Daily Archives: January 20, 2026

Authors: Abubakar Sadiq Yusha’u, Aminu Aliyu Abdullahi

Abstract: Artificial Intelligence (AI) systems are increasingly embedded in public governance for decision-making in areas such as welfare distribution, predictive policing, taxation, immigration, and electoral administration. While these systems promise efficiency and scalability, they also introduce significant risks of algorithmic bias with direct implications for equity, accountability, and democratic legitimacy. This study presents a systematic literature review (SLR) on metrics for identifying algorithmic bias in AI-driven governance models, with a particular emphasis on novel and governance-aware measurement approaches. The review follows PRISMA guidelines and analyzes peer-reviewed journal articles, conference proceedings, and high-impact policy reports published between 2014 and 2025. Literature was sourced from Scopus, Web of Science, IEEE Xplore, ACM Digital Library, and SpringerLink using structured search strings related to algorithmic bias, fairness metrics, and AI governance. After a multi-stage screening and eligibility process, the selected studies were subjected to qualitative thematic synthesis and comparative analysis. The results reveal that traditional statistical fairness metrics such as demographic parity, equalized odds, and predictive parity are widely used but insufficient for governance contexts due to their lack of contextual, temporal, and institutional sensitivity. The review identifies and classifies emerging bias metrics into five major categories: causal metrics, intersectional metrics, temporal and dynamic metrics, structural–institutional metrics, and explainability-driven indicators. These novel metrics demonstrate stronger alignment with governance principles, particularly in addressing power asymmetries, historical discrimination, and policy constraints. The study contributes a consolidated taxonomy of bias metrics and proposes an integrated, multi-dimensional framework for evaluating algorithmic bias in AI-driven governance systems. The findings offer practical guidance for policymakers, regulators, and system designers, while highlighting critical research gaps related to standardization, empirical validation, and Global South governance contexts.

DOI: http://doi.org/10.5281/zenodo.18312609

Published by: vikaspatanker

Authors: Vansh Shisodia, Saibee Alam, Anish Kushwaha, Aarchi Goyal

Abstract: This research constructs a hybrid system for one- step-ahead (H=1) stock forecasting, addressing the non-linear and non-stationary nature of financial time-series. The objective is twofold: a regression task for the Adjusted Close Price and a binary classification task for directional movement. The pro- posed ensemble design combines three model families: classical econometrics (ARIMA), deep learning (LSTM) for long-term dependencies, and ensemble tree methods (XGBoost, RF) for non- linear feature interactions. The methodology emphasizes rigorous feature engineering, including technical indicators and GARCH- derived volatility features, and robust validation using Time Series Cross-Validation (TSCV) and Nested Cross-Validation (nCV). The system culminates in a stacked ensemble (blending layer) and utilizes advanced loss functions like Huber Loss to manage heavy-tailed return distributions Evaluation is based on both statistical fit and financial utility metrics, such as directional accuracy and the Sharpe Ratio.

DOI:

Published by: vikaspatanker

Authors: Sandhyarani Balasaheb Kunjir, Suraj Rajiv Jaybhaye, Pradeep Sanjay Kapse, Abhishek Sunil Adagale, Mrs. Adagle P. M

Abstract: Tunnel electrification is essential for road safety and visibility inside tunnels. Conventional tunnel lighting consumes high power because lights remain ON continuously irrespective of traffic density. This research paper presents an ESP32 based smart lighting and safety system for road tunnels. The system uses sensors such as IR/Ultrasonic sensor for vehicle detection and LDR sensor for ambient light detection. Based on real-time sensor input, the ESP32 controller activates tunnel lighting section-wise, which reduces unnecessary electricity consumption. The system is further expandable with IoT monitoring through Wi-Fi for remote supervision and fault indication. The proposed smart tunnel electrification system improves energy efficiency, enhances safety and provides an economical solution for smart city infrastructure.

Published by: vikaspatanker

Authors: Gauri Bhambere, Roshani Gaikwad, laxmi Ingole, Sanjivini Gore, prof. Prachi Walunj

Abstract: Urban drainage and sewer manholes often pose serious safety risks due to the accumulation of toxic gases and abnormal temperature rise, which can lead to explosions, health hazards, and infrastructure damage. This project presents an IoT-based Manhole Monitoring System designed to continuously monitor hazardous gas levels and temperature inside manholes in real time. The system employs gas sensors to detect harmful gases such as methane, hydrogen sulfide, and carbon monoxide, along with temperature sensors to identify overheating or fire risks. Sensor data is collected by a microcontroller and transmitted wirelessly to a cloud platform using IoT communication technologies. When abnormal conditions are detected, instant alerts are sent to authorities via a web or mobile application, enabling quick preventive action. The proposed system improves worker safety, enhances public safety, reduces manual inspection efforts, and supports smart city infrastructure by providing reliable, real-time monitoring of underground manhole conditions.

DOI: http://doi.org/

Published by: vikaspatanker

Authors: Prof. Abhijit Chakraborty, Vinayak Ramakrishna Bhat, Samartha Vinayak Hegde, Prasanna Vighneshwara Hegde

Abstract: The rapid expansion of sustainable investment has created an urgent demand for reliable, comprehensive, and verifiable ESG information. Yet, despite its growing importance, the field continues to struggle with fragmented reporting standards, selective disclosures, and the increasing prevalence of greenwashing, all of which undermine the integrity of sustainability-focused financial decisions. This study provides an in-depth qualitative exploration of how Artificial Intelligence (AI) and Big Data are beginning to address these persistent issues and reshape the foundations of sustainable investment strategies. Drawing on a wide range of scholarly publications, institutional reports, and contemporary discussions from 2020 to 2025, the research examines how emerging digital tools are being used to interpret and validate sustainability performance. The literature shows that AI techniques such as natural language processing, intelligent screening algorithms, and pattern recognition models are improving the credibility of ESG evaluations by identifying inconsistencies, revealing undisclosed risks. Big Data strengthens this process by incorporating diverse and externally sourced evidence, including satellite-based environmental monitoring, supply-chain traceability systems, climate-risk datasets, and real-time operational. These combined capabilities not only enhance transparency but also reduce information asymmetry, allowing investors to form a more accurate understanding of a firm’s sustainability behavior and long-term risk exposure. The study finds that the use of AI and Big Data is gradually shifting sustainable investing from a disclosure-driven model dependent on voluntary corporate reporting to a more evidence-based and analytically rigorous approach. This transition supports stronger investor confidence, encourages more accountable corporate behavior, and aligns investment decisions more closely with global sustainability objectives. While challenges remain, including data standardization and ethical concerns in AI use, the overall trajectory suggests that AI and Big Data are poised to become essential pillars of future sustainable finance. This study examines how advanced analytical technologies contribute to improving the reliability, transparency, and investment relevance of ESG assessments. Using secondary data from a sample of forty publicly listed companies across multiple industry sectors, the study employs descriptive statistics, sector-wise analysis, regression modelling, and one-way ANOVA to examine patterns in ESG performance and sustainability risk. The analysis reveals significant sectoral differences in ESG scores, with technology and healthcare firms demonstrating relatively higher sustainability performance compared to energy and manufacturing sectors. Regression results indicate a strong negative relationship between ESG scores and sustainability risk, suggesting that higher sustainability performance is associated with improved risk management outcomes. The findings also show that firms adopting AI-driven analytics and structured sustainability reporting practices tend to achieve higher ESG scores and lower risk exposure.

Published by: vikaspatanker