Dr. Rakesh Kumar Mandal, Dr. JKM Sadique Uz Zaman, Dr. Rajesh Kumar Mandal |
||||||
| Automated Classification Skin Images into Psoriatic and Nonpsoriaticusing Convolutional Neural Network (CNN)-based Model | ||||||
Background:Skin Psoriasis is a chronic autoimmune skin disorder the diagnosis and detection of which can be
a challenging task because of its versatility in clinical presentation and it also resembles with many skin
conditions. This disease may manifest in various ways in difference people and sometimes appears like eczema
and tineacorporis. Furthermore in some areas the issue may be more challenging due to lack of access to
specialized dermatology care..........
Skin Psoriasis, Deep Learning, Convolutional Neural Network (CNN), Skin Disease Classification, Medical Image Analysis, Computer-Aided Diagnosis, Image Augmentation.
[1]. Parisi R, Symmons DPM, Griffiths CEM, Ashcroft DM. Global epidemiology of psoriasis: a systematic review of incidence and
prevalence. J Invest Dermatol. 2013;133(2):377–85.
|
Usman M. Akindele, Jeleel A. Adebisi, Ismaila I. Ahmed |
||||||
| Lithium Carbonate Extraction from Zankan Spodumene Concentrate via Decrepitation and Hydrometallurgical Processes | ||||||
It has been established that Nigeria is endowed with a variety of lithium ores, coupled with global interest in
lithium production due to growing demand as an alternative source of energy. Therefore, thermal treatment of
the obtained concentrate for lithium carbonate production cannot be overemphasised. Spodumene concentrate
obtained from Zankan lithium ore was subjected to a decrepitation process and a sulfuric acid extraction
process was used to obtain lithium carbonate from beta spodumene, with Na2CO3 as the leaching agent. In the
process, temperature differences (200 °C, 225 °C, 250 oC, 275 °C, and 300 °C) of the acid roasting show a
considerable significance grade of lithium carbonate; the highest grade of 78% was extracted at 250 °C. This
suggests effective production of Li2CO3 as a key substance in lithium-ion batteries, even though further refining
could lead to a higher yield for energy applications.
..............
[1]. N. K. Salakjani, P. Singh, and A. N. Nikoloski, "Production of lithium–A literature review. Part 2. Extraction from spodumene," Mineral Processing and Extractive Metallurgy Review, vol. 42, no. 4, pp. 268-283, 2021.
|
Vanathi. N |
||||||
| An Empirical Study on Ceremonies of Hindu Marriage in India | ||||||
Marriage is the union of two adults who, along with their families, form a union and, as a result,
provide matrimony legal status. This union is known as a "holy union" in Indian civilization because the people
here believe that it is solemnised in the presence of the Gods.But when such partnerships are solemnised by
particular traditional or customary procedures, they are considered to be full. Here the main objective of the
study is to find out The ceremonies performed in the Hindu marriage .The researcher has followed the
Empirical research method using convenient sampling method.The sample size of the study is 201.The result
observed from the study is that most people are aware about all the ceremonies I.e. Kanyadan, Saptapadi and
Sagai.Religion shapes people's perspectives on particular issues and has an impact on a number of institutions,
including the institution of marriage. Personal freedom and a person's needs are given a lot of weight in the
individualistic culture.
Kanyadan, Saptapadi, Sagai, Homa and Pani grahan.
[1]. Ramalinggam Rajamickam ,Hindu Marriage and its position in the Malaysian Marriage law, International Journal of Arts and
Commerce, October 2012, Vol 1, Issue 5.
|
Michael F. Edafeajiroke, Umejuru Daniel, Anthony Onyinyechi Vivian |
||||||
| Pneumonia Prediction Using Shap and Lime Explainable Boruta– Random Forest Model | ||||||
This study develops an explainable machine learning model to enhance the accuracy and transparency of
pneumonia diagnosis. The research addresses the critical "black-box" problem in clinical AI by integrating the
Boruta algorithm for robust feature selection with a Random Forest classifier for prediction. The pipeline
employs SHAP (SHapley Additive exPlanations) for global and local interpretability and LIME (Local
Interpretable Model-agnostic Explanations) for intuitive, case-specific rationales..........
Pneumonia Prediction, Explainable AI (XAI), Boruta Algorithm, SHAP and LIME, Clinical Decision
Support
[1]. Ahmad, T., Munir, A., Bhatti, S. H., Aftab, M., & Raza, M. A. (2022). A hybrid random forest and support vector machine model
|
John Lander Ichenwo, Ogwu Philip |
||||||
| Self-supervised Learning on Unlabelled Downhole Sensor Data for Anomaly Detection | ||||||
Continuous streams of pressure, temperature, vibration and sound readings are produced by downhole sensors
and are essential for monitoring production performance and wellbore integrity. The efficiency of traditional
supervised machine learning techniques for anomaly detection is limited by expensive, time-consuming, and
often unavailable manual labeling of such data. To identify anomalous operating conditions without labeled
examples, this work proposes a self-supervised learning (SSL) system that utilizes unlabeled downhole sensor
information. The framework learns robust feature representations that capture operational.........
....
[1]. Abdullah, M., Rahman, F. & Said, A. (2023) 'Self-supervised feature learning for industrial IoT anomaly detection', IEEE
Internet of Things Journal, 10(4), pp. 3550–3562.
|
John Lander Ichenwo, Ogwu Philip |
||||||
| Graph Neural Network for Modeling Hydraulic Fracture Networks and Connectivity to Production | ||||||
Hydraulic fracturing generates a complex network of fractures that controls hydrocarbon flow and, hence, the
production performance in unconventional reservoirs. While numerical simulation is able to characterize such
fracture networks, it is computationally intensive and hence difficult to use in real-time decision-making. The
present study develops a GNN-based approach to model hydraulic fracture connectivity and predict well
production performance. Simulation results of 3D discrete fracture network (DFN) systems were converted into
graph representations and nodes are fracture segments and edges are connection indicators.........
Graph Neural Networks, Hydraulic Fracturing, Fracture Connectivity, Stimulated Reservoir Volume,
Production Prediction.
[1]. Chen, Y., Li, B., & Zhao, X. (2023).Machine learning approaches for production forecasting in unconventional reservoirs: A
review and future directions.Journal of Petroleum Science and Engineering, 224,
111238.https://doi.org/10.1016/j.petrol.2022.111238
|
T.N.Vignesh, Mrs. K.Vasumathi, Dr. S.Selvakani |
||||||
| An Intelligent Data Protection Model for Relational Database Systems through SQL Encryption | ||||||
The fact that the data owners outsource their data to external service providers introduces many security and
privacy issues. Among them, the most significant research questions relate to data confidentiality and user
privacy. Encryption was regarded as a solution for data confidentiality. The privacy of a user is characterized
by the query he poses to the server and its result. We explore the techniques to execute the SQL query over the
encrypted data without revealing to the server any information about the query such as the query type or the
query pattern, and its result........
Database outsourcing, database encryption, user privacy, access pattern privacy, access privacy.
[1]. "A Generic Data Privacy Approach for Relational Databases and Data Warehouses" – Rahul Kumar Sharma & Vivek Kapoor
(2023).
|
Okpala Charles Chikwendu, Nwamekwe Charles Onyeka and Onukwuli Somto Kenneth |
||||||
| Ergonomics in the Age of Industry 5.0: A Multilevel Data Analytics Approach Linking Human-Robot Collaboration, Cognitive Load, and Productivity in Smart Manufacturing Systems | ||||||
Industry 5.0 advances a human-centric and sustainability-driven vision of smart manufacturing, yet empirical
evidence that links ergonomic system design to measurable environmental performance remains limited. This
study develops and validates a multilevel data analytics framework that connectsHuman–Robot Collaboration
(HRC), cognitive load dynamics, productivity variability, and sustainability outcomes in digitally integrated
manufacturing environments. Data were collected from 12 smart factories across automotive, electronics, and
precision assembly sectors, comprising 486 operators and 18,742 task cycles over 14 months........
Industry 5.0, human–robot collaboration, cognitive load, sustainable manufacturing, multilevel
modeling, digital twin simulation, ergonomic intelligence
[1]. Ajaefobi, J. O., and Okpala, C. C. (2026). Optimization of smart manufacturing systems through renewable energy integration
and sustainable material utilization. International Journal of Engineering Inventions, 15(2).
https://www.ijeijournal.com/papers/Vol15-Issue2/15021832.pdf
|
Ajaefobi Joseph Obichukwu, Okpala Charles Chikwendu |
||||||
| Six Sigma in the Era of Industry 4.0: A Bibliometric and Benchmarking Review | ||||||
The rapid diffusion of Industry 4.0 technologies likeArtificial Intelligence (AI), the Internet of Things (IoT), big
data analytics, and digital twinshave transformed how organizations pursue operational excellence and
sustainability. Six Sigma, traditionally grounded in statistical process control and structured DMAIC problemsolving,
is increasingly being augmented by these digital capabilities, and thus giving rise to what is often
termed Digital Six Sigma or Six Sigma 4.0. This study presents a comprehensive bibliometric and benchmarking
review of 214 peer-reviewed publications that were published between..........
Six Sigma 4.0, Industry 4.0, digital quality management, sustainability benchmarking, artificial
intelligence, smart manufacturing, operational excellence
[1]. Aguh, P. S., and Okpala, C. C. (2025). Learning in the age of artificial intelligence tutors: Cognitive outcomes and equity in
automated education systems. International Journal of Engineering Research and Development, 21(12).
https://ijerd.com/paper/vol21-issue12/21128898.pdf
|
Chukwunedum Ogochukwu Chinedum, Okpala Charles Chikwendu, Udu Chukwudi Emeka |
||||||
| A Data-Driven Integration of Total Productive Maintenance and Industry 4.0 Technologies: A Machine Learning ramework for Predictive OEE Optimization | ||||||
Manufacturing firms are increasingly required to achieve high equipment reliability while simultaneously
reducing energy consumption, material waste, and carbon emissions. Although Total Productive Maintenance
(TPM) has historically improved equipment effectiveness, its traditional preventive orientation limits
responsiveness in digitally intensive production environments. This study proposes and empirically validates a
Data-Driven Predictive TPM (P-TPM) framework that integrates Industrial Internet of Things (IIoT) sensing,
hybrid machine learning, digital twin simulation, and explainable artificial intelligence to optimize Overall
Equipment Effectiveness (OEE) while delivering measurable sustainability gains..........
total productive maintenance, industry 4.0, machine learning, predictive maintenance, overall
equipment effectiveness, sustainable manufacturing, digital twin
[1]. Ahuja, I. P. S., & Khamba, J. S. (2008). Total productive maintenance: Literature review and directions. International Journal of
|
Onukwuli Somto Kenneth, Okpala Charles Chikwendu, Udu Chukwudi Emeka |
||||||
| Antibiotic Removal from Water in the Era of Antimicrobial Resistance: A Global Systematic Review and Performance Benchmarking of Adsorption Technologies | ||||||
Antibiotic contamination of aquatic systems has emerged as a critical environmental driver of Antimicrobial
Resistance (AMR), as it intensifies global concerns over water security and public health. Despite rapid
advances in adsorption-based treatment technologies, comparative evaluation remains fragmented, with limited
integration of sustainability and scalability metrics. This study presents a PRISMA-guided global systematic
review of 412 peer-reviewed articles that were published between 2000 and 2025, and synthesizes performance
data across five major antibiotic classes and six adsorbent categories. Adsorption capacities ranged from 50 to
1,200 mg g⁻ ¹, with Metal–Organic Frameworks (MOFs) and carbon nanomaterials demonstrating the highest
laboratory-scale efficiencies.........
Antibiotic removal, Adsorption technologies, Antimicrobial resistance, Sustainability benchmarking,
Biochar composites, Life-cycle assessment, Water treatment systems
[1]. Ahmed, M. B., Zhou, J. L., Ngo, H. H., Guo, W., & Chen, M. (2015). Progress in the biological and chemical treatment
technologies for emerging contaminant removal from wastewater: A critical review. Journal of Hazardous Materials, 282, 52–77.
https://doi.org/10.1016/j.jhazmat.2014.06.045
|
Udu Chukwudi Emeka, Okpala Charles Chikwendu, OnukwuliSomto Kenneth |
||||||
| Supply Chain Resilience in the Age of Global Disruptions: AI Driven Risk Modeling and Optimization Frameworks for Climate, Conflict, and Pandemic Shocks | ||||||
Global supply chains are increasingly exposed to overlapping and systemic disruptions which arise from
climate change, geopolitical conflicts, and pandemics, thereby challenge traditional risk management and
sustainability strategies. Recent crises have revealed that reactive and static resilience approaches often
exacerbate environmental impacts while failing to ensure continuity under compound shocks. This study
proposes an integrated AI-driven risk modeling and optimization framework that is designed to enhance supply
chain resilience, while delivering measurable sustainability benefits...........
supply chain resilience, artificial intelligence, disruption risk modeling, sustainability optimization,
climate shocks, geopolitical conflict, pandemic disruptions
[1]. Aguh, P. S., and Okpala, C. C. (2025). Learning in the age of artificial intelligence tutors: Cognitive outcomes and equity in
automated education systems. International Journal of Engineering Research and Development, 21(12).
https://ijerd.com/paper/vol21-issue12/21128898.pdf
|
Abhir Maske, Harsh Mahendra, Dipanshu pathare, Darshan Kinekar, Pravesh Dhabekar |
||||||
| Person Recognition from Crowd Using Python and Open CV | ||||||
Spotting people in busy settings matters more now, thanks to uses like city monitoring, keeping
crowds safe, helping machines understand humans, and watching video feeds. Figuring out who is who gets
tough when bodies block each other, lighting shifts, angles change, visuals are fuzzy, or surroundings get
messy. This summary digs into up-to-date methods that aim to name persons in packed scenes - pulling apart
how these tools work on photos and footage, mainly through code built with Python and powered by OpenCV.
Starting off, the article outlines key steps in identifying people: spotting a person first, pulling out
distinguishing traits, then matching that identity...........
.......
[1]. Sun, D., Huang, J., Hu, L., Tang, J., & Ding, Z. (2022). ―Multitask Multigranularity Aggregation with Global Guided Attention
for Video Person Re-Identification‖. IEEE Transactions on Circuits and Systems for Video Technology, 32(11), 7758–7771.
|
Augustine, O., Osayande, A. D. |
||||||
| Synergistic Degradation of Shallow Aquifer Integrity in the Niger Delta Basin: A Critical Hydrogeochemical and Bacteriological Review of Urbanization, Industrial Effluence, and Atmospheric Acidification in Choba, Rivers State, Nigeria | ||||||
Potable water security represents one of the most critical public health challenges in coastal Sub-Saharan Africa,
yet the shallow unconfined aquifers of the Niger Delta Basin remain among the least-protected freshwater systems
on the continent. This review synthesizes hydrogeochemical and bacteriological data from hand-dug wells and
riverine systems across four communities in the Obio/Akpor Local Government Area, Rivers State, Nigeria—Choba,
Rumuokparali, Rumuekini, and Ozuoba—with the objective of characterizing the compounded threat landscape
confronting the Benin Formation aquifer. Measured pH values ranging from 4.60 to 5.78 confirm a state of critical
aquifer acidification that falls far below..........
Hydrogeochemistry; Niger Delta; Benin Formation; Acid Rain; Lead Toxicity; Water Governance;
Pathogenic Risk; Groundwater Contamination; Sub-Saharan Africa.
[1]. American Public Health Association (APHA). (2012). Standard methods for the examination of water and wastewater (22nd ed.).
American Water Works Association.
|
