You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.

Search for Articles:

Title / Keyword

Author / Affiliation / Email

Journal

Article Type

Advanced Search

Section

Special Issue

Volume

Issue

Number

Page

Logical OperatorOperator

Search Text

Search Type

Knowledge Management in Manufacturing: Current Practices, Barriers, and Automation Potential for LLM-Supported Systems
Model-Contingent Polarity Bias in Large Language Model Annotation: Implications for Semantic Multimedia Personalization
A Framework for Implementing AI in KM

Journal Description

Computers

Computers is an international, scientific, peer-reviewed, open access journal of computer science, including computer and network architecture and computer–human interaction as its main foci, published monthly online by MDPI.

Open Access— free for readers, with article processing charges (APC) paid by authors or their institutions.
High Visibility: indexed within Scopus, ESCI (Web of Science), dblp, Inspec, Ei Compendex, and other databases.
Journal Rank: JCR - Q2 (Computer Science, Interdisciplinary Applications) / CiteScore - Q1 (Computer Science (miscellaneous))
Rapid Publication: manuscripts are peer-reviewed and a first decision is provided to authors approximately 15.4 days after submission; acceptance to publication is undertaken in 3.9 days (median values for papers published in this journal in the first half of 2026).
Recognition of Reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.
Journal Cluster of Artificial Intelligence: AI, AI in Medicine, Algorithms, BDCC, MAKE, MTI, Stats, Virtual Worlds, Computers and Journal of Superintelligence.

Impact Factor: 5.2 (2025); 5-Year Impact Factor: 4.4 (2025)

Imprint Information Journal Flyer Open Access ISSN: 2073-431X

Latest Articles

40 pages, 1258 KB

Open AccessArticle

Cryptographically Secured Machine Learning for Resilient Multi-Tier Supply Chains

by Alfaiz Madhiya, Vijay Solanki, Khandakar Rabbi Ahmed, Sakib Salam Jamee, Mainul Islam Khan and S. M. Rezvi

Computers 2026, 15(9), 592; https://doi.org/10.3390/computers15090592 (registering DOI) - 7 Sep 2026

As we move further into a more digital supply chain, we have seen tremendous improvements in terms of efficiency, but we have also seen a rise in the risks that data vulnerabilities pose, particularly for intermediary supply chain nodes. As a result, traditional [...] Read more.

As we move further into a more digital supply chain, we have seen tremendous improvements in terms of efficiency, but we have also seen a rise in the risks that data vulnerabilities pose, particularly for intermediary supply chain nodes. As a result, traditional security measures have proven inadequate in protecting critical data that flows through these intermediary supply chain nodes, making them more susceptible to possible security breaches and tampering. In this paper, we introduce a novel solution that utilizes cryptography and Artificial Intelligence (AI)-powered predictive modeling for the security of supply chain data. Unlike other solutions that only protect endpoint data, our solution provides a more comprehensive security solution that extends cryptography for intermediary supply chain data, making it more secure and protected from possible breaches and tampering. To further improve our solution, we have utilized AI models, namely, XGBoost, Random Forest, and LightGBM, for predictive modeling. To prevent target leakage, features arithmetically derived from the recovery-duration target were excluded from the predictor set prior to training. The results indicate that, once the leakage-affected features are removed and hyperparameters are properly tuned, all five models achieve modest but genuine predictive accuracy, with

R^{2}

values in the range of 0.542–0.552. The best-performing model on this leakage-audited feature set is XGBoost, with an

R^{2}

value of 0.5525 and a test RMSE of 38.16 days, closely followed by Linear Regression and Ridge Regression (RMSE = 38.22 days,

R^{2}

= 0.5512), with the practical difference between the two being small (0.06 days RMSE) despite being statistically consistent across ten random splits. This demonstrates the solution’s effectiveness in reducing security risks while maintaining realistic, leakage-free predictive accuracy. Full article

(This article belongs to the Special Issue Privacy-Preserving Computation and Secure Data Sharing in Modern Networks)

► Show Figures

Figure 1

21 pages, 1471 KB

Open AccessArticle

Generative Adversarial Network-Based AI Framework for Adaptive Job Shop Scheduling in Industry 5.0

by Prince Waqas Khan, Sayantee Roy, Imene Bareche, Khizar Abbas and Thorsten Wuest

Computers 2026, 15(9), 591; https://doi.org/10.3390/computers15090591 (registering DOI) - 7 Sep 2026

In smart manufacturing, efficient job shop scheduling (JSS) and resource management remain critical challenges, especially in dynamic production environments. Traditional methods often struggle to adapt to real-time changes and unexpected events. To address these limitations, this paper proposes a novel Generative Adversarial Network [...] Read more.

In smart manufacturing, efficient job shop scheduling (JSS) and resource management remain critical challenges, especially in dynamic production environments. Traditional methods often struggle to adapt to real-time changes and unexpected events. To address these limitations, this paper proposes a novel Generative Adversarial Network (GAN)-based generative AI framework that augments scheduling data with realistic synthetic scenarios and integrates Local Outlier Factor (LOF)-enhanced Q-learning-based reinforcement learning (QRL) for adaptive JSS optimization in Industry 5.0 environments. The GAN is trained to generate realistic synthetic scheduling scenarios, which are combined with real-world data from a state-of-the-art Festo Didactics Cyber Physical Lab to augment the diversity and coverage of training samples. The LOF algorithm enables real-time bottleneck detection, while the QRL agent learns robust scheduling policies that minimize makespan and prioritize bottleneck mitigation. Experimental results demonstrate that the proposed GAN-LOF-QRL approach achieves an average makespan reduction of 70.8% across varying production volumes (12, 15, and 18 orders), significantly improving scheduling efficiency and resource utilization compared to traditional RL and heuristic methods. This research advances smart manufacturing initiatives and Industry 5.0 goals by providing a scalable, adaptive scheduling solution that leverages generative AI to address the complexities of modern supply networks. Full article

(This article belongs to the Special Issue Generative Artificial Intelligence and Machine Learning in Industrial Processes and Manufacturing)

► Show Figures

Figure 1

26 pages, 4965 KB

Open AccessArticle

YOLOv11m–CA: Lightweight Coordinate Attention for Tiny Person and Bicycle Detection in a VOC-Based Setting

by Jinyi Zhu, Hao Wu and Yi Cao

Computers 2026, 15(9), 590; https://doi.org/10.3390/computers15090590 (registering DOI) - 7 Sep 2026

Detecting small person and bicycle instances with lightweight models is relevant to resource-aware visual sensing, but evidence from a category-filtered general-purpose dataset cannot establish performance in dense surveillance, traffic monitoring, or aerial environments. This study therefore examines a narrower question: whether replacement-style Coordinate [...] Read more.

Detecting small person and bicycle instances with lightweight models is relevant to resource-aware visual sensing, but evidence from a category-filtered general-purpose dataset cannot establish performance in dense surveillance, traffic monitoring, or aerial environments. This study therefore examines a narrower question: whether replacement-style Coordinate Attention (CA) integration can improve coordinate-sensitive representation in YOLOv11m under a controlled VOC-based person and bicycle setting without increasing model complexity. In the official Ultralytics YOLO11m architecture, the Spatial Pyramid Pooling–Fast (SPPF) layer is followed by a C2PSA block. The proposed configuration replaces this post-SPPF C2PSA block with CA, while retaining the remaining backbone, neck, and detection head. CA encodes directional positional information along the horizontal and vertical axes. Experiments are conducted on a filtered subset of PASCAL Visual Object Classes (VOC) 2012 that retains only the person and bicycle categories; this subset is not a dedicated small-object or surveillance benchmark. Within this setting, the proposed model improves mean average precision at an intersection-over-union threshold of 0.50 (mAP@50) from 79.2% to 81.5%. It also improves mean average precision averaged over thresholds from 0.50 to 0.95 (mAP@50–95) from 53.9% to 54.8% and small-instance average precision (

{AP}_{s}

) from 68.1% to 72.4%. The parameter count decreases from 20.03M to 19.07M, and the model achieves 90 frames per second (FPS) on the tested NVIDIA GeForce RTX 4060 Laptop GPU (NVIDIA Corporation, Santa Clara, CA, USA). These results provide incremental evidence for a complexity-aware CA replacement strategy within the evaluated VOC distribution; they do not demonstrate cross-domain generalization or deployment performance in real surveillance or aerial scenarios. No embedded platform was evaluated, and the reported RTX 4060 throughput should not be interpreted as evidence of edge-device latency, energy efficiency, or deployment readiness. Full article

(This article belongs to the Special Issue Advanced Image Processing and Computer Vision (3rd Edition))

► Show Figures

Figure 1

23 pages, 8120 KB

Open AccessArticle

A Two-Stage Embedded Detect-to-Cut Vision Pipeline for Date Palm Branch Analysis on Jetson Orin NX

by Ahlem Maghzaoui, Said Riahi, Emna Aridhi, Sadok Ben Yahia and Abdelkader Mami

Computers 2026, 15(9), 589; https://doi.org/10.3390/computers15090589 (registering DOI) - 6 Sep 2026

Date palm harvesting requires reliable localization of anatomically appropriate cutting sites under cluttered orchard conditions, variable illumination, and frequent occlusion. This study presents an embedded two-stage detect-to-cut vision pipeline for date palm branch analysis on NVIDIA Jetson Orin NX. In the first stage, [...] Read more.

Date palm harvesting requires reliable localization of anatomically appropriate cutting sites under cluttered orchard conditions, variable illumination, and frequent occlusion. This study presents an embedded two-stage detect-to-cut vision pipeline for date palm branch analysis on NVIDIA Jetson Orin NX. In the first stage, a YOLOv8-based detector localizes candidate fruit-bearing branches in the full image. In the second stage, a YOLOv8-Pose model operates on cropped regions of interest to estimate four harvest-relevant anatomical keypoints, namely the peduncle base, cut point, rachis base, and rachis tip. Under the reported evaluation setting, the detection stage achieved a precision of 0.893, a recall of 0.881, an mAP@0.5 of 0.942, and an mAP@0.5:0.95 of 0.669. For keypoint localization, the pose stage achieved a Pose mAP@0.5 of 0.952 and a Pose mAP@0.5:0.95 of 0.840, while cut-point accuracy, assessed using peduncle-normalized PCK, reached 0.605, 0.801, and 0.871 at

α = 0.1

,

0.2

, and

0.5

, respectively. On-device evaluation further showed a mean end-to-end latency of 380.34 ms per frame (4.00 FPS) across multi-ROI scenes and 135.01 ms per frame (7.79 FPS) in a continuous single-bunch video scenario. Taken together, these results support the feasibility of the proposed pipeline as a leakage-controlled within-domain embedded perception prototype for cut-point localization in the studied Deglet Nour orchard setting, rather than as a broadly validated field-ready harvesting solution. Full article

(This article belongs to the Section AI-Driven Innovations)

► Show Figures

Figure 1

21 pages, 966 KB

Open AccessArticle

Dual-Cascade GAN with Frequency-Domain Priors for Motor Imagery EEG Data Augmentation

by Chenyang Liu and Ming Meng

Computers 2026, 15(9), 588; https://doi.org/10.3390/computers15090588 (registering DOI) - 5 Sep 2026

Goal: Deep learning-based motor imagery EEG classification is limited by data scarcity, which constrains model generalization and performance. Methods: We propose a dual-cascade generative adversarial network (dcGAN) framework with a variable focused attention (VFA) module for MI-EEG data augmentation. The first stage learns [...] Read more.

Goal: Deep learning-based motor imagery EEG classification is limited by data scarcity, which constrains model generalization and performance. Methods: We propose a dual-cascade generative adversarial network (dcGAN) framework with a variable focused attention (VFA) module for MI-EEG data augmentation. The first stage learns latent frequency-domain priors from random noise through an adversarial training scheme; the second stage then synthesizes artificial EEG samples with a U-Net generator conditioned on these priors, augmented by the VFA module and a time-domain consistency loss. A VFA-enhanced EEGNet is subsequently trained on the combination of real and generated samples for classification. Results: On the BCI Competition IV 2a and 2b datasets, the proposed method achieves classification accuracies of 84.92% and 91.79%, with Cohen’s Kappa coefficients of 0.79 and 0.81, respectively, outperforming baseline methods. Conclusions: The integration of structured frequency-domain priors and attention mechanisms improves the fidelity of generated EEG samples, which in turn enhances downstream classification performance. Full article

30 pages, 4530 KB

Open AccessArticle

FHDG-YOLO: A Frequency-Domain Hybrid Deformation and Geometry-Regression Network for Photovoltaic Crack Detection

by Chenyang Wang, Xinyu Wang, Yilin Wang, Danyu Li, Song Wang and Ying Song

Computers 2026, 15(9), 587; https://doi.org/10.3390/computers15090587 (registering DOI) - 5 Sep 2026

Visible-light photovoltaic (PV) inspection is affected by periodic grid-line backgrounds, low-contrast cracks, irregular crack topology, and the extreme aspect ratios of slender defects. To address these difficulties, a frequency-domain hybrid deformation and geometry-regression YOLO network, termed FHDG-YOLO, is proposed in this study. The [...] Read more.

Visible-light photovoltaic (PV) inspection is affected by periodic grid-line backgrounds, low-contrast cracks, irregular crack topology, and the extreme aspect ratios of slender defects. To address these difficulties, a frequency-domain hybrid deformation and geometry-regression YOLO network, termed FHDG-YOLO, is proposed in this study. The method introduces frequency-domain dynamic decoupled convolution to attenuate periodic background responses, incorporates a high-resolution P2 detection head and efficient multi-scale attention to retain and recalibrate shallow spatial details, embeds DCNv2 to adapt convolutional sampling to irregular defect boundaries, and replaces the original regression loss with MicroShape-IoU for geometry-sensitive localization. Experiments are conducted on a reorganized two-class visible-light PV dataset containing 6493 images, comprising 6262 screened public images and 231 field images collected by the authors. On the 1300-image validation split, FHDG-YOLO obtains a Precision of 0.954, Recall of 0.943, mAP@0.5 of 0.971, and mAP@0.5:0.95 of 0.861. Compared with YOLOv8n, mAP@0.5 and mAP@0.5:0.95 increase by 3.6 and 6.9 percentage points, respectively. On the held-out 649-image test split, the corresponding mAP values are 0.970 and 0.860, compared with 0.931 and 0.785 for YOLOv8n. Under the original four-class Panel Solar validation protocol, FHDG-YOLO obtains mAP@0.5 and mAP@0.5:0.95 values of 0.954 and 0.843, compared with 0.929 and 0.780 for YOLOv8n. Full article

(This article belongs to the Special Issue AI Applications for Smart Grid Energy Management and Industrial Electrical Systems)

22 pages, 19060 KB

Open AccessArticle

WICA-Net-M: MRI-Based Brain Tumour Classification Using a Lightweight Wavelet-Integrated Coordinate Attention Network with Frequency-Aware Learning

by Md Ashik Khan, Abu Saleh Musa Miah, Md Abdur Rahim, Jungpil Shin and Mohd Nizam Husen

Computers 2026, 15(9), 586; https://doi.org/10.3390/computers15090586 - 4 Sep 2026

Background/Objectives: Reported performance on public brain tumour MRI benchmarks is hard to interpret because of near-duplicate train/test overlap, ImageNet pretraining bias, and single-seed evaluation. We address this with a leakage-aware evaluation protocol and a compact model trained entirely from scratch. Methods: WICA-Net-M is [...] Read more.

Background/Objectives: Reported performance on public brain tumour MRI benchmarks is hard to interpret because of near-duplicate train/test overlap, ImageNet pretraining bias, and single-seed evaluation. We address this with a leakage-aware evaluation protocol and a compact model trained entirely from scratch. Methods: WICA-Net-M is a 2.47 M-parameter CNN whose gated Haar Discrete Wavelet Transform (DWT) separates low- and high-frequency components and fuses them through a learnable gate, complemented by Coordinate Attention. We evaluate it on the standard and image-level deduplicated splits of the Nickparvar brain tumour MRI dataset under a three-seed, leakage-aware protocol, benchmark it against five ImageNet-pretrained baselines and conduct a near-duplicate overlap audit against BRISC 2025. Results: WICA-Net-M reaches 99.42 ± 0.16% accuracy on the standard V1 split and 95.25 ± 0.32% accuracy/95.17 ± 0.31% macro F1 on the deduplicated V2 split, closely matching five ImageNet-pretrained baselines (95.17–95.67%) with fewer parameters, with sub-half-point differences across three seeds indicating comparable rather than superior accuracy. The audit identifies 861 exact SHA-256 pairs involving 857 of the 1000 BRISC test images against the full Nickparvar collection. Alongside perceptual-hash candidate pairs, this exact overlap shows that BRISC cannot serve as independent external validation. Conclusions: The descriptive 4.17-point V1-to-V2 difference reflects the combined effects of duplicate removal, class rebalancing, and altered sample composition, with none separable from public releases, though it shows that a scratch-trained compact model can approach pretrained performance on the controlled split. Patient-level leakage remains unresolved because patient identifiers are unavailable. Leakage-aware, multi-seed evaluation should be standard before clinical translation. Full article

26 pages, 1343 KB

Open AccessArticle

A Three-Phase Explainable Deep Learning Approach for Reliable Wrist Fracture Identification from X-Ray Images

by Naeem Ullah, Muhammad Hassan, Rahman Ullah and Javed Ali Khan

Computers 2026, 15(9), 585; https://doi.org/10.3390/computers15090585 - 4 Sep 2026

Wrist fractures present significant challenges in clinical diagnosis, often leading to treatment delays and compromised recoveries. Manual diagnosis is resource-intensive and error-prone. To address these challenges, we develop DeepWristFNet, a compact convolutional architecture designed for end-to-end wrist fracture classification using a small dataset [...] Read more.

Wrist fractures present significant challenges in clinical diagnosis, often leading to treatment delays and compromised recoveries. Manual diagnosis is resource-intensive and error-prone. To address these challenges, we develop DeepWristFNet, a compact convolutional architecture designed for end-to-end wrist fracture classification using a small dataset of 193 wrist X-ray images. The DeepWristFNet architecture integrates multi-scale convolutional operations with Fire and Shuffle modules within a compact network design, followed by fully connected layers for binary classification. We applied data pre-processing techniques such as data augmentation, image enhancement, and image resizing to increase the number of images, improve image quality, and resize images to match the DeepWristFNet input size. The proposed method comprised three phases. In the first phase, we trained, validated, and tested end-to-end and achieved validation and testing accuracies of 99.04% and 87.93%, respectively. Testing was performed on a hold-out subset of image instances that was kept separate from model development. The evaluated hold-out images originated from the same dataset distribution and included the corresponding augmented variants. In the second phase, we further evaluated the learned representation by extracting deep features from the first fully connected layer of DeepWristFNet. ReliefF was then used to select informative features, which were subsequently evaluated using 10 conventional machine learning classifiers. Out of 10 classifiers, 5 classifiers, i.e., Efficient linear SVM, quadratic SVM, Narrow NN, wide NN, and medium NN, achieved 100% testing accuracy on unseen samples. In the third phase, an auxiliary Fuzzy Inference System provides an intensity-based foreground-background representation of the X-ray images. This representation provides complementary visual information for interpretation but is not intended to directly classify or localize fractures. Grad-CAM is additionally used to visualize image regions contributing to the DeepWristFNet predictions, providing a model-specific explanation of the classification decision. Additionally, we evaluated how well the proposed DeepWristFNet approach performed against cutting-edge deep transfer learning models. In the evaluated experiments, DeepWristFNet outperformed the compared pre-trained deep learning architectures on the unseen hold-out subset from the same dataset distribution (test set). This study demonstrates the potential of DeepWristFNet for wrist fracture classification under a small-data setting. However, further evaluation on larger, independently collected clinical datasets is required to establish its robustness, generalizability, and suitability for clinical decision support. Full article

(This article belongs to the Special Issue Advances in Explainable and Multimodal AI for Intelligent Systems and Medical Applications)

► Show Figures

Figure 1

36 pages, 578 KB

Open AccessArticle

Opportunities and Challenges in Big Data Analytics for Decision Making: An Integrated Framework

by Wafa’ Za’al Alma’aitah, Fatima N. AL-Aswadi, Addy Quraan, Nader Abdel Karim, Hussein Alahmer and Mohamad Y. Mustafa

Computers 2026, 15(9), 584; https://doi.org/10.3390/computers15090584 - 4 Sep 2026

Big Data Analytics (BDA) has evolved from a predominantly technical batch function into a socio-technical capability integrating cloud-native platforms, stream processing, Lakehouse architecture, machine learning operations (MLOps), visualization, governance, and managerial judgment. This paper proposes an integrated BDA decision-making framework developed through a [...] Read more.

Big Data Analytics (BDA) has evolved from a predominantly technical batch function into a socio-technical capability integrating cloud-native platforms, stream processing, Lakehouse architecture, machine learning operations (MLOps), visualization, governance, and managerial judgment. This paper proposes an integrated BDA decision-making framework developed through a structured conceptual synthesis of research on data platforms, analytical capabilities, decision processes, organizational readiness, technology adoption, governance, and responsible artificial intelligence. The framework comprises seven interconnected stages: data sources, ingestion and integration, storage and platform, processing, analytics and artificial intelligence, visualization and interpretation, and decision, action, and learning. Governance, human oversight, organizational readiness, task characteristics, and continuous feedback influence all stages. Key implementation requirements include data quality, interoperability, security, privacy, scalability, cost, explainability, bias, skills, and sustainability. The proposed configurable reference architecture links technical integration, task–analytics fit, governance assurance, human judgment, and organizational readiness with decision quality and organizational outcomes. Organizational size and maturity, sectoral risk, decision criticality, technological context, and regulatory environment are defined as boundary conditions for future empirical validation. Full article

(This article belongs to the Section Human–Computer Interactions)

► Show Figures

Figure 1

11 pages, 893 KB

Open AccessArticle

Modality-Shared Anti-Spoofing for Face and Fingerprint

by Mohamed Cheniti, Zahid Akhtar and Chandranath Adak

Computers 2026, 15(9), 583; https://doi.org/10.3390/computers15090583 - 4 Sep 2026

Multi-modal anti-spoofing aims to differentiate live users from spoofing attacks using multiple biometric modalities during model training. While existing anti-spoofing methods often incorporate just one biometric modality, the effectiveness of attacking two or more biometric traits remains questionable. In this work, we introduce [...] Read more.

Multi-modal anti-spoofing aims to differentiate live users from spoofing attacks using multiple biometric modalities during model training. While existing anti-spoofing methods often incorporate just one biometric modality, the effectiveness of attacking two or more biometric traits remains questionable. In this work, we introduce the multi-modal anti-spoofing approach to detect spoofing attacks across face and fingerprint. Our framework is built around an Angular Margin Loss (ArcFace) that increases interclass separation without disrupting cross-modal alignment, which enables reliable spoof detection across both face and fingerprint biometric characteristics. Moreover, to enhance model generalization against unseen spoof attacks, we include three adversarial attacks (i.e., FGSM, PGD, DeepFool) to evaluate our system. Extensive experiments on multi-modal benchmarks show that the proposed method not only significantly outperforms previous anti-spoofing methods but also uniquely offers the ability to handle potential attack types. Full article

(This article belongs to the Special Issue Multimedia Data and Network Security: Emerging Trends and AI-Driven Threats and Defenses)

► Show Figures

Figure 1

26 pages, 6563 KB

Open AccessArticle

INDI: A Low-Cost LLM-Enabled Multimodal Campus Guide Robot

by José Varela-Aldás, Christian P. Carvajal, Josue Cadena and Carolina Del-Valle-Soto

Computers 2026, 15(9), 582; https://doi.org/10.3390/computers15090582 - 3 Sep 2026

University technology campuses contain specialized laboratories, academic programs, and services that can be difficult for first-time visitors to identify. This paper presents INDI, a custom mobile campus guide robot that combines spoken interaction, synthesized speech, touchscreen feedback, animated facial states, head motion, and [...] Read more.

University technology campuses contain specialized laboratories, academic programs, and services that can be difficult for first-time visitors to identify. This paper presents INDI, a custom mobile campus guide robot that combines spoken interaction, synthesized speech, touchscreen feedback, animated facial states, head motion, and predefined mobile guidance behaviors. The platform retains the modular mechanical concept of an earlier prototype while replacing its Raspberry Pi and open-loop remote-control architecture with an NVIDIA Jetson Nano, an Arduino Uno motor-control bridge, ROS 1 nodes, encoder feedback, and dual PID speed loops. The robot weighs 2.37 kg, measures

39 \times 27 \times 69.5

cm, reaches a software-limited maximum speed of 0.4 m/s, and provides 27 min of continuous operation in the reported tests. Ten repetitions of each motion test produced mean displacements of 1.058 m and 2.182 m for 1 m and 2 m commands, respectively, and mean rotations of 89.2° and 180.3° for 90° and 180° commands. Voice trials achieved 90% correct interaction in a quiet environment and 70% under nearby conversational noise. In an exploratory user study with 13 participants, 16 of 20 assigned tasks were completed and the mean overall rating was 4.31/5. The results demonstrate the feasibility of an integrated, modular, physically embodied information service, while also revealing accumulated linear-motion error, sensitivity to ambient speech, limited battery duration, and the need for grounded institutional knowledge and autonomous localization. These findings are presented as preliminary evidence of technical and interaction feasibility rather than as confirmatory evidence of usability or campus-scale autonomous navigation. Full article

(This article belongs to the Special Issue Advanced Human–Robot Interaction 2026)

► Show Figures

Graphical abstract

25 pages, 3357 KB

Open AccessArticle

Few-Shot Federated Learning for State-of-Charge Prediction Across Privacy-Isolated Personal Mobile Devices

by Chenyue Xu and Chen Huang

Computers 2026, 15(9), 581; https://doi.org/10.3390/computers15090581 - 3 Sep 2026

Accurate state-of-charge (SOC) prediction on personal mobile devices requires a model that can represent heterogeneous discharge mechanisms, transfer knowledge across users, and adapt from scarce target records while raw telemetry remains privacy isolated. This study proposes a module-decomposition-driven SOC prediction model that separates [...] Read more.

Accurate state-of-charge (SOC) prediction on personal mobile devices requires a model that can represent heterogeneous discharge mechanisms, transfer knowledge across users, and adapt from scarce target records while raw telemetry remains privacy isolated. This study proposes a module-decomposition-driven SOC prediction model that separates baseline drain, synchronous state response, and asynchronous multi-scale event memory within one discharge-dynamics formulation. The same three semantic coefficient blocks remain aligned through local source learning and round-wise sample-count-weighted federated aggregation. Target-side personalization then adjusts one locally derived personal discharge-rate scalar while preserving the shared temporal response, and forward SOC propagation produces threshold-based time-to-empty (TTE) estimates. A user-held-out evaluation on a public small-sample smartphone-log dataset uses eight target partitions and 447 final evaluation origins. Personalized fine-tuning reduced TTE MAE by 67.07% and RMSE by 71.88%, yielding an

R^{2}

of 0.936. The resulting task-specific architecture connects module-structured data processing, federated synthesis, few-shot adaptation, and local TTE inference while raw usage logs remain within user-specific data boundaries. Full article

► Show Figures

Figure 1

23 pages, 8798 KB

Open AccessArticle

Design of a New Lightweight Hash Function FLUX-128 and Experimental Evaluation of Its Diffusion and Statistical Properties

by Kunbolat Algazy, Yerkebulan Alimzhan, Kairat Sakan, Nursulu Kapalova and Ardabek Khompysh

Computers 2026, 15(9), 580; https://doi.org/10.3390/computers15090580 - 3 Sep 2026

The rapid growth of the Internet of Things and embedded platforms increases the demand for cryptographic primitives that provide adequate security under strict resource constraints. This paper introduces FLUX-128 (Fast Lightweight Universal miXing), a new lightweight hash function targeting constrained devices. FLUX-128 is [...] Read more.

The rapid growth of the Internet of Things and embedded platforms increases the demand for cryptographic primitives that provide adequate security under strict resource constraints. This paper introduces FLUX-128 (Fast Lightweight Universal miXing), a new lightweight hash function targeting constrained devices. FLUX-128 is built on a modified sponge construction with a 216-bit state, a 72-bit absorption rate, and a 128-bit tag length. Its main design feature is an additional lightweight diffusion function

G

applied before the core transformation

F

, improving mixing while keeping the architecture compact. Diffusion was evaluated via the Strict Avalanche Criterion (SAC) on 5000 messages using systematic single-bit input inversions and a corresponding probability matrix of output-bit changes. In addition, the concatenated output bitstream was tested with the NIST Statistical Test Suite, where all reported p-values exceed the 0.01 significance threshold. Overall, the results provide empirical evidence of near-ideal bit mixing and the absence of pronounced statistical defects within the adopted experimental setup. Together with the security objectives defined by the 128-bit output and the 144-bit sponge capacity, these results support FLUX-128 as a promising lightweight hash construction for integrity-oriented applications in resource-constrained IoT environments. The SAC and NIST STS results are considered complementary experimental evidence of the expected cryptographic behavior rather than stand-alone proofs of resistance to all classes of cryptanalytic attacks. Full article

(This article belongs to the Section ICT Infrastructures for Cybersecurity)

► Show Figures

Figure 1

30 pages, 580 KB

Open AccessArticle

Toward Intelligent Blockchain Consensus: A Machine Learning-Enhanced Redbelly Framework for Scalable, Secure, and Energy-Efficient Decentralized Networks

by Ismail Fdilat, Khadija Louzaoui and Khalid Benlhachmi

Computers 2026, 15(9), 579; https://doi.org/10.3390/computers15090579 - 3 Sep 2026

Blockchain consensus still forces a hard choice among scalability, security, and energy use. Redbelly, a leaderless Byzantine Fault Tolerance protocol, largely settles the scalability-versus-energy side of that tension, yet it accepts any cryptographically valid transaction without judging whether it is economically fraudulent or [...] Read more.

Blockchain consensus still forces a hard choice among scalability, security, and energy use. Redbelly, a leaderless Byzantine Fault Tolerance protocol, largely settles the scalability-versus-energy side of that tension, yet it accepts any cryptographically valid transaction without judging whether it is economically fraudulent or whether the node behind it is misbehaving. That blind spot is what we target. We present ML-Redbelly, a formally specified extension that attaches four learning components to the Redbelly pipeline: a LightGBM gradient-boosted fraud classifier, an Isolation Forest behavioural anomaly detector, a tabular Q-Learning agent for adaptive committee selection, and a Paillier-based federated learning aggregator that keeps model updates private. We prove that this layer leaves Redbelly’s safety and liveness intact, give pseudocode and complexity bounds for every component, and measure the system on the IEEE-CIS Fraud Detection benchmark (400,000 transactions) paired with a faithful discrete-event Redbelly simulator parameterised from measured inputs and validated against the published Redbelly deployment. LightGBM reaches an F1 of 0.783 (precision 0.858, recall 0.719, AUROC 0.963), a 34 percent relative F1 gain over the conference-baseline Random Forest at five times the inference speed. The Isolation Forest detector attains recall 0.885 at a false-positive rate of 0.047, and the Q-Learning agent settles into a stable policy within about 200 rounds across normal, bursty, and Byzantine-attack conditions. End to end, the framework sustains 48,844 TPS on 32 validators (mean over 30 seeds), and because the leaderless superblock commits every proposer’s block in parallel, this throughput advantage over leader-based BFT grows with the validator count (5.0 times PBFT and 2.9 times HotStuff at 32 validators). The learning layer costs only about 4 percent in throughput, since the measured ML inference is small next to the geo-distributed consensus round. Per-transaction energy is comparable across BFT protocols, being dominated by signature verification, and is orders of magnitude below proof-of-work chains, which expend energy on mining. One federated update epoch takes 36 s across 10 nodes with 2048-bit Paillier keys and reconstructs gradients with negligible error. All performance figures are emergent outputs of the discrete-event simulation, which reproduces the published Redbelly benchmark to within a conservative factor of about 1.7. Taken together, these results outline a simulation-validated design for making consensus intelligent as well as fast and identify the steps needed toward real-cluster deployment. Full article

(This article belongs to the Special Issue Intelligence at the Edge: AI/ML for IoT Systems)

► Show Figures

Figure 1

23 pages, 2525 KB

Open AccessArticle

A Deep Mixed-Image Augmentation Strategy for Few-Shot Image Classification

by Rui Wang and Xiaomin Liu

Computers 2026, 15(9), 578; https://doi.org/10.3390/computers15090578 - 3 Sep 2026

Few-shot image classification suffers from severe data scarcity and unstable generalization. Existing data augmentation strategies still have three major limitations: pixel-level fusion strategies are incompatible with the support–query structure of episodic learning, category selection for cropping-based augmentation is overly simplistic, and most approaches [...] Read more.

Few-shot image classification suffers from severe data scarcity and unstable generalization. Existing data augmentation strategies still have three major limitations: pixel-level fusion strategies are incompatible with the support–query structure of episodic learning, category selection for cropping-based augmentation is overly simplistic, and most approaches rely on a single augmentation method, limiting robustness. To address these issues, this study proposes a deep mixed data augmentation framework that jointly enhances both the support set and the query set. The method first performs global pixel-level fusion to construct fused support and query sets. A Hopfield network then turns fused-support similarities into a pairing matrix

H

, which assigns a different-class gallery partner for query-side cropping–mixing. Finally, cropping–mixing produces an enhanced query set for model training. The framework is validated using ResNet18+BDC as the backbone. Experimental results on MiniImageNet demonstrate that the proposed method is competitive in few-shot classification, attaining a five-seed test mean of

73.25

%/

81.88

% under 5-way 1-shot and 5-shot. A single complementary run on FC100 attains

66.63

%/

77.80

% and is not a same-backbone ranking against heterogeneous published protocols. Full article

► Show Figures

Figure 1

40 pages, 7091 KB

Open AccessArticle

TrustEdge-V2X: Deployment-Aware Edge Intelligence for V2X/IoV Intrusion and Misbehavior Detection

by Hesham A. Sakr, Mina Shenouda, Nadeem Sarwar, Ibrahim Elewah, Vitalii Lapin and Maria Lapina

Computers 2026, 15(9), 577; https://doi.org/10.3390/computers15090577 - 2 Sep 2026

Most studies on vehicular cybersecurity focus on classification accuracy but fail to evaluate the applicability of the models to the edge. This paper proposes a secure edge intelligence framework for V2X/IoV intrusion and misbehavior detection, called TrustEdge-V2X, which is deployment-aware. The framework combines [...] Read more.

Most studies on vehicular cybersecurity focus on classification accuracy but fail to evaluate the applicability of the models to the edge. This paper proposes a secure edge intelligence framework for V2X/IoV intrusion and misbehavior detection, called TrustEdge-V2X, which is deployment-aware. The framework combines dataset-role qualification, attack taxonomy, AI model benchmarking, feature-budget analysis, deployment ranking based on EdgeScore, offline risk-aware orchestration, external validation, robustness testing, explainable AI, repeated-run statistical analysis and ablation studies. Three datasets are assigned different experimental roles: VeReMi_NextGen is used for core V2X/VANET misbehavior detection, CICIoT2023 is used for supporting edge/IoT intrusion experiments and HCRL_CarHacking is used for external IoV/CAN validation. LightGBM outperformed all other AI models in EdgeScore (0.9383), F1-score (0.9878), MCC (0.9758), and inference latency (0.009419 ms per sample) across all eight AI models and six scenarios on VeReMi_NextGen for binary detection. In five dataset-task cases, the accuracy-best model was different from the EdgeScore-best model, which is the most important point to note: the best model in terms of accuracy is not necessarily the best model in terms of EdgeScore. Compact feature subsets were competitive, and robustness testing demonstrated an average F1 decrease of 0.1423 when tested under stress. The orchestration layer was found to be beneficial for the tasks, but it did not always perform better than the best fixed policy. As a whole, TrustEdge-V2X offers a systematic approach to the assessment and selection of vehicular cybersecurity models based on the operational and deployment conditions, not only on the classification accuracy. Full article

► Show Figures

Figure 1

40 pages, 7162 KB

Open AccessArticle

SSPA: Enhancing Pseudo-Corpus Quality on Tibetan Machine Translation via Semantic-Syntax Prealignment

by Yidong Sun, Dongxu Liu, Jiale Zhang and Youcheng Wang

Computers 2026, 15(9), 576; https://doi.org/10.3390/computers15090576 - 2 Sep 2026

Tibetan-to-English machine translation (MT) models frequently falter under extreme domain data scarcity, often producing translations that violate the distinctive agglutinative rules of Tibetan and suffer from domain-specific stylistic mismatches. To overcome these limitations, we propose Semantic-Syntax Prealignment (SSPA), an innovative corpus generation framework. [...] Read more.

Tibetan-to-English machine translation (MT) models frequently falter under extreme domain data scarcity, often producing translations that violate the distinctive agglutinative rules of Tibetan and suffer from domain-specific stylistic mismatches. To overcome these limitations, we propose Semantic-Syntax Prealignment (SSPA), an innovative corpus generation framework. SSPA constructs high-quality pseudo-parallel pairs by explicitly minimizing the deviation between the syntactic-semantic profiles of generated samples and professional reference texts. Specifically, source-target structural representations are standardized through length-unified truncation and terminology normalization, followed by a dual-domain alignment process that maximizes syntactic cosine similarity under rigorous structural constraints. We further augment these aligned frames via a cross-length dynamic filling mechanism, which is integrated with an Expectation-over-Transformation (EOT)-based style regularization mechanism specifically adapted for stylistic perturbations, to simulate authentic linguistic variations. Extensive evaluations on our newly constructed Tibetan Medicine-Tibetan English (TM-TE) dataset demonstrate that SSPA significantly outperforms existing competitive baselines. Notably, SSPA achieves a BLEU-4 score of 36.2 and improves long-sentence BLEU-4 by 16.8 points, with a parser-verified grammatical compliance rate of 96.2%. The framework exhibits remarkable cross-domain adaptability and stylistic consistency, offering a robust, versatile solution for low-resource Tibetan professional domain MT. Full article

► Show Figures

Figure 1

1 pages, 122 KB

Open AccessCorrection

Correction: Wisanwanichthan, T.; Thammawichai, M. A Lightweight Intrusion Detection System for IoT and UAV Using Deep Neural Networks with Knowledge Distillation. Computers 2025, 14, 291

by Treepop Wisanwanichthan and Mason Thammawichai

Computers 2026, 15(9), 575; https://doi.org/10.3390/computers15090575 - 2 Sep 2026

In the original publication [...] Full article

25 pages, 12816 KB

Open AccessArticle

Frutopia: A Hybrid Tangible Serious Game for Multisensory Interaction and Tactile Exploration

by Marco Santórum, David Morales-Martínez, Mayra Carrión-Toro, Thomás Tapia, Jose Aguilar, Karen Santórum and Patricia Acosta-Vargas

Computers 2026, 15(9), 574; https://doi.org/10.3390/computers15090574 - 2 Sep 2026

Serious games have demonstrated significant potential for supporting learning, cognitive stimulation, and skill development. However, most existing solutions rely predominantly on visual and auditory interaction, while the integration of real tactile experiences remains limited despite their potential to support richer multisensory interaction. Frutopia [...] Read more.

Serious games have demonstrated significant potential for supporting learning, cognitive stimulation, and skill development. However, most existing solutions rely predominantly on visual and auditory interaction, while the integration of real tactile experiences remains limited despite their potential to support richer multisensory interaction. Frutopia is a hybrid tangible serious game designed to integrate physical interaction with digital gameplay in order to support tangible interaction and tactile exploration. The game was developed following a structured process that combines the iPlus methodology for educational game design with the Scrum agile framework, enabling the systematic definition, implementation, and refinement of gameplay mechanics, tangible interaction, and usability-oriented features. The resulting system incorporates tangible user interaction through conductive physical objects with different textures connected via a Makey Makey interface, enabling players to control in-game actions through real tactile exploration. The game features progressive maze-based challenges inspired by Ecuadorian cultural environments and representative fruits from Ecuadorian regions, integrating multisensory feedback, gamification techniques, and embodied interaction principles to foster engagement and sensory exploration. The system was implemented using the Godot Engine and evaluated through functionality and usability assessments. Functional validation achieved a success rate of 94.74% across the defined test cases, demonstrating the technical stability of the proposed solution. Additionally, a usability evaluation involving 50 participants was conducted using the Serious Games Usability Evaluation Instrument (SGUEI). The assessment produced a final rating of 90.37%, reflecting favorable perceptions of the interaction quality and overall user experience. The results demonstrate the feasibility of integrating tangible interaction and multisensory feedback within serious game environments and suggest that hybrid tangible interfaces can enrich user engagement and interaction quality. This work contributes to the design and development of hybrid tangible serious games by presenting a structured development workflow and providing preliminary evidence of the technical feasibility and usability of tangible interaction in serious game environments. The proposed system establishes a foundation for future studies involving the intended target population and the evaluation of educational and cognitive outcomes. Full article

(This article belongs to the Special Issue Advances in Game-Based Learning, Gamification in Education and Serious Games)

► Show Figures

Figure 1

18 pages, 8125 KB

Open AccessFeature PaperArticle

Hybrid Image Encryption via BCC-Algebraic Dynamic Key Generation and AES-CBC

by Zainab Radhi Mousa, Karrar Aljawaheri, Alaa Mohammed Redha Abdulhasan, Tabark Mohammed Alkhaldi, Furqan Abbas Albo jwaid, Marwa Ali Alhamdany and Mohanad R. Aljanabi

Computers 2026, 15(9), 573; https://doi.org/10.3390/computers15090573 - 1 Sep 2026

Traditional chaotic image encryption systems frequently suffer from phase-space periodic degradation and finite-precision limitations. To overcome these inherent vulnerabilities, this paper presents a novel dynamic image encryption framework combining finite BCC-algebraic structures, SHA-256 cryptographic hashing, and an HMAC-based Key Derivation Function (HKDF). The [...] Read more.

Traditional chaotic image encryption systems frequently suffer from phase-space periodic degradation and finite-precision limitations. To overcome these inherent vulnerabilities, this paper presents a novel dynamic image encryption framework combining finite BCC-algebraic structures, SHA-256 cryptographic hashing, and an HMAC-based Key Derivation Function (HKDF). The scheme establishes a plaintext-aware key synthesis mechanism utilizing dynamic matrix representations of finite BCC-algebra. Primary key seeds and Initialization Vectors (

I V s

) are dynamically generated by performing bitwise XOR operations between the SHA-256 hash digest of the input image and vectorized algebraic structures, followed by rigorous HKDF sub-key derivation. Spatial confusion and diffusion are subsequently achieved using the AES-CBC mode. Extensive security evaluations and formal provable security analysis (

IND - CPA

) demonstrate that the proposed system achieves high resistance against differential, linear, statistical, and Chosen-Plaintext Attacks, with an information entropy consistently approaching the theoretical optimum of

8.0

and optimal NPCR/UACI differential performance. Full article

(This article belongs to the Special Issue Advanced Cryptographic Techniques for Digital Watermarking, Encryption, and Steganography)

► Show Figures

Figure 1

More Articles...

Submit to Computers Review for Computers

Journal Menu

Journal Browser

► Journal Browser

Highly Accessed Articles

View More...

Latest Books

More Books and Reprints...

E-Mail Alert

News

1 September 2026
MDPI INSIGHTS: The CEO’s Letter #38 – 2 Million Published Articles, Outstanding Reviewers, Michele Parrinello Award, AIS 2026 & WSF-12

26 August 2026
Meet Us at the 6th International Conference on Autonomous Unmanned Systems, 18–20 September 2026, Harbin, China

17 August 2026
Empowering Virtual MDPI Academic Publishing Workshop at the International College of Digital Innovation, Chiang Mai University, 9 September 2026

More News & Announcements...

Topics

Propose a Topic

Topic in Computers, Electronics, Future Internet, IoT, Network, Sensors, JSAN, Technologies, BDCC

Challenges and Future Trends of Wireless Networks Topic Editors: Stefano Scanzio, Ramez Daoud, Jetmir Haxhibeqiri, Pedro Santos
Deadline: 30 September 2026

Topic in AI, Applied Sciences, Computers, Electronics, Entropy, Future Internet, Information, IoT, Sensors, Telecom

Advances in Sixth Generation and Beyond (6G&B) Topic Editors: Luis Javier García Villalba, Ana Lucila Sandoval Orozco
Deadline: 31 October 2026

Topic in Applied Sciences, Electronics, Computers, Digital, Smart Cities

Artificial Intelligence Models, Tools and Applications: 2nd Edition Topic Editors: Phivos Mylonas, Katia Lida Kermanidis, Manolis Maragoudakis
Deadline: 30 November 2026

Topic in Applied Sciences, Computers, JSAN, Technologies, BDCC, Sensors, Telecom, Electronics

Electronic Communications, IOT and Big Data, 2nd Volume Topic Editors: Teen-Hang Meen, Charles Tijus, Cheng-Chien Kuo, Kuei-Shu Hsu, Jih-Fu Tu
Deadline: 31 December 2026

More Topics

Conferences

Propose a Conference Collaboration

12–14 April 2027 International Conference on Intelligent Electronics and Micro/Nanosystems (Intelectro)

28–30 June 2027 The 1st International Online Conference on Algorithms and Computers

More Conferences...

Special Issues

Propose a Special Issue

Special Issue in Computers

Artificial Intelligence (AI) in Medical Informatics Guest Editor: Tiehang Duan
Deadline: 30 September 2026

Special Issue in Computers

Advancing Software Engineering with Artificial Intelligence Guest Editors: Waddah Saeed, AbdulRahman Alsewari
Deadline: 30 September 2026

Special Issue in Computers

Wireless Sensor Networks in IoT Guest Editors: Shaolin Liao, Jinxin Li, Tiaojie Xiao
Deadline: 30 September 2026

Special Issue in Computers

Computational Advances in Artificial Intelligence and Game Science for Education Guest Editors: Petros Lameras, Panagiotis Petridis, Sylvester Arnab
Deadline: 30 September 2026

More Special Issues

Back to TopTop