Kongu Engineering College

About: Kongu Engineering College is a based out in . It is known for research contribution in the topics: Computer science & Cluster analysis. The organization has 2001 authors who have published 1978 publications receiving 16923 citations.

Artificial intelligence in tomato leaf disease detection: a comprehensive review and discussion

Abstract: Accurate and fast tomato plant disease identification is significant to enhance its sustainable agricultural productivity. In the conventional technique, human experts in the field of agriculture have been accommodated to find out the anomalies in tomato plants caused by pests, diseases, climatic conditions, and nutritional deficiencies. Automatic tomato leaf disease identification is initially solved through conventional image processing and machine learning approaches which result in less accuracy. In order to produce greater prediction accuracy, deep learning-based classification is introduced. This paper provides an overall review of recent work performed in the field of tomato leaf disease identification using image processing, machine learning, and deep learning approaches. And also discuss both public and private datasets available to detect tomato leaf disease, methods employed, and adopted deep learning frameworks. Consequently, suggestions are provided to figure out the appropriate techniques in order to obtain the better prediction accuracy. Finally, the challenges encountered in implementing the machine learning and deep learning models are discussed.

A comprehensive model to prioritise lean tools for manufacturing industries: a fuzzy FMEA, AHP and QFD-based approach

Abstract: This paper describes a start-to-end lean tools (LTs) selection model for manufacturing industries. The integrated model utilises value stream mapping (VSM) and plant layout for identifying wastes from current state of the organisation. For prioritising the wastes along with associated risks, failure mode and effects analysis (FMEA) is adopted. Selection of LTs is done using analytic hierarchy process (AHP) and house of quality (HoQ). This model utilises fuzzy logic (FL) to convert the linguistic judgements into numerical values for computation. Future state map deployed with the shortlisted LTs is developed to compare current and future states. The model is applied in PVC pipe manufacturing industry and the results show notable improvements. The raw material saving of 2.5 kg, 3% reduction of value added time, 7% reduction of non-value added time and 5% reduction of lead time in the production of PVC pipes per batch are obtained in future state.

A novel approach for Human Computer Interface based on eye movements for disabled people

Abstract: Several researches have been carried out in recent years for developing Human Computer Interface (HCI) Human Computer Interface as an assistive technology helps the people with motor disabilities and who can't move their arms Eye tracking techniques can be used for the communication of these people In this paper, image based eye tracking technique is used for interaction The aim of this paper is to help the disabled people to use the computer efficiently It is based on con-trolling cursor movements on the screen using only the eyes The system proposed in this paper uses a low resolution webcam which is attached to a wearable glass frame, for eye tracking The images obtained from the webcam are processed to locate the iris center This is used to estimate the eye gaze The cursor is moved in the desired direction on the screen based on the estimated eye gaze The selection of the tabs is also carried out by blinking The proposed system shows good performance in good lighting conditions

A method for broken bar fault diagnosis in three phase induction motor drive system using Artificial Neural Networks

Abstract: This paper presents a high accuracy detection of Broken Rotor Bar (BRB) fault by Artificial Neural Network (ANN) through advanced signal processing tool as Hilbert Transform (HT) where three phase ...

Implementation of Energy Management Structure for Street Lighting Systems

Abstract: This work aims to develop an Energy efficient and low cost solution for street lighting system using Global System for Mobile communication [GSM] and General Packet Radio Service [GPRS]. GSM and GPRS are used to establish a communication between the streetlights and the Central Monitoring Station [CMS] at the operator side. The whole setup provides the remote operator to turn off the lights when not required, regulate the voltage supplied to the streetlights and prepare daily reports on glowing hours. Power shut downs also can be intimated to the remote CMS operator through GSM and GPRS communication setup. The energy meter placed at the lighting system sends the readings to the remote CMS in the form of short message [SMS]. From the data collected at CMS, energy report is prepared using visual basic programming.