Browsing by Author "Kamath, A.K."

Now showing 1 - 4 of 4

Achieving Guaranteed Performance for Protection Traffic in Smart Grid Wide-Area Networks
(2019) Adrah, C.M.; Kamath, A.K.; Bjornstad, S.; Tahiliani, M.P.
Recent years, tele-protection applications in utility grids have been deployed using Ethernet. However, Ethernet without Time Sensitive Network (TSN) mechanisms is nondeterministic. Hence, challenges of the queuing delays occurring on multi-hop paths result in Packet Delay Variations (PDV) and may even result in packet losses due to buffer overflows. There have been recommendations to use Priority Scheduling (PS) to lower the latency of tele-protection messages. However, for PS, maximum PDV occurs on higher priority packets when contending with lower priority packets, needing to wait until a lower priority packet with maximum length have exited a switch. In this paper, we explore through a performance simulation study the suitability of applying FUSION in smart grid tele-protection applications. FUSION is a packet switched principle applying Ethernet, offering circuit-switched quality of service with deterministic latency, zero packet loss and ultra-low PDV for high priority packets. We demonstrate FUSION performance in tele-protection for power system networks, and compare it with Strict Priority Queuing (SPQ), which is recommended for realtime industrial applications. Our results show that by applying FUSION, we are able to guarantee a fixed delay, zero PDV and packet loss through the network. Furthermore, we show that through proper network dimensioning, lower priority traffic can additionally be added with delays within acceptable limits. � 2019 IEEE.
Achieving Guaranteed Performance for Protection Traffic in Smart Grid Wide-Area Networks
(Institute of Electrical and Electronics Engineers Inc., 2019) Adrah, C.M.; Kamath, A.K.; BjoÌŠrnstad, S.; Tahiliani, M.P.
Recent years, tele-protection applications in utility grids have been deployed using Ethernet. However, Ethernet without Time Sensitive Network (TSN) mechanisms is nondeterministic. Hence, challenges of the queuing delays occurring on multi-hop paths result in Packet Delay Variations (PDV) and may even result in packet losses due to buffer overflows. There have been recommendations to use Priority Scheduling (PS) to lower the latency of tele-protection messages. However, for PS, maximum PDV occurs on higher priority packets when contending with lower priority packets, needing to wait until a lower priority packet with maximum length have exited a switch. In this paper, we explore through a performance simulation study the suitability of applying FUSION in smart grid tele-protection applications. FUSION is a packet switched principle applying Ethernet, offering circuit-switched quality of service with deterministic latency, zero packet loss and ultra-low PDV for high priority packets. We demonstrate FUSION performance in tele-protection for power system networks, and compare it with Strict Priority Queuing (SPQ), which is recommended for realtime industrial applications. Our results show that by applying FUSION, we are able to guarantee a fixed delay, zero PDV and packet loss through the network. Furthermore, we show that through proper network dimensioning, lower priority traffic can additionally be added with delays within acceptable limits. Â© 2019 IEEE.
Sobriety Testing Based on Thermal Infrared Images Using Convolutional Neural Networks
(2019) Kamath, A.K.; Karthik, A.T.; Monis, L.; Mulimani, M.; Koolagudi, S.G.
This paper proposes a method to test the sobriety of an individual using infrared images of the persons eyes, face, hand, and facial profile. The database we used consisted of images of forty different individuals. The process is broken down into two main stages. In the first stage, the data set was divided according to body part and each one was run through its own Convolutional Neural Network (CNN). We then tested the resulting network against a validation data set. The results obtained gave us an indication of which body parts were better suited for identifying signs of drunken state and sobriety. In the second stage, we took the weights of CNN giving best validation accuracy from the first stage. We then grouped the body parts according to the person they belong to. The body parts were fed together into a CNN using the weights obtained in the first stage. The result for each body part was passed to a simple back-propagation neural network (BPNN) to get final results. We tried to identify the most optimal configuration of neural networks for each stage of the process. The results we obtained showed that facial profile images tend to give very good indications of sobriety. The results also showed that combining the results of multiple body parts using a simple BPNN gives a higher accuracy than that of individual ones. � 2018 IEEE.
Sobriety Testing Based on Thermal Infrared Images Using Convolutional Neural Networks
(Institute of Electrical and Electronics Engineers Inc., 2018) Kamath, A.K.; Karthik, A.T.; Monis, L.; Mulimani, M.; Koolagudi, S.G.
This paper proposes a method to test the sobriety of an individual using infrared images of the persons eyes, face, hand, and facial profile. The database we used consisted of images of forty different individuals. The process is broken down into two main stages. In the first stage, the data set was divided according to body part and each one was run through its own Convolutional Neural Network (CNN). We then tested the resulting network against a validation data set. The results obtained gave us an indication of which body parts were better suited for identifying signs of drunken state and sobriety. In the second stage, we took the weights of CNN giving best validation accuracy from the first stage. We then grouped the body parts according to the person they belong to. The body parts were fed together into a CNN using the weights obtained in the first stage. The result for each body part was passed to a simple back-propagation neural network (BPNN) to get final results. We tried to identify the most optimal configuration of neural networks for each stage of the process. The results we obtained showed that facial profile images tend to give very good indications of sobriety. The results also showed that combining the results of multiple body parts using a simple BPNN gives a higher accuracy than that of individual ones. Â© 2018 IEEE.