International Journal of Interpreting Enigma Engineers (IJIEE)

An Enhanced Machine Learning Framework for Cyberbullying Detection in Social Media Text Messages

Nithya Lakshmi N — 2026-03-21

The rapid usage of internet makes it easy for the people to communicate across the globe and use the social media. Cyberbullying is considered to be a form of online harassment that creates harsh consequences like mental health issues, social isolation and even suicide. Nowadays Cyber bullying on social media has become a widespread issue in digital age that causes harmful and negative impacts on people. This paper mainly focuses on finding those cyberbullying messages employing language processing methods thereby processing textual data and few machine learning algorithms to characterize them and detect correlating them with the preprocessed data. From the observations, it is noted that when compared to all the other machine learning used the gradient descent method seems to perform better and with the prediction results a warning message is sent to the sender if the text data in the social media contains bullying kind of messages. Also, a block notification is sent to the receiver asking him to block the text from the sender.

IoT-Enabled Smart Street Lightning With Integrated EV Charging Hub

B. Vijaya Lakshmi — 2026-03-21

This project talks about creating a smart street light system that uses renewable energy, specifically solar power and piezoelectric energy. The energy produced is kept in a 12volt lead-acid battery and controlled to provide power to an Arduino microcontroller. The LDR sensor checks how bright it is outside, and the IR sensor looks for cars or people nearby. The Arduino uses signals from sensors to turn on and off a 12-volt LED street light automatically through a relay. The system lowers energy use by turning on the light just when it's needed. A portable charging port is also included for extra convenience. The system suggested is affordable, uses less energy, and works well in smart city environments.

Next Genric-BI ML-Based Resume Intelligence System

Dr Gavini Sreelatha — 2026-03-21

Hiring’s become a real challenge these days. Companies can get hundreds of resumes for just one job, all pouring in from job boards and online platforms. Sorting through that pile by hand is exhausting—and honestly, it’s easy to make mistakes or let bias sneak in. So we built a Resume Intelligence System powered by machine learning and natural language processing to make things simpler.

Here’s how it works: the system automatically scans every resume, grabs the important stuff like skills, education, and work history, then stacks those details up against what the job actually needs. It uses a similarity score to show, at a glance, who’s the closest match for the job. And forget about staring at endless spreadsheets—the results pop up in a Power BI dashboard, with clear charts and reports anyone can understand.

With this setup, recruiters skip the dull, repetitive tasks and spend more time on real decision-making. Everything moves faster. Plus, the whole process is more consistent and fair, since we’re letting the data do the heavy lifting. In the end, it means companies find the right people, with less hassle and less risk of missing great talent.

A Comprehensive Study on Malicious URL Detection: Leveraging Large-Scale Web Data for Accurate and Scalable Threat Identification

Posina Anusha — 2025-03-20

The rapid growth of cyber-attacks launched through the internet, such as phishing, spreading of malware, and cyber-attacks involving hacking of websites, has added a sense of challenge in malicious URL detection. Conventional techniques that rely upon blacklists of malicious patterns lack efficient strategies for handling dynamically changing URLs. Keeping these limitations in mind, in the suggested research work, a novel approach has been introduced for malicious URL detection using techniques in deep learning and ensembling, wherein an efficient approach for classifying large-scale data is being proposed using Convolutional Neural Networks, Bidirectional Long Short-Term Memory, and XGBoost. The data on which experiments are carried out is a publicly available large-scale dataset that consists of more than 650,000 URLs, which can be classified as benign, phishing, defacement, and malware types. The model that is proposed in this research work is compared with other approaches using various baseline techniques such as logistic regression, SVM, XGBoost, and CNN. Performance parameters that are used are accuracy, precision, recall, F1 score, ROC curve, and confusion matrix. The experimental results have shown that the proposed model achieves an accuracy of 96%, compared to all the other models, and hence proves that simply by combining the concepts of deep sequential features and gradient boosting, a better model can be obtained that can give better results while detecting malicious URLs.

An Intelligent AI-Driven Framework for Phishing Domain Detection

Nithya Lakshmi N* — 2026-03-21

The rapid increase in phishing attacks emerged as a major threat to users worldwide, with attackers utilizing different ways to mimic authentic domains and compromise user credentials. This paper recommends to develop an intelligent system that uses machine learning techniques to detect phishing domains particularly focusing on newly registered websites sourced from open and publicly available databases. By making use of the power of artificial intelligence, the proposed system assigns probability scores to identify the closeness of a domain to a genuine one. Moreover, it prioritizes the timely detection of new phishing domains improving the overall cyber security. This work deals with the significant requirement for an automated, intelligent tool to combat phishing attacks by proactively identifying malicious domains, ultimately safeguarding user credentials and cyber security measures.