Search Results (32)

Medical-image retrieval systems must balance semantic relevance with storage and search cost while remaining robust to errors introduced by hierarchical routing. This work presents an anatomy-aware hierarchical contrastive hashing framework for radiograph classification and retrieval. A calibrated ConvNeXt-Tiny classifier first estimates anatomical-region probabilities, after which a shared Swin-Tiny encoder and lightweight anatomy-specific heads produce fine-grained predictions and compact binary codes. The hashing objective combines embedding-level supervised contrastive learning with hash-space semantic supervision, route-specific binary prototypes, a sign-margin constraint, quantization, and route-wise bit balance. Confidence-adaptive multi-route database indexing and top-r query routing are used to reduce irrecoverable failures caused by hard Stage-1 assignment. Experimental results on IRMA and MURA datasets reveal that the proposed framework improves retrieval performance and efficiency over competing deep-feature and hashing-based approaches. The Stage-1 classifier on IRMA achieved 97.05% sample-level accuracy, 93.15% macro recall, and 95.33% macro-F1, whereas Stage 2 reported 96% accuracy and 93.2% macro-F1. 128-bit hash codes achieved Precision@20 of 0.96, and mAP of 0.871. On MURA, Stage 1 achieved 96.93% anatomy-classification accuracy, 96.44% macro-F1, and a calibration error of 0.0126. The 14-class Stage 2 model achieved 75.13% accuracy and 74.84% macro-F1. Joint anatomy–abnormality retrieval showed a code-length-dependent trade-off: 32-bit codes obtained the highest mAP of 0.646, while 256-bit codes achieved the best early-rank performance with Precision@10 of 0.631 and nDCG@10 of 0.626. Study-level normal/abnormal prediction achieved an AUROC of 0.860, AUPRC of 0.857, and accuracy of 80.46%. These results support the use of anatomy-aware routing and compact semantic hashing for efficient radiograph retrieval, while also showing that abnormality-level discrimination remains substantially more challenging than anatomical categorization. Full article

While large language models (LLMs) have shown impressive performance on free-text questions, their reliability on tabular question answering (Tabular QA) is constrained, especially for multi-step reasoning and numerical aggregation. These challenges are amplified in Arabic due to orthographic variation, dual numeral systems, and invisible Unicode artifacts that disrupt table matching and structured execution. While code-centric pipelines mitigate arithmetic errors by executing generated programs, most rely on fixed multi-stage workflows that do not adapt to question difficulty. We introduce Gate2Code, a difficulty-aware pipeline for Arabic Tabular QA combining three components: (i) LLM-based difficulty routing, (ii) Arabic-aware table normalization, and (iii) hybrid function-level code generation with controlled fallback execution. Easy questions are answered directly, whereas compositional reasoning questions are routed to structured planning followed by deterministic program synthesis. We evaluate Gate2Code on a 615-question Arabic Tabular QA benchmark spanning LLM-generated, real-world, and Wikipedia tables. On reasoning questions, DeepSeek and Mistral zero-shot baselines achieve 51.49% and 43.95% macro-accuracy, respectively, whereas Gate2Code reaches 95.49% and 90.82% reasoning macro-accuracy. Compared with a state-of-the-art code-generation pipeline, Gate2Code matches or exceeds the baseline’s accuracy while reducing inference time by 12–46%, token consumption by 27–49%, and LLM calls by 4.75–12%. These results suggest that adaptive difficulty routing, combined with Arabic-aware normalization and structured code execution, can substantially narrow the gap between LLM capabilities on free-text and structured-input tasks in Arabic settings. Full article

Bandwidth-limited aerial–ground sensing requires an explicit trade-off among payload size, decoded-map quality, and downstream route utility. This paper evaluates a strict RGB-D edge-perception interface in which the receiver accesses only a quantized C × 16 × 16 tensor and no encoder-side skip features. Under a fixed AeroScapes protocol, five-seed latent-8 training gives a test intersection over union (IoU) of 0.5617 ± 0.0585 and route utility of 0.0539 ± 0.0227; the strongest validation-selected checkpoint reaches an IoU of 0.6584 but is reported only as a checkpoint-specific result. Acontrolled five-seed width ablation identifies a Pareto set: latent-8 is the lowest-rate operating point at 16.448 kbit, latent-16 has the smallest IoU standard deviation, and latent-32 gives the highest mean IoU (0.5788) and route utility (0.0921), with no significant pairwise differences between widths. A paired threeseed stabilization test likewise finds no significant IoU improvement from depth dropout, a soft topology loss, or their combination (p ≥ 0.6060); the combined configuration raises mean IoU to 0.5700 but increases dispersion. Relative to a practical reference combining JPEG (quality 75) RGB and 8-bit PNG depth, latent-8 reduces the mean payload by a factor of 4.32. The digital-link study extends the additive-noise analysis to fading, intersymbol interference, timevariation, packet and burst errors, near–far interference, and corrupted range metadata. Conventional short codes, source-aware unequal protection, and a 3GPP NR LDPC implementation are evaluated with framing, automatic repeat request, mediumaccess overhead, and transmission delay. Cross-domain evaluation establishes an important limitation: zero-shot AeroScapes-to-UAVid transfer is weak, whereas sequence-disjoint tenseed UAVid training improves the eight-class mean IoU from 0.2417 ± 0.0221 for RGB-only to 0.2602 ± 0.0129 for strict RGB-D (p = 0.0161). Lightweight depth, visibility, missingdepth, weighted-topology, and coarse-to-local refinement experiments further delimit deployment. Together, these experiments provide an auditable cross-layer evaluation linking source representation, channel reliability, protocol cost, spatial error, and receivergrid connectivity without equating one favorable checkpoint with general superiority. Full article

Dynamic heterogeneous vehicle routing with time windows requires reoptimization whenever customer arrivals and network disruptions change the decision space and the set of feasible routes. A reoptimized plan is useful in practice only if it does not rewrite the schedule that crews are already executing. This paper presents DNSGA-II-ALNS, an epoch-based dynamic multi-objective evolutionary algorithm. It couples an event-conditioned warm-start projection with an exact marginal assignment cost, feasibility-aware destroy-and-repair search and NSGA-II selection. The projection is not claimed to be a new optimization paradigm: it is a deterministic map between consecutive decision spaces that is defined even when a customer arrival changes their dimension, that introduces no constraint violation, and that leaves every customer unaffected by the event on its current vehicle. The algorithm is compared with seven alternatives under a paired protocol. All 56 Solomon instances are used with ten independent runs, and every method sees the same stored event stream for a given instance and run, a population of 50 and 8000 objective evaluations per epoch. The main empirical finding concerns plan stability. DNSGA-II-ALNS reassigns 11.1% of the persisting customers after an event, whereas a cold restart reassigns 89.2%, and the two groups do not overlap on any of the 56 instances. The reduction is not accompanied by a loss of solution quality, since the eight methods differ by at most 2.6% in total distance and 0.6% in makespan and all of them serve every customer within its time window. In front quality, the algorithm is not separated from the best-ranked method by the applied tests: it obtains the second-best Friedman mean rank (3.000 against 2.446), and the difference is smaller than the Nemenyi critical difference of 1.403. Advantages over the cold restart, MOPSO-ALNS and a memory-MOEA/D control are statistically significant with rank-biserial effect sizes of 0.84–0.87, while the comparisons with MODE-ALNS and the memory-NSGA-II control are not significant. An ablation indicates that the destroy-and-repair operators govern front quality, exceeding a routing-specific genetic control by 6.8–8.7% and a generic real-coded control by 15.9–26.4%. Quality is retained up to 200 customers at a fixed fleet density, but the mean response time rises from 33 to 716 s per epoch, which limits applicability to real-time dispatching. The contribution is accordingly operational rather than a new optimization methodology: comparable front quality at an order of magnitude less plan churn. Full article

Geospatial data provide an important basis for urban governance, resource management, disaster assessment, and public health analysis by linking spatial locations, attribute information, and dynamic processes. However, complex geospatial analysis still requires substantial expertise in spatial databases, spatial SQL, and GIS computation tools. Although large language model-based Text-to-SQL methods have lowered the barrier to natural language-driven data querying, most existing approaches rely on single-step SQL generation and remain unstable for spatial tasks that involve attribute retrieval, spatial relationship evaluation, geometric operations, and statistical aggregation. To address this limitation, this paper proposes a Code Generation-Driven Query–Computation Separation Framework (CGD-QCSF). The framework is based on the separation of query and computation, and decomposes complex geospatial analysis into a staged execution process. CGD-QCSF coordinates intent understanding, schema pre-filtering, planning, execution state management, SQL generation, and spatiotemporal computation. A structured planner and an execution state manager coordinate task decomposition, capability-aware routing, and evidence-based recovery. A SQL Code Generation Agent (SCGA) handles database access, attribute filtering, and intermediate data extraction, while a Spatiotemporal Computation Agent (STCA) performs out-of-database spatial computation and statistical aggregation in an isolated Python sandbox. We construct a benchmark of 200 tasks, covering easy, medium, and hard spatial tasks. In the main experiment with Qwen3.7-Plus as the foundation model, CGD-QCSF achieves a Strict Structured Accuracy (SSA) of 90.5%. Removing the Planner reduces SSA to 84.5%, while removing the STCA reduces it to 70.5%. The ablation experiments show that removing either the Python sandbox or the Planner Agent degrades performance on complex tasks. These results indicate that CGD-QCSF extends complex geospatial analysis from single-step SQL generation into a multi-staged execution process. By explicitly separating query and computation, the framework reduces interference between spatial computation logic and database schema information, thereby improving the stability and success rate of natural language-driven geospatial analysis. Full article

Main memory carries data outside the processor’s trust boundary, so commodity systems-on-chip (SoCs) increasingly encrypt it; yet, in-line memory encryption engine itself becomes a differential power analysis (DPA) target whose key, if recovered, unlocks all of dynamic random-access memory (DRAM). We present PACE, a page-adaptive, cache-anchored memory encryption engine for RISC-V that makes nth-order DPA resistance practical and keeps cryptographic latency off the cache eviction critical path. PACE inserts a TileLink adapter between the last-level cache and the memory port and applies, per physical page, one of four policies (plaintext/confidentiality/confidentiality+integrity/+masking-order-d) selected from RISC-V page table bits through a memory-mapped control plane. Confidentiality uses counter mode whose per-line keystream is precomputed during cache residency; integrity is tree-free at the embedded operating point via on-chip counters and tags, with a live split counter block-MAC Bonsai Merkle tree for scale-out. DPA resistance is layered: ISAP-style fresh re-keying caps the data complexity per key at $q\approx 1$, and domain-oriented masking (DOM, d + 1 shares) protects the sole key processing block to order d. We implement PACE in Chisel on a Rocket SoC (Chipyard) and evaluate it with open-source tooling. A deterministic TileLink-level harness proves ciphertext-in-memory and detects tamper/replay/splice, and the live Tier-B engine (DRAM counters and per-line message authentication codes (MACs) plus an on-chip-rooted block-MAC tree) is validated from end to end on full Rocket and BOOM SoCs and on the FPGA; the masked Ascon-p S-box is proven order-d secure (d = 1, 2) under a glitch- and transition-aware model by three independent formal tools (COCO, PROLEAD, and SILVER, the last also deciding the full composability lattice and confirming exact glitch-robust order-2 probing security), with COCO extending the exact verdict to the highest synthesized order d = 3 (secure at probing orders 1–3); a simulated trace correlation power analysis (CPA) recovers the full key from an unprotected core and is defeated by masking, with a mutual information analysis confirming the $N\propto {\sigma }^{2(d+1)}$ trace amplification law. We further realize PACE on field-programmable gate array (FPGA) silicon: the engine plus an on-chip ring oscillator power sensor is placed, routed, timing-closed at 100 MHz, and programmed on a Xilinx XC7Z020, and we drive a fixed-vs-random Test Vector Leakage Assessment (TVLA) campaign read back entirely over a JTAG (Joint Test Action Group). A multi-core configuration and a Linux control-plane driver are likewise validated. Across synthetic access patterns and named application kernels (AES, SHA-256, matrix multiplication, pointer chasing) on both in-order Rocket and out-of-order BOOM, application-level overhead is within measurement noise of plaintext for cache resident workloads (masking, in particular, is cycle-identical to plain confidentiality), and we characterize the cost of each policy, masking order, and re-keying interval, demonstrating side-channel-hardened memory encryption on open RISC-V hardware. Full article

Objectives: To describe and compare decadal antibiotic prescribing patterns and trends by diagnosis groups among ophthalmology inpatients at two private-sector hospitals in Central India. Methods: This observational surveillance study was conducted prospectively for a decade in the ophthalmology inpatient departments of a teaching hospital (TH) and a non-teaching hospital (NTH). Patient-level data on demographics, diagnoses, and antibiotic prescriptions were collected by nurses using a standardised form. Antibiotic utilisation was analysed using WHO’s Anatomical Therapeutic Chemical (ATC) codes and Defined Daily Doses (DDDs), as well as AWaRe groups (Access, Watch, Reserve). Diagnoses were classified into infectious and non-infectious categories, and surgical and non-surgical groups. Prescribing trends were analysed using descriptive statistics and linear regression models. Results: Of 7561 patients (TH: 7305; NTH: 256), antibiotics were prescribed to almost all inpatients (TH: 99%; NTH: 90%). Fluoroquinolones were the most prescribed (TH: 94%; NTH: 71%), predominantly by the oral route (73%). Access-group antibiotics were considerably under-prescribed relative to WHO targets (TH: 3%; NTH: 4%). Watch-group antibiotics comprised 97% (TH) and 96% (NTH) of all prescribed antibiotics, and their prescribing increased significantly over 10 years (p < 0.05). Conclusions: Watch-group fluoroquinolones dominated antibiotic prescribing at both hospitals and increased over the study period. Access-group antibiotics were substantially underutilised. These findings highlight an urgent need for context-specific antibiotic prescribing guidelines and stewardship programmes in ophthalmology settings in LMICs. Full article

Implicit hate speech is difficult to detect because hostile intent is often conveyed through metaphor, irony, coded expressions, stereotypes, or culturally situated allusions rather than direct insults. We first construct a fine-grained Chinese implicit hate speech dataset containing 19,939 samples from Zhihu and Baidu Tieba, covering nine target categories and three expression labels. Based on this dataset, we propose FICHS, a fine-grained and implicit Chinese hate speech detection framework with three synergistic modules built on a RoBERTa-based base detector: an Explicit–Implicit Supervised Contrastive Module that learns a discriminative semantic space between explicit and implicit hate speech, a Semantic Opacity-Aware Routing and Adjudication module that selectively routes low-confidence but high-implicitness samples to an LLM for secondary judgment, and a Pattern-Guided Retrieval-Augmented Recovery Module that retrieves socio-cultural risk patterns to support second-round review and false-negative recovery. Experimental results demonstrate that FICHS effectively improves Chinese implicit hate speech detection, achieving a weighted F1 score of 0.8391, with precision of 0.8428 and recall of 0.8396, outperforming both the SOTA detector and standalone LLM baselines. Full article

Time-reversed Young (TRY) interferometry reconstructs interference from a fixed detector by reading out a programmable source-label distribution. This work formulates the architecture as a source-coded Bayesian response sensor. For a perturbation parameter $\theta$, the detected source-label histogram is a posterior distribution determined by a programmed source prior, an optical likelihood for a fixed-detector click, and an evidence factor equal to the click probability. The key point is not the Bayesian identity itself, but its physical implementation: in TRY the prior is imposed before propagation and can therefore reshape the response ensemble actually sampled by the detector. The normalized posterior is shown to respond through a centered likelihood score, and the detected-event Fisher information is the posterior variance of this score. This identifies posterior-weighted score contrast, rather than local response magnitude alone, as the relevant sensing resource. The framework separates posterior-shape information from evidence information, giving a resource-aware way to judge near-null response enhancement. It also yields practical design rules: a two-label source code converts a weak perturbation into a fixed-detector label imbalance, while the multiparameter score covariance provides a route to nuisance rejection and gives a minimal-label rank condition for sensing multiple perturbations. A passive double-slit implementation with weak one-slit phase and loss perturbations is proposed, requiring only fixed-detector source scans before and after calibrated perturbations. Practical tolerances associated with source-programming error, drift, background, imperfect coherence, and polarization mismatch are analyzed, and extensions to multi-aperture and integrated photonic systems are formulated. The results position TRY as a source-programmable Bayesian sensing architecture complementary to conventional detector-plane Young interferometry. Full article

Retrieval-Augmented Generation (RAG) grounds large language models in external evidence, but many RAG systems represent knowledge either as flat text chunks or as automatically constructed indexing graphs. This assumption is incomplete for curated thematic corpora, including religious scriptures, legal codes, clinical guidelines, educational taxonomies, policy documents, and library classification systems, where domain experts have already organized knowledge into thematic paths and citeable canonical units. This paper investigates how RAG can exploit such expert-authored structures while pruning evidence to a compact and query-specific set. We conduct a critical survey supported by a bibliometric analysis of 2815 Scopus-indexed RAG-related records exported on 26 May 2026, of which 2809 records were retained after duplicate removal. The bibliometric results indicate rapid growth in RAG research but limited explicit consolidation around curated thematic paths, canonical evidence units, or thematic path-guided evidence pruning. We therefore propose ThemePath-RAG, a retrieval framework that retrieves curated thematic paths as high-recall semantic routes, expands candidate canonical evidence, and applies query-aware scoring and global pruning before generation. To assess operational feasibility, we implement ThemePath-RAG for Qur’anic question answering and compare it with a Vector RAG baseline on 150 paired questions using RAGAS context relevance with gpt-4o-mini as the LLM evaluator. Both methods return approximately three final ayat per question. Vector RAG achieves higher mean context relevance than ThemePath-RAG ($0.920$ versus $0.798$; $p<0.001$). Thus, the proof of concept establishes the feasibility of thematic-path-guided retrieval and identifies evidence-selection challenges, rather than demonstrating superiority over conventional vector retrieval. The paper clarifies the framework’s relationship to GraphRAG, LightRAG, HippoRAG, PathRAG, ontology-based RAG, and AI-augmented bibliometric systems, and outlines a language-matched, multi-baseline evaluation agenda for future cross-domain validation. Full article

Existing CNN-based visual malware classification methods are often constrained by inductive bias mismatch: standard isotropic convolution kernels and global pooling operations neglect the inherent structural anisotropy of malware images, and these methods struggle to address the spatial rearrangement of code blocks caused by obfuscation, which we term the “Malware Picasso Problem”. To overcome these limitations, we propose AD-CapsFPN, an end-to-end framework representing a significant step toward spatial reasoning over texture memorization, with a synergistic “Rectification–Fusion–Inference” mechanism. Our approach rectifies anisotropic inductive biases in the feature extraction stage, dynamically aggregates cross-scale discriminative features in intermediate layers, injects row-aware spatial biases, and adopts a global pooling-free spatial routing strategy in the classification stage, effectively reconstructing logical associations between obfuscated and scattered code blocks. Experiments on the large-scale Fusion dataset and the obfuscated Androdex dataset demonstrate significant performance improvements: our method achieves a 16.22% boost in macro F1-score over the MobileNetV4 baseline on the Fusion dataset (reaching 97.98%), and hits 92.45% macro F1-score on the highly challenging Androdex-Set1, outperforming state-of-the-art methods such as MDC-RepNet (88.97%) and TAEfficientNet (88.15%). This work confirms that embedding malware domain priors into architecture design is the key to robust malware classification. Full article

By incorporating opportunistic coding, network throughput is enhanced, resulting in improved overall performance. However, applying this paradigm to Flying Ad-hoc Networks (FANETS) faces significant challenges due to the highly dynamic topology caused by the high-velocity mobility of UAVs, alongside the NP-hard complexity of identifying optimal coding opportunities in rapidly evolving aerial network architectures. To address these challenges, this paper proposes a novel coding-aware routing protocol based on Multi-Agent Deep Deterministic Policy Gradient (MADDPG). We formulate the routing problem as a multi-agent continuous decision-making process, employing the MADDPG algorithm to optimize routing policies in real-time through decentralized execution and centralized training. To maximize network utility, we design a comprehensive reward function that integrates coding benefits, throughput, energy distribution, and end-to-end delay, ensuring a balance between throughput maximization and the energy sustainability of individual UAV nodes. Simulation results demonstrate that the proposed protocol significantly outperforms state-of-the-art coding-aware routing protocols in terms of throughput, Packet Delivery Ratio (PDR), and transmission delay, exhibiting superior robustness in highly dynamic FANET scenarios. Notably, at a network density of 20 UAVs, MARL-CAR outperforms COPE, DCAR, TSCAR, and RLCAR in terms of coding ratio by 32.23%, 18.93%, 20.35%, and 5.5%, respectively. This research provides a scalable and intelligent networking solution for the next generation of autonomous UAV swarms and collaborative aerial missions. Full article

Vehicle-to-Grid (V2G) technology enables controlled bidirectional energy exchange between electric vehicles (EVs) and the power grid, allowing EVs to operate as flexible storage resources that support renewable-energy integration, peak-load reduction, and ancillary services. As EV adoption grows, deploying V2G at scale requires a comprehensive understanding of the electrochemical, power-electronic, communication, and mobility foundations that determine system performance. This review presents an integrated assessment of the essential components of V2G and broader Vehicle Grid Integration (VGI). First, the technical foundations are examined, including traction batteries, battery management systems, bidirectional converter topologies, charger architectures, connector standards, and grid-code compliance. Battery degradation mechanisms under V2G cycling are analyzed, with emphasis on depth of discharge, cycling frequency, and thermal conditions. Second, charging-infrastructure architectures and grid-integration considerations are evaluated across AC, DC, on-board, and off-board charging systems. Third, communication and interoperability frameworks, including ISO 15118, OCPP, OCPI, and cybersecurity requirements, are reviewed to assess the security and scalability of V2G operations. Finally, grid-aware mobility applications are discussed, covering coordinated charging, energy-aware routing, shared and autonomous mobility services, and dynamic pricing within coupled power and transport networks. The review concludes by identifying key technical and operational insights that support the development of robust V2G and VGI ecosystems. Full article

Financial document understanding remains a critical challenge for Large Language Models, primarily due to the complex interplay between narrative text and structured numerical tables. Existing Retrieval-Augmented Generation (RAG) systems often treat these modalities in isolation, leading to significant failures in tasks requiring joint reasoning. This study introduces HierFinRAG, a novel hierarchical multimodal framework designed to unify tabular and textual data processing. Our approach employs a Table-Text Graph Neural Network (TTGNN) to explicitly model semantic and structural dependencies between table cells and corresponding text, coupled with a Symbolic–Neural Fusion module that routes queries between a neural generator and a symbolic calculator for precise arithmetic operations. We evaluate the system on the FinQA and FinanceBench datasets, comparing performance against strong baselines including Vanilla RAG and GPT-4o with Code Interpreter. Results demonstrate that HierFinRAG achieves an Exact Match score of 82.5% on FinQA, surpassing the best baseline by 6.5 percentage points, while maintaining a 3.5× faster inference latency than agentic approaches. These findings indicate that integrating hierarchical structural awareness with hybrid reasoning significantly enhances the accuracy and interpretability of financial artificial intelligence systems. Full article

We develop detailed quaternionic and octonionic frameworks for quantum computation grounded on normed division algebras. Our central result is to prove the polynomial computational equivalence of quaternionic and complex quantum models: Computation over $\mathbb{H}$ is polynomially equivalent to the standard complex quantum circuit model and hence captures the same complexity class BQP up to polynomial reductions. Over $\mathbb{H}$, we construct a complete model—quaternionic qubits on right $\mathbb{H}$-modules with quaternion-valued inner products, unitary dynamics, associative tensor products, and universal gate sets—and establish polynomial equivalence with the standard complex model; routes for implementation at fidelities exceeding $99\%$ via pulse-level synthesis on current hardware are discussed. Over $\mathbb{O}$, non-associativity yields path-dependent evolution, ambiguous adjoints/inner products, non-associative tensor products, and possible failure of energy conservation outside associative sectors. We formalize these obstructions and systematize four mitigation strategies: Confinement to associative subalgebras, $G_2$-invariant codes, dynamical decoupling of associator terms, and a seven-factor algebraic decomposition for gate synthesis. The results delineate the feasible quaternionic regime from the constrained octonionic landscape and point to applications in symmetry-protected architectures, algebra-aware simulation, and hypercomplex learning. Full article