Search Results (378)

Reinforced concrete flat slab design commonly relies on a fragmented workflow: finite element models are built through graphical interfaces, reinforcement demands are manually interpreted, and code-compliance checks are performed separately. This fragmentation is time-consuming, error-prone, and difficult to reproduce, particularly for slabs with non-convex geometries such as re-entrant corners and openings, where manual column classification and reinforcement zoning become especially unreliable. This study presents a Python-based parametric framework that integrates geometry definition, finite element model generation, Eurocode load-combination assembly, reinforcement design, and code-compliance verification into a single traceable Jupyter Notebook workflow. The framework connects to a commercial finite element environment through its Component Object Model Application Programming Interface (COM API). A percentile-based zoning algorithm converts continuous element-wise reinforcement demands into discrete, constructable layouts, and a geometry-aware classification procedure extends automated punching-shear verification to non-convex slab geometries. The framework is validated against a published equivalent-frame reference solution and three additional benchmark problems. Bottom reinforcement agrees within 10%, and punching-shear resistance matches exactly (vRd,c = 0.399 MPa). The automated workflow reduces modelling and design time from 30–90 min to approximately 1–2 min. The principal scientific contributions are (1) a reproducible methodology for transforming continuous FEM demand fields into discrete, constructable reinforcement layouts, and (2) a geometry-aware column classification that enables automated Eurocode punching-shear checks for non-convex flat slabs. Full article

The oven is a critical component in lithium-ion battery coating equipment, and its customized design often involves repetitive modeling tasks and long development cycles. This study proposes an integrated process-parameter-driven framework for parametric CAD (Computer Aided Design) modeling and automated assembly of side-air-inlet drying ovens based on the secondary development of SolidWorks. Relationships between key process parameters and oven structural parameters were established, and Visual Basic programming combined with the SolidWorks API (Application Programming Interface) was used to realize parametric component generation and automatic assembly. The proposed framework reduces repetitive modeling operations and improves model-generation efficiency. The automatically generated oven geometry was further transferred to a CFD (Computational Fluid Dynamics) workflow for airflow- and temperature-field evaluation. The CFD results captured the main characteristics of hot-air circulation, temperature distribution, and local airflow non-uniformity, demonstrating that the proposed framework provides a suitable geometric basis for subsequent CFD-based engineering analysis. Full article

The rapid adoption of artificial intelligence (AI) programming assistants has raised questions about the actual benefits they provide in professional software development. This exploratory longitudinal case study compares configurations of three AI programming assistants (GitHub Copilot, ChatGPT, and Cursor)—specific combinations of tool, underlying model, interaction interface, and period of use—by reimplementing a full-stack thesis management application (a .NET Core 8.0 representational state transfer (REST) application programming interface (API) and a React.js client with 25 functionalities) that was first developed manually to establish a baseline. Each tool was evaluated using a seven-criteria framework covering code correctness, prompt complexity, context awareness, number of prompts, bug count, bug severity, and recorded implementation time. All three configurations significantly reduced the total recorded implementation time relative to manual implementation (by 66%, 63%, and 83% for Copilot, ChatGPT, and Cursor, respectively; p < 0.001). The Cursor configuration ranked best on four of the five evaluation criteria, with significantly higher context awareness and significantly fewer bugs than Copilot; because the tools were applied in a fixed order between January and November 2025, a period during which the underlying models were upgraded, and Cursor was both applied last and received the largest such upgrade, these results reflect tool–model–interface–time configurations rather than the tools in isolation. All tools performed significantly worse on the multi-layer API than on the client application. All 336 recorded bugs were organized into a fourteen-category taxonomy, in which hallucinated code elements and incomplete multi-file modifications were the most frequent failure modes, a pattern consistent with the tools’ limited ability to track context across files and architectural layers. The results indicate that AI programming assistants are most effective as pair programming tools whose output requires systematic human review before integration. Full article

This study addresses the growing demand for efficient customization in industrial design by proposing a structured approach to automate Computer Aided Design (CAD) assembly generation and documentation. The objective is to reduce repetitive engineering effort while maintaining consistency and integration within existing digital environments. The methodology combines parametric modelling, configuration-driven design, and Visual Basic for Applications (VBA)-based scripting through CAD Application Programming Interfaces, supported by integration with a Product Lifecycle Management system. A structured data model and reorganised modular CAD architecture enable automated generation of assemblies, selection of configurations, and creation of technical drawings. The approach is validated through an industrial case study involving configurable mechanical assemblies, where performance is evaluated using a quantitative time-based framework. The results show a reduction in total configuration time from 8 to 16 h to approximately 2–3 h, corresponding to an average time saving of 79% and a significant decrease in effective engineering workload. Assessment of scalability indicates that engineering effort becomes largely independent of the number of configurations, while economic evaluation indicates strong return-on-investment potential under typical industrial conditions. The findings confirm that systematic CAD automation can substantially improve productivity and consistency in configuration-driven design processes, provided that parametric models and data structures are properly standardised. Full article

This paper presents a systematic, data-driven literature review of research on Physical Artificial Intelligence (AI) based on the top 100 Google Scholar publications related to the search terms “Physical Artificial Intelligence” and “Physical AI”. The rapid advancement of Physical AI, driven by the convergence of advanced sensor technologies and foundation world models, has resulted in a diverse and fragmented research landscape that lacks comprehensive quantitative overviews. To address this gap, we implement and apply an AI-assisted computational analysis pipeline to this domain. The collected publications are processed using a Large Language Model accessed via a Python-based Application Programming Interface (API), enabling a structured computational analysis of the literature to assist thematic categorization. Based on this approach, the publications are grouped into five data-driven thematic clusters reflecting primary research perspectives within the analyzed sample. Specifically, the identified clusters comprise “Sensor Infrastructure and Architectures”, “Core Learning and Modeling Methodologies”, “Sim-to-Real and Digital Twins”, “Applications”, and “Safety, Governance, and Ethics”. By synthesizing the literature in a structured manner, this work provides a consolidated overview of central research patterns, identifies key operational challenges, and highlights fragmentation across Physical AI research, establishing a solid foundation for future trustworthy autonomous systems. Full article

Clinical adoption of large language models (LLMs) in public healthcare faces a structural impasse: the capital expenditure of centralised high-performance computing on one side and the privacy risk of routing patient data through third-party cloud interfaces on the other. Italian local health authorities (Aziende Sanitarie Locali, ASL) operate large fleets of clinical workstations that remain idle outside peak administrative hours. We present OmniMed Federated, a browser-native architecture using the WebGPU application programming interface (API) and the WebLLM framework to distribute LLM inference tasks across these existing workstations. The system federates task allocation rather than model training or partitioned inference: each query executes in full on one node, selected under a data residency constraint. A five-tier escalation model, coordinated by a metadata-only PHP back end, ranks tiers by data exposure rather than capability, with commercial cloud fallback disabled by default. In a pilot three-node testbed (50 queries), federated throughput reached 19.5 versus 8.2 tokens/second standalone, peak per-node memory fell 62%, and node discovery took 140 ms; query content remained within the institutional perimeter throughout. These figures establish infrastructural feasibility at pilot scale. Clinical output quality, security hardening, and scalability remain unevaluated. Full article

Agentic AI is changing enterprise cybersecurity as AI systems move beyond passive content generation toward autonomous planning, tool use, delegated execution, and operational action. As agents connect to email, code repositories, security operations center (SOC) platforms, finance workflows, cloud services, and enterprise application programming interfaces (APIs), they increasingly function as dynamic non-human identities rather than conventional software tools or service accounts. Existing identity and access management (IAM), Zero Trust, machine identity, and AI-governance approaches remain fragmented in their treatment of delegated authority, task intent, autonomy, runtime tool use, and auditable organizational consequences. This paper addresses these gaps by proposing the AIGATE (Agentic Identity Governance, Authority, Tool-Control and Evidence) Framework. AIGATE integrates eight governance layers: agent identity registration, lifecycle governance, delegated authority mapping, intent-bound access, least agency and least privilege, runtime tool-call control, audit evidence and accountability, and revocation and resilience. The framework treats agents as governed non-human enterprise identities whose actions remain attributable to designated human and organizational roles. AIGATE is developed through a structured critical synthesis of the recent literature on agentic AI security, machine identity, Zero Trust, runtime enforcement, and AI governance, with literature-derived governance requirements mapped explicitly to the eight framework layers. Three SOC, DevOps, and finance scenarios are used as illustrative applications rather than empirical validation. The contribution is an integrated governance architecture connecting identity, delegated authority, autonomy, runtime enforcement, evidence, and revocation across the agent lifecycle. Full article

Automated vehicular traffic management in Latin American cities requires solutions capable of capturing, processing, and visualizing events through measurable operational update intervals. Conventional automatic number plate recognition (ANPR) pipelines can return plate text while leaving the visual adequacy of the associated crop unassessed and disconnected from downstream cloud persistence, alerts, and monitoring. Because this separation can propagate visually unreliable evidence into operational records, a unified workflow is needed to evaluate plate-crop legibility before the event is exposed to operators. This work presents a three-phase methodology, applied to the SAVH system (Sistema de Aforo Vehicular, Vehicle Counting System), which integrates a Dahua ANPR camera (Zhejiang Dahua Vision Technology Co., Ltd., Hangzhou, China) with a cloud architecture on Amazon Web Services (AWS). The camera captures the vehicle and performs textual reading of the license plate, sending vehicle notifications directly to the FastAPI service deployed on Amazon EC2. This service extracts the visual evidence and runs the YOLOv8n classification variant (YOLOv8n–CLS), which classifies the legibility of the plate crop into two classes: legible plate and non-legible plate. Structured events and visual evidence are persisted in managed storage services, and a serverless function serves the web dashboard queries through an application programming interface (API) managed by Amazon API Gateway. The model was trained on a relabeled dataset derived from the public LPLCv2 collection, split into training, validation, and test subsets. Evaluation on 720 independent images from the test set achieved 97.78% overall accuracy, with 97.75% macro precision, 97.82% macro recall, 97.78% macro F1-score, and an AUC of 0.9981. External validation on 2000 real Guayaquil images achieved 86.10% accuracy, 85.84% macro F1-score, and an AUC of 0.9742. The external results show a performance gap consistent with domain shift and motivate cautious interpretation of deployment results. The contribution is the integration and evaluation methodology rather than a new neural architecture: YOLOv8n–CLS, FastAPI, and the AWS services are existing components assembled into a documented operational workflow. Full article

Although fire service accessibility has been extensively studied for urban public facilities such as hospitals and parks, it remains largely unexplored for high-risk industrial facilities such as fireworks manufacturers. In this study, fire risk and transportation network conditions are jointly considered, and a dynamic risk-weighted fire service accessibility evaluation framework is developed. An empirical study was conducted using 35 fire stations and 410 fireworks manufacturers in Liuyang City, China. Fire truck travel times were simulated via online map application programming interfaces (APIs) at 10–30 min intervals over a continuous three-day period, generating 193 evaluation scenarios and 158,260 data samples. The results indicate that the total average travel time of different types of fire trucks to demand points with varying risk levels was found to range from 570.33 to 1362.18 s, and risk-weighted fire service accessibility ranges from 16.84 to 57.26, reflecting a generally poor level of fire service accessibility within the current transport network. To resolve these constraints, it is recommended to optimize the spatial configuration of micro fire stations, promote the collaborative planning of shared enterprise-based fire units, and cross-integrate accessibility metrics into regional industrial land-use planning. These spatial measures are expected to significantly enhance the spatial resilience of transportation systems serving peripheral high-risk industrial clusters. Full article

Signature-based malware detection is undermined by obfuscation and packing, motivating dynamic analysis of Application Programming Interface (API) call sequences. Existing image-based classifiers reach high accuracy but rarely explain why a sample belongs to a given family. In this paper, our goal is not to maximize classification accuracy but to demonstrate and characterize an explainable pipeline that both classifies and explains: API call sequences from the WinMET dataset are encoded as order-preserving Gramian Angular Field (GAF) images and classified with a ResNet-50, after which Grad-CAM activations are reverse-mapped to the contributing API calls, whose names, categories, arguments, and return values are passed to a single large language model (LLM) that generates a natural-language rationale. We evaluate classification and explanation jointly on ten malware families (16,771 samples) through three experiments: a GAF-versus-heatmap comparison under identical conditions, a per-family Grad-CAM faithfulness analysis, and a reference-free LLM-as-a-Judge assessment of interpretation quality. Consistent with this explanatory aim, GAF matched the heatmap on overall accuracy (about 0.80) while performing comparably on Macro-F1 (0.63 versus 0.61: higher on the single fixed split, with Welch’s t-test $p=0.015$, but statistically comparable under five-fold cross-validation); per-family faithfulness varied widely (0.08 to 0.80), and, under two independent LLM judges (GPT-4o and GPT-4.1), supplying argument-level context significantly reduced—rather than improved—the judged quality (best score from a zero-shot prompt without parameters: 13.34 of 15); a small human expert evaluation further indicated that the automated judges rewarded fluent but over-attributed rationales. This work contributes a feasible, fully containerized and reproducible framework for explainable malware family classification. Full article

This study presents a materials-oriented, code-based parametric optimization of the load-bearing steel tubular arch girder in a tied-arch footbridge inspired by the Father Bernatek Footbridge in Krakow. The objective was to reduce structural steel demand by minimizing the arch-girder weight under Eurocode load combinations with ultimate limit state (ULS) and serviceability limit state (SLS) constraints, while accounting for discrete tubular cross-section changes within a realistic finite element model. A semi-automated workflow linked Autodesk Dynamo, Python scripts, and Autodesk Robot Structural Analysis to generate bridge geometry, build the finite element method (FEM) model, apply code-based loads and combinations, and evaluate structural response using a discrete, non-gradient-based search. A preliminary sensitivity screening was performed for the full set of design parameters, while the final optimization was governed mainly by arch rise, hanger number, and ULS-controlled discrete arch cross-section changes. The optimization reduced the arch-girder weight by 10.7% relative to the reference configuration, from 360.3 × 10³ kg to 321.6 × 10³ kg, within the adopted design domain. The optimum solution corresponded to an arch rise of 23.4 m, 31 hangers, and a deck spacing of 6.0 m. Hanger arrangement strongly affected force redistribution in the arch girder, while the final optimum was controlled by code-based utilization thresholds. The results show that an application programming interface (API)-driven parametric workflow can support early-stage optimization of tied-arch footbridges under code-based design constraints. The scientific contribution of the study lies not in automating Eurocode verification alone, but in identifying the structural mechanisms that govern the minimum-weight solution, including the interaction between arch rise, hanger arrangement, force redistribution, ULS utilization, and discrete tubular cross-section changes. Full article

In a closed-inventory large language model (LLM) system such as Online-CADCOM, which recommends engineering tools from a verified inventory, we measure inventory non-compliance, that is, a mention-level event in which the model recommends a tool not present in the verified inventory. We use this inventory-relative sense of hallucination throughout: an out-of-inventory mention may be a fabricated tool or a real commercial tool absent from the curated inventory, so the metric reports inventory non-compliance rather than factual fabrication. We evaluate a three-mechanism mitigation stack consisting of database-grounded context injection, fixed vocabulary constraints, and enforced JavaScript Object Notation (JSON) output across three commercial LLM providers (OpenAI, Anthropic, Google), two model generations, and two output modes (standard and reasoning), totaling 6912 Application Programming Interface (API) calls over 12 configurations. Under a recall-equalized detector adopted as the primary metric, the inventory non-compliance rate, which we denote the hallucination rate (HR) following common usage, decreases from roughly 69–80% to 4–13% under the full architecture. The cross-provider average is similar across the two generations tested (8.5% Generation 1 (Gen1), 6.9% Generation 2 (Gen2)), although per-provider directions diverge. We also examine the C3 configuration, in which only JSON output enforcement is active without grounding. A naive detector reports a large hallucination increase over the unconstrained baseline (+10.1 percentage points (pp) Gen1, +15.1 pp Gen2), but we show this gap is largely a detection-format artifact: structured JSON fields make out-of-inventory tools easy to extract, whereas the same real tools are frequently missed in free text. Under a recall-equalized detector the gap narrows to +2.6 pp (Gen1) and +4.8 pp (Gen2) and remains statistically significant only for two current-generation models, indicating a small, current-generation effect rather than a universal one. Reasoning-mode models provide no statistically significant improvement under architectural constraints. A frequency-weighted audit shows that the majority of remaining out-of-inventory mentions correspond to real engineering tools absent from the platform’s inventory. Under the full architecture, roughly half of responses (pooled $P_{\mathrm{any}}\approx 49.5\%$) still contain at least one such mention, indicating that handling unseen tools remains an open challenge for closed-inventory recommendation systems. Our evidence comes from a single engineering platform with four related electronic-design and power-electronics domains, so the findings characterize this setting rather than recommendation domains in general. Full article

Continuous glucose monitoring (CGM) plays a central role in modern diabetes management, yet CGM data are often confined within proprietary manufacturer ecosystems, limiting interoperability and reuse. This paper presents OpenGluco, an open-source and provider-independent platform designed to unify CGM data from multiple commercial systems, including Abbott Freestyle Libre, Dexcom, and Medtronic. OpenGluco implements a modular server architecture that abstracts vendor-specific data access, normalizes heterogeneous glucose time series, and exposes standardized access through an application programming interface designed to support future scalability. The platform supports individual users as well as institutional and research deployments. Performance evaluation demonstrates reliable data ingestion, consistent API responsiveness within the evaluated deployment environment, and robust handling of heterogeneous sampling characteristics. Validation of data normalization shows preservation of clinically relevant metrics such as Time in Range. By emphasizing interoperability, user-authorized data access, and open-source transparency, OpenGluco provides a flexible foundation for clinical monitoring, education, and future analytics-driven decision-support applications in diabetes care. Full article

Artificial intelligence (AI) agents increasingly need credentials such as application programming interface (API) keys and Secure Shell (SSH) credentials, but placing those secrets in the agent process exposes them to prompt injection, tool misuse, and exfiltration through ordinary agent outputs. We present CapSeal, a capability-based broker that replaces direct secret access with session-bound, non-exportable handles. Agents request policy-evaluated actions, while the broker performs credential-bearing Hypertext Transfer Protocol (HTTP) and SSH execution through typed executors with schema validation, replay protection, revocation epochs, and tamper-evident audit logging. We extend this design to hosted settings where the broker operator is not trusted with tenant secrets. Our main contribution is operator-blind secret mediation: a split-broker architecture in which a small trusted tenant gateway cooperates with an untrusted operator service that stores the master secret only as a fully homomorphic encryption (FHE) ciphertext and evaluates per-request derivations without decrypting it. We formalize the model and prove computational operator blindness from indistinguishability under chosen-plaintext attack (IND-CPA) security of the FHE scheme, together with conditional capability binding for any secure pseudorandom function/message authentication code (PRF/MAC) instantiation. We implement an end-to-end TFHE-rs prototype that exercises split-broker derivation, multi-tenant revocation and rate limiting, audit integration, and HTTP/SSH mediation. The prototype uses a non-cryptographic homomorphic stand-in and measures the cost of crossing the operator-untrusted boundary at about 9 s per request, roughly 17 million times slower than the plaintext path. We also give LowMC and Rasta transciphering designs and compare FHE with trusted execution environment (TEE)- and secure multiparty computation (MPC)-based alternatives, positioning each trust boundary by assurance and performance. Full article

Purpose/Background: Small and medium-sized enterprises (SMEs) that deploy Enterprise Resource Planning (ERP) systems face a persistent paradox: although ERP centralises organisational data, frontline users frequently lack the technical expertise to navigate complex menu structures, preventing efficient information retrieval for decision-making. This study presents a preliminary Research and Development (R&D) effort to design, build, and qualitatively evaluate a prototype intelligent question-answering system that connects to Odoo ERP through application programming interfaces (APIs) via Retrieval-Augmented Generation (RAG), enabling natural-language access to real SME business data. Methods: A single-organisation R&D case study was conducted at an SME in Khon Kaen Province, Thailand. The development cycle comprised problem analysis and requirement specification, system architecture design, prototype construction, integration and deployment, iterative testing and refinement, and multidimensional evaluation. The prototype was implemented with Chainlit (conversational interface), FastAPI (orchestration and tool-calling layer), and Odoo XML-RPC/JSON-RPC APIs (structured data retrieval). A fixed set of 20 test questions spanning four complexity levels (easy, moderate, complex, out-of-scope) was evaluated by three automated tools (OpenAI Evals, DeepEval, Ragas), by real-task verification against live ERP data, by five domain experts using 5-point Likert-scale questionnaires, and by three end users from the case-study organisation, who additionally completed the System Usability Scale (SUS). Given the very small expert and user samples, all human evaluation results are reported descriptively as preliminary, exploratory indicators rather than as statistically generalisable measures. Results: Automated evaluation achieved indicative pass rates of 95.00% (OpenAI Evals, 19/20), 90.00% (Ragas, 18/20), and 85.00% (DeepEval, 17/20). Descriptive expert feedback (n = 5) yielded an overall mean of 3.82 (high level), and descriptive end-user feedback (n = 3) yielded an overall satisfaction mean of 4.33 (highest level). The SUS score was 66.67/100, sitting at the boundary between ‘OK’ and ‘Good’ and revealing a divergence between high stated satisfaction and lower confidence in independent system use (item 9, raw mean = 2.33) and a stronger perceived need for expert assistance (item 4, raw mean = 2.67). These results are interpreted as preliminary diagnostic signals for further development rather than as confirmatory evidence. Conclusions: This preliminary R&D study suggests that a RAG-based ERP chatbot can meaningfully simplify ERP data access for SME users, while exposing persistent gaps in multi-step reasoning, user confidence, and data privacy boundaries that must be addressed in subsequent development cycles. The SUS pattern, in particular, suggests a ‘novelty effect’ in which users are enthusiastic about the natural-language interface yet remain anxious about correctness and stability during real tasks. Originality/Value: This work contributes a transparent, replicable preliminary R&D blueprint that combines (i) live API-mediated RAG over structured ERP data, (ii) a complementary multi-tool automated evaluation set (OpenAI Evals + DeepEval + Ragas), (iii) descriptive expert and end-user feedback, and (iv) SUS-based usability assessment, all documented for a single Thai SME using Odoo 18. The study explicitly positions itself as an early step toward larger, multi-site, and on-premise deployments of trustworthy ERP-integrated conversational agents. Full article