Compleated and Ongoing Projects
Design of Reliable and Energy Efficient Transport Layer Protocol for Wireless Sensor Networks
Sponsored by: Department of Science and Technology, Government of India
The overall objective of this project is to design reliable and energy efficient transport layer protocol for ad-hoc and sensor network. a. We proposed an enhanced protocol for channel reservation to reduce packet drops using cross layer approach. It shares information between transport layer and data link layer. Especially, availability of buffer space is considered prior to sending the confirmation message (CTS) to sender node. BA-MAC is recommended for dense wireless networks where most of the nodes face congestion and drop packets due to buffer overwhelming. This protocol achieves 2.81 % improvement in energy consumption. Also, it reduces packet drop rate by 14.6 %. Thus BA-MAC enriches efficiency of the network by 15 % (approximately) as compared to default MAC layer protocols.
AI/ML-Driven Intrusion Detection Framework for IoT Enabled Cold Storage Monitoring
Sponsored by: Data Security Council of India (DSCI) | A NASSCOM Initiative
An IoT-based monitoring system remotely controls and manages intelligent environments. Sensors in the monitoring system communicate themselves and transmit data over wireless communication. A node (insider or outsider) is in the communication range; then, it can send data to sensors of the deployed monitoring system. Due to such nature, it is more vulnerable to intrusions or attacks. An intrusion detection system is an efficient mechanism to detect malicious traffics and prevents abnormal activities. This work suggests an intrusion detection framework for the cold storage monitoring system. In this, the temperature affects the environment and harms stored products. A malicious node work as a false data injection attack that manipulates temperature and forwards manipulated data; whenever a flooding attack disturbs the existing network. However, single parameter analysis (or threshold) based detection mechanism is not shown an efficient detection rate (67.33%). To handle these attacks, we have generated and collected a dataset for training the intrusion detection system. Then, we have applied the supervised learning (Bayesian Rough Set) and unsupervised intrusion detection (micro-clustering) techniques. These intrusion detection methods perform better and show high performance. Moreover, this work also provides the comparative analysis of the generated dataset to different behavior IDS datasets.
Solar Powered Industrial Unmanned Aerial Vehicle (UAV) for Surveying and Seed Dropping.
Sponsored by: Ministry of Micro, Small and Medium Enterprises, Government of India
Since 2012, more than 3.0 billion USD has been invested in drone companies worldwide and 2018 was a record year with 702 million USD in disclosed global investments. India is the fastest-growing drone market in the world, having increased in size exponentially since the legalization of drones in 2018. According to 6Wresearch, the Indian drones market is poised to grow at a CAGR of 18 during 2017–23 in terms of revenue. Although these numbers will continue to be led by the long range UAV segment, medium and mini-drones are also poised to register healthy growth. Data provided by the Stockholm International Peace Research Institute (SIPRI) indicates that with 22.5% of the world’s drone imports, India tops the list of drone-importing nations. According to study conducted by BIS Research, it is predicted that the market for commercial end-use of drones might supersede the military market by 2021, cumulatively hitting approximately 900 million USD. In this project we have attempted to develop IoT based digital Twin framework for predictive maintenance of UAV. Another objective is to integrate solar powered energy harvesting module on UAV in such a manner that the tradeoff between weigh and power consumption of the entire design can be balanced. We are experimenting with the-state-of-the art AI & machine learning technique to develop a solution that increases the lifetime and energy efficiency of the industrial UAV system.
Interoperability Issues in Fog-Cloud Infrastructure for IoT Applications
Sponsored by: Science and Engineering Research Board, Government of India \
A Retrospective Review on Trend in the Shift of Crop Plantation Index With the Change in Climatic Conditions
Sponsored by: Agro glean system (AGS), Enterprise, India
Advanced technology in agriculture can help to know about suitable environmental conditions, soil health status, water and fertilizer requirements, and crop monitoring at every plant growth stage, resulting in higher yield. In the past few decades, many countries have witnessed different rain and temperature patterns due to change in environmental conditions. The plantation schedule imparts mark-able effects on the crop yield. The correct and well-planned schedule can result in getting maximum productivity with limited resources. The work under this project presents rule-based fuzzy classification method, for predicting the sowing fuzziness based on environmental conditions. The proposed study is a three-step procedure that identifies the sowing time of Cotton, Maize, and Groundnut. First, the knowledge and rule base of the fuzzy inference system is designed. In the second step rule base of the fuzzy inference system is optimized using multi-objective evolutionary algorithm NSGA-II, which helps maximize the accuracy and minimize the number of fuzzy rules taken for classification. Finally, the fuzziness of crop sowing in different slots is determined. Set of solutions in NSGA-II are validated through a cross-validation approach. Further, the fuzziness of the sowing slot of Cotton, Maize, and Groundnut is correlated to yield in a given year to measure the model’s effectiveness.