National Institute of Technology, Meghalaya

About: National Institute of Technology, Meghalaya is a education organization based out in Shillong, India. It is known for research contribution in the topics: Control theory & Computer science. The organization has 503 authors who have published 1062 publications receiving 6818 citations. The organization is also known as: NIT Meghalaya & NITM.

Decision Support Model under Transactive Energy Markets for Profit Maximization

Abstract: The proliferation of distributed energy resources (DER) demands a flexible marketplace in the distribution level to fully harness the local resources. Creation of local flexible market under transactive energy (TE) framework would enable small to medium-sized prosumers to participate in the energy market locally for transactions. In this context, a new decision support model is proposed to optimize the player's negotiations for day-ahead market. The proposed model assists the small players to maximize their profits in the market exchanges and is operates on the nature-inspired based water cycle algorithm (WCA). The efficiency of the proposed model is tested on a microgrid consisting of both dispatchable and non-dispatchable distributed generators. Moreover, the performance of WCA based technique is compared with other heuristic techniques such as particle swarm optimization and genetic algorithm. The reliability of the model is also studied for different energy markets. The results show that the proposed method is quite capable to minimize the overall day-ahead operational costs and explores the benefits of local energy transactions.

M-Way Balanced Tree Data Aggregation Approach for Clustered Wireless Sensor Networks

Abstract: Energy efficiency has been the prime design issue for wireless sensor networks as sensor nodes are embedded with limited energy. Clustering algorithms are considered as energy-efficient approach for wireless sensor network. Cluster head nodes have been overburdened in most of clustering algorithms that result in load unbalanced network. Work of this paper presents a layout of work in progress of proposed m-way balanced tree data aggregation approach for clustered wireless sensor networks that aggregates the data at each level of m-way balanced tree instead of performed by the cluster head solely and also reduces the wake-up time period of cluster head.

Ensemble-Based Machine Learning for Predicting Sudden Human Fall Using Health Data

Abstract: We attempt to predict the accidental fall of human beings due to sudden abnormal changes in their health parameters such as blood pressure, heart rate, and sugar level. In medical terminology, this problem is known as Syncope. The primary motivation is to prevent such falls by predicting abnormal changes in these health parameters that might trigger a sudden fall. We apply various machine learning algorithms such as logistic regression, a decision tree classifier, a random forest classifier, K-Nearest Neighbours (KNN), a support vector machine, and a naive Bayes classifier on a relevant dataset and verify our results with the cross-validation method. We observe that the KNN algorithm provides the best accuracy in predicting such a fall. However, the accuracy results of some other algorithms are also very close. Thus, we move one step further and propose an ensemble model, Majority Voting, which aggregates the prediction results of multiple machine learning algorithms and finally indicates the probability of a fall that corresponds to a particular human being. The proposed ensemble algorithm yields 87.42% accuracy, which is greater than the accuracy provided by the KNN algorithm.