DATA SCIENCE IN SCIENCE, TECHNOLOGY, ENGINEERING AND MATHEMATICS
- 1. Data Science in STEM BY N ILANGO Assistant Professor, Department of MBA Sri Ramakrishna College of Arts & Science, CBE
- 2. Data Science Data Science is the study of: ‘Collecting’ Structured & Unstructured data ‘Processing’ & ‘Cleaning’ it Applying Algorithms, Statistical Models & Machine Learning ‘Communicating’ Results through “Visualization” & Reporting Data Science acts as a powerful analytical & predictive tool that enhances research, innovation & practical outcomes
- 3. Data Science in STEM Data Science in STEM refers to the use of: data collection, analysis, modeling and interpretation techniques : to solve complex problems in the fields of Science, Technology, Engineering and Mathematics (STEM) Involves combining statistics, computing & domain knowledge to: Extract Insights, Make Predictions & Support Decision-making
- 4. Importance of Data Science in STEM BENEFIT IMPACT Improves research quality By using data-driven insights instead of assumptions Supports innovation Through pattern recognition, predictive models, and simulations Reduces cost and time Automating analysis and optimizing solutions Enhances decision-making Providing measurable evidence and forecasts Enables real-time monitoring & testing Especially in engineering, technology, and medical research
- 5. Applications of Data Science in STEM SCIENCE Bioinformatics: Analyzing genetic data (e.g., Human Genome Project) Climate Science: Predicting weather patterns, analyzing CO trends ₂ Physics: Particle data from experiments (Hadron Collider) Astronomy: Mapping galaxies using data from telescopes like Hubble Eg: NASA uses data science to predict spacecraft behavior & analyze satellite imagery for planetary research
- 6. Applications of Data Science in STEM TECHNOLOGY Software Engineering: Bug prediction models & code optimization Cybersecurity: Detecting anomalies in network traffic to prevent breaches IoT: Processing sensor data from smart devices AI & Robotics: Training intelligent systems using big datasets Eg: Google uses data science for improving search algorithms and YouTube recommendations
- 7. Applications of Data Science in STEM ENGINEERING Civil Engineering: Analyzing infrastructure sensor data for maintenance Mechanical Engineering: Predictive maintenance using machine data Electrical Engineering: Power load forecasting in smart grids Manufacturing: Quality control using real-time production data Eg: Tesla uses data science to monitor vehicle sensors and improve autonomous driving features
- 8. Applications of Data Science in STEM MATHEMATICS Statistical Modeling: Predicting outcomes in finance & logistics Operations Research: Optimizing transportation & resource allocation Actuarial Science: Risk prediction using historical & current data Cryptography: Data patterns used for secure encryption Eg: Mathematicians use data science to optimize airline scheduling or supply chains using predictive modeling.
- 9. CROSS-DISCIPLINARY Applications of Data Science Healthcare Medical diagnostics using image processing, disease prediction models Education Personalized learning platforms using student performance data Agriculture Crop yield prediction & pest detection using satellite data Finance Fraud detection, credit scoring & stock price forecasting Environmental Science Deforestation tracking using satellite image classification Transportation Route optimization & traffic flow prediction using real-time GPS data
- 10. Data Science: Real World Example COVID-19 Pandemic During the pandemic, data scientists collaborated with: Scientists - to study virus mutation patterns Engineers - to build ventilators using optimized materials Mathematicians - to model the spread of virus Technologists - to track apps & develop dashboards This was a STEM-powered, data-driven global response
- 11. Data Science: Case Study Data Science for Predictive Maintenance in Industrial Engineering @ General Electric (GE) Traditionally in manufacturing & engineering industries, machinery maintenance was either: / scheduled (preventive) or / reactive (after failure) Both methods often led to: Unnecessary downtime Wasted resources Unexpected equipment failures
- 12. Data Science: Case Study General Electric (GE) adopted a data science-based predictive maintenance system using IoT sensors & machine learning algorithms Objective is to predict equipment failures before they happen by using real-time sensor data : reducing downtime & : optimizing maintenance costs
- 13. Data Science: Case Study Engineering Field Involved Mechanical Engineering – machines, turbines, engines Electrical Engineering – motor performance, power supply monitoring Industrial Engineering – workflow, operations, efficiency Data Science Techniques Used Time Series Analysis Analyze sensor data over time Anomaly Detection Detect unusual behavior in machine performance Machine Learning (Random Forest, SVM) Predict likelihood of part failure Clustering Categorize machines by failure pattern or age Visualization Dashboards Show real-time system health and predictions
- 14. Data Science: Case Study How It Worked Sensors on machines collected data (temperature, vibration, noise, pressure) Data was sent to GE’s Predix Platform (an Industrial IoT data cloud) Data scientists built models to detect deviation from normal behavior Maintenance teams received alerts days or weeks before potential failure Maintenance was scheduled just-in-time, minimizing disruption
- 15. Data Science: Case Study METRIC BEFORE DATA SCIENCE AFTER DATA SCIENCE Unplanned Downtime High Reduced by 30 – 50% Maintenance Cost Fixed scheduled cost Reduced by 20 – 25% Equipment Life Span Moderate Increased through early repair Safety & Reliability Reactive Proactive & Predictive OUTCOMES
- 16. Data Science: Case Study Key Learning Points Enables engineers to move from……. Repairing Machines to Preventing Breakdowns Real-time analytics + machine learning = Smarter, Safer & Cost-effective Engineering Interdisciplinary Skills are critical both…. Data & Domain Knowledge
- 17. END