest there. I came in
with the tail. We would change all that!
After dinner I made straight for the drawing-room. Something
seemed to tell me that I had better make the running while I could.
It was the pace which would win. Besides, the consciousness that I
was once more in Dora's near neighbourhood had on me the same
queer effect which it evidently had on Archie. I found her talking to
the Whortleberry. Presently the millionairess went off with Mary
Porteous. I had Dora to myself.
It was odd how the recognition of this fact gave me what
positively amounted to a thrill. And yet, for a moment or two,
neither of us spoke. She sat opening and shutting her fan. I sat and
watched her performance. And when I did speak at last, my voice
actually trembled.

I have been thinking of what you said to me the other evening.
What was that?
Have you forgotten?
Haven't you?
I could scarcely have been thinking of it if I had forgotten.
What did I say?
You gave me courage.
Courage?
Yes.
Were you in want of courage?
Of that particular sort of courage. Some men only get that
particular sort of courage from a woman. I know you gave it me.
She glanced up with those strange eyes of hers.
Tell me what you mean.
It would take me an hour to explain. Don't you know?
You never struck me as being in want of courage of any sort or
kind.
There was an ironic intonation in her voice, which, in some subtle
fashion, recalled her father.
Is that meant as a reproach?

No. She hesitated, as if to consider. Then went on, It is not so
much your courage which I should have questioned, as the direction
in which it has been shown. It is a sufficiently rare quality to make it
unfortunate that any of it should be wasted. How much of it has
been wasted you know even better than I do.
I understand you. I thank you, not only for what you say, but
also for what you leave unsaid. I am not only going to turn over a
new leaf, Miss Jardine; I am going to commence a new volume.
Though I shall always feel, myself, that you have commenced it for
me.
I am content, so long as it is a volume of a certain kind.
What did she mean? I seldom knew quite what she did mean. She
puzzled me almost as much as her father. She was not like the
average girl one bit. As she looked at me with her curiously smiling
eyes, with the suggestion of strength which they conveyed to me, I
felt that it was probable that she knew much more of the contents of
my volume, the one which I claimed to be just closing, than I was
likely to know of hers.
Do you know, Miss Jardine, that you are making of me a
proselyte.
In what sense?
I have never, hitherto, believed in the influence of women. You
are making of me a believer.
That certain women have influence over certain men I think
there can be no doubt whatever. I have influence over you; you have
influence over me. Only--she stopped my speaking with a
movement of her fan--I should be on my guard against your
influence over me until I felt that my influence over you had
produced certain results.

I suppose that any attempts on my part to guard against your
influence would be vain.
You would not attempt to make them. You are not that kind of
man.
Miss Jardine!
You are not. You would not attempt to resist the influence of any
woman. You would rather welcome it as a sort of study in sensation,
as far as it would go. But it would not go far. It would soon reach a
bed-rock of resistance. As soon as it reached that rock it would
vanish into nothing.
You flatter me by making so close a study of my peculiarities.
I do not flatter you. I take an interest in you, because, for one
reason, you take an interest in me. Now, Mr. Townsend, I am sure
that I should find that bed-rock of resistance at a greater distance
from the surface. If ever you welcomed my influence you might find
it go much farther than you had at first intended. So I warn you in
advance.
I was silenced, not so much by her words as by her bearing. Her
eyes had an effect on me which no eyes had ever had on me before.
They mastered me, and made me conscious of a sense of
satisfaction at being mastered.
You make me afraid of you.
Just now you said I gave you courage.
The two things are compatible. Fear of you might give me
courage.
You mean fear of appearing contemptible to me?

Exactly.
Then that sort of courage I should like to give you. A gleam
came into her eyes which was almost like a flash of lightning.
Perhaps I will.
Do I not tell you that you have given me a taste of it already?
We might have reached delicate ground. When a man and a
woman deal in personalities, and persevere in them, a situation of
some sort is apt to ensue. Archie's appearance postponed the crisis
which I was beginning to think was nearer even than I had
supposed. Archie seemed in a condition of almost feverish
exaltation. In the look with which he favoured me there was
something which certainly was not altogether friendly. Dora did not
seem to notice it. She welcomed him with a smile. As he sat down
on the other side of her I got up. I left them together.
Poor chap! I told myself as I strolled off, let him have his
innings. He must be badly burned or he would make a more
strenuous endeavour to avoid the fire.
Lounging into the little drawing-room beyond, I came into
collision with the aunt. She had the place to herself. She appeared to
be just waking up from the enjoyment of forty winks. I daresay if I
had not come upon the scene she would have had another. At the
sight of me she roused. She beckoned me to occupy an adjacent
chair. She was the aunt, and I still was unattached. I sat beside her.
What do you think of Dora? Her tone was confidential. She
spoke to me under cover of her handkerchief. Seeing that I was
puzzled, she explained--I mean, how do you think she's looking?
I think she's looking very well.
Isn't she! Wonderfully well! Don't you think she's lovely?

I hardly knew what to say. She could scarcely expect me to be
ecstatic.
Indeed I do.
Of course you would! She smiled--such a smile. And she's all
she looks, and more. She is good as she is beautiful, and so clever.
Extraordinarily so! She's a wonderful girl! She closed her eyes, as if
the wonder was too great for visual contemplation. I often think
that it is unfortunate that she was not born a man.
You can scarcely expect me to agree with you there.
You wicked creature! She prodded me with her fat fingers in the
arm. Mrs. Crashaw was one of those old women who, whenever
they can, punctuate their remarks on the persons of their listeners.
She arranged her bracelets on her wrists. Haselton tells me that he
has a very high opinion of you, Mr. Townsend.
I am very glad to hear it. I only hope he does not think more
highly of me than I deserve.
I hope not. Young men nowadays are so wicked. They deserve
so little. As you probably are aware, Mr. Townsend, I am Haselton's
only sister. He reposes in me his entire confidence. He has no
secrets from me.
I believed her! She might be his only sister, but Sir Haselton
Jardine was as likely to repose his entire confidence in a woman of
Mrs. Crashaw's type as in the first town crier. Whatever he told her
would probably be told with, at least, one eye to advertisement.
My brother Haselton is a man of peculiar gifts. A remarkable
man. A man of genius if ever there was one. He is, of course,
respected by all of us, by his country and his Queen. He has a
marvellous knowledge of the world, and a great esteem for those
sacred things which are too often disregarded. And when I learn that

Welcome to our website – the ideal destination for book lovers and
knowledge seekers. With a mission to inspire endlessly, we offer a
vast collection of books, ranging from classic literary works to
specialized publications, self-development books, and children's
literature. Each book is a new journey of discovery, expanding
knowledge and enriching the soul of the reade
Our website is not just a platform for buying books, but a bridge
connecting readers to the timeless values of culture and wisdom. With
an elegant, user-friendly interface and an intelligent search system,
we are committed to providing a quick and convenient shopping
experience. Additionally, our special promotions and home delivery
services ensure that you save time and fully enjoy the joy of reading.
Let us accompany you on the journey of exploring knowledge and
personal growth!
textbookfull.com

Emerging Trends and Applications in Cognitive Computing Pradeep Kumar Mallick

More Related Content

Similar to Emerging Trends and Applications in Cognitive Computing Pradeep Kumar Mallick (20)

Recently uploaded (20)

Emerging Trends and Applications in Cognitive Computing Pradeep Kumar Mallick