Skip to Content

1,695 Results Found

  • Article
  • Open Access
2,440 Views
23 Pages

The growing number of domain-specific machine learning benchmarks has driven methodological progress, yet real-world deployments require a different evaluation approach. Model-aware synthetic benchmarks, designed to emphasize failure modes of existin...

  • Article
  • Open Access
516 Views
29 Pages

Sequence-Aware Dataset Auditing for Leakage-Free Benchmarking of YOLO Detectors for Bottle Detection

  • Rafael Reveles-Martínez,
  • Sebastián Burciaga-Sosa,
  • José M. Celaya-Padilla,
  • Salvador Castro-Tapia and ,
  • Huizilopoztli Luna-García,
  • Humberto Morales-Magallanes,
  • Mayra N. Regalado-Pérez,
  • César Landeros-Soriano,
  • Umanel A. Hernández-González and
  • Hamurabi Gamboa-Rosales
  • + 6 authors+ 1 author

This work presents a reproducible YOLO-based pipeline for bottle detection in sandy environments, emphasizing dataset integrity, leakage-free evaluation, and deployment-oriented model selection. A one-class dataset of 1585 images and 3167 annotated b...

(This article belongs to the Section Environmental Technology)
  • Article
  • Open Access
980 Views
33 Pages

8 May 2026

Nonlinear classification problems such as XOR are widely used to evaluate machine learning models beyond linear separability. In this study, a comprehensive benchmark is proposed to analyze eight classifiers (Logistic Regression, Linear SVM, RBF SVM,...

  • Article
  • Open Access
661 Views
17 Pages

28 April 2026

Automatic detection of deceptive intent in negotiation dialogue remains difficult because deceptive utterances are rare, context-dependent, and pragmatically subtle. This study develops a deployment-oriented evaluation pipeline for negotiation analyt...

  • Article
  • Open Access
1 Citations
1,489 Views
17 Pages

SADAMB: Advancing Spatially-Aware Vision-Language Modeling Through Datasets, Metrics, and Benchmarks

  • Giorgos Papadopoulos,
  • Petros Drakoulis,
  • Athanasios Ntovas,
  • Alexandros Doumanoglou and
  • Dimitris Zarpalas

29 September 2025

Understanding spatial relationships between objects in images is crucial for robotic navigation, augmented reality systems, and autonomous driving applications, among others. However, existing vision-language benchmarks often overlook explicit spatia...

(This article belongs to the Topic Visual Computing and Understanding: New Developments and Trends)
  • Article
  • Open Access
5 Citations
3,761 Views
20 Pages

16 January 2026

A growing challenge in mobile robotics is the reliance on complex graphical interfaces and rigid control pipelines, which limit accessibility for non-expert users. This work introduces a latency-aware benchmarking framework that enables natural-langu...

(This article belongs to the Special Issue Multimodal Sensing, Fusion, and VLMs for Scene Understanding and Robot Vision)
  • Article
  • Open Access
1 Citations
2,115 Views
18 Pages

Large language models (LLMs) have begun to function as assistants or teammates in language learning, teaching, and research. However, what prerequisites are required for LLMs to reliably play these roles, and how such prerequisites should be measured...

(This article belongs to the Topic Learning to Live with Gen-AI)
  • Article
  • Open Access
148 Views
26 Pages

Causal Multivariate Forecasting of Diesel Hydrotreating Variables on a Reproducible Synthetic Benchmark

  • Gulzhan Uskenbayeva,
  • Salimzhan Tassanbayev,
  • Gulnara Abitova,
  • Guldana Taganova and ,
  • Aliya Shukirova,
  • Ardak Mukhamedrakhimova,
  • Korlan Kulniyazova and
  • Lili Nurliyana Abdullah
  • + 3 authors+ 0 author

26 October 2026

This study evaluates a causal, six-target, 30 min forecasting component for diesel hydrotreating using campaign-separated synthetic data, not a deployed digital twin. An empirical, engineering-constrained simulator generated 30 original campaigns; th...

(This article belongs to the Section Evolutionary Algorithms and Machine Learning)
  • Article
  • Open Access
465 Views
30 Pages

A large heel can develop within seconds on a small fishing vessel, so a short-horizon forecast of inclination is useful for safety only if it reports both the predicted angle and its uncertainty and is turned into an explicit warning decision. We pre...

(This article belongs to the Special Issue AI-Driven Optimization of Ship Performance and Navigation Safety)
  • Article
  • Open Access
1 Citations
2,826 Views
41 Pages

A Reproducible Benchmarking Methodology for Machine Learning Hardware: Performance–Energy Trade-Offs from GPUs to Apple Silicon

  • Oscar H. Sierra-Herrera,
  • Mario Eduardo González Niño,
  • Edwin Francis Cárdenas Correa,
  • Jersson X. Leon-Medina and
  • Francesc Pozo

4 May 2026

While hardware selection is widely recognized as a key factor in machine learning performance, systematic and reproducible evaluation across heterogeneous and accessible platforms remains limited, particularly when jointly considering execution time,...

(This article belongs to the Collection Feature Papers in Algorithms for Multidisciplinary Applications)
  • Review
  • Open Access
12 Citations
6,719 Views
30 Pages

A Comprehensive Review and Benchmarking of Fairness-Aware Variants of Machine Learning Models

  • George Raftopoulos,
  • Nikos Fazakis,
  • Gregory Davrazos and
  • Sotiris Kotsiantis

16 July 2025

Fairness is a fundamental virtue in machine learning systems, alongside with four other critical virtues: Accountability, Transparency, Ethics, and Performance (FATE + Performance). Ensuring fairness has been a central research focus, leading to the...

(This article belongs to the Special Issue AI-Driven Solutions for Smart Systems in Engineering, Computing, Education, and Society)
  • Article
  • Open Access
712 Views
32 Pages

16 September 2026

Large language models (LLMs) are increasingly applied to software vulnerability detection, but evaluations report accuracy while ignoring inference cost and energy and under-represent open-weight models relative to proprietary systems. We benchmark e...

(This article belongs to the Special Issue Trustworthy and Efficient Large Language Models: Methods, Systems and Applications)
  • Article
  • Open Access
889 Views
21 Pages

Computer-aided drug discovery increasingly depends on virtual-screening workflows that remain reliable under severe class imbalance, chemical redundancy and early-recognition constraints. In this study, we developed a leakage-aware prioritization wor...

(This article belongs to the Special Issue Computer-Aided Drug Discovery: Computational Chemistry and Cheminformatics)
  • Article
  • Open Access
96 Views
23 Pages

Deep models report accuracies at or above 99% on the 5G-NIDD benchmark, yet much of that headline reflects how the data are prepared. We show that two forms of leakage (a random split that mixes capture sessions, and identifier-like features that sta...

(This article belongs to the Section Security Engineering & Applications)
  • Article
  • Open Access
872 Views
19 Pages

Difference visual question answering (Diff-VQA) aims to answer questions by identifying and reasoning about differences between medical images. Existing methods often rely on simple feature subtraction or fusion to model image differences, while over...

(This article belongs to the Section Medical Imaging)
  • Perspective
  • Open Access
883 Views
16 Pages

Standardizing Benchmarks for Plant Genomic Prediction

  • Min Yan,
  • Wenying Wang,
  • Ying Zhang,
  • Han Guo and ,
  • Zhen Xue,
  • Xueyang Wang and
  • Jun Yan
  • + 2 authors+ 0 author

9 June 2026

Genomic prediction (GP) is now widely used in crop improvement, but the rapid expansion of GP methods has outpaced the development of standardized evaluation practices. Reported gains from deep learning and other complex models are difficult to inter...

(This article belongs to the Special Issue Precision Assistance for Crop Genetic Improvement: Big Data, Artificial Intelligence and Machine Learning)
  • Article
  • Open Access
1 Citations
824 Views
23 Pages

Leakage-Aware Transfer Learning with Explainable AI and CPU-Efficient Deployment for Mango Leaf Disease Classification on the MangoLeafBD Benchmark

  • Wirapong Chansanam,
  • Avshalom Elmalech,
  • Suparp Kanyacome,
  • Prasert Luekhong and ,
  • Natthakan Iam-On and
  • Tossapon Boongoen
  • + 1 author+ 0 author

12 July 2026

Background and Aim: Mango (Mangifera indica) is a globally important fruit crop whose productivity is repeatedly threatened by foliar diseases such as anthracnose, bacterial canker, powdery mildew, die-back, and sooty mould. Although deep learning ha...

(This article belongs to the Special Issue The Application of Deep Learning in Image Processing)
  • Article
  • Open Access
372 Views
37 Pages

GARS: Gap-Aware Residual Selection for Long-Horizon Time-Series Forecasting

  • Sunwoo Yeon,
  • Jaeyong Kim,
  • Hyeonjung Kim,
  • Jihwan Won and ,
  • Hyeonwoo Kim,
  • Donggyu Sim and
  • Cheolsoo Park
  • + 2 authors+ 0 author

12 September 2026

Intelligent systems deployed in smart cities, smart grids, environmental monitoring, and other data-driven applications increasingly depend on reliable multivariate time-series forecasting. Recent deep forecasting models have achieved strong performa...

(This article belongs to the Special Issue Machine/Deep Learning Applications and Intelligent Systems, 2nd Edition)
  • Article
  • Open Access
349 Views
33 Pages

Does the Quantum Layer Help? A Leakage-Aware Benchmark of Hybrid Quantum–Classical Models for Brain Tumor MRI Classification

  • Tuan-Linh Duong,
  • Pande Wikantyasa Maswita,
  • Tony Sumaryada,
  • Sitti Yani and ,
  • Thanh-Tai Duong,
  • Hiba Omer,
  • Nissren Tamam and
  • Abdelmoneim Sulieman
  • + 3 authors+ 0 author

24 October 2026

Background/Objectives: Hybrid quantum–classical neural networks are reported to classify brain tumors on magnetic resonance imaging (MRI) accurately, but these reports rarely control for data leakage or test whether the quantum circuit contribu...

(This article belongs to the Special Issue Quantum Machine Learning in Medical Image and Signal Processing)
  • Article
  • Open Access
1 Citations
717 Views
20 Pages

Mental health discourse may reflect social relationships, cultural norms, and religious factors that shape how individuals express and interpret distress. Existing NLP research on mental health has advanced the detection of depression, anxiety, suici...

(This article belongs to the Special Issue Low-Resource Languages in the Age of Large Language Models)
  • Article
  • Open Access
1,880 Views
28 Pages

1 March 2026

Large language models (LLMs) are increasingly deployed as information systems that evolve over time, where managing internal knowledge—acquisition, retention, and removal—becomes essential. In practice, these processes are primarily reali...

(This article belongs to the Special Issue Learning and Knowledge: Theoretical Issues and Applications)
  • Article
  • Open Access
1 Citations
782 Views
24 Pages

Enhancing Thai Sentiment Analysis with WangchanBERTa and Instance-Class-Aware Dynamic Kernel Selection

  • Panida Songram,
  • Suchart Khummanee,
  • Jirapond Muangprathub and
  • Khanabhorn Kawattikul

25 May 2026

Thai sentiment analysis on social media remains challenging due to the lack of explicit word boundaries, informal expressions, code-mixing, short text length, and severe class imbalance, particularly in the WISESIGHT benchmark dataset. Although trans...

  • Article
  • Open Access
1 Citations
5,449 Views
25 Pages

Benchmarking with a Language Model Initial Selection for Text Classification Tasks

  • Agus Riyadi,
  • Mate Kovacs,
  • Uwe Serdült and
  • Victor Kryssanov

The now-globally recognized concerns of AI’s environmental implications resulted in a growing awareness of the need to reduce AI carbon footprints, as well as to carry out AI processes responsibly and in an environmentally friendly manner. Benc...

(This article belongs to the Section Data)
  • Article
  • Open Access
1 Citations
1,756 Views
20 Pages

28 July 2025

Occlusion remains a major challenge in person re-identification, as it often leads to incomplete or misleading visual cues. To address this issue, we propose a dual-branch occlusion-aware network (DOAN), which explicitly and implicitly enhances the m...

  • Article
  • Open Access
793 Views
28 Pages

Multimorbidity risk identification in elderly health consultation scenarios is challenging because chronic disease history and medication exposure may interact through complex causal pathways. Existing LLM-, RAG-, and graph-based retrieval methods of...

(This article belongs to the Topic Generative AI and Interdisciplinary Applications)
  • Article
  • Open Access
409 Views
37 Pages

Bridge-Aware Reinforced Compositional Exploration and Decomposition for Biomedical Multi-Hop Answering

  • Warodom Phungjununt,
  • Kanabadee Srisomboon,
  • Wilaiporn Lee,
  • Akara Prayote and
  • Luepol Pipanmekaporn

Biomedical question answering requires multi-hop reasoning over implicit relationships—e.g., identifying gene-associated diseases to retrieve target drugs. However, closed-book frontier language models achieve only ~14.57% precision on two-hop...

(This article belongs to the Special Issue Trustworthy AI: Integrating Knowledge, Retrieval, and Reasoning)
  • Article
  • Open Access
357 Views
22 Pages

Touchless interfaces for embedded systems require models that are both compact and evaluated under protocols that reflect realistic generalization. Public low-resolution gesture datasets can obscure this requirement because repeated samples, temporal...

  • Article
  • Open Access
171 Views
22 Pages

12 October 2026

Demand-side flexibility is inherently determined by complex local operations, whereas system-level coordination requires a compact and tractable representation of this flexibility. Bridging this gap is essential for economically coordinating heteroge...

(This article belongs to the Special Issue Challenges in Energy Management System for Wholesale, Retail, and Peer-to-Peer Energy Trading)
  • Article
  • Open Access
21 Views
38 Pages

Toward a Lifecycle-Aware Decision Support System Using Fundamental Data for Robust Stock Selection and Asset Allocation

  • Ali Abrishami,
  • Jafar Habibi,
  • Amirali Jarrahi,
  • Dariush Amiri and
  • Mohammadamin Fazli

18 November 2026

As AI-driven decision systems move from research prototypes into continuous industrial operation, the central engineering challenge shifts from accuracy to system-level reliability, accountability, and lifecycle integration. Financial decision suppor...

(This article belongs to the Special Issue Decision Intelligence and Its Applications)
  • Article
  • Open Access
1 Citations
741 Views
30 Pages

Dynamic Multi-Exposure HDR Reconstruction via Dual-Branch Base-Detail Collaboration

  • Qin Zhou,
  • Min Chen,
  • Feifan Cai,
  • Zihao Zhang and
  • Youdong Ding

23 April 2026

Dynamic multi-exposure high dynamic range (HDR) image reconstruction remains challenging because it must preserve globally consistent luminance and structure while recovering fine-grained local textures from low dynamic range (LDR) inputs corrupted b...

(This article belongs to the Special Issue Recent Advances and New Trends in Computer Vision and Image Processing)
  • Article
  • Open Access
889 Views
47 Pages

APCI: A Complexity-Aware Framework for Computational Software Effort Estimation in Machine Learning-Based Intrusion Detection Systems

  • Vignaraj Ananth Vikraman,
  • Sumendra Yogarayan,
  • Kalaiarasi Sonai Muthu and
  • Manikandan Thirumalaisamy

11 August 2026

The increasing adoption of machine learning and deep learning techniques in intrusion detection systems (IDSs) has substantially increased the computational complexity of model development due to large-scale datasets, sophisticated model architecture...

(This article belongs to the Special Issue Anomaly and Intrusion Detection in Networks)
  • Article
  • Open Access
3 Citations
1,928 Views
17 Pages

11 September 2023

Aspect-level sentiment classification (ALSC) is a fine-grained sentiment analysis task that aims to predict the sentiment of the given aspect in a sentence. Recent studies mainly focus on using the Graph Convolutional Networks (GCN) to deal with both...

(This article belongs to the Special Issue Advancement of Mathematical Methods in Feature Representation Learning for Artificial Intelligence, Data Mining and Robotics, 2nd Edition)
  • Article
  • Open Access
4 Citations
2,950 Views
16 Pages

Visual State Space Model for Image Deraining with Symmetrical Scanning

  • Yaoqing Zhang,
  • Xin He,
  • Chunxia Zhan and
  • Junjie Li

9 July 2024

Image deraining aims to mitigate the adverse effects of rain streaks on image quality. Recently, the advent of convolutional neural networks (CNNs) and Vision Transformers (ViTs) has catalyzed substantial advancements in this field. However, these me...

(This article belongs to the Special Issue Advances in Computer Vision, Pattern Recognition, Machine Learning and Symmetry)
  • Article
  • Open Access
369 Views
27 Pages

Resilience Metric and Enhancement for Adversarial Operational Loop Networks via Reinforcement Learning

  • Jidong Sun,
  • Xiaobo Li,
  • Zhi Zhu,
  • Wei Li and ,
  • Tao Wang,
  • Zhijie Huang and
  • Jie Zhang
  • + 2 authors+ 0 author

19 September 2026

Resilience optimization in adversarial Multi-Agent Mission Systems (MAMSs) requires a decision mechanism whose objective is explicitly aligned with the resilience metric, not merely resilience measurement. This paper proposes a net-effectiveness-base...

(This article belongs to the Section Systems Engineering)
  • Article
  • Open Access
3 Citations
1,435 Views
37 Pages

Unauthorized farmland excavation is a prominent manifestation of farmland non-agriculturalization, and its effective monitoring depends on structured representations of objects and their spatial interactions in complex scenes. However, the existing c...

(This article belongs to the Topic Geospatial AI: Systems, Model, Methods, and Applications)
  • Article
  • Open Access
642 Views
28 Pages

The proliferation of Internet of Things (IoT) devices operating at the network edge has created unprecedented demand for distributed machine learning capable of functioning under severe resource constraints. Federated learning (FL) has emerged as a p...

(This article belongs to the Special Issue 15th Anniversary of Journal of Low Power Electronics and Applications)
  • Article
  • Open Access
2 Citations
1,123 Views
28 Pages

LSTM-VAE for Temporal Anomaly Detection in Drone Trajectory Analysis: A Comparative Study for Critical Infrastructure Protection

  • Hari Hara Babu Saripalli,
  • Jyothsna Laxmi Saripalli,
  • Leonel Lagos and
  • Himanshu Upadhyay

Unauthorized commercial drone activity around critical infrastructure motivates the development of trajectory-level anomaly detection. We present a rigorous benchmarking study of variational autoencoder methods for drone trajectory anomaly detection...

(This article belongs to the Special Issue Wireless Sensor Networks and Internet of Things—2nd Edition)
  • Feature Paper
  • Article
  • Open Access
877 Views
19 Pages

Path-aware networking architectures, such as SCION, give endpoints explicit visibility into multiple inter-domain paths, opening new opportunities for data-driven path selection, reliability prediction, and automated diagnosis. However, the lack of s...

(This article belongs to the Topic Machine Learning in Communication Systems and Networks, 3rd Edition)
  • Article
  • Open Access
1 Citations
732 Views
27 Pages

9 April 2026

Accurate medium-horizon load forecasting and risk-aware unit commitment are critical for high-load power systems. This study develops an integrated prediction–optimization framework that couples 744 h recursive load forecasting with uncertainty...

(This article belongs to the Special Issue Mathematical Modelling and Numerical Analysis in Electrical Engineering, 3rd Edition)
  • Review
  • Open Access
426 Views
78 Pages

20 October 2026

Object detection has evolved from classical feature-based approaches to deep learning-based frameworks, with the YOLO (You Only Look Once) family emerging as one of the most widely adopted paradigms for real-time object detection. Despite rapid archi...

  • Review
  • Open Access
1 Citations
674 Views
28 Pages

Quantitative structure–activity relationship (QSAR) modeling has conventionally relied on expert-designed molecular descriptors to encode chemical structures. DeepSnap is a descriptor-free QSAR approach that converts prepared three-dimensional...

(This article belongs to the Section Molecular Pharmacology)
  • Article
  • Open Access
10 Citations
4,298 Views
18 Pages

Accurate forecasting of multivariate traffic flow poses formidable challenges, primarily due to the ever-evolving spatio-temporal dynamics and intricate spatial heterogeneity, where the heterogeneity signifies that the correlations among locations ar...

(This article belongs to the Topic Spatial Decision Support Systems for Urban Sustainability)
  • Article
  • Open Access
4 Citations
2,782 Views
17 Pages

31 January 2024

The benchmarking of force control algorithms has been significantly investigated in recent years. High-fidelity experimental benchmarking outcomes may require high-end electronics and mechanical systems not to compromise the algorithm’s evaluat...

(This article belongs to the Section Control Systems)
  • Article
  • Open Access
684 Views
39 Pages

USX-PGD: Uncertainty-Aware, Sparse, and Explainable Reduced-Order Modelling for Two-Phase Reservoir Simulation

  • Walid Tebib,
  • Idir Belaidi,
  • Tarek Berghout and
  • Mohamed Abdessamed Ait Chikh

16 August 2026

High-fidelity reservoir simulation is too costly for multi-query tasks such as history matching and production optimisation. Existing reduced-order models (ROMs) mitigate this cost but generally lack uncertainty quantification, spatial sparsity, and...

(This article belongs to the Section Petroleum and Low-Carbon Energy Process Engineering)
  • Article
  • Open Access
459 Views
26 Pages

Learning to Expect the Unexpected: Benchmarking and Detecting Unexpected Road Hazards

  • Temirova Zubayda Okmirzaevna,
  • Shehzad Ali,
  • Rafał Scherer,
  • Arslan Munir and
  • Khan Muhammad

29 September 2026

Unexpected road hazards remain a critical challenge for driving safety, as they exhibit irregular appearances, vary widely in scale, and frequently arise under adverse environmental conditions. Existing detection approaches often struggle to achieve...

(This article belongs to the Special Issue Deep Computing Approaches in the Internet of Things and Computer Vision)
  • Article
  • Open Access
443 Views
16 Pages

Battery condition directly affects the reliability, resilience, and safety of microgrids, making physically interpretable battery information an important input to situation awareness. In practical microgrid operation, battery monitoring commonly rel...

(This article belongs to the Special Issue Advancements in Battery Fault Modeling, Detection, Diagnosis, and Digital Twin Technologies)
  • Article
  • Open Access
521 Views
21 Pages

Secure vehicle-to-vehicle communication is essential for electric-vehicle platoons because broadcast wireless links may expose safety and control messages to passive eavesdropping. This paper investigates a physical-layer security (PLS) framework for...

(This article belongs to the Topic Intelligent Optimization, Decision-Making and Privacy Preservation in Cyber–Physical Systems)
  • Article
  • Open Access
1,048 Views
19 Pages

Benchmarking Spatial Clustering Methods for Mass Spectrometry-Based Spatial Metabolomics

  • Yunning Lu,
  • Zhanlong Mei,
  • Haoke Deng,
  • Yun Zhao and ,
  • Chunlu Feng and
  • Siqi Liu
  • + 1 author+ 0 author

Background: Mass spectrometry imaging (MSI) enables in situ mapping of metabolite distributions within tissues, and spatial clustering is a key step for delineating metabolically distinct regions. Nevertheless, spatial clustering methods have not bee...

(This article belongs to the Special Issue Mass Spectrometry Imaging and Spatial Metabolomics—2nd Edition)
  • Article
  • Open Access
4 Citations
3,187 Views
13 Pages

Enhancing QoE for Mobile Users by Environment-Aware HTTP Adaptive Streaming

  • Weizhan Zhang,
  • Hao He,
  • Shuyan Ye,
  • Zhiwen Wang and
  • Qinghua Zheng

27 October 2018

HTTP adaptive streaming (HAS) has become a dominated media streaming paradigm in today’s Internet, which enriches the user’s experience by matching the video quality with the dynamic network conditions. A range of HAS mechanisms have been...

(This article belongs to the Section Sensor Networks)
  • Article
  • Open Access
5 Citations
1,170 Views
19 Pages

FACMamba: Frequency-Aware Coupled State Space Modeling for Underwater Image Enhancement

  • Li Wang,
  • Keyong Shen,
  • Haiyang Sun,
  • Xiaoling Cheng and ,
  • Jun Zhu and
  • Bixuan Wang
  • + 1 author+ 0 author

27 November 2025

Recent advances in underwater image enhancement (UIE) have achieved notable progress using deep learning techniques; however, existing methods often struggle with limited receptive fields, inadequate frequency modeling, and poor structural perception...

(This article belongs to the Section Ocean Engineering)

of 34