Kongu Engineering College

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

Visual attention-based leukocyte image segmentation using extreme learning machine

Abstract: The existence of computer aided automatic analysis came to light over a century ago and yet the acquisition of visual attention-based segmentation is still in its infancy despite mammoth advances in clinical leukocyte analysis, advanced neurocomputing and fast growing engineering technology. This paper presents a framework for novel segmentation model for leukocyte images using extreme learning machine ELM. The automatic analysis of microscopic leukocyte is an important task for diagnosticing many types of diseases namely leukaemia, malaria, psoriasis, AIDS, etc. The effective samples for training are obtained by saliency map of visual attention-based model. While in the learning stage, the effective samples are trained using ELM and segment leukocytes from blood smear images. The proposed framework is fully automatic and the experimental results outperform the state-of-the-art approaches.

Improving enzymatic saccharification of cassava stem using peroxide and microwave assisted pre-treatment techniques

Abstract: The effectiveness of microwave assisted alkali (MAA) and alkaline hydrogen peroxide (AHP) pre-treatment methods in improving the enzymatic saccharification of cassava stem was investigated. Ground cassava stems were by MAA method by varying microwave power, NaOH concentration and pre-treatment time. AHP method was performed at various H2O2 concentrations, pre-treatment temperatures and times. The results showed that reducing sugar yield was higher from MAA pretreated stem when compared with AHP pre-treatment, which demonstrated that MAA pre-treatment was effective in releasing sugars. SEM studies on the pre-treated samples revealed extensive distortion of fibres in MAA pre-treated than AHP pre-treated samples, which showed pores and cracks in the fibrous structure. Spectral studies showed the change in the chemical structure of pre-treated samples. The work revealed that the studied pre-treatment methods were effective in improving the enzymatic saccharification of cassava stem.

Real-time implementation of SMC–PID for Magnetic Levitation System

Abstract: Magnetic levitation is significant in almost all arenas of engineering. This principle is used to levitate objects such as a bullet train, flywheel, etc. This paper presents an experimental set-up of Magnetic Levitation System (MLS) in which a ball is levitated to a desired position and is sustained at a desired level for a stipulated time. The ball position is measured using an optoelectronic sensor and a controller is used to determine the time span of the ball at desired heights. To achieve this, a Sliding Mode Controller (SMC) is designed in such a way so as to regulate the current, which in turn controls the position through an electromagnet. Real-time observations of such ball positions have been recorded and compared to those of conventional PID (Proportional Integral Derivative) and robust SMC. Disturbance rejection, servo operation and set point tracking have also been tested and verified for the same. The outcome of such results processed through MATLAB proves that SMC’s performance is predominant over other controllers.

Occupational physical risk factors and prevalence of musculoskeletal disorders among the traditional lacquerware toy makers of South India.

Abstract: Background The majority of handicraft workers in India falls under the informal sector, which plays a prominent role in the employment generation. Artisans in handicraft sectors encounter various hazards and risks causing occupational diseases. Objective The key objective of the study is to identify the prevalence of musculoskeletal disorders and occupational risk factors among the artisans involved in making traditional lacquerware toys in Karnataka and Andhra Pradesh, South India. Methods The subjects considered in this study are 177 artisans who work in mechanized lathes at Channapatna of Karnataka and Etikoppaka of Andhra Pradesh, South India. The information regarding the reported work-related musculoskeletal disorders (WMSD) symptoms from 7 days to 12 months are collected through modified Standardized Nordic Questionnaire and by direct observations. Moreover, the intervention of WMSD in their day-to-day life and the overall comfort of their body are also determined. The questionnaire survey is conducted through face-to-face interviews and by direct field study. Results From the statistical analysis, it is found that about 76.83%of the study population (77.4%male and 74.28%female) has self-reported WMSDs. The prevalence of WMSD is most common in the age group of 30-40 years. Physical factors like workplace adaptability, stress at work, body postures, health status, body mass index, active and enough breaks during work and body condition at the end of work have a significant association with WMSD. Conclusion In this study, many of the work-related and lifestyle/health-related factors show a significant association with WMSD in artisans. The sub-standard working environment and the nature of work expose artisans to many occupational risks in their day-to-day life. To mitigate the occupational risks and musculoskeletal disorders, the workspace needs to be resigned ergonomically.

Detection of fire prone environment using Thermal Sensing Drone

Abstract: Drones of various types are currently in great demand because of their flexible applications to facilitate human life. At acceptable constant quality levels, they can perform tasks in a repetitive manner. A drone is intended and built in the current work to evaluate the area vulnerable to fire and its surface area at an altitude of 10 meters. In the event of a forest fire disaster, evaluating the impacted area is very complicated. This approach needs to be adaptable and easily controlled in order to solve it. Thus, both the manual and autopilot mode are built and controlled by a quad copter drone with an ardupilot, which drives the drone to the specified location. The drone is fed with the specification of the Global Positioning System ( GPS) and flies with the aid of an ardupilot to the spot. With the aid of a thermal imaging sensor, the drone senses the surface area with its captured image. With the aid of coding dumped in it, the image is sent to the base station and the vision building is achieved with the help of the thermal camera fitted in the front part of the drone and then it interacts with the base station where it is possible to view the surface area. This allows average individuals to recognize the region impacted by the tragedy and to predict the amount of impact they have made in a shorter period of time. Human interference is minimized by this detection method in the areas affected by fire with the extent of fire prediction.