Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
8 results
Search Results
Item Analysis and Prediction of Fantasy Cricket Contest Winners Using Machine Learning Techniques(Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2021) Karthik, K.; S. Krishnan, G.S.; Shetty, S.; Bankapur, S.; Kolkar, R.; Ashwin, T.S.; Vanahalli, M.K.Cricket is one of the well-known sports across the world. The increasing interest of cricket in recent years resulted in different forms like T20, T10 from test and one day format. The craze of all these formats of cricket matches today has come into online fantasy cricket league games. Dream11 is one such app that is most popular in this context, along with many similar apps. Creating a dream team of 11 players from playing 11 of both teams involves skills, ideas and luck. Predicting a winner among all the joined contestants based on the previous historical data is a challenging task. In this paper, we used a feed-forward deep neural network (DNN) classifier for predicting the winning contestant for the top three positions in a fantasy league cricket contest. The performance of the DNN approach was compared against that of state-of-the-art machine learning approaches like k-nearest neighbours (KNN), logistic regression (LR), Naive Bayes (NB), random forest (RF), support vector machines (SVM) and in predicting the fantasy cricket contest winners. Among the methods used, DNN showed the best results for all three positions, showing its consistency in predicting the winners and outperforms the state-of-the-art machine learning classifiers by 13%, 8% and 9%, respectively, for first, second and third winning positions, respectively. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Human Activity Recognition in Smart Home using Deep Learning Techniques(Institute of Electrical and Electronics Engineers Inc., 2021) Kolkar, R.; Geetha, V.To understand the human activities and anticipate his intentions Human Activity Recognition(HAR) research is rapidly developing in tandem with the widespread availability of sensors. Various applications like elderly care and health monitoring systems in smart homes use smartphones and wearable devices. This paper proposes an effective HAR framework that uses deep learning methodology like Convolution Neural Networks(CNN), variations of LSTM(Long Short term Memory) and Gated Recurrent Units(GRU) Networks to recognize the activities based on smartphone sensors. The hybrid use of CNN-LSTM eliminates the handcrafted feature engineering and uses spatial and temporal data deep. The experiments are carried on UCI HAR and WISDM data sets, and the comparison results are obtained. The result shows a better 96.83 % and 98.00% for the UCI-HAR and WISDM datasets, respectively. © 2021 IEEE.Item IoT-based Human Activity Recognition Models based on CNN, LSTM and GRU(Institute of Electrical and Electronics Engineers Inc., 2022) Kolkar, R.; Singh Tomar, R.P.; Vasantha, G.Smartphones' ability to generate data with their inbuilt sensors has made them used for Human Activity Recognition. The work highlights the importance of Human Activity Recognition (HAR) systems capable of sensing human activities like the inertial motion of a human body. The sensors are worn on a body part and tracked from whole-body motions and monitoring. Real-time signal processing is used to sense human body movements using wearable sensors. The work aims to provide opportunities for promising health applications using IoT. There are many challenges to recognising human activities, including accuracy. This work analyses Human Activity recognition concerning CNN, LSTM, and GRU deep learning models to improve the accuracy of the human activity recognition in the UCI-HAR and WISDM datasets. The comparative analysis shows promising results for Human activity recognition. © 2022 IEEE.Item Online Video Stabilization using Mesh Flow with Minimum Latency(Institute of Electrical and Electronics Engineers Inc., 2023) Devaguptam, D.; Thanmai, K.; Raj, L.S.; Naik, D.; Kolkar, R.Most existing video stabilization techniques are used for post-processing, where previously recorded videos are given to the model to obtain stabilized versions. Online video stabilization usually relies on sensors like gyroscopes or assumes constant motion, which is not suitable for videos with changing motions. This work introduces a video stabilization technique with just one-frame latency. The algorithm operates at the spatial level in the infrequent domain, tracking the motion of mesh vertices. Motion tracks of feature marks are combined with the nearest mesh vertex using two median gauges, assigning each vertex a smooth motion track. The proposed approach, called anticipated foster track leveling, smoothes the motion profiles by utilizing previous motions and adapting accordingly for smoother results. This method can handle changes in movement in space and time and works in real-time, allowing applications in security systems, robotics, and unmanned aerial vehicles (UAVs). When evaluated against other models, MeshFlow gives an overall good performance in all comparison metrics evaluated. Hence MeshFlow can be used as a reliable low-latency technique for real-time video stabilization in remote devices. © 2023 IEEE.Item Single Person Occupancy Detection Using PIR Sensors(Springer Science and Business Media Deutschland GmbH, 2024) Kolkar, R.; Geetha, V.; Salvi, S.The occupancy detection system presented in this study utilizes a combination of two PIR sensors and a micro-controller board to detect and store occupancy information in different rooms accurately. The PIR sensors detect motion within their field of view while the micro-controller processes the sensor inputs and controls the storage of occupancy data in a memory device. The circuit provides real-time occupancy status updates and allows for data retrieval for further analysis. The setup offers significant advantages such as energy efficiency, simplicity, and cost-effectiveness. The experimental results demonstrate the system's effectiveness in accurately detecting and storing occupancy information. The results show the elderly spend time in various rooms. The combined circuit has potential applications in various domains, including smart homes, energy management, and security systems, where knowledge of room occupancy patterns is crucial for optimizing resources and enhancing user experiences. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Item Li-Fi for Secured Access to Wireless Network During Online Examination in Classrooms(Springer Science and Business Media Deutschland GmbH, 2024) Salvi, S.; Apune, S.; Gutte, V.; Gawade, M.; Kolkar, R.The traditional conduction of examinations needs to use physical copies of question paper and answer sheets, which are then evaluated by the evaluators. However, in a post-pandemic era, where the emphasis is more on the minimal usage of physically transferable materials, safe conduction of examinations in the classroom environments becomes challenging. Conduction of examination in complete online mode requires wireless access to the Wi-Fi access points; however, as the range of the Wi-Fi access point goes beyond the classrooms, there is the possibility of accessing the network from outside classroom which is not desired. With an aim to address these issues, in this paper a novel approach for providing dynamically changing passwords using visible light communication is designed, implemented and tested for connecting to the wireless network. The setup is useful in the environment where restricted physical access is needed to ensure system and network security. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.Item Human Activity Behavioural Pattern Recognition in Smart Home with Long-Hour Data Collection(Springer, 2023) Kolkar, R.; Geetha, V.The research on human activity recognition has provided novel solutions to many applications like health care, sports, and user profiling. Considering the complex nature of human activities, it is still challenging even after effective and efficient sensors are available. The existing works on human activity recognition using smartphone sensors focus on recognizing basic human activities like sitting, sleeping, standing, stair up and down, and running. However, more than these basic activities is needed to analyse human behavioural pattern. The proposed framework recognizes basic human activities using deep learning models. Also, ambient sensors like PIR, pressure sensors, and smartphone-based sensors like accelerometers and gyroscopes are combined to make it hybrid sensor-based human activity recognition. The hybrid approach helped derive more activities than the basic ones, which also helped derive human activity patterns or user profiling. User profiling provides sufficient information to identify daily living activity patterns and predict whether any anomaly exists. The framework provides the base for applications such as elderly monitoring when they are alone at home. The GRU model’s accuracy 95% is observed to recognize the basic activities. Finally, Human activity patterns over time are recognized based on the duration and frequency of the activities. It is observed that human activity pattern, like morning walking duration, varies depending on the day of the week. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.Item Human activity recognition using deep learning techniques with spider monkey optimization(Springer, 2023) Kolkar, R.; V, G.The human activity recognition (HAR) system recognizes human actions in daily life. There is a need for HAR to build a smart home and an intelligent healthcare environment. HAR is challenging, considering the complexity and heterogeneity of sensors used to recognize it. Deep learning models are the one area where the researcher applies to recognize the activities. However, effective feature engineering and optimization methods help improve the recognition model’s performance. In this work, Spider Monkey Optimization is applied for training the deep neural network. UCI HAR, WISDM, KTH action and PAMAP2 datasets are used to evaluate the proposed system. The dataset has the activities like walking, standing, lying, jogging, stair-up and stair-down activities. Here, the spider monkey model’s fitness function is initialized in the hidden layer of the Recurrent Neural Network to enhance accuracy and precision. The experiment results show improvements in performance as compared to other state-of-the-art methods like DL-Q, End to End DNN and SVM. With various assessments and experimentation, it is observed that the proposed SMO-based performs better in terms of accuracy of 98.92%, precision of 98.12%, recall of 98.9%, and F1-score 95.90%, respectively for the WISDM dataset. There is an improvement in performances for other datasets. Also, the Error rate has reduced to 2.8% as compared to other state-of-the-art methods. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.