Sri Ramakrishna Engineering College

About: Sri Ramakrishna Engineering College is a based out in . It is known for research contribution in the topics: Computer science & Control theory. The organization has 1030 authors who have published 843 publications receiving 3822 citations.

A survey : Predictive Model Based Electrical Consumption

Abstract: The data mining is the task of analyzing of large quantities of data to derive previously unknown, interesting patterns such as groups of data records, unusual records, and dependencies. It has the ability to turn raw data into useful information. One of the important invention of mankind is electricity. It is considered as a blessing. The availability of this power is very much needed for development and economical stability of the nations. The electricity board in various states and countries perform tasks such as generation, transportation and distribution of electricity to its customers effectively. In this study the various data mining techniques are applied to derive information from the electricity consumption databases.

An Automatic Test Generation Method for Crosstalk Delay Faults Using Modified FAN Algorithm

Abstract: Many automatic test generation algorithms are developed for generating tests for crosstalk delay faults.

Survey on Security Aspects in Smart Grid: Performance and Parametric Analysis

Abstract: Smart grid is a great new aspect of the power industry. It integrates various advanced technologies and information and communication capabilities to deal with problems found to occur with the existing electrical networks. Such integration facilitates and improves efficiency and accessibility of the electric power system with the additional features of regularly supervising, calculating, and administrating customer demands. This leads to the excessive deployment of smart meters in order to recognize the actual benefits. But, the deployment of smart meters brings up different concerns on the security of information among both consumers and service providers. This paper aims to focus on the major attacks on smart meter security which challenges the overall grid security.

Risk Assessment System for Prevention of Decubitus Ulcer

Abstract: The purpose of this paper is to develop a risk assessment system to prevent the occurrence of decubitus ulcers and to monitor the patient’s conditions via the Braden scale assessment tool. This ulcer is a type of wound that happens to bedridden people admitted for different diseases for an extended period. To prevent and alleviate the occurrence of decubitus or pressure ulcers, a system has been proposed consisting of a sheet embedded with various sensors like pressure sensor, temperature sensor, tactile sensing array, and moisture sensor interfaced with PIC microcontroller programmed using MPLAB. This sheet continuously monitors the activities of the patient through the aid of the Braden scale. The result indicates the patient’s pressure risk level calculated on basis of the Braden scale risk criteria and thereby updates it regularly to the hospital and the doctor's system through the display monitor and enables centralized control over the patient.

Comprehensive Analysis to Predict Hepatic Disease by Using Machine Learning Models

Abstract: One of the tests and crucial elements in treatment planning that extends a patient’s survival is detecting the segmentation abnormalities in the liver. The death rate increases because the side effects of liver cancer cannot be recognized until the malignancy has progressed. The most excellent method to control cancer progression and preserve lives is to diagnose it early and monitor it closely. Traditional liver cancer screening methods take a long time to compute and are complex. Logistic Regression, AdaBoost, and artificial neural network approaches are utilized to predict liver disease in a person to reduce the computational procedure's complexity and improve diagnostic exactness. Artificial neural network had the highest precision, recall, and F1-score values of 0.98, 0.95, and 0.96, respectively, among the techniques discussed above. As a result, the artificial neural network can accurately identify liver illness in a person with 97.4% accuracy.