Module 5: Algorithms for WSN (7 Hours) ML algorithms for localization, Coverage & connectivity, Anomaly detection, Fault detection, object tracking, routing, clustering and data aggregation, query processing, and MAC protocols synchronization, congestion control, Target tracking, event detection, mobile sink scheduling and energy harvesting and QoS for Wireless Sensor Networks Module 6: Applications and Integrations of WSNs (7 Hours) Cyberphysical systems (CPS), machine-to-machine (M2M) communications, and Internet of things (IoT) technologies -intelligent decision-making and autonomous control, Future applications of machine learning in wireless sensor networks Text Books 1. D. Praveen Kumar, Tarachand Amgoth Chandra Sekhara Rao Annavarapu, “Machine learning algorithms for wireless sensor networks: A survey”, Journal of Information Fusion, Vol 49, September 2019, pp. 1-25. 2. Clint Smith, Daniel Collins, “Wireless Networks”, McGraw Hill, 2014. Reference Books 1. Mohammad Abu Alsheikh, Shaowei Lin, Dusit Niyato, and Hwee-Pink Tan, “Machine Learning in Wireless Sensor Networks:Algorithms, Strategies, and Applications”, IEEE Communication Surveys & Tutorials, Vol. 16, No. 4, Fourth quarter 2014. 2. Siva Ram Murthy C and Manoj BS, “Adhoc Wireless Networks Architecture and Protocols”, Pearson Education, 2008. 3. Alpaydin E, “Machine Learning”, MIT Press, 2010. 4. Mitchell T, “Machine Learning”, McGraw-Hill, 2010. 5. Hastie T, Tibshirani R and Friedman J, “Elements of Statistical Learning”, Springer, 2001. 19EE2046
Soft Computing
L 3
T 0
P 0
C 3
Course Objectives 1. To learn about artificial neural networks and Fuzzy systems. 2. To impart knowledge on Neuro Fuzzy modeling. 3. To get familiarized with the different applications involved in neural networks and fuzzy logic. Course Outcomes At the end of this course, students will demonstrate the ability to 1. Understand the concepts artificial neural networks. 2. Explain the architecture of ANN and their training algorithms. 3. Differentiate between classical sets and Fuzzy sets. 4. Formulate fuzzy logic based expert systems 5. Understand Neuro-Fuzzy concepts 6. Apply artificial neural networks and fuzzy logic for solving engineering problems Module 1: Introduction to Neural Networks (7 Hours) Introduction, Humans and Computers, Organization of the Brain, Biological Neuron, Biological and Artificial Neuron Models, Characteristics of ANN, McCulloch-Pitts Model. Module 2: Architectures and Training Algorithms (8 Hours) Operations of Artificial Neuron, Types of Neuron, Activation Function, ANN Architectures, Classification Taxonomy of ANN – Connectivity, Neural Dynamics (Activation and Synaptic), Learning Strategy (Supervised, Unsupervised, Reinforcement), Learning Rules. Module 3: Feed Forward Neural Networks (8 Hours)Introduction, Perceptron Models: Discrete, Continuous and Multi Category, Limitations of the Perceptron Model, Hebb network, BPN, Hopfield neural network, Kohonen neural network, Radial basis function neural network, Counter propagation neural network, Deep learning neural networks. Module 4: Classical & Fuzzy Sets (8 Hours) Introduction to classical sets – properties, Operations and relations; Fuzzy sets, Membership, Uncertainty, Operations, properties, fuzzy relations, cardinalities, membership functions – Fuzzy Inference Systems. ELECTRICAL AND ELECTRONICS ENGINEERING (2020)