Computer Science and Mathematics

Abstract: This technical note introduces a reproducible kernel-damping evidence protocol for the SORT-AI Core-3 applications AI.01 (Interconnect Stability Control), AI.04 (Runtime Control Coherence), and AI.13 (Agentic System Stability). These applications span complementary structural coupling regimes in advanced AI systems: physical/interconnect coupling, logical/runtime-control coupling, and semantic/agentic coupling. The protocol evaluates whether declared structural risk-transition scenarios admit a Gaussian kernel-damping reconstruction under the declared canonical SORT scale parameter σ 0 = 0.00190643. The analysis is restricted to the structural analysis layer and does not claim production deployment, vendor-specific measurement, empirical benchmarking, runtime optimization, or execution by MOCK v4. MOCK v4 is treated as the frozen structural reference architecture, not as a runtime engine. The accompanying archived evidence release contains machine-readable scenario inputs, declared risk-transformation rules, executable scripts, expected outputs, generated outputs, and a reproduction manifest sufficient to reproduce all reported κ, ξ, scenario-level means, sample dispersions, and coefficients of variation. The contribution is methodological: the note formalizes a reproducibility protocol through which SORT-AI Core-3 applications can be tested as structurally defined damping regimes without converting MOCK v4 into an execution environment or introducing a new MOCK version.

Abstract: Reliable visual detection of small floating objects on the water surface is a prerequisite for environmental monitoring and clean-up tasks performed by unmanned surface vehicles (USVs) on inland waterways. Such scenes are routinely degraded by low illumination at dawn and dusk, strong specular reflections, ripple-induced clutter, and large object-scale variations, which together cause missed detections, false alarms, and unstable localization. This paper proposes YOLO11-LREP, a lightweight detection framework built upon YOLO11n and tailored for water-surface floating-object recognition under such adverse conditions. Four complementary improvements are integrated: (i) a Coordinate Attention (CoordAtt) module is inserted at the top of the backbone to enhance positional encoding and highlight obstacle-related semantic regions; (ii) three Efficient Channel Attention (ECA) modules are embedded at the multi-scale fusion nodes of the Neck so that reflection- and ripple-induced spurious channel responses can be suppressed at almost no extra cost; (iii) the Powerful-IoU (PIoU) loss replaces the original regression loss to enforce four-side boundary alignment and stabilize convergence on small, blurred-edge targets; and (iv) a joint low-light and reflection augmentation strategy, together with CutMix region-level mixing, broadens the training distribution along the illumination and occlusion axes. Experiments on the public FloW-Img dataset, split into 1,200 training and 800 validation images (2,024 instances) and run under a fixed random seed (seed = 0, deterministic = true), show that YOLO11-LREP attains AP₅₀ = 80.1 %, AP₅₀:₉₅ = 38.5 %, and AP_S = 24.3 % with only 2.84 M parameters and 9.3 GFLOPs. On an NVIDIA RTX 4060 Laptop GPU, the model runs at 3.3 ms total per 640×640 image (≈303 FPS), satisfying real-time perception requirements while retaining lightweight deployability. Ablation experiments verify the individual and complementary contributions of each component, and a systematic threshold sensitivity analysis (F₁ fluctuation < 0.2 %) demonstrates the stability of the final model.

Abstract: Tennis match prediction has been studied extensively, yet the literature offers no controlled comparison of Elo ratings, classical machine learning, and deep neural networks under identical experimental conditions, leaving practitioners without clear guidance on model selection. We address this gap with a unified empirical study on 133,138 professional men’s tennis matches from the Association of Tennis Professionals tour (1968–2024). Four approaches are evaluated on the same temporally split data with a common 16-feature set and an aligned evaluation protocol: an enhanced Elo rating system, ten classical machine learning algorithms, seventeen deep neural network configurations spanning 207,000 to 21,000,000 parameters, and a hybrid Elo–machine learning (ELO-ML) approach that augments classical learners with three Elo-derived features. A tuned Elo baseline alone reaches 65.87% accuracy, the best of ten classical machine learning algorithms reaches 66.30%, seventeen deep neural network configurations cluster at 66.15–66.22%, and the hybrid ELO-ML approach reaches 67.52% (McNemar’s test, p < 0.001 for all ELO-ML pairwise comparisons). All four approaches sit within a 1.65 pp band whose upper edge lies below the 70–72% accuracy commonly cited for bookmaker odds, indicating that pre-match prediction under universally available features is a difficult task in which Elo alone already captures most of the predictable signal and algorithmic sophistication adds only marginal headroom. Deep neural networks deliver substantially better probability calibration than the other approaches (Expected Calibration Error 0.0077 vs. 0.0142). Model capacity exhibits sharply diminishing returns: all seventeen network configurations, spanning a 100-fold range in parameter count (207,000 to 21,000,000), fall within a 0.07 pp accuracy band. The study establishes a controlled benchmark for tour-level tennis prediction, quantifies how narrow the headroom above Elo actually is, provides modest but consistent empirical support for the Statistically Enhanced Learning framework, and supplies deployment-ready operating points for sports analytics practitioners.

Abstract: Foundation models have emerged as a dominant paradigm in machine learning, enabling broad generalization and efficient adaptation across diverse tasks and domains. While this paradigm has achieved remarkable success in language and vision data, its extension to structured data remains far less understood. Foundation models for structured data are an emerging yet highly impactful research area with a rapidly growing body of literature. In this survey, we provide a systematic analysis of foundation models for structured data, focusing on tabular, time series, and graph data, covering over 150 representative methods. We analyze the intrinsic properties and inductive biases of structured data, clarify the core concepts of foundation models, and conduct an in-depth analysis of the key challenges that hinder the development of foundation models for structured data. Building on these insights, we organize existing approaches into a coherent taxonomy based on tokenization, architectures, pre-training objectives, and adaptation strategies. Finally, we discusse merging research directions and open problems, aiming to provide guidance toward more principled and scalable foundation models for structured data.

Abstract: Background: Multi-Agent Path Finding (MAPF) has been widely studied in recent years. However, the computational cost of solving MAPF and MAPF for large agents (LA-MAPF) grows exponentially as the number of agents increases. This challenge is particularly severe for LA-MAPF, primarily due to the increased overhead of conflict detection between geometric agents. Objectives: To reduce the computational cost of solving MAPF and LA-MAPF problems, a general method is needed that can accelerate a variety of MAPF algorithms. Methods: We propose a framework that decomposes an LA-MAPFproblem into multiple subproblems, which are solved independently to reduce computational costs. The framework is general and compatible with various MAPF algorithms (e.g., CBS or LaCAM). The decomposition of an LA-MAPF problem is formulated as a combinatorial optimization problem and solved using neighborhood search. To handle unsolvable subproblems generated during decomposition, we introduce a solvability safeguard mechanism that merges subproblems until all are solvable. Results: Our experiments demonstrate the performance of the framework across various mapsasthenumberofagentsincreases, showing substantial acceleration of both MAPF and LA-MAPF methods. Specifically, after applying Break Loops, the average runtime of CBS and LA-CBS is reduced from 49.0 s to 6.8 s and from 54.0 s to 18.65 s, respectively; LaCAM and LA-LaCAM are reduced from 9.5 s to 7.0 s and from 52.9 s to 16.2 s, respectively. The success rate of CBS and LA-CBS increases from 0.27 to 0.98 and from 0.11 to 0.72, respectively; LaCAM and LA-LaCAM increase from 0.85 to 0.97 and from 0.10 to 0.77, respectively. Conclusions: Our results show that incorporating Break Loops into MAPF and LA-MAPF methods significantly reduces computational costs and improves success rates. These f indings demonstrate that solving MAPF problems can be accelerated by decomposing them into subproblems. To facilitate further research, we have made the source code for the framework publicly available at https://github.com/JoeYao-bit/LayeredMAPF/tree/main/algorithm/LA-MAPF.

Abstract: Recently, Mamba based on State Space Models (SSMs) has shown great potential for hyperspectral image (HSI) classification due to its long-range modeling capability and linear complexity. However, existing Mamba-based methods usually employ fixed and limited scanning directions, restricting anisotropic spatial modeling. Moreover, full-pixel scanning introduces substantial computational redundancy. To address these issues, this paper proposes DESDA-Mamba, a direction-adaptive Mamba network with diagonal-enabled strided scanning for HSI classification. Specifically, a lightweight direction adaptation module is designed to implicitly predict suitable scanning directions from learned direction-sensitive feature-channel responses and perform batch-level unified direction aggregation, revealing that finer patch-level direction routing does not necessarily improve performance. In addition, a strided scanning strategy is introduced to skip redundant adjacent pixels during sequence serialization, reducing computational cost while enlarging the effective receptive field. Furthermore, two diagonal scanning modes, namely main-diagonal and anti-diagonal scanning, are proposed to improve the modeling of oblique spatial structures. Efficient diagonal scanning is implemented through coordinate-sequence indexing and caching mechanisms, enabling flexible diagonal strided scanning. Extensive comparison, ablation, and model-variant experiments on four public HSI datasets demonstrate that DESDA-Mamba achieves superior classification performance with competitive efficiency. The source code is available at https://github.com/ll-netizen/DESDA-MAMBA.

Abstract: Precise semantic matching between natural language queries and unconstrained videos remains a fundamental yet unresolved challenge in multimedia retrieval. Although recent transformer-based dual encoders and CLIP-style contrastive frameworks have improved global text–video alignment, they still struggle in complex scenes where (i) spatiotemporal cues are highly entangled among objects, motion patterns, and background context, and (ii) cross-modal interactions are easily biased by spurious correlations, resulting in brittle retrieval performance under compositional or ambiguous language. To overcome these limitations, we propose a unified framework that enhances text–video correspondence through three closely coupled components: Query-adaptive Semantic Routing (QSR), Counterfactual Bi-directional Alignment (CBA), and Temporal Causal Regularization (TCR). QSR introduces a query-conditioned routing mechanism that decomposes video representations into multiple semantic experts and dynamically assigns token-level relevance, allowing the model to selectively emphasize appearance, motion, and contextual cues according to the textual query. Based on the routed representations, CBA performs reciprocal attention in both text-to-video and video-to-text directions, while introducing a counterfactual alignment branch to suppress background-driven shortcuts; this encourages robust matching based on causal evidence rather than incidental correlations. Finally, TCR imposes temporal causality-aware consistency by penalizing alignment instability under lightweight temporal perturbations, thereby improving motion sensitivity without requiring dense frame sampling. For scalable deployment, we further incorporate parameter sharing across experts and quantization-friendly projections, achieving a favorable accuracy–latency trade-off. Experiments on MSR-VTT, MSVD, and VATEX demonstrate consistent improvements over strong baselines, achieving Recall@1 scores of 55.0%, 60.3%, and 68.5%, respectively, while maintaining high inference efficiency.

Abstract: Operational technology (OT) and information technology (IT) have become increasingly integrated, expanding the attack surface of OT systems. Power from shore has also become more widespread for offshore critical infrastructure, and has introduced new dependencies and the potential for a single point of failure. In addition, the cyber threat landscape is escalating, with state-sponsored actors demonstrating the capabilities and willingness to target industrial systems. Threat actors have been seen using living off the land techniques, such as with the Industroyer malware, which utilized legitimate but malicious IEC 104 commands. To evaluate these vulnerabilities, this study applies a Design Science Research approach to map a generalized substation and develop a Software in the Loop simulator. The simulator was used to test specific attack vectors against substation automation systems. The results confirm that an adversary with local network access can successfully inject valid IEC 61850 MMS commands to trigger unauthorized circuit breaker operations. Furthermore, the results show that it is possible to use a simulated substation as a tool when developing ICS malware. These findings demonstrate that common operational technology protocols lack fundamental security by design, meaning the technical barrier to execute a disruptive attack is low once network access is achieved. Protecting these critical environments requires a robust defense-in-depth strategy that accounts for supply chain risks and enforces strict network segmentation.

Abstract: Human activity recognition (HAR) based on smartphone and wearable sensor data is commonly addressed using statistical learning methods and deep neural networks that often provide strong predictive performance, but at the expense of limited interpretability and substantial computational and energy requirements. Such limitations reduce their suitability for deployment in practical sensing environments where model decisions must be transparent, verifiable and executable on resource-constrained devices. In this work, we investigate the Convolutional Tsetlin Machine (CTM) for multimodal HAR using the UCI-HAR dataset. The Tsetlin Machine is a novel neuro-symbolic machine learning approach that offers two important advantages over many conventional machine learning methods: (i) it learns logic-based decision rules that are human-readable and formally verifiable, and (ii) it operates with comparatively low computational complexity, making it well suited to efficient and low-power on-device learning. The proposed study systematically analyses the contribution of different feature modalities by decomposing the inertial signals space into semantically defined subsets according to: (i) sensor source: accelerometer or gyroscope; (ii) physical component: body or gravity; (iii) coordinate: x, y or z. A separate CTM classifier was trained for each modality and their combination in order to determine the relative discriminative value of each modality group for activity classification. In addition to predictive performance the study emphasizes the interpretability of the CTM model ensured by expressing each decision in the form of propositional clauses, thereby enabling visualization and direct inspection of the modality-specific patterns supporting each activity class. Owing to its symbolic structure and modest computational demands, the CTM provides a principled framework for the design of explainable, resource-efficient and deployable HAR systems. The proposed work therefore contributes toward trustworthy multimodal sensing by jointly addressing predictive performance, interpretability and suitability for embedded and mobile platforms.

Abstract: Air quality forecasting and environmental health research at urban and regional scales depend on the combination of measurements from heterogeneous sensor networks, yet the construction of integrated multi-source datasets is rarely described or released as a self-contained deliverable. This paper presents an open dataset that combines four sensor-derived sources covering the whole of Spain over the period 2022 to 2024: hourly air quality observations from the 588 stations of the national network operated by the Ministerio para la Transición Ecológica y el Reto Demográfico (MITECO), daily meteorological records from the Agencia Estatal de Meteorología (AEMET), daily mobility indicators derived from anonymised mobile telephony events published by the Ministerio de Transportes y Movilidad Sostenible (MITMA) at the municipality level, and a calendar of national and Autonomous-Community public holidays. The processing pipeline harmonises sources that differ in temporal resolution, spatial codification and quality regime into a tidy hourly table indexed by station and timestamp, with a fixed feature schema of 56 variables per record. Air quality stations are paired with their nearest AEMET station through a three-tier distance rule, and the daily exogenous features are aligned to the air quality time axis through a two-variant temporal-alignment scheme (lag-and-expand to the hourly grid for the hourly release, same-calendar-day join for the daily release). A complementary daily-resolution variant of the dataset is also released, with 72 columns and the same feature schema except for the air quality block, which is aggregated to daily mean, minimum and maximum. The integrated dataset contains approximately 14 million hourly records across the 588 stations and is released on Zenodo (DOI 10.5281/zenodo.20196221) under a Creative Commons Attribution 4.0 International (CC BY 4.0) licence. It is intended as a substrate for research on air quality forecasting, environmental epidemiology and multi-source data fusion at nationwide scale.

Abstract: TinyML autoencoder anomaly detection is widely proposed for embedded sensor networks because the autoencoder’s learned latent representation supports downstream signal characterization that pure threshold detectors structurally cannot. However, the standard frozen-threshold architecture relies on a calibration-time frozen reconstruction-error threshold whose validity has not been characterized on signals containing slow envelope drift. We test a Hammad-style multilayer-perceptron autoencoder baseline against the non-stationary noise model previously used to validate the Temporal Spectral Noise-Floor Adaptation (TSNFA) detector [1] on Cortex-M4F-class hardware, in both per-node-trained and shared-pre-trained variants. Across the configuration matrix we find a structural false-alarm-rate floor in the order of one thousand false alarms per hour per node, two to three orders of magnitude above TSNFA on the same input realisations. Sweeping the proportion of training frames containing transient bursts and the threshold coefficient confirms the ceiling is not transient-driven but correlated to drifting noise. We then introduce a hybrid architecture in which a single scalar drift estimate sourced from a TSNFA detector normalizes each frame before the autoencoder receives it, leaving the autoencoder weights and frozen threshold unchanged. The hybrid delivers two quantified findings. First, full suppression of false positives: the false-alarm cluster rate collapses from 17.95 clusters per hour per node (MLP TinyML-Shared baseline) to 0.00 clusters per hour per node (hybrid) at 12 dB SNR on a 50-node network, matching TSNFA on the same input realisations, with network load reduced by a factor of 260. Second, signal classification: the autoencoder's 8-dimensional bottleneck output separates background noise from two synthetic event classes at 96.0 % balanced accuracy in the hybrid, against 83.1 % in the baseline detector under the same drift — a feature the binary TSNFA detector cannot provide. The hybrid is therefore not a replacement for TSNFA on detection alone-TSNFA dominates at roughly 200× lower compute, but it becomes the operationally-preferred deployment path whenever downstream signal characterization is required alongside binary detection.

Abstract: (1) Background: Evolutionary Strategies (ESs) are optimization metaheuristics largely adopted in Evolutionary Computation (EC). Since their introduction in early 70s, researchers in the field attempted to improve the efficacy of these algorithms. The most advanced ESs, such as Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES) and Exponential Natural Evolution Strategies (xNES), make use of covariance matrices storing relationships between parameters to be optimized, which enable the algorithms to fasten the search in the solution spaces. However, the computational cost of calculating covariance matrices linearly scales with the number of parameters. Recently, OpenAI Evolutionary Strategy (OpenAI-ES) emerged as an effective ES in different domains, thanks to the parameter information stored in two momentum vectors. Furthermore, OpenAI-ES gains an advantage from the usage of symmetric sampling and weight decay techniques. (2) Methods: In this work, we delve into the application of symmetric sampling and weight decay to CMA-ES, xNES and Separable Natural Evolution Strategies (sNES), with the aim to improve their performance in domains in which they get stuck in local minima outcomes. Specifically, we propose three novel variants for each ES and verify their efficacy with respect to the Pybullet halfcheetah and hopper robot locomotion problems, and two collective tasks (i.e., swarm aggregation and swarm foraging). (3) Results: Our findings reveal that symmetric sampling produces performance enhancements in all the domains, whereas the effect of weight decay varies across the considered problems. Furthermore, symmetric sampling allows ESs to keep parameter size limited, which is paramount in these scenarios. (4) Conclusions: This research identifies techniques enhancing the success of modern ESs, proposes several ES variants, and discusses relationship between algorithmic performance and task properties.

Abstract: The given research paper is an end-to-end architecture of grayscale clothing image classification with a lightweight Convolutional Neural Network (CNN) with the Fashion-MNIST dataset. Its architecture consists of three convolutional layers with Batch normalization to stabilize training, Dropout to avoid overfitting, MaxPooling to reduce spatial, and data augmentation (random rotation, shifting, zooming, flipping) to increase the effective training set. Early Stopping callback was used to terminate training when the validation performance leveled off. The model obtained 88.63%. test accuracy, which indicates that a tailor-crafted lightweight CNN can be used to perform competitively on Fashion-MNIST without resorting to complex heavyweight architectures. The precision and F1-scores were high when it came to categories that had distinct visual characteristics (trousers, sandals, bags) and categories with similar textures and outlines (T-shirts, pullovers, coat) were likely to be misclassified. The paper also contextualizes these findings concerning the development of CNN architecture of LeNet-5 to AlexNet and VGGNet, and explains the implications of the results to the effective use of AI in resource-restricted settings.

Abstract: This paper presents TALOS, a beyond-state-of-the-art unified-reusable 6G CryptoProcessor architecture for high-assurance symmetric security services under a 256-bit private-key operating baseline. The work is driven by a fundamental hardware-design challenge: future 6G systems will require simultaneous support for heterogeneous strong symmetric primitives; yet conventional per-cipher hardware replication is area-intensive, power-inefficient, and structurally unflexible. TALOS addresses this problem through a processor oriented architecture that combines a Hierarchical Common Data Path (HCDP) with a three-tier cryptographic encapsulation model spanning AES-256, Snow 5G/SNOW-V class, and ZUC-256. The proposed methodology separates reusable structures by exact operator class: Tier-1 captures native nonlinear substitutions, Tier-2 captures bounded arithmetic nonlinearities through micro-S-box compilation, and Tier-3 captures shared permutations, XOR, affine, diffusion, and state-transport fabrics. This decomposition enables for exact operator-level unification without forcing structurally dissimilar cipher families into an artificial common form. As a result, TALOS preserves cipher correctness while exposing the strongest realistic sharing opportunities across the substitution, arithmetic, and linear transport layers. The architecture further supports (CIA) confidentiality processing together with integrity- and authentication-supporting service integration through a common control and resource framework. In contrast to monolithic universal-box concepts or loosely aggregated multi-core designs, TALOS establishes a disciplined and scalable hardware taxonomy for crypto-agile 6G symmetric-core realization. The proposed framework, therefore, advances the state of the art by unifying rigorous methodological exactness, architectural reuse, and implementation-oriented practicality within a single CryptoProcessor design paradigm.

Abstract: The given research paper describes a CNN model of classifying images belonging to more than two classes on the Fashion-MNIST data. The model performed a test accuracy of 92.44% and test loss of 0.2533 the greatest accuracy as compared to similar studies with similar architectures. The architecture has three convolutional-pooling blocks, a dense layer with dropout regularization (0.3), and a softmax output layer. The analysis of training and validation curves demonstrates mild overfitting of the later epochs, and the validation loss starts growing even though the training loss continues to decrease. In-depth analysis using confusion matrix and classification report identifies certain patterns of misclassification between visually similar categories. The paper also discusses implications on batch normalization, data augmentation as well as Vision Transformer architecture.

Abstract: Dynamic community detection seeks to identify changing structural groups in temporal graphs; however, current neural methodologies are susceptible to misinterpreting transient edges, noisy temporal variations, or unusual spectral disturbances as authentic structural changes. This research introduces TriMeta-BFNet, a tri-meta stacked atypical-frequency Bayesian Fourier neural network designed for hallucination-resistant community discovery. The proposed system presents a three-dimensional meta-counterbalance mechanism that includes topological consistency, Fourier-domain atypical frequency modeling, and Bayesian posterior uncertainty estimation. Initially, temporal graph signals are converted into the Fourier domain to distinguish stable low-frequency community patterns from erratic high-frequency disturbances. Secondly, unusual frequency points are detected by spectral energy deviation and integrated into a stacked neural representation module, enabling the model to differentiate significant structural alterations from extraneous oscillations. Third, Bayesian inference is employed to assess posterior uncertainty regarding community assignments, therefore mitigating overconfident predictions in the presence of ambiguous or noisy graph evolution. The three components are simultaneously optimized via a cohesive objective function that integrates community detection loss, structural consistency regularization, atypical-frequency penalty, temporal stability management, and Bayesian calibration loss. The resultant structure offers both resilient community divisions and comprehensible hallucination-risk assessments. TriMeta-BFNet theoretically conceptualizes hallucination in dynamic community detection as an imbalance of structural, spectral, and uncertainty factors, and it develops a mathematically rigorous counterbalance mechanism to mitigate erroneous community evolution. The suggested model presents a novel approach to uncertainty-aware, frequency-sensitive, and interpretable dynamic graph learning.

Abstract: In this paper, we examine how the VTP2 extended persistence timeout policy affects and influences the performance of distance-vector and link-state routing protocols in the ad hoc network of the New Generation of Open Digital Universities (DOUNG). The problem addressed is that conventional SCTP retransmissions lack good performance when losses result from a path break rather than congestion. In classical SCTP, missing acknowledgments may trigger retransmissions even when the loss is caused by a temporary route failure rather than by congestion. The proposed evaluation uses an NS-3-compatible methodology with IEEE 802.11, SCTP, AODV, DSDV, DSR and OLSR under increasing node mobility. Results are organized by protocol to improve figure readability. The reference outputs show that VTP2 improves packet delivery ratio, throughput, end-to-end delay, SCTP retransmissions and energy consumption. The average gains are higher for AODV, DSDV and DSR than for OLSR, confirming that extended persistence is more beneficial to protocols exposed to route discovery, repair and maintenance phases. These results indicate that VTP2 is a relevant cross-layer mechanism for improving quality of service in mobile, heterogeneous and distributed digital-university environments.

Abstract: Solving the 3D Point Cloud Place Recognition (3D-PCPR) task is essential for the localization and mapping of depth-based perception systems. Visual Place Recognition methods are highly dependent on image texture information, while the limited number of available point cloud datasets for 3D-PCPR causes the methods to overfit to specific data. Our objective is to use the latest foundation models for 3D point clouds. These models are trained using enormous 3D object datasets where the density is nearly uniform. However, the point clouds produced by the LiDAR sensors are sparse and non-uniformly distributed. We propose a new approach, Unified Point Cloud 3D Place Recognition (Uni-PCPR), effectively maintaining the expressiveness of features generated by the foundation model. We have evaluated the performance of Uni-PCPR on several datasets and found that it generalizes well to unseen data, outperforming other methods. The code will be available upon acceptance.

Abstract: The rapid digitalization of energy systems and the increasing integration of distributed energy re-sources, renewable energy technologies, and prosumer-oriented infrastructures have accelerated the development of IoT-enabled Smart Grids as a foundation for intelligent and adaptive energy management. Modern Smart Grids increasingly depend on the coordinated interaction of IoT ar-chitectures, artificial intelligence, distributed analytics, and decentralized control mechanisms to ensure reliability, scalability, and real-time operational flexibility. Despite extensive research activ-ity, existing studies remain predominantly technology-centric, focusing on isolated architectural layers or individual intelligent methods without providing a unified system-level perspective on their coordinated operation and interoperability. This article presents a system-level integrative review and challenge-oriented comparative synthesis of intelligent operational and architectural foundations of IoT-enabled Smart Grids. The study analyzes data-driven, model-driven, knowledge-driven, agent-based, and hybrid-oriented intelligent paradigms within multi-layer IoT energy infrastructures. In addition, the research establishes a cross-layer mapping between Smart Grid operational challenges, enabling technologies, and corresponding analytical approaches while identifying interoperability constraints, scalability limitations, and coordination challenges associ-ated with decentralized energy ecosystems. The conducted synthesis demonstrates that hy-brid-oriented intelligent approaches represent the most promising direction for future Smart Grid evolution due to their ability to integrate AI, ML, digital twins, semantic reasoning, and decen-tralized multi-agent coordination within unified IoT architectures. The presented results provide a conceptual foundation for the prospective development of adaptive, interoperable, scalable, and explainable Smart Grid ecosystems integrating decentralized computing, distributed energy re-source coordination, vehicle-to-grid interaction, and intelligent cyber–physical orchestration.

Abstract: The rapid digitization of the real estate and architectural design industries has created a high demand for automated tools capable of parsing 2D raster floor plans. Traditional manual measurement and visual inspection are not only time-consuming but also highly susceptible to human error. In this paper, we propose a comprehensive, end-to-end deep learning framework designed to automatically extract rich semantic information from unstructured 2D floor plan images and provide professional design guidance via Large Language Models (LLMs). Our integrated pipeline employs the state-of-the-art YOLOv8 object detection model to accurately localize and classify 18 distinct architectural symbols and furniture items (e.g., doors, windows, beds, cupboards). Simultaneously, a U-Net architecture with a ResNet34 encoder is utilized for the precise semantic segmentation of structural elements, specifically walls and interior room spaces. To translate pixel-level predictions into actionable real-world metrics, we introduce a robust area calculation algorithm based on user-defined reference scale calibration. Furthermore, to bridge the gap between raw geometric data and actionable architectural intelligence, we introduce an LLM-driven evaluation module utilizing a local Ollama deployment and a Retrieval-Augmented Generation (RAG) pipeline to assess design compliance and quality. To overcome the scarcity of annotated architectural datasets, we implement a systematic data augmentation strategy, expanding a core dataset of 101 manually annotated floor plans to 303 varied instances, thereby significantly enhancing model generalization. Experimental results indicate that our YOLOv8-based detection module achieves a mean Average Precision (mAP50) of 92.3%, while the U-Net segmentation module achieves a mean Intersection over Union (mIoU) of 95.71%. Furthermore, the integrated system is deployed as a user-friendly, interactive web application, acting as an intelligent architectural assistant and demonstrating its practical viability and high efficiency for real-world engineering and architectural applications.