1 October 2019 in International Journal of Electrical and Computer Engineering (IJECE)
SSSathish Kumar Selvaperumal
Sathish Kumar Selvaperumal
The emergence of many internet industries ushers in IOT era, and about to bring us to the point of universal connectivity. In the field of education, the IOT technology has a broad applicable prospect for a more interactive and intelligent way by improving the quality of teaching and management. The proposed class affair management system is mean to enrich the interaction between lecturers and students which in an efficient and smart way. Based on the existing model, a layered architecture is proposed to build the beacon based campus management system. Backend device and protocols compose the physical layer to collect the raw data from physical objects. Data link layer and control layer are responsible for forming required package and sending to corresponding layer. Beacon technology used for proposed design applies Bluetooth low energy 4.0 standard which allowing devices exchange data through Bluetooth at an extremely low power consumption-using a single coin cell battery can last for several years. Saved up to 97 percentage energy compared with similar system. The entire proposed platform allows participants to bring personally owned devices to access campus management system. Through location information, teaching activities and personalized information notification can be automatically accomplished, which will inspire the innovation and development of classroom teaching mode. Beacon technology has a great potential that can be completely transplanted into other scenario such as the hypermarket and library.
31 December 2019 in Journal of Advanced Research in Dynamical and Control Systems
SSSathish Kumar Selvaperumal
Sathish Kumar Selvaperumal
1 August 2022 in International Journal of Electrical and Computer Engineering (IJECE)
Falls have long been one of the most serious threats to elderly people's health. Detecting falls in real-time can reduce the time the elderly remains on the floor after a fall, hence avoiding fall-related medical conditions. Recently, the fall detection problem has been extensively researched. However, the fall detection systems that use a traditional internet of things (IoT) architecture have some limitations such as latency, high power consumption, and poor performance in areas with unstable internet. This paper intends to show the efficacy of detecting falls in a resource-constrained microcontroller at the edge of the network using a wearable accelerometer. Since the hardware resources of microcontrollers are limited, a lightweight fall detection deep learning model was developed to be deployed on a microcontroller with only a few kilobytes of memory. The microcontroller was installed in a low-power wide-area network based on long range (LoRa) communication technology. Through comparative testing of different lightweight neural networks and traditional machine learning algorithms, the convolutional neural network (CNN) has been shown to be the most suited, with 95.55% accuracy. The CNN model reached inference times lower than 37.84 ms with 61.084 kilobytes storage requirements, which implies the capability to detect fall event in real-time in low-power microcontrollers.
1 June 2018 in International Journal of Electrical and Computer Engineering (IJECE)
This papaer entitled electronic toll collection system based on Radio Frequncy Identification System explained in detail based on current issue at toll collection system. There are some obstacles faced every day where the users spent their valuable time in queue at tollgate due to traffic congestion as well as using traditional manual method in most existing toll ETC system to collect toll from road users. Besides that, the barrier design where each vehicle stop waiting until barrier lift which consider source of time delay. To tackle stated problems, an electronic toll collection system is proposed which based on RFID technology. The integrated system consists of two main sections, electronic sides where all input data received from while database management office is where all necessary information stored. To compare the current ETC system, in this research elaborated internet of things where all data transmit through cloud and then to the main office in real time. Not only that, there is some enhancement based on barrier design where, gate is remained open for all vehicles with sufficient tags without requiring to stop to eliminate time delay.By check system throughput compare to existing toll systems, various tests have been carried out in different method where proposed system throughput much higher percentage the current system.
1 February 2024 in International Journal of Electrical and Computer Engineering (IJECE)
This paper describes an implementation of a deep learning-based predictive maintenance (PdM) system for industrial rotational machinery, built upon the foundation of a long short-term memory (LSTM) autoencoder and regression analysis. The autoencoder identifies anomalous patterns, while the latter, based on the autoencoder’s output, estimates the machine’s remaining useful life (RUL). Unlike prior PdM systems dependent on labelled historical data, the developed system doesn’t require it as it’s based on an unsupervised deep learning model, enhancing its adaptability. The paper also explores a robust condition monitoring system that collects machine operational data, including vibration and current parameters, and transmits them to a database via a Bluetooth low energy (BLE) network. Additionally, the study demonstrates the integration of this PdM system within a web-based framework, promoting its adoption across various industrial settings. Tests confirm the system's ability to accurately identify faults, highlighting its potential to reduce unexpected downtime and enhance machinery reliability.