Computers

21 pages, 2463 KB

Open AccessArticle

DFSel-FT: A Differentiable Feature Selection and FT-Transformer Framework for Interpretable Thyroid Disease Classification Using Tabular Data

by Ganga Sagar Soni, Abhinav Shukla, R Kanesaraj Ramasamy, Pritendra Kumar Malakar and Parul Dubey

Computers 2026, 15(6), 332; https://doi.org/10.3390/computers15060332 (registering DOI) - 22 May 2026

Abstract

Thyroid diseases are very common endocrine diseases that afflict millions of people around the world and need proper and timely diagnosis to ensure proper treatment. Although machine learning and hybrid metaheuristic methods have advanced, current models have high computation costs, low interpretability, and low probability calibration, which limit their use in clinical settings. In this research, a new DFSel-FT (Differentiable Feature Selection and an FT-Transformer) system is suggested, which combines DFSel-FT to allow one to diagnose thyroid disease effectively and interpretably. It employs Concrete (Gumbel-Softmax) gates to select the features end-to-end to make sure that only the most relevant clinical attributes are carried through the training. A Transformer-based architecture is then used to process the chosen features to learn intricate interdependencies. The model is trained with class-balanced focal loss and temperature scaling to better enhance calibration. Experimental evaluation on the UCI Thyroid Disease Dataset (22,632 samples) showed that the proposed model achieved 97.85% accuracy, 97.65% Macro-F1, and 98.10% AUC-OVR, showing competitive performance compared with traditional machine learning models, modern tabular deep learning baselines, and hybrid metaheuristic methods. Other indicators of robustness and reliability include MCC (0.955), Cohen Kappa (0.951), and small calibration error (ECE = 0.021). SHAP and LIME explainability analysis reveals clinically relevant features that include TSH, TT4, and T3. The proposed framework provides a balanced integration of predictive performance, interpretability, and probability calibration, making it a promising benchmark-level framework for interpretable and calibrated thyroid disease classification, requiring external clinical validation before real-world deployment. Full article

(This article belongs to the Special Issue Application of Artificial Intelligence and Modeling Frameworks in Health Informatics and Related Fields)

► Show Figures

Graphical abstract

58 pages, 1723 KB

Open AccessArticle

Detection and Mitigation of Mythos-Class Frontier Model Capabilities: A Layered Reference Architecture

by Robert Campbell

Computers 2026, 15(6), 331; https://doi.org/10.3390/computers15060331 - 22 May 2026

Abstract

Anthropic’s April 2026 Claude Mythos Preview release established a new operational threat category: frontier AI systems whose extended-context reasoning, recursive self-correction, native system-tool integration, and agentic scaffolding render dominant AI safety paradigms—RLHF, output filtering, contractual access vetting, human-in-the-loop supervision—insufficient as sole controls. This paper develops a defense-in-depth reference architecture against that category, structured around four named contributions: a five-indicator operational definition of the Mythos-class (capability conjoined with scaffold, access pattern, autonomy depth, and persistence); the Mythos-Class Posture Rubric (MCPR), a three-tier detection framework spanning evaluation, deployment, and runtime with explicit routing to mitigation layers; a four-layer mitigation stack comprising the Vetted-Access Operational Pattern (VAOP), Authority-Bound Output Release (ABOR) cryptographically grounded in FIPS 203/204/205 post-quantum primitives, and the Compute-Plane Isolation Profile (CPIP); and an integrated architecture that crosswalks to the NIST AI Risk Management Framework, NIST Cybersecurity Framework 2.0, and CISA Zero Trust Maturity Model 2.0. The architecture is applied to three deployment surfaces—post-quantum cryptography migration, federal AI supply-chain assurance, and critical-infrastructure operational technology defense—demonstrating that the four contributions generalize across heterogeneous operational contexts. The contribution is a reference design rather than a deployed system; limitations, falsifiability criteria, and a research agenda for empirical refinement are developed. Full article

21 pages, 3620 KB

Open AccessReview

Serious Games in Science Education: A Systematic Bibliometric and Content Analysis

by Deniz Poyraz Gök and Nuri Kara

Computers 2026, 15(6), 330; https://doi.org/10.3390/computers15060330 - 22 May 2026

Abstract

This study examines recent research trends in the use of serious games for science education through a bibliometric analysis of 340 articles and a qualitative content analysis of 56 studies published between 2020 and 2025 in the Web of Science Core Collection. By combining these approaches, the study provides a comprehensive view of both research patterns and how serious games are designed and used in science education. The findings indicate that the field is maturing, with research moving beyond general effectiveness toward understanding how serious games support learning in different contexts. Most studies report positive effects compared to traditional instructional methods. However, results vary across contexts and depend on factors such as design, implementation, and learner characteristics. Research is mainly focused on higher education and is largely driven by leading countries such as the USA and China, although participation from developing countries is increasing. The growing use of immersive technologies, such as augmented and virtual reality, offers new opportunities for interactive and multimodal learning but may also increase cognitive load in certain contexts. There is also growing interest in non-digital games, which have received limited attention despite their effectiveness. Overall, the findings show that more systematic research and clearer design frameworks are needed to better understand how serious games can be used in science education. Full article

(This article belongs to the Special Issue STEAM Literacy and Computational Thinking in the Digital Era)

► Show Figures

Figure 1

23 pages, 705 KB

Open AccessArticle

LLM-SGCF: A Robust Malware Detection Framework with Spatially Guided Convolution

by Lina Zhao, Hua Huang, Ning Li, Yunxiao Wang and Ming Li

Computers 2026, 15(6), 329; https://doi.org/10.3390/computers15060329 - 22 May 2026

Abstract

With the rapid evolution of cyberattack techniques, identifying dynamic behavioral intents from Application Programming Interface call sequences has become a fundamental modality for ensuring reliable malware detection and information security. However, existing detection methods face the dual challenges of semantic sparsity and inadequate spatial dependency modeling when processing these sequences, which fundamentally undermines their stability against complex structural variations and in-the-wild evasive patterns. To address these critical vulnerabilities, we propose LLM-SGCF, a highly effective malware detection framework that jointly models deep behavioral semantics and spatial structures. Specifically, our framework leverages generative Large Language Models, which are subsequently encoded by BERT, to transform sparse API calls into rich and contextualized descriptions. Concurrently, it employs a novel Spatially Guided Convolution (SGC) module to localize critical malicious segments and extract cross-position dependencies in a two-dimensional semantic space. Extensive experiments on the public Aliyun and Catak datasets demonstrate that LLM-SGCF exhibits exceptional resilience to real-world structural complexity and significantly outperforms state-of-the-art baselines, achieving a peak binary-classification accuracy of 95.82%. Further ablation analyses confirm that the synergistic fusion of semantic enhancement driven by Large Language Models and spatial structural modeling dramatically improves the resilience of the framework against complex attack chains, providing a highly reliable paradigm for next-generation malware recognition systems. Full article

(This article belongs to the Special Issue AI-Powered IoT (AIoT) Systems: Advancements in Security, Sustainability, and Intelligence)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Computers, Volume 15, Issue 6 (June 2026) – 4 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI