1 October 2026
Microbiome-based classification of multiple neurological conditions is challenged by sparse features, class imbalance, and heterogeneity between studies. We propose Multi-Stream Adaptive Feature Integration (MASFI), which combines CLR-transformed gen...
1 October 2026
Adversarial policies provide a practical means of stress-testing reinforcement-learning agents by inducing failure through environment interactions without modifying the deployed victim policy. Learning effective adversarial policies under partial ob...
1 October 2026
Speech-to-Summary cascade performance for low-resource, morphologically rich languages depends on interactions among language, recognition errors, and translation direction. This study develops an adaptive Speech-to-Summary pipeline for six Turkic la...
Efficient and scalable numerical methods for time-dependent partial differential equations are of central importance. This study extends our previous examinations of OpenCL-based parallel implementation of three explicit finite difference schemes: th...
Chaos-based image ciphers may exhibit favorable statistical outputs while retaining exploitable algebraic relations. Following Kerckhoffs’s principle, this paper analyzes a published memristive Hopfield neural network color image cryptosystem a...
Digital-image protection often requires two safeguards at once: the content must remain unintelligible to an unauthorized reader, and the communication itself should not be conspicuous. We introduce AQI-HNS, an encryption-first framework that couples...
Most neural decoding methods prioritize predictive accuracy but provide limited means to test hypotheses about latent representational geometry. Guided by projection geometry, we recorded neural activity from the ENTO–MVL pathway of five pigeon...
Surface electromyography (sEMG) gesture classifiers consistently achieve high accuracy under random-split validation, yet performance degrades substantially under participant-independent evaluation, and classification accuracy alone does not establis...
Gallstones, also known as cholelithiasis, are hardened deposits of bile (digestive fluid) formed in the gallbladder. Gallstones are a common gastrointestinal condition. They often lead to complications like cholecystitis, biliary obstruction, and pan...
Machine learning inference is moving to the edge due to latency, energy, and privacy constraints. The growing complexity of edge workloads places increasing pressure on memory hierarchies, making data movement a major limitation for both performance...
The precise and prompt identification of ocular conditions, such as diabetic retinopathy (DR), diabetic macular edema (DME), or glaucoma, often depends on the collaborative analysis of medical imaging techniques such as fundus photography or optical...
This paper reports a document-based, multiple-case study of six Internet of Things (IoT) prototypes designed and simulated during a one-week immersive course, “IoT for Data Intelligence,” delivered in July 2026 within the professional Mas...
This study conducts a comprehensive bibliometric analysis of research on generative-AI/LLM-enabled e-assessment in higher education, drawing on 243 peer-reviewed journal articles published between 2023 and 2026 and indexed in the Scopus database. Emp...
Background: Although gamification can enhance learner motivation and engagement, increased engagement does not consistently translate into improved conceptual learning. This discrepancy may be particularly relevant for novice medical learners process...
Tool-capable multi-agent systems can improve cybersecurity response, but collaboration also creates new failure modes: compromised agents can bias shared evidence, overconfident recommendations can propagate through a coalition, and apparently correc...
This paper presents, as a proof-of-concept, a novel geometrically constrained, aerodynamics-guided variational autoencoder generative adversarial network (GCAG-VAEGAN) framework for aerofoil design, aimed at improving the aerodynamic feasibility and...
Data centers consumed 415 TWh of electricity in 2024, about 1.5% of global demand, and foundation model training and inference are a growing part of this load. As training and inference continue to grow, energy-efficient foundation models are becomin...
Cryptographic inventories and runtime detection identify cryptographic use but do not establish implementation conformance or policy satisfaction. We present a deterministic composition linking admitted runtime evidence, provenance closure, exact imp...
Web security audits of SQL injection (SQLi) vulnerabilities still depend primarily on the analyst’s skill and knowledge to select the right tools, interpret results, and determine whether there is any vulnerability. This work presents SQLiAgent...
Architectural erosion and technical debt make it difficult to preserve intended design principles in long-lived enterprise software systems. Clean Architecture offers principles for separating business rules from frameworks, persistence and interface...
Routine clinical data can support the identification of individuals with diabetes, but model performance may change when disease prevalence and feature distributions differ across datasets. We evaluated a machine learning framework that combines clin...
Assurance for autonomous agents depends on operational evidence about policy decisions, actions, execution, effects, provenance, and enforcement. This study tests whether bounded assurance claims remain semantically admissible when that evidence is a...
Reactive autoscalers compress workload state into a scalar, but bounded ceiling partitions jointly induced by signal and target determine replica recommendations. We formalize five signals and distinguish the positive target, bounded desired recommen...
The rapid growth of video streaming, which now accounts for over 70% of global internet traffic, has intensified scrutiny of the energy footprint of end-user streaming devices. This paper presents FAMIUM Green, a fully automated hardware-in-the-loop...
Human–AI teaming is increasingly attractive also for safety-critical industrial decision making, where the reliability of the joint system depends not only on the accuracy of the AI but also on the sequence in which the human and the AI contrib...
The proliferation of IoT deployments has exposed critical vulnerabilities in MQTT-based systems, particularly ciphertext-repetition leakage in telemetry encryption, where identical plaintext blocks under a fixed key—common for static sensor rea...
In physical education (PE), computer vision (CV) technologies are increasingly used to analyze learners’ movements and provide performance-related feedback. However, the overall effectiveness of CV-assisted instruction and the conditions associ...
Cyber risk assessment often combines likelihood and impact, but likelihood is difficult to justify when incident data are scarce and threat relevance depends on a specific actor. Existing attacker-aware methods improve context but frequently require...
Global Navigation Satellite Systems (GNSSs) are widely integrated into military missile guidance systems to provide positioning, velocity, and timing information for accurate navigation and targeting. However, GNSS signals are inherently vulnerable d...
LLM-based systems used for tutoring can produce fluent and apparently plausible explanations, but they do not guarantee Technical Correctness, which is paramount in STEM fields such as Electrical Circuit Analysis. This study investigates how three LL...
Although speech-based depression assessment has received considerable attention, achieving reliable confidence and cross-corpus applicability with explanation of prediction still remains challenging. This study presents a reliability-aware framework...
Educational games are widely used to introduce programming concepts and foster computational thinking skills among young learners by offering engaging and interactive environments that enhance motivation and encourage active participation. However, l...
Wireless communication developments have significantly improved communications with each generation. The upcoming sixth-generation (6G) cellular wireless standard has raised expectations, particularly for Internet of Things (IoT) applications. 6G-bas...
Java Card virtual machines execute from non-volatile memory in secure elements, where repeated reference indirection adds latency to frequently executed instructions. This paper proposes link-time bytecode quickening for the statically resolvable inv...
An implementation that passes internal round-trip tests may still produce artifacts that another library cannot consume. We present an auditable workflow for selected-vector conformance and raw-artifact interoperability testing of ML-KEM and ML-DSA i...
Modern network infrastructures are under attack from increasingly sophisticated attacks that static, rule-based defenses cannot adequately mitigate. We introduce a multilayer anomaly detection and mitigation framework for Software-Defined Networking...
Monthly electricity demand forecasts are often affected by outliers and moving-holiday effects. This study proposes a forecasting framework that integrates regression with ARIMA errors (regARIMA), Hodrick–Prescott (HP) filter decomposition, and...
This research provides deep insights into the capabilities of encoder models, offering a unique, controlled benchmark of over 20 state-of-the-art models. The aim is to analyze the viability of a potentially advantageous recommender architecture that...
Cryptographic dependency updates can install cleanly and pass visible regression tests while changing project-facing behavior or leaving an application inside a vulnerable version range. This study presents VeriCrypt-Agent, an evidence-grounded workf...
Single-board computers (SBCs) are increasingly being used in embedded and edge computing applications, where power stability can affect computational reliability. This work experimentally characterizes an ARM-based SoC in a Raspberry Pi 5 under contr...
Background/Objectives: Real-time arthroscopic bone drilling in simulators requires high graphics and haptic update rates while deforming bone visually. We present a fully GPU-resident, shader-based pipeline for the Virtual Rotator Cuff Arthroscopic S...
Artificial Intelligence (AI) and Media and Information Literacy (MIL) are recognised as vital components of adult secondary education. However, we know little about how adult learners engage with AI in authentic educational contexts, given that AI ad...
Substation-level carbon-emission factors (CEFs) are operationally relevant because substations concentrate transformer losses, auxiliary consumption, and sulfur hexafluoride (SF6) leakage at the interface between transmission and distribution. Howeve...
Generative artificial intelligence (AI) can improve students’ work while assistance is available, but better AI-assisted performance does not necessarily show what students have learned or can do independently. The methodological gap is that ou...
Multimodal large language models (MLLMs) often struggle with open-ended questions requiring the integration of visual evidence, indirect textual clues, and background knowledge. We investigate whether team-based inference improves performance on Russ...
Adversarial patch attacks pose a tangible physical-world threat to traffic sign recognition in autonomous driving systems. Current state-of-the-art defenses based on image reconstruction require dual-model deployment and add per-frame inference laten...
Deep networks for optical coherence tomography (OCT) classification usually learn directly from image appearance, which leaves coherent speckle, depth-dependent attenuation, point-spread-function blur, and refractive distortion entangled with patholo...
Medical image classification models often struggle to generalise across heterogeneous clinical domains owing to variations in visual characteristics, acquisition conditions, and class imbalance. Existing studies largely address these challenges indep...
Log anomaly detection requires models that capture long-range event dependencies without the quadratic sequence-length cost of self-attention. We present LogMamba, a reconstruction-based model that combines a bidirectional selective state-space branc...
Multilingual code-switched language identification remains a challenging task due to frequent language alternation, lexical ambiguity, and the limited availability of annotated corpora for low-resource languages. While transformer-based language mode...
