Home
Issues List
1 Aug 13, 2023
MACHINE LEARNING AND NATURAL LANGUAGE PROCESSING FOR INTELLIGENT HIRING WITH RESUME PARSER AND RANKING

Using Natural Language Processing (NLP) and Machine Learning (ML), this intelligent system ranks resumes of any format in accordance with the provided limitations or the following requirements provided by the client company. The majority of the input resumes will come from the client organization, which will also provide the specifications and constraints used by our system to rank the resumes. Our algorithm will also look at the candidates' social media accounts (such as those on LinkedIn, Github, etc.), which will provide more precise information about the candidate, in addition to the data it gathers from resumes....

Authors: Akash Sharma, Saurabh Sharm.

2 Aug 13, 2023
UTILIZING A MACHINE LEARNING METHOD TO PREDICT POPULAR RESEARCH TOPICS

Machine learning (ML) has changed over the past few decades from an endeavor of a few computer enthusiasts exploring the idea of computers learning to play games and a branch of mathematics (Statistics) that rarely considered computational approaches to an independent research field that has not only developed various algorithms that are frequently used in learning procedures but also provided the necessary foundation for statistical-computational principles of learning procedures. This essay aims to compare the three most prominent machine learning algorithms based on certain fundamental ideas, as well as to explain the concept and evolution of machine learning. The performance of each method in terms of training time, prediction time, and prediction accuracy has been documented and compared using the Sentiment140 dataset....

Authors: Poonam Raikwar, Vishal Paranjape.

3 Aug 13, 2023
PREDICTION OF HEART DISEASE USING MACHINE LEARNING

Predicting heart disease is one of the most challenging challenges in the medical industry today. Approximately one person dies from heart disease every minute in the modern era. Processing a vast amount of data in the healthcare industry requires data science. Since predicting cardiac illness is a complex undertaking, it is necessary to automate the process in order to reduce risks and warn the patient well in advance. The heart disease dataset from the UCI machine learning repository is used in this study. The suggested work uses various data mining algorithms, including DecisionTree, Knn, Logistic Regression, and Random Forest, to forecast the likelihood of heart disease and categorize patient risk. In order to compare the effectiveness of various machine learning algorithms, this paper will do so. The trial results show that, when compared to other ML algorithms used, the Random Forest approach has the highest accuracy (90.16%)....

Authors: Sonal Shakya, Jayesh Jain .

4 Aug 13, 2023
ML TECHNIQUE-BASED SENTIMENT ANALYSIS FOR MEASURING IMPACT OF SOCIAL MEDIA DATA USING PYTHON TOOL

Sentiment analysis focuses on recognising and categorising the thoughts and feelings represented in a piece of writing. Sharing thoughts and feelings on social networking platforms has become a regular practise these days. As a result, a significant volume of data is created each day, from which valuable information may be gleaned via data mining. These data may be used for the sentiment analysis to get a consolidated view on certain items. Because of the prevalence of slang as well as misspellings, doing sentiment analysis on Twitter may be challenging. In addition, new words are continually being encountered, making it more difficult to interpret and calculate the emotion. A tweet on Twitter can only be 140 characters long. As a result, another hurdle to overcome is gleaning useful information from condensed texts. The analysis of feelings in tweets may greatly benefit from a "knowledge-based approach" as well as machine learning. In this study, we'll look at what individuals are saying about Covid-19 in their tweets. To better serve the views, a simple sentiment score might be computed and then classified as either good or negative by individuals all around the globe....

Authors: Preeti Mehrotra ,Devashri Deoskar.

5 Aug 13, 2023
ADVANCING RAILWAY SIGNALING SYSTEMS: DEEP LEARNING-DRIVEN VERIFICATION AND VALIDATION

This research paper explores the potential of deep learning, specifically Convolutional Neural Networks (CNNs), in advancing the verification and validation of railway signaling systems. By leveraging deep learning algorithms, the aim is to improve the accuracy, efficiency, and reliability of train operations. Case studies and experiments demonstrate the effectiveness of CNNs in anomaly detection and signal classification, surpassing traditional methods. The integration of deep learning techniques enhances safety, reliability, and operational efficiency in railway signaling. Ethical considerations, data acquisition challenges, real-time integration, and interpretability of deep learning models are ad- dressed as important factors in the application of deep learning to railway signaling systems. This research highlights the significant potential of deep learning, specifically CNNs, in advancing the verification and validation of railway signaling systems, ultimately contributing to enhanced safety and efficiency....

Authors: Bheema Shanker Neyigapula.

Announcements

  • Calling Papers For Volume 13, Issue 4 Last Deadline For Paper Submission 22-July-2023 Posted by Admin Posted by Admin.