Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
4 results
Search Results
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 A USER AUTHENTICATION AND ACCESS CONTROL SCHEME FOR IoT-BASED HEALTHCARE USING BLOCKCHAIN(Institute of Electrical and Electronics Engineers Inc., 2021) Geetha, V.; Balakrishnan, B.IoT devices do not possess the potential to protect themselves from risk of the attackers as they are resource-constrained. Blockchain is arising as a decentralized and distributed technology with proficiency in delivering secure management, access control and user authentication for protecting data and services of IoT devices, guaranteeing integrity, confidentiality and availability. IoT-based healthcare applications has many benefits like reduced cost of healthcare, improved quality, remote monitoring of patients etc. Ensuring a robust and secure interactions between patient and healthcare providers is very important to protect sensitive medical data. A distributed and reliable user authentication and access control scheme to be used in IoT based Healthcare is designed and implemented here with the help of local gateways directly interfaced to smart contract based Ethereum Blockchain. The local gateways can manage multiple local IoT devices and improve scalability. This reduces the overhead of performing resource-consuming authentication tasks and blockchain-communication at the IoT devices. To exhibit the working of the framework, a case study is presented with two laptops and a Raspberry Pi. © 2021 IEEE.Item Deployment of Computer Vision Application on Edge Platform(Institute of Electrical and Electronics Engineers Inc., 2021) Geetha, V.; Kiran, C.; Sharma, M.; Rakshith Kumar, J.In our work, we propose a low cost device which will aid visually impaired people to understand what is in their surroundings without the requirement of internet. Current technology makes use of Cloud Architecture and would require internet to achieve this purpose. But these systems will not work in areas with poor internet connectivity. Edge platform built on Raspberry Pi powered with Intel Neural Compute Stick is used by us for this purpose. Multi Label Image Classification Deep Learning Model is trained in the cloud. It is later optimised and deployed on Edge Device which is Raspberry Pi. Setup also consists of PiCamera which will record the video and give it as input to deployed model. Model will describe the items present in video, basically describing the surroundings. The output is in the form of audio which is played through speakers, thus enabling visually impaired people to understand their surroundings without the requirement of internet. Deployment of popular Machine Learning and Deep Learning Models is also examined in the edge device and a comprehensive performance evaluation is performed. © 2021 IEEE.Item Software Based Solution for Efficient Energy Utilization of an IoT Node PSoC6-Dual Core Using a Scheduler(Institute of Electrical and Electronics Engineers Inc., 2022) Geetha, V.; Shrinidhi, M.Embedded systems are an integral part of today's time with a wide range of specific applications. Increasing design requirements has emphasized the need to focus on sectors such as power consumption, flexibility, cost, performance, and robustness. Power consumption is the major issue in embedded systems that needs to be addressed to sustain long term functionality of the devices. PSoC 6 MCU is a System-on-chip, specifically designed for Internet of Things with enhanced computation and communication capabilities. However, the task to be executed on dual core need scheduling to further improve on energy efficiency. This work proposes a solution based on queuing techniques for task scheduling based on complexity of the job. © 2022 IEEE.