Smart sort AI Driven Automated Waste Segregiation
- 1. Smart Sort AI-Driven Automated Waste Segregation System Project Members: Abhishek Kumar :41140003 Ayush Kumar Singh :41140014 Guide Name : Dr.D. Godwin Immanuel Professor Department of EEE
- 2. OBJECTIVE To design & implement a compact, low cost and user friendly waste segregation system to streamline the waste management process. To design a system that segregate the waste into two categories i.e. biodegradable and non-biodegradable for ensuring a high quality of material is retained for recycle. To reduce the difficulty & occupational hazard for worker involved in the collection of waste. To reduce the pollution by collecting biodegradable waste directly for biogas. To reduce the overall time required for processing post segregation.
- 3. LITERATURE REVIEWS SL.NO. TITLE AUTHORS YEAR MAJOR FINDING 1. Automatic Waste Segregation i. Nimisha S Gupta ii. Deepthi V iii. Nikhil Binoy 2018 The waste has a higher potential for recovery & the occupational hazards of waste separating workers is also reduced. 2. Automated Waste Segregation System and its approach towards generation of Ethanol i. Abhishek Madankar ii. Minal Patil iii. Dr. Prabhakar Khandait 2019 It is intended to sort the loss into 3 noteworthy classes, to be specific metallic, wet and dry, in this manner making waste administration increasingly powerful. 3 Electronically assisted automatic waste segregation i. Nandhini S ii. Mrinal Sharma S iii. Naveen Balachandran 2019 the waste and place it on a binary classifier platform which has a camera attached to capture the image and an algorithm to classify the waste as biodegradable or non- biodegradable into their respective bins 4. Artificial intelligence for waste management is smart cities i. Bingbing Fang1 ii. Jiacheng Yu iii. Zhonghao Chen 2023 Artificial intelligence combined with chemical analysis improves waste pyrolysis, carbon emission estimation, and energy conversion
- 4. LITERATURE REVIEWS SL.NO. TITLE AUTHORS YEAR MAJOR FINDING 5. Design of Distributed Intelligent Waste Sorting and Dropping System Based on RS-485 i. Fanyu Zhang ii. Jianwen Li iii. Jun Kang 2022 The system is more expandable and the free combination of the drop system is more convenient, which achieves the intelligent construction of waste separation and disposal. 6. Automated waste-sorting and recycling classification using artificial neural network and features fusion i. Mazin Abed Mohammed ii. Mahmood Jamal Abdulhasan iii. Mashael S. Maashi 2022 This model is validated by extracting relevant information from the dataset containing 2400 images of possible waste types recycled across three categories. 7. A Design and Implementation Using an Innovative Deep-Learning Algorithm for Garbage Segregation i. Jenilasree Gunaseelan ii. Sujatha Sundaram iii. Bhuvaneswari Mariyappan 2023 The model boosts performance to predict waste generation and classify it with an increased 98.9% accuracy, which is more than the existing system. 8. IoT-Based Waste Segregation with Location Tracking and Air Quality Monitoring for Smart Cities i. Abhishek Kadalagere Lingaraju ii. Mudligiriyappa Niranjanamurthy iii. Priyanka Bose 2023 The waste management productivity by categorizing waste into three types: wet, dry, and metallic
- 5. LITERATURE REVIEWS SL.NO. TITLE AUTHORS YEAR MAJOR FINDING 9. IoT-Enabled Smart Waste Management Systems for Smart Cities i. INNA SOSUNOVA ii. JARI PORRAS 2022 Identified the main promising directions and research gaps in the field and services, we developed recommendations for the implementation of city-level and SGB- level SWM systems 10. Artificial intelligence for waste management in smart cities i. Bingbing Fang, ii. Jiacheng Yu iii. Mohamed Farghali 2023 Artificial intelligence in waste logistics can reduce transportation distance by up to 36.8%, cost savings by up to 13.35%, and time savings by up to 28.22%. 11. Artificial Intelligence Based Smart Waste Management i. Nusrat Jahan Sinthiya ii. Tanvir Ahmed Chowdhury 2022 AI based systems are used to tackle complicated problems, handle uncertainty, and exhibit the efficiency of smart systems. 12. Deep Learning based Automated Waste Segregation System based on degradability i. Resmi R ii. G Purnima iii. Surendra Kumar Koganti 2021 The individual waste item placed on a conveyor belt that carries the waste to the respective dustbin based on the classification done by Pi module.
- 6. LITERATURE REVIEWS SL.NO. TITLE AUTHORS YEAR MAJOR FINDING 13. Automatic Waste Segregation System i. Lonut Robert Badoi ii. Loan Lie 2022 The system can efficiently in waste recognition and automatic navigation functions. 14. Electronically assisted automatic waste segregation i. S Nandhini ii. Sharma S Mrinal iii. Naveen BalaChandran 2019 The waste and place it on a binary classifier platform which has a camera attached to capture the image and an algorithm to classify the waste as biodegradable or non- biodegradable into their respective bins. 15. Automatic Waste Segregation and Management i. Ajay V.P ii. Vaishnavi Kumar 2020 The smart dustbin which is also very cheap, at small and medium companies or industries which are sent directly for processing. 16. An Automatic Waste Segregation Machine Using Deep Learning i. Md Kishor Morol ii. Shurva Das iii. Dip Nandi 2023 The system is made to provide the services at a low cost with higher accuracy level in terms of the technological advancement in the field of Artificial Intelligence
- 7. LITERATURE REVIEWS SL.NO TITLE AUTHOR YEAR MAJOR FINDING 17. Automatic waste segregator i. A. Sharanaya ii. U. Harika iii. N. Sriya 2017 Arduino UNO which makes the working of the system to be smooth and convenient making the design to be less complicated 18. Automated Waste Segregation System and its approach towards generation of Ethanol i. Abhishek Madankar ii. Minal Patil 2019 It is intended to sort the loss into 3 noteworthy classes, to be specific metallic, wet and dry, in this manner making waste administration increasingly powerful. 19. Automated Waste Segregator i. Nikhil U Baheti ii. Nitin Kumar Krishna 2014 The AWS employs parallel resonant impedance sensing mechanism to identify metallic items, and capacitive sensors to distinguish between wet and dry waste. 20. An Evaluation of Automated Waste Segregation Systems i. Yuree Ann B.Edris ii. Mary Jane C 2021 The highest rating is 4.375 or 87.5% in effectiveness, and 4.125 or 82.5% rating of efficiency as the advantages of the systems while the disadvantage of 2.875 rate or 57.5% in learnability.
- 8. 1. Initialize Components: • Set up LCD, servo motors, ultrasonic sensors, gas sensor, and serial communication. 2. Measure Garbage Bin Levels: • Use ultrasonic sensors to check bin fullness. • If full, turn on an alert (LED) and display a warning on the LCD. 3. Receive Waste Type from Serial Communication: • Read the incoming character (a, b, c, d). 4. Control Servo Motors for Waste Segregation: • 'a' (Food Waste): Move Servo1 & Servo2 to dump waste. • 'b' (Paper): Move Servo1 & Servo2 accordingly. • 'c' (Metal): Move Servo1 & Servo3 for disposal. • 'd' (Plastic): Move Servo1 & Servo3 to direct plastic waste. 5. Monitor Air Quality (Smell Sensor): • If gas sensor value ≥ 700, trigger an alert and display “SMELL HIGH” on the LCD. 6. Repeat the Process Continuously. MACHINE LEARNING ALGORITHMS
- 9. CAMERA TRANSFORMER STEPDOWN 12V BIODEGRADABLE WASTES LAPTOP ML PROCESS NON- BIODEGRADABLE WASTES POWER SUPPLY UNIT SERVO MOTOR SERVO MOTOR INFRARED SENSOR MQ3 SENSOR INDUCTIVE SENSOR INFRARED SENSOR LCD BUZZER BLOCK DIAGRAM
- 10. COMPONENTS Fig: Servo Motor Fig: MQ-3 Sensor Fig: Inductive Proximity Sensor Fig: Infrared Sensor Fig: Buzzer Sensor
- 11. Classify the type of the waste. Type of the waste Biodegra dable Modify the image according to the trained image dataset Run servomotor 1 in clockwise Non- biodegra dable START NO YES YES Run servomotor 1 in anticlockwise Dry YES NO Wet YES Plastic Metal YES NO Run servomotor 2 in clockwise Run servomotor 2 in anticlockwise Run servomotor 3 in clockwise Run servomotor 3 in anticlockwise YES WORK FLOW OF THE PROJECT Capture the image of waste
- 12. SIMULATION
- 15. PROJECT IMAGES
- 17. PROJECT IMAGES
- 18. CONCLUSION Present system of management should be upgraded. Segregation of waste at source for recyclable material should be encouraged so that the quantity of waste to be disposed can be minimized and recycling should be adopted. It plays a crucial role in lightening the burden on government exchequer and municipality by recycling.
- 19. • Arroub, B. Zahi, E. Sabir, and M. Sadik, ‘‘A literature review on smart cities: Paradigms, opportunities and open problems,’’ in Proc. Int. Conf. Wireless Netw. Mobile Commun. (WINCOM), Oct. 2016, pp. 180–186, doi: 10.1109/WINCOM.2016.7777211. 2. • T. Anagnostopoulos, A. Zaslavsky, K. Kolomvatsos, A. Medvedev, P. Amirian, J. Morley, and S. Hadjieftymiades, ‘‘Challenges and opportunities of waste management in IoT-enabled smart cities: A survey,’’ IEEE Trans. Sustain. Comput., vol. 2, no. 3, pp. 275–289, Jul. 2017 3. • T. Addabbo, A. Fort, A. Mecocci, M. Mugnaini, S. Parrino, A. Pozzebon, and V. Vignoli, ‘‘A LoRa-based IoT sensor node for waste management based on a customized ultrasonic transceiver,’’ in Proc. IEEE Sensors Appl. Symp. (SAS), Mar. 2019, pp. 1–6, doi: 10.1109/SAS.2019. 8705980. • R. Fujdiak, P. Masek, P. Mlynek, J. Misurec, and E. Olshannikova, ‘‘Using genetic algorithm for advanced municipal waste collection in smart city,’’ in Proc. 10th Int. Symp. Commun. Syst., Netw. Digit. Signal Process. (CSNDSP), Jul. 2016, pp. 1–6, doi: 10.1109/CSNDSP.2016.7574016. • L. Abbatecola, M. P. Fanti, A. M. Mangini, and W. Ukovich, ‘‘A decision support approach for postal delivery and waste collection services,’’ IEEE Trans. Autom. Sci. Eng., vol. 13, no. 4, pp. 1458–1470, Oct. 2016, doi: 10.1109/TASE.2016.2570121. • M. Marchiori, ‘‘The smart cheap city: Efficient waste management on a budget,’’ in Proc. IEEE 19th Int. Conf. High Perform. Comput. Commun., IEEE 15th Int. Conf. Smart City, IEEE 3rd Int. Conf. Data Sci. Syst. (HPCC/SmartCity/DSS), Dec. 2017, pp. 192–199, doi: 10.1109/HPCCSmartCity-DSS.2017.25. REFERENCES
- 20. THANK YOU