@hkbk.edu.in
Professor, Dept of Computer Science & Engineering
HKBK college of Engineering
Working as Professor in the Computer Science & Engineering Department, HKBKCE. Motivating and Talented Sociological professor driven to inspire students to pursue academic and personal excellence. Consistently strive to create a challenging and engaging learning in which students become life-long scholar and learner. Deeply invested in achieving tenure through administrative service committee contributions and an accomplishment oriented approach to teaching.
BE., M.Tech., PhD.
Computer Engineering, Artificial Intelligence, Computer Science Applications, Computer Networks and Communications
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Suhas G K, Ashwini Singh S, Trupthi V, Keerthishree P V, Deepak N R, and Loganathan R
IEEE
The car business is changing as a result of recent developments in lithium-ion (Li-ion) storage technology. Fully electric cars (EVs) have the greatest range of autonomy and can operate in a variety of driving and environmental conditions. Stated differently, the same State of Charge (SOC) on two similar model EVs does not always equate to the same distance traveled because other factors affect how well the EVs perform, including the driver's style of behavior, the route, and even the State of Health (SOH) of the battery. The ratio of the battery's rated capacity to its current maximum capacity is known as the state of health, or SOH. It is an essential metric for characterizing the level of deterioration in a battery for a fully electric car. It also acts as a critical reference point for assessing the condition of a retired battery and computing its driving range. Support vector regression is used to estimate the state of health (SOH) of lithium-ion batteries, which is essential for their safe and lifetime-optimized operation.
Kiran M P and Deepak N R
IEEE
Agriculture plays a crucial role for the production of food in Indian regions. Indian regions mainly produces crops like rice, wheat, maize and many other types of crop. It is generally known that, the soil, climate, pesticides, Fertilizers and ground water is influencing the essential factor for enhancing the productivity of any crop. Let us consider soil, which is the key element involved in providing nutrients for proper development and growth of crops. Secondly, climate is also having major role in agriculture as crop growth depends on rainfall, humidity, temperature etc. Thirdly, Pesticides is widely used to control pest and prevents the damage of crops. Fourthly, Fertilizers can improve the quality of crops. Finally, ground water enriches the nutrients in soil. The main goal of this research work is to know about the ways to improve the crop prediction by using data mining techniques, which in turn help the farmers to take better decision. The current study centres around different information mining procedures utilized in various conditions of India and anticipate future harvest along-side reasonable information mining calculation saw during the period(1920-2019). The parameters considered for the examination were soil, atmosphere, water thickness, pesticides and composts and Crop informational collection. The Classification calculations utilized in study were Adaptive boosting classification, Excess tree classification, neural based classification, Multiple Process classification, Decision making classification, K-closest neighbours, Bayesian theory classification, decision Forest classification, support group machine, and Randomized Gradient Classification. The Experimental results show predicted crop, suitable algorithm and algorithm accuracy in that particular state of India respectively.
Thanuja N and Deepak N R
IEEE
In recent years, deep neural network approaches have been generally embraced for AI undertakings, including characterization. Nonetheless, they were demonstrated to be helpless against antagonistic assaults. This research work proposes a GAN based model, another system that utilizes the expressive ability of generative models to protect profound neural organizations against such assaults. Security assaults are getting progressively predominant as digital aggressors abuse framework vulnerabilities for monetary benefit. The digital interruptions imperil our gadgets constantly, they have numerous extreme results, for example, the unapproved divulgement of data, the altering, decimation, and expungement of information. Consequently, unsupervised and viable identification is required to react to these malevolent interruptions against systems and PCs. Many investigations have been finished with both measurable learning strategies and neural networks. Present day arranged frameworks are getting enormous measured and dynamic. Therefore, existing security models experience the ill effects of adaptability issue, where it gets infeasible to utilize them for present day arranged frameworks that contain hundreds and thousands of hosts and vulnerabilities. The objective of this examination is to build up a repeatable procedure to distinguish digital assaults that is quick, exact, and adaptable. The procedure ought to assess various information sources so as to increase a far-reaching image of client action over different frameworks. Client action designs experience typical changes for the duration of the day, and frequently those examples contrast from designs that happen on ends of the week. The model is required to separate between typical changes and anomalous client exercises. A profound learning calculation is utilized to prepare a neural system to distinguish suspicious client exercises.
N. R Deepak and S. Balaji
IEEE
The use of Multiple Inputs Multiple Outputs (MIMO) over the wireless network is increasing rapidly in present years and is expected to be more in future too. The multiple transmit antennas and receive antennas can be introduced in the next generation of wireless network standards for image communication in real time. The image communication has the requirement of large bandwidth. The image data representation requires large information that leads data at high rates and it in turns the high communication energy with distortions in the transmitted image. Various competing MIMO transmission techniques, namely, ODQ, BST, OBST, RO and CO are used to improve the image quality. The paper discussed the few transmission techniques of MIMO for image quality over the 4G wireless network.
Working as Software Engineer for Automation Testing Domain