Browsing by Author "Bhowmik, B.R."
Now showing 1 - 9 of 9
- Results Per Page
- Sort Options
Item Item An IoT-Enabled Stress Detection Scheme Using Facial Expression(Institute of Electrical and Electronics Engineers Inc., 2022) Angalakuditi, A.; Bhowmik, B.R.Depression is a significant problem in our society, as it is the cause of many health problems. The ongoing burden of intellectual function and continuous technological development, leading to constant change and the need for flexibility, makes the situation even more significant for people. It is necessary to see it early to prevent stress from becoming chronic and irreversible irritability. Unfortunately, a way to detect automatic, continuous, invisible pressure does not exist. This work involves monitoring a person's attention and emotional state across the ages. An IoT-enabled unobtrusive real-time monitoring system is developed to detect the person's emotional states by analyzing facial expression videos. The proposed method identifies individual emotions in each video frame, and a decision on the level of stress is made at the sequence level. © 2022 IEEE.Item ANN-Based Performance Prediction in MoCs(Springer Science and Business Media Deutschland GmbH, 2022) Bhowmik, B.R.Due to high integration density and technology scaling, the manycore networks-on-chip (NoCs) often experience higher evaluation time by traditional simulations for a set of common performance characteristics. Artificial intelligence (AI) is being employed as an altered solution over the simulation-based performance evaluation. However, many AI techniques’ accuracy and estimation time are low and high. This paper proposes an artificial neural network (ANN) based framework to quickly and more accurately evaluate mesh-based NoCs (MoCs). Experiments show that the essential performance metrics latency, throughput, and energy consumption are 16.53–40.76 cycles, 7.63–76.46 × 10 - 3 flits/cycle/IP, and 1417–1625 μ J, respectively. The proposed ANN framework achieves an accuracy of up to 96%. It is around 50% more compared to many previous works. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Automated Detection of Maize Leaf Diseases in Agricultural Cyber-Physical Systems(Institute of Electrical and Electronics Engineers Inc., 2022) Verma, A.; Bhowmik, B.R.Agricultural cyber-physical systems (ACPS) are an ever-increasing sector that affects the quality and quantity of agricultural products as the population increases rapidly. Maize, also known as 'corn,' is one of the world's old food crops, consumed every part of Bharat with 1.4 billion masses across the globe. But a disease, whether on seeds, leaves, or other parts of a crop plant, poses a significant risk to food security. For example, a Maize leaf experiences three diseases-blight, common rust, and gray leaf spot. Early detection and correct identification of these diseases can help restrict the spread of infection and ensure crop quality for long-Term health. This paper proposes a deep convolutional neural network (DCNN) framework for Maize leaves named "MDCNN"that detects these diseases. The proposed MDCNN model undergoes training and is tuned to detect four prevalent classes of the conditions. The proposed model exercises a voluminous dataset of the diseases. Experimental results demonstrate that the proposed model achieves a training and test accuracy up to 95.51% and 99.54%, respectively. Furthermore, it outperforms many existing methods and delivers a superior disease control solution for Maize leaf diseases. © 2022 IEEE.Item DeCS: A Deep Neural Network Framework for Cold Start Problem in Recommender Systems(Institute of Electrical and Electronics Engineers Inc., 2022) Mondal, R.; Bhowmik, B.R.With the exponential growth of e-commerce platforms, recommendation systems are widely used in predicting user interests, improving user experience, and increasing the number of sales. However, recommendation performance degrades for users who have very little interaction or new users who have never opted for the service. Consequently, the recommender systems cannot suggest items and services to these users due to the cold start issue. Naturally, a compelling demand for an efficient recommender system is essentially needed to guide users toward items of their interests. This paper proposes a deep neural network (DNN) framework that addresses the cold start problem in recommendation systems. The proposed framework named 'DeCS' works primarily in stages that involve creating embeddings and vectors followed by training and prediction of three fundamental metrics-mean square error (MSE), mean absolute error (MAE), and root MSE (RMSE) by the framework. Several experiments evaluate the DeCS framework for different recommender metrics at various datasets. Predictions show that the proposed DeCS model achieves the MSE, RMSE, and MAE metrics in the range of 0.4338-1.2911, 0.6883-1.1362, and 0.4691-0.8745, respectively. Further, the result shows that the proposed approach improves these metrics by 15.81% compared to many state-of-the-art methods. © 2022 IEEE.Item Hybrid MoCs for Long-Distance On-Chip Communications(Institute of Electrical and Electronics Engineers Inc., 2022) Karali, A.; Bhowmik, B.R.The contemporary networks-on-chip (NoCs) are becoming a viable on-chip communication architecture to serve the demand of high-performance requirements of multicore platforms. Mesh-based NoCs (MoCs) that provide efficient, interconnected infrastructures are popularly accepted as the scalable medium to the requirements. However, the MoCs fall short of meeting the stringent system requirements while the network size increases and resulting in the issue of long-distance communications. This paper presents altering a traditional MoC to corresponding Hybrid architecture that addresses the problem and provides improved performance. The proposed scheme transforms an MoC with a few wireless routers to handle the long-distance communication in MoCs. Evaluation of the proposed method on a 32-bit 8× 8 Hybrid MoC shows that the network achieves latency as of 30167.897 cycles, network throughput of 12.8824 flits/cycle, and energy consumption as of 29.9182\ μJ, respectively. Compared to the traditional 8× 8 MoC, the proposed Hybrid architecture improves packet loss, latency, and throughput metrics up to 96%, 98.36%, and 25.77%, respectively. This achievement is about 8× faster than many existing approaches. © 2022 IEEE.Item IoT-Enabled Driver Drowsiness Detection Using Machine Learning(Institute of Electrical and Electronics Engineers Inc., 2022) Guria, M.; Bhowmik, B.R.The most important procedure for preventing traffic accidents in recent years, maybe on a global scale, is the identification of sleepy drivers. Every day, over 350 people are killed in traffic accidents, and almost 1,000 more suffer injuries. Recent technological advancements could reduce this tendency by 40%. It is still possible to get these benefits despite significant challenges. This paper develops an intelligent alerting method to prevent accidents caused by drivers falling asleep at the wheel. As part of smart cars, the proposed method with the total capacity prevents sleepy driver impairment automatically. The proposed approach detects drowsiness in analyzing the live streaming of drivers' videos. Eye Aspect Ratio (EAR) and the Euclidean distance of the eye are used to analyze the input video stream to identify sleepy drivers. Experimental results show that the proposed scheme can lower dangerous accidents and injuries caused by road traffic. © 2022 IEEE.Item QuSAF: A Fast ATPG for SAFs in VLSI Circuits Using a Quantum Computing Algorithm(Institute of Electrical and Electronics Engineers Inc., 2022) Manjunath, T.D.; Bhowmik, B.R.The gate count in semiconductor chips is overgrowing. On the contrary, the feature size of the chip is continuously decreasing, resulting in higher design complexity. Consequently, circuit components in chips are exposed to various faults. A stuck-at fault is mostly addressed in circuits. We need good test patterns that trigger the defects to test the stuck-at marks. In large combinational circuits, the search space for test patterns grows exponentially with the number of inputs. Therefore an efficient test pattern generation technique is needed. An ATPG method discussed in the literature provides a time complexity of O(n) or more with the search space size n. This paper presents a fast ATPG technique named "QuSAF"that employs a Quantum Computing algorithm (QCA). The proposed QuSAF technique converts ATPG into Boolean Satisfiability (SAT) and then solves the resultant SAT expression using Grover's Search Algorithm (GSA). The proposed approach generates the test patterns for a circuit by O(√n) time. Experiments are performed with various basic logic gates to show the effectiveness of the proposed technique. © 2022 IEEE.Item Sixer: A low-overhead, fully-distributed test scheme with guaranteed delivery of packets in networks-on-chip(Elsevier Ltd, 2023) Bhowmik, B.R.The guaranteed delivery of application packets from source to destination in a network-on-chip (NoC) is increasingly becoming an essential design issue. Channel faults may cause a significant amount of packet loss and subsequently degrade the system's performance. In particular, open-channel defects threaten the loss of reliability, yield, and service quality. Hence, their detection and localization during the system's runtime are highly needed. However, coexistent short-channel faults might mitigate the threats to a certain extent. This paper presents a low-cost test method that detects open-channel faults to preserve the connectivity between a source and destination pair in NoCs. The procedure is extended to address the channel's self-repairing mode by covering the short-channel defects via fault masking. Further, a fully distributed test-scheduling technique named “Sixer” is presented to reduce the test cost and make the scheme scalable with NoCs. Experimental results show hardware synthesis incurs nearly 6.72% and 21.85% area overhead while single and multiple channel-fault models are assumed, respectively. The test method takes 8 and 38 clocks for the same fault models. Also, fault simulation shows full and (nearly 95%) fault coverage for these models. Online evaluation of the “Sixer” reveals various performance metrics. A detailed comparison study shows the proposed scheme improves hardware area and test-time overhead up to 66.12% and 97%, respectively. Simultaneously, performance overhead is improved by 43.78%, 54.75%, and 62.97% concerning packet loss, latency, and energy consumption, respectively. © 2023 Elsevier Ltd