Journal of Science Engineering Technology and Management Science

Artificial Intelligence (AI) has emerged as a transformative force in contemporary recruitment and selection, reshaping how organizations identify, assess, and hire talent. The growing adoption of AI-enabled tools including automated resume screening, recruitment chatbots, predictive analytics, algorithmic matching systems, and video-based assessments has generated both opportunities and challenges for human resource management. This narrative review synthesizes scholarly literature published between 2015 and 2025 to examine the evolving role of AI in recruitment and selection and its implications for organizational decision-making. The review identifies four dominant themes: the transformation of recruitment processes through automation and data-driven decision support; the changing roles of recruiters and applicants; ethical concerns relating to algorithmic bias, transparency, and privacy; and the growing importance of human–AI collaboration in hiring decisions. The analysis indicates that AI can enhance recruitment efficiency, scalability, consistency, and candidate matching while reducing administrative workload. However, these benefits are contingent upon the quality of underlying data, the transparency of algorithmic systems, effective governance mechanisms, and continued human oversight. The review argues that AI should be viewed as a decision-support technology rather than a substitute for professional judgment. By integrating technological, organizational, ethical, and human-centered perspectives, the study advances understanding of responsible AI adoption in recruitment and selection. It further proposes that sustainable hiring outcomes depend on balancing technological capabilities with fairness, accountability, transparency, and human involvement in decision-making processes.

Keywords : Artificial Intelligence; Recruitment and Selection; Human Resource Management; Algorithmic Hiring; Human–AI Collaboration; Responsible AI.

Author : Jallipalli A. N. K. Jayanth¹, Sanka Lithish Gupta², Kella Yasaswini³

Title : Impact of Artificial Intelligence on Recruitment and Selection

Volume/Issue : 2026;03(06)

Page No : 1-23

—In today's digital financial landscape, the rise of internet banking, electronic payment systems, blockchain, and cryptocurrencies has created a significant challenge for financial fraud. Due to their inability to identify complicated relations between connected entities, conventional fraud detection techniques, such rule-based and statistical models, are inadequate for detecting more sophisticated fraud schemes. Thanks to AI's use of cutting-edge machine learning (ML) and deep learning (DL) technologies, fraud detection has never been more effective. Graph Neural Networks (GNNs) are one approach that has attracted a lot of attention; they employ GNNs to examine the relationships between commodities, customers, merchants, and devices, as well as between accounts and devices. GNNs can identify hidden fraud trends, coordinated fraud rings, money laundering, identity theft and cryptocurrency crimes among other things, using relational and structural information. This article covers all aspects related to AI fraud detection solutions, ranging from simple statistical techniques to more advanced methods like ML, DL, and graph-based solutions. Furthermore, the paper explores the primary GNN architectures, including Graph Attention Networks, Graph Convolutional Networks, and Temporal Graph Neural Networks, delving into their applications, advantages, and disadvantages in financial fraud detection. The review finds that the GNN-based methods demonstrated high detection accuracy, good real-time surveillance ability, and could be applied to develop scalable, interpretable and privacy-preserving financial security frameworks.

Keywords : Financial Fraud Detection, Artificial Intelligence (AI), Graph Neural Networks (GNNs), Machine Learning, Deep Learning, Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs).

Author : Dr. Prashant Kumar Srivastava

Title : AI-Driven Financial Fraud Detection: A Review of Graph Neural Network Approaches

Volume/Issue : 2026;03(06)

Page No : 24-34

The growing integration of artificial intelligence and algorithmic systems into Human Resource Management (HRM) has transformed organisational decision-making processes while simultaneously intensifying concerns surrounding fairness, transparency, and ethical accountability. Although existing scholarship has extensively examined the operational benefits of algorithmic HRM, comparatively limited attention has been devoted to understanding how organisations can balance algorithmic efficiency with human-centred equity in consequential employment decisions. Addressing this gap, the present study develops a conceptual characterisation of Algorithmic Human Resource Management through the integration of socio technical systems theory, augmented decision-making theory, and the algorithmic fairness literature. Methodologically, the study adopts an integrative literature review approach supplemented by comparative case analysis of three widely discussed organisational cases: Amazon’s abandoned AI recruitment system, Unilever’s hybrid AI-assisted hiring model, and HireVue’s algorithmic video interview platform. These cases are further contextualised through a theoretically constructed vignette designed to examine the limits of narrow algorithmic filtering and the continuing relevance of human evaluative judgment. Through this multi-layered analysis, the paper investigates the governance structures required for effective human–AI integration in HRM and explores the broader tension between predictive efficiency and procedural equity.

Keywords : Algorithmic Human Resource Management; Artificial Intelligence in HRM; Algorithmic Governance; Human-in-the-Loop Systems; Algorithmic Fairness; Ethical AI; Socio Technical Systems Theory; HR Analytics.

Author : Ruwayda Hussain¹*, Dalli Vineetha Reddy²

Title : Towards a Characterisation of Algorithmic Human Resource Management: Exploring the Duality of Efficiency and Equity

Volume/Issue : 2026;03(06)

Page No : 35-58

Detecting pedestrians in low-light and nighttime environments is a major challenge for autonomous systems, mainly due to poor visibility and the limitations of relying on a single sensor. To address this issue, this project introduces a multimodal pedestrian detection framework that combines infrared (IR) imaging with millimeter-wave (MMW) radar data to improve detection accuracy, reliability, and real-time performance during night conditions. An enhanced YOLOv5-based deep learning model is utilized to extract meaningful spatial and semantic features from infrared images, while radar signals are processed to obtain important information such as distance, speed, and position of moving objects. To further enhance tracking accuracy, an Extended Kalman Filter (EKF) is applied to reduce noise in radar data and to predict the motion of pedestrians over time. The system performs spatiotemporal fusion by aligning radar target points with corresponding regions in infrared images, followed by a correlation gating mechanism to ensure proper association between the two data sources. Finally, a decision-level fusion strategy integrates the outputs to produce precise and consistent pedestrian detection results. Experimental results show that the proposed approach outperforms single-sensor methods, offering improved precision and robustness under challenging nighttime conditions. This work contributes to enhancing the safety and reliability of autonomous vehicles and intelligent monitoring systems operating in low-visibility environments.

Keywords : autonomous vehicles, pedestrian detection, sensor fusion, YOLOv5, infrared camera, millimeter-wave radar, target tracking, Extended Kalman Filter, nighttime detection, real-time object detection

Author : G.Swathi Reddy1, Boga Venkat Sai2, Bommadeni Sricharan3, Bookya Madhu Nayak4, Chininga Praveen5, Jula Shiva Rama Krishna6

Title : Infrared and Millimeter-Wave Radar Fusion for Robust Night Pedestrian Recognition

Volume/Issue : 2026;03(06)

Page No : 59-64

The electrification of transportation, especially city buses, is becoming increasingly important for achieving sustainable mobility and reducing environmental impact. However, designing and operating battery electric buses (BEBs) efficiently requires a deep understanding of real-world driving conditions, including variations in speed, passenger load, traffic congestion, and route characteristics. One of the major challenges in this domain is accurately predicting energy demand, as uncertainties often lead to overly conservative system designs, resulting in higher costs, oversized batteries, and reduced operational efficiency. This study addresses these challenges by introducing a set of novel explanatory variables that effectively capture speed patterns and driving behavior. These variables provide a more detailed representation of real-world conditions and are integrated into advanced machine learning models to enhance prediction accuracy. A total of five different algorithms were developed and evaluated, considering factors such as prediction accuracy, robustness, computational efficiency, and practical applicability. The experimental results demonstrate that the proposed models achieve prediction accuracy above 94%, indicating their strong capability in modeling complex energy consumption patterns. Additionally, the approach reduces reliance on complex physical simulations, making it more scalable and suitable for real-time applications. This enables fleet operators to make better decisions regarding route planning, battery sizing, and charging infrastructure placement. Overall, the proposed methodology contributes to cost reduction, improved operational efficiency, and supports the wider adoption of clean and sustainable public transportation systems. Furthermore, the proposed framework can be easily adapted to different cities and operational scenarios, making it highly flexible for future deployments. It also opens opportunities for integrating real-time data analytics and smart transportation systems, enabling continuous monitoring and optimization of energy usage. This adaptability ensures long-term benefits in evolving urban mobility environments.

Keywords : Electric buses, energy demand prediction, machine learning, speed profile analysis, sustainable transportation, battery electric vehicles, fleet optimization

Author : Dr.Amita Johar1, Bobbala Bhavana2, Annarapu Meghana3, Chavva Vishwateja4, G Arpan Varma5

Title : Data-Driven Analysis of Energy Efficiency in Battery Electric City Buses

Volume/Issue : 2026;03(06)

Page No : 65-70

This study introduces an AI-driven system for detecting and localizing road surface damage using deep learning methods. The approach employs three variants of the YOLO (You Only Look Once) architecture—YOLOv5, YOLOv7, and YOLOv8—to analyze and classify road images. A custom dataset containing multiple categories of road defects, including potholes, cracks, and surface irregularities, was used for training and evaluation. Comparative results indicate that YOLOv8 delivers the best performance, achieving an accuracy of 85%, followed by YOLOv7 at 82% and YOLOv5 at 65%. Additional evaluation metrics such as precision, recall, and confusion matrices further confirm the superior detection capability of YOLOv8 with reduced misclassification rates. The system also supports real-time detection, visually marking damaged areas with bounding boxes. Overall, the proposed framework demonstrates the effectiveness of deep learning in automating road condition assessment, with practical applications in smart infrastructure management and autonomous transportation systems.

Keywords : road damage detection, YOLOv5, YOLOv7, YOLOv8, deep learning, object detection, computer vision, image processing, automated road maintenance, smart infrastructure

Author : G.Swathi Reddy1, Maidamshetti Ajay2, Palagani Anil3, Chowdari Eshwar4, Bhukya Somesh5, Alugulla Vamshi Kiran6

Title : Automated Road Damage Detection via UAV Imaging and Deep Neural Networks

Volume/Issue : 2026;03(06)

Page No : 71-77

Cloud storage has become a popular solution for handling large volumes of data, but its centralized nature raises serious concerns related to security and data privacy. To address these issues, this work presents a decentralized approach using blockchain technology, which eliminates dependency on a single storage authority. In this system, any node connected to the internet can participate in the network, forming a peer-to-peer structure that improves resource utilization and reliability. The proposed model ensures data security by encrypting user files before storage and distributing them across multiple nodes using the IPFS protocol. IPFS generates a unique hash value for each file, which acts as an identifier and is securely recorded on the blockchain. This approach ensures data immutability, transparency, and easy retrieval. Overall, the system provides a secure, efficient, and highly available method for storing data in a decentralized cloud environment.

Keywords : Blockchain, Decentralized Cloud Storage, Data Security, IPFS, Peer-to-Peer Network, Data Encryption, Distributed Systems, Data Integrity, Secure Storage, Cloud Computing

Author : Dr.A.Anil Kumar Reddy1, Kankatala Kiran2, Kurakula Kushlu3, Oribindi Ramakrishna4, Samala Badrinath5

Title : Blockchain-Enabled Secure Data Storage in Decentralized Cloud Environments

Volume/Issue : 2026;03(06)

Page No : 78-83

Floods are one of the most destructive natural disasters, causing serious damage to lives, agriculture, and infrastructure. Predicting floods in advance is a difficult task due to changing environmental conditions and complex water systems. This study presents a flood forecasting model based on federated learning, which allows multiple locations to train models without sharing raw data. This approach helps reduce network delays while maintaining data privacy and security. Instead of sending large datasets to a central server, local models are trained and only the learned parameters are shared. The proposed system analyzes data from 18 different stations to identify areas at risk and provides flood alerts up to five days in advance. A feedforward neural network (FFNN) is used to predict water levels using factors such as rainfall, snowmelt, flow routing, and hydrodynamics. The model was tested on data from 2010 to 2015 and achieved an accuracy of 84%.

Keywords : Flood Forecasting, Federated Learning, CNN2D, FFNN, Water Level Prediction, Hydrological Data, Rainfall-Runoff, Disaster Management

Author : P.Arun Reddy1, Pemmanaboina Rohith Karthikeya2, Ettaboina Shiva Krishna3, Dadige Shiva Kumar4, Navapet Sharan Kumar Yadav5

Title : Advanced Flood Prediction Using Federated Learning with 2D Convolutional Networks

Volume/Issue : 2026;03(06)

Page No : 84-89

Lung cancer is one of the most life-threatening diseases, mainly because it is often detected at a late stage. Identifying the disease early and determining its stage accurately can greatly improve a patient’s chances of survival. Although various techniques such as image processing, biomarker analysis, and automated systems are available, achieving high accuracy in early diagnosis still remains a major challenge for medical professionals. In this study, CT scan images obtained from the LIDC-IDRI dataset are used to develop an improved detection system. Unlike traditional approaches that depend on manual observation, this research introduces a Hybrid Neural Network-based method called Cancer Cell Detection using Hybrid Neural Network (CCDC-HNN). The model uses deep learning techniques to extract important features from CT images, which helps in identifying cancer at an early stage. Additionally, a 3D Convolutional Neural Network is applied to enhance the accuracy of detection and to clearly distinguish between benign and malignant tumors. The performance of the proposed model is evaluated using standard statistical measures, and the results show that it provides reliable and accurate predictions, making it a promising approach for early lung cancer diagnosis.

Keywords : Lung Cancer Detection, Hybrid Neural Network, Deep Learning, 3D Convolutional Neural Network (3D-CNN), CT Scan Imaging, Early Diagnosis, Feature Extraction, Tumor Classification, Benign and Malignant Detection, Medical Image Analysis, LIDC-IDRI Dataset, Computer-Aided Diagnosis (CAD).

Author : Aseena Shaik Babu1, Oruganti Aravindu2, Komatireddy Sai Vardhan3, Dupati Abhilash4, Empati Harshit5

Title : An Integrated Hybrid Neural Network Framework for Early Prediction of Lung Cancer

Volume/Issue : 2026;03(06)

Page No : 90-95

The rapid progress in natural language generation has made it easier to create realistic text, which can be misused to influence opinions on social media platforms. Modern deep learning models are capable of generating content that closely resembles human-written text, making it difficult to distinguish between genuine and machine-generated messages. This creates serious concerns regarding misinformation and the spread of misleading content through automated accounts. To address this issue, this study focuses on detecting machine-generated tweets using a deep learning approach. A Convolutional Neural Network (CNN) model is designed and combined with FastText word embeddings to effectively capture semantic patterns in text data. The model is trained and evaluated using the Tweepfake dataset, which contains both human-written and bot-generated tweets. For comparison, several baseline machine learning models and alternative deep learning architectures such as LSTM and CNN-LSTM are also tested. The results show that the proposed CNN with FastText embeddings achieves an accuracy of around 93%, demonstrating its effectiveness in identifying synthetic tweets. This approach offers a reliable solution for improving the detection of fake content on social media

Keywords : Deep Learning, Deepfake Detection, Machine-Generated Text, Social Media Analysis, FastText Embeddings, Convolutional Neural Network (CNN), Tweet Classification, Natural Language Processing, Fake Content Detection

Author : P.Arun Reddy1, Md Rabbani2, Chowla Manikya Kalyan3, Masampally Venkat Ramana4, Sriperumbuduru Shyam Sundar5, Gudeti Vivek Vardhan6

Title : Detection of Machine-Generated Social Media Content Using Hybrid Deep Learning and Fast Text Representation

Volume/Issue : 2026;03(06)

Page No : 96-101