8,100+ papers published18,500+ authors published44 countriesPublishing since 2014

Manuscripts

Recent Papers

Research Paper

Uncertainty-Calibrated and Explainable Machine Learning for Early Prediction of Academic Performance and Identification of At-Risk University Students

Early identification of students who may experience unsuccessful academic outcomes can support timely academic guidance, provided that predictions are evaluated for both discrimination and reliability. This study evaluates a Logistic Regression workflow using the Open University Learning Analytics Dataset (OULAD). Student outcomes were converted to a binary target, with Pass and Distinction treated as successful outcomes and Fail and Withdrawn as unsuccessful outcomes. Models were evaluated at weeks 2, 4, 6, and 8 using student characteristics, enrolment information, and virtual learning environment (VLE) activity. A second configuration added assessment-related features. The best single-split result occurred at week 8 for the activity-plus-assessment configuration (accuracy = 0.7789, F1 = 0.7796, ROC-AUC = 0.8654). Its Brier score and log loss were 0.1463 and 0.4394, respectively. Across confidence thresholds, selective accuracy increased as coverage decreased; at week 8 and a threshold of 0.90, the activity-plus-assessment configuration retained 29.7% of cases with 97.1% accuracy. Across three random seeds, its week-8 mean ROC-AUC was 0.8629 (SD = 0.0029). These findings suggest that later cutoffs and assessment-related information can improve predictive performance in this dataset. However, the availability time of assessment scores must be verified to rule out temporal leakage, and results require external validation before practical deployment.

Published by: Mohammad Zaid, Steave Saji, Rayhan Abdulla Thalsim

Author: Mohammad Zaid

Paper ID: V12I5-1256

Paper Status: published

Published: October 28, 2026

Full Details
Review Paper

AI-Driven Anomaly Detection, Identification and Countermeasures for Unmanned Aerial Vehicles: A Review of Sensor-, Flight-Data- and Counter-UAV-Based Approaches

Abstract Unmanned aerial vehicles (UAVs) are now used in logistics, agriculture, surveillance and the low-altitude economy, but their growth has created two linked problems: keeping UAVs themselves safe from faults and attacks, and protecting airspace from unauthorized UAVs. This paper reviews 111 studies compiled from seven source papers published between 2019 and 2026 (two comprehensive surveys on counter-UAV sensing and flight-data anomaly detection, one survey on machine learning and large language models (LLMs) for UAV safety and security, and four technical studies). The studies are organized into five areas: (i) multi-sensor detection, identification and localization of hostile UAVs; (ii) physical and cyber countermeasures; (iii) flight-data anomaly detection and recovery; (iv) sensor-malfunction and GNSS-spoofing detection; and (v) vibration-based fault detection and AI-driven safety and security, including LLMs. For each area we summarize the methods, reported accuracy and stated limitations, and compare them in tables. The review shows that deep learning with sensor fusion consistently outperforms single-sensor and classical methods, but that results are hard to compare because datasets differ, anomalies are usually injected artificially, and real-flight validation is rare. We close with a set of research gaps and future directions: public benchmarks, real-flight testing, onboard-efficient models, federated and LLM-based approaches, and joint safety-security frameworks.

Published by: Tuba Reyaz, Aftab Alam, Dr. Faiyaz Ahmad

Author: Tuba Reyaz

Paper ID: V12I5-1226

Paper Status: published

Published: October 28, 2026

Full Details
Research Paper

Quantum-Inspired Deep Learning for High-Dimensional Data Processing in Finance

This paper explores the application of quantum-inspired deep learning techniques for processing high-dimensional financial data, specifically focusing on predicting stock price movement using Apple Inc. (AAPL) stock data. We investigate the effectiveness of a quantum-inspired model in comparison to a standard Long Short-Term Memory (LSTM) network. The study incorporates various technical indicators as features and evaluates model performance using standard classification metrics and visualizations. The challenges of high-dimensional data in finance are discussed, and the potential benefits of quantum-inspired approaches in this domain are explored.

Published by: Manupati Ramana Kumar, Kokkiligadda Nischal varma, Kamireddy Yaswanth Reddy

Author: Manupati Ramana Kumar

Paper ID: V11I3-1184

Paper Status: published

Published: October 27, 2026

Full Details
Research Paper

A Comparative Review of Nanomaterials for Neuroprotection in Neurodegenerative Diseases

Neurodegenerative illnesses like Alzheimer's, Parkinson's, and ALS cause progressive injury to the brain, causing loss of memory, movement, and cognitive functions over time. The problem with these diseases is that most drugs cannot pass through the brain's protective barrier—the blood-brain barrier (BBB). In this review, the new use of nanomaterials—extremely tiny particles measured in nanometers—is described to transport drugs across the BBB without harming brain cells. We analyzed eight of the most well-researched types of nanomaterials: fat-based, plastic-like, dendrimers, carbon-based, gold, cerium oxide, iron oxide nanoparticles, and quantum dots. Each was assessed on its ability to deliver drugs to the brain, safety, stability, and performance in laboratory tests. Fat-based and plastic-like nanoparticles outperformed all others based on biocompatibility and drug delivery ability. Gold nanoparticles were highly multifunctional and versatile for therapy and imaging. Cerium oxide proved to be a great antioxidant and could protect neurons from injury. However, some nanomaterials like carbon nanotubes and quantum dots were of concern due to toxicity. The review concludes that just as there is no single nanomaterial that is perfect, their benefits can be leveraged in hybrid systems to enable more powerful, targeted, and safer treatment. In fact, nanotechnology has tremendous potential for future advances in the fight against brain disease by enabling precise and protective drug delivery to the brain.

Published by: Ayaan Bansal

Author: Ayaan Bansal

Paper ID: V11I3-1369

Paper Status: published

Published: October 27, 2026

Full Details
Research Paper

“Design of Peptide Inhibitors Targeting MYC Oncogenic Protein Complexes”

Cancer remains one of the leading causes of death worldwide, with the MYC oncogene being a key driver of tumor progression through its role in promoting uncontrolled cell growth. This study aims to design and evaluate peptide inhibitors targeting the interaction between MYC and DNA, which is essential for MYC’s oncogenic function. Utilizing advanced computational methods, including RF diffusion, AlphaFold, and PyMOL, 30 potential peptide candidates were identified. These peptides were assessed based on their IPAE values, which ranged from 6.151 to 9.981, reflecting their effectiveness in disrupting MYC-DNA interactions. The use of AlphaFold enabled accurate prediction of the 3D structures of the MYC-MAX-DNA complex, while PyMOL provided visualization and structural analysis to confirm binding sites and key hotspots where the peptides interact. This detailed analysis confirmed that the peptides effectively target critical regions within the complex. Our findings underscore the potential of these peptides as novel inhibitors of MYC-driven cancer progression. The promising results suggest that these peptides could serve as the basis for new targeted cancer therapies. Moving forward, experimental validation of the peptide candidates will be conducted to confirm their binding affinity and biological activity. Additionally, structural refinement and optimization of the peptide designs will be pursued to enhance their therapeutic potential. Preclinical studies will be essential to evaluate the efficacy and safety of these peptide inhibitors in vivo. This research provides a foundation for developing innovative treatments aimed at targeting MYC-driven cancers.

Published by: Varshika Ram Prakash

Author: Varshika Ram Prakash

Paper ID: V11I3-1379

Paper Status: published

Published: October 27, 2026

Full Details
Research Paper

Autonomous Threat Detection and Response in Cloud Environments Using AI And Machine Learning: Focus on Real-Time AI Driven Anomaly Detection and Self-Healing Cloud Security Architectures

Cloud threat detection and response technologies are at the forefront of maintaining cybersecurity amid growingly dynamic and complex infrastructures. The technologies are programmed to identify, assess, and respond to likely threats in real time to provide cloud service integrity and availability. Static rule-based mechanisms and manual control mechanisms find it challenging to keep pace with evolving attack patterns, and this has necessitated the use of automated, intelligent solutions. This paper explores the employment of autonomous threat detection and response systems using artificial intelligence (AI) and machine learning (ML). The binary classification model was used to identify harmless and threat-related network traffic from a Kaggle-based DDoS dataset. The data underwent rigorous preprocessing, exploratory data analysis, and feature engineering. Five machine learning (ML) models were trained and evaluated against performance measures like accuracy, precision, F1-score, and detection time. The Decision Tree model gave better performance, with high accuracy of 98.0% and real-time capability. Its integration into cloud infrastructures allows for self-healing, adaptive cybersecurity defenses.

Published by: Mariam Sanusi, Tolulope Onasanya, Oduwunmi Odukoya, Moyinoluwa Senjobi

Author: Mariam Sanusi

Paper ID: V11I3-1375

Paper Status: published

Published: October 27, 2026

Full Details