International Journal of Engineering Applied Science and Management

ISSN (Online): 2582-6948


Notice Board :

Call for Paper
Vol. 7 Issue 3

Submission Start Date:
March 01, 2026

Acceptence Notification Start:
March 10, 2026

Submission End:
March 25, 2026

Final MenuScript Due:
March 31, 2026

Publication Date:
March 31, 2026
                         Notice Board: Call for PaperVol. 7 Issue 3      Submission Start Date: March 01, 2026      Acceptence Notification Start: March 10, 2026      Submission End: March 25, 2026      Final MenuScript Due: March 31, 2026      Publication Date: March 31, 2026




Volume VII Issue I

Paper Title
Developing a Strategic Roadmap for AI-Driven IT Governance in India’s Digital Economy
Author Name
Balakrishnan Kanniah, Trilok Singh
Year Of Publication
2026
Volume and Issue
Volume 7 Issue 1
Abstract
India’s digital economy is experiencing a rapid transformation fueled by the integration of advanced technologies such as Artificial Intelligence (AI), cloud computing, and automation. As organizations accelerate digital adoption, the need for a resilient and adaptive IT Governance framework has become paramount. This research paper aims to develop a strategic roadmap for AI-driven IT Governance that aligns technology innovation with organizational objectives, regulatory compliance, and risk management in the Indian context. Through a comprehensive analysis of existing governance models, regulatory frameworks, and case studies from leading Indian enterprises, this study identifies the key challenges, enablers, and success factors in adopting AI within governance structures. The proposed roadmap emphasizes data-driven decision-making, automation of governance processes, predictive compliance monitoring, and AI-enabled risk intelligence to enhance transparency, accountability, and operat
PaperID
2026/IJEASM/1/2026/3303

Paper Title
Machine Learning–Based Modelling and Predictive Analytics for Cancer Detection
Author Name
Mohammad Qasim Khan, Pawan Meena
Year Of Publication
2026
Volume and Issue
Volume 7 Issue 1
Abstract
Early and accurate cancer detection is critical for patient outcomes. Advances in machine learning (ML), especially deep learning and multimodal fusion, enable high-performance, scalable detection systems that combine medical imaging, genomics, and clinical data. This paper presents a modular ML framework for cancer detection and predictive analytics that (1) fuses multimodal inputs, (2) leverages state-of-the-art deep architectures and gradient-boosted trees for tabular data, and (3) provides uncertainty estimates for clinical use. We evaluate the system on three public benchmarks covering imaging and genomics, compare single-modality and multimodal models, and demonstrate that multimodal fusion yields consistent gains in AUC and sensitivity while calibrated uncertainty reduces high-risk false positives. Our best model achieves AUCs of 0.96 (skin dermoscopy), 0.94 (breast histopathology), and 0.92 (lung CT nodule malignancy probability) under cross-validation. We also present an ablat
PaperID
2026/IJEASM/1/2026/3306

Paper Title
Development of an Adaptive Machine Learning Framework for Real-Time Sensing and Recognition of Human Activities
Author Name
Asra Khalid, Pawan Meena
Year Of Publication
2026
Volume and Issue
Volume 7 Issue 1
Abstract
Human Activity Recognition (HAR) plays a vital role in applications such as healthcare monitoring, smart environments, human–computer interaction, and safety systems. While traditional HAR systems achieve good accuracy under controlled conditions, their performance often degrades in real-world deployments due to user variability, sensor noise, and concept drift. This paper presents the development and evaluation of an adaptive machine learning framework for real-time sensing and recognition of human activities. The proposed framework integrates streaming sensor data processing, lightweight deep learning models, and online adaptation mechanisms to maintain high recognition accuracy over time. Experiments conducted on benchmark wearable sensor datasets demonstrate that the adaptive framework consistently outperforms non-adaptive baselines, particularly in cross-subject and long-term evaluation scenarios. The results confirm the effectiveness of adaptive learning in addressing real-world
PaperID
2026/IJEASM/1/2026/3307

Paper Title
Application of Direct Torque Control in Robotic Actuation Systems: Performance Analysis and Industrial Relevance-A Review
Author Name
Vikram Singh, Devendra Bisen, Anurag Soni, Kamlesh Vishwakarma
Year Of Publication
2026
Volume and Issue
Volume 7 Issue 1
Abstract
Direct Torque Control (DTC) has emerged as a powerful motor control technique due to its fast dynamic response, simple control structure, and robustness against parameter variations. In the robotics industry, precise torque and speed control are critical for achieving high accuracy and efficiency. This paper investigates the application of Direct Torque Control in robotic actuation systems. A detailed theoretical analysis of DTC is presented along with its implementation in robotic joints. Performance parameters such as torque ripple, speed response, and disturbance rejection are analyzed and compared with conventional Field Oriented Control (FOC). Simulation results demonstrate that DTC provides superior dynamic performance, making it suitable for modern robotic applications.
PaperID
2026/IJEASM/1/2026/3310