International Journal of Technology Research and Management Beta

ISSN (Online): 2348-9006
* UGC Approved Journal * Till - May 2018
Click here for Details


Notice Board :

Call for Paper
Vol. 13 Issue 6

Submission Start Date:
June 01, 2026

Acceptence Notification Start:
June 10, 2026

Submission End:
June 30, 2026

Final MenuScript Due:
July 05, 2026

Publication Date:
July 10, 2026
                         Notice Board: Call for PaperVol. 13 Issue 6      Submission Start Date: June 01, 2026      Acceptence Notification Start: June 10, 2026      Submission End: June 30, 2026      Final MenuScript Due: July 05, 2026      Publication Date: July 10, 2026




Volume XIII Issue II

Paper Title
An Intelligent Hybrid Framework for Phishing Email Detection Using Machine Learning and Deep Learning Techniques
Author Name
Monika Dhanak, Mohit Jain
Year Of Publication
2026
Volume and Issue
Volume 13 Issue 2
Abstract
Phishing emails are still a major menace in online communication in that they manipulate the users with misleading information and therefore, proper and correct detection systems are required. The proposed research is a hybrid phishing email detection system comprising of machine learning and deep learning to classify emails as either phishing or legitimate. The system takes a phishing email dataset, which is distributed in either CSV format or XLSX format and manipulates it with Python-based data handling libraries. Originally, the appropriate features are chosen and pre-processed to address missing values and label encoding are carried out.
PaperID
2026/IJTRM/02/2026/46115

Paper Title
Evaluating the Performance of an Eye-Gaze Tracking System Using the VGG16 Deep Learning Technique
Author Name
Manisha Chouhan, Mohit Jain
Year Of Publication
2026
Volume and Issue
Volume 13 Issue 2
Abstract
Eye gaze tracking systems have become increasingly important due to their diverse applications across various fields. This study introduces an innovative eye gaze tracking system utilizing the VGG16 algorithm, designed to precisely estimate and track the direction of an individual's gaze based on their eye movements. The system follows a multi-step process, including pre-processing, region of interest (ROI) segmentation, feature extraction, and training with VGG16 for gaze tracking. The proposed system addresses challenges such as variations in eye appearance, head movements, real-time performance, and adaptability, through effective calibration and personalization.
PaperID
2026/IJTRM/02/2026/46116

Paper Title
An Adaptive Federated Graph Neural Network Framework for Real-Time Financial Fraud Detection
Author Name
Aashish Panwar, Mohit Jain
Year Of Publication
2026
Volume and Issue
Volume 13 Issue 2
Abstract
As financial systems grow increasingly complex and interconnected, traditional fraud detection methods struggle to keep up with sophisticated and evolving fraudulent activities. This paper introduces FraudGNN-RL, an innovative framework that combines Graph Neural Networks (GNNs) with Reinforcement Learning (RL) to enable adaptive and context-aware financial fraud detection. By modeling financial transactions as a dynamic graph—where entities such as users and merchants are nodes and transactions are edges—our novel Temporal-Spatial-Semantic Graph Convolution (TSSGC) captures temporal patterns, spatial relationships, and semantic information simultaneously.
PaperID
2026/IJTRM/02/2026/46117

Paper Title
Study of various technique for Anomaly Detection in Network Security
Author Name
Sunil Kumar, Aman Prakash Janoriya
Year Of Publication
2026
Volume and Issue
Volume 13 Issue 2
Abstract
Anomaly detection in network security plays a vital role in identifying malicious activities, intrusions and abnormal behaviors that deviate from normal network operations. With the increasing sophistication and volume of cyber attacks, traditional rule-based and signature-based intrusion detection systems are often inadequate for detecting novel or evolving threats. This survey presents a comprehensive review of various anomaly detection techniques applied in network security, encompassing statistical methods, machine learning algorithms and deep learning approaches. It examines their underlying principles, strengths, limitations and suitability for different network environments. The paper also explores hybrid and ensemble models that combine multiple detection strategies to enhance accuracy and reduce false alarms. Furthermore, recent advancements leveraging artificial intelligence and big data analytics for real-time anomaly detection are discussed. By comparing existing methodolog
PaperID
2026/IJTRM/02/2026/46118