Person: Mishra, Rahul
Loading...
Name
Rahul Mishra
Job Title
Email Address
Telephone
Birth Date
Specialization
Search Results
Now showing 1 - 3 of 3
Publication Metadata only Machine Learning-based Interference Mitigation in Long-Range Networks for High-Ceiling Smart Buildings(IEEE, 18-08-2023) Kumar, Ramakant; Gupta, Hari Prabhat; Mishra, Rahul; Pandey, Shubham; DA-IICT, GandhinagarLong-Range networks are increasingly used in smart spaces due to their ability to provide longer communication range while consuming low energy. To facilitate communication among different Long-Range nodes, a gateway is used. For instance, in smart buildings such as airports, railway stations, indoor stadiums, and auditoriums, sensory data from multiple sites are transferred to a base station through a Long-Range gateway. However, when multiple nodes transmit data simultaneously to the gateway, it generates network interference, especially in high-ceiling smart buildings where Long-Range nodes with sensors are attached to monitor the building�s health. In this paper, we present a new method for identifying interfering Long-Range Nodes (LNs) in high-ceiling smart buildings using a classification model. Our approach involves gathering and analyzing network parameters, such as signal-to-noise ratio and received signal strength indicator, from the signals to extract features that the classifier uses for interference classification. The approach categorizes interference based on the number of interfering LNs, with each class representing a distinct number of interfering LNs. We also introduce a push-based mechanism to detect and adjust the power levels of faulty LNs, reducing interference. Our method is cost-effective as it is hardware-independent, making it feasible to implement on the LG platform. Finally, we present a dataset of network interference generated by varying the number of nodes, obstacles, and other parameters. We train the model on the generated dataset and evaluate its effectiveness using a test bed. The experimental results demonstrate that the approach can successfully identify interference nodes in a complex network.Publication Metadata only Huber SVR-Based Hybrid Models for Significant Wave Height Forecasting Using Buoy Sensors(IEEE, 17-11-2023) Anand, Pritam; Jain, Shantanu; Mishra, Rahul; DA-IICT, Gandhinagar; Jain, Shantanu (202011026)Ocean buoy sensors stand out as the most reliable means of recording Significant Wave Height (SWH). However, accurate forecasting of SWH is still challenging in energy production. To circumvent such a challenge, this work introduces a Huber Support Vector Regression (SVR) based wave hybrid model for short-term Significant Wave Height (SWH) forecasting using data collected from the buoy sensors. The model employs three distinct signal techniques, including wavelet decomposition, empirical mode decomposition, and variational mode decomposition, along with particle swarm optimization to fine-tune the parameters of the Huber SVR model. Our extensive experimental analysis encompassed six cases from buoys located at four different geographical regions. We compared the Huber SVR-based wave hybrid models with twelve alternative models incorporating�?�-SVR, LS-SVR, or LSTM models with different decomposition methods. The results of our numerical experiments demonstrate that the Huber SVR-based wave hybrid models yield superior SWH predictions compared to the other existing models.Publication Metadata only A Federated Learning Approach With Imperfect Labels in LoRa-Based Transportation Systems(IEEE, 09-02-2023) Kumar, Ramakant; Mishra, Rahul; Gupta, Hari Prabhat; DA-IICT, GandhinagarIntelligent Transportation System (ITS) helps to improve vehicle health, driver safety, and passenger comfort. Remotely sharing the information of ITS to train the machine and deep learning models hamper data privacy and generate security threats to the passenger, driver, and vehicle owners. Moreover, sharing the information requires huge networking resources such as high data rate, low latency, and low packet loss. Federated learning provides privacy-preserving model training on the vehicle without sharing the information. However, due to poor annotation mechanisms, federated learning may suffer from imperfect labels. This paper proposes a federated learning approach for ITS that can handle imperfect labels in the datasets of the participants. The approach also uses a Long-Range network to provide communication efficient connectivity. The approach initially estimates class-wise centroids of the datasets at the participants and server and then identifies participants with imperfect labels using similarity scores. Such participants demand the fraction of the correctly annotated dataset at the server to improve performance. We further derive the expression for the optimal fraction of the dataset requested by a participant. We finally verify the effectiveness of the proposed approach using the existing model and publicly available dataset.