Search Results (16)

The rapid integration of artificial intelligence (AI) into mental healthcare presents opportunities and ethical challenges, particularly for complex conditions like obsessive–compulsive disorder (OCD). In this perspective, we argue for a Dual Imperative: establishing safety architectures for AI-powered therapeutic tools to prevent algorithmic sycophancy (symptom accommodation), while mandating explainable AI (XAI) in prognostic models to ensure clinical auditability. In therapeutics, we propose a Guardian Angel architecture that utilizes patient-specific fear hierarchies and linguistic stance detection to distinguish compulsive reassurance-seeking from legitimate patient questions. This approach transforms potential therapeutic ruptures into opportunities for distress tolerance via the Digital Ulysses Pact, a patient-authorized, algorithmically enforced response prevention protocol. In diagnostics, we address the black box problem in precision psychiatry. We argue that as AI evolves from detection to high-stakes treatment selection, safety and accountability become a prerequisite for clinical application. Although distinct in implementation, these architectures form an integrated framework for aligning therapeutic and diagnostic AI. These architectures are not parallel tracks but a unified ecosystem: A patient’s XAI-audited profile can inform the Guardian Angel’s configuration, while the longitudinal data gathered during therapy enriches diagnostic precision. Grounded in ethical principles and best practices in OCD, this suggests a path toward AI that is auditable in its diagnostic logic, firm in its therapeutic boundaries, and enforceable through emerging regulatory frameworks. Full article

Objectives: To develop and rigorously evaluate a Hybrid Multi-Path Attention Convolutional Neural Network (HMPA-CNN) for the classification of kidney diseases across heterogeneous institutional datasets and imaging modalities. Materials and Methods: The proposed HMPA-CNN employs dual parallel pathways to disentangle spatial (3 × 3 convolutions) and textural (5 × 5 convolutions) representations, followed by attention-based feature recalibration and gated fusion. Performance was assessed on five geographically distinct datasets comprising 29,148 CT and MRI images collected from Turkey, Bangladesh, Jordan, Iraq, and publicly available international sources. The evaluation framework included three-class tumor discrimination, four-class renal pathology classification, six-class tumor subtyping, binary kidney stone detection, and chronic kidney disease (CKD) assessment under cross-modality conditions. Results: The model achieved 99.76% overall accuracy on the KidneyNeXt three-class dataset, 99.96% on the four-class multi-institutional CT dataset, and 99.74% on the independent Jordan cohort under a four-class configuration. In the more granular six-class tumor subtyping task, overall accuracy was 96.36%. The same architecture achieved 93.85% overall accuracy on the MRI-based CKD classification task, suggesting that the framework can be adapted to a different imaging modality. Across most classification tasks, specificity exceeded 99%, with benign–malignant misclassification remaining below 2%. Performance declined to 91.96% for kidney stone detection, reflecting the intrinsic difficulty of small-object localization in axial CT images. Conclusions: The dual-path architecture consistently preserved high discriminative performance across institutions, diagnostic granularities, and imaging modalities. Its stable specificity and low benign–malignant confusion suggest potential utility as a supportive tool within renal imaging workflows, particularly for screening and structured diagnostic assistance. Clinically, benign–malignant misclassification is the most critical error, as it may delay oncologic evaluation or lead to unnecessary follow-up. Therefore, the model should be used as a decision-support tool rather than an autonomous diagnostic system. Further prospective validation is required to determine its impact in routine clinical practice. Full article

Accurate detection of ship targets in complex marine environments is fundamental to ensuring maritime security and safeguarding maritime rights. With the increasing diversity of vessel types and configurations, achieving precise identification of multiple ship classes amidst dynamic interference and cluttered backgrounds has emerged as a formidable challenge in marine surveillance. To address three pervasive issues in ship target detection—namely, high false-negative rates for small targets, inadequate feature discrimination, and imprecise localization—this paper proposes AK-DSAM-YOLOv13, a multi-scale detection algorithm specifically tailored for complex marine scenarios. Built upon the YOLOv13n architecture, the proposed algorithm implements integrated optimizations across the backbone network, neck structure, and loss function. First, a lightweight cross-scale feature extraction module, AKC3k2, is constructed by incorporating Alterable Kernel Convolutions (AKConv) to reconstruct the feature extraction path, thereby significantly enhancing the representation of multi-scale targets. Second, a Dynamic Up-Sampling Dual-Stream Attention Merging (DyDSAM) structure is designed, which integrates the DySample operator with a Dual-Stream Attention Mechanism (DSAM) to effectively suppress background clutter and improve feature fusion accuracy. Third, an Accuracy-Intersection-over-Union (AIoU) loss function is introduced to jointly optimize overlap area, center distance, and aspect ratio, enhancing localization robustness for small-scale objects. Experimental results on the self-built CM-Ships dataset, as well as the public SeaShips and McShips datasets, demonstrate that AK-DSAM-YOLOv13 significantly outperforms baseline models in detection accuracy, recall, and generalization capability while maintaining a low computational overhead. This research provides an efficient and reliable technical framework for intelligent maritime visual monitoring in complex environments. Full article

Stereo matching constitutes a critical technology in applications such as autonomous driving and robot navigation. Conventional algorithms, however, often encounter limitations in real-time performance and resource efficiency when deployed on embedded platforms. This paper presents a real-time stereo matching system implemented on a Field-Programmable Gate Array (FPGA), which is built around a lightweight, hardware-optimized dual-path Semi-Global Matching (SGM) algorithm. The proposed method simplifies the traditional eight-path cost aggregation into horizontal and vertical dual-path aggregation, substantially reducing hardware resource consumption while preserving matching accuracy. The system employs a pipelined architecture that integrates image capture, DDR3 caching, and HDMI display output. Experimental results demonstrate that under the configuration of a 5 × 5 matching window and a disparity range of 64, the system generates stable disparity maps at 60 frames per second, with total power consumption below 2.2 W and FPGA core logic utilization under 30%. Compared to the conventional eight-path SGM, the dual-path strategy incurs only a marginal 6% increase in average bad pixel rate on standard stereo datasets while reducing Block RAM (BRAM) usage by approximately 30%. This achieves an effective practical balance between accuracy, computational efficiency, and power consumption. Full article

The paper introduces a computationally efficient semantic-aware route planning framework for indoor mobile robots, designed for real-time execution on resource-constrained edge hardware (Raspberry Pi 5, CPU-only). The proposed architecture fuses monocular object detection with 2D LiDAR-based range estimation and integrates the resulting semantic annotations into the Nav2 Route Server for penalty-weighted route selection. Object localization in the map frame is achieved through the Angular Sector Fusion (ASF) pipeline, a deterministic geometric method requiring no parameter tuning. The ASF projects YOLO bounding boxes onto LiDAR angular sectors and estimates the object range using a 25th-percentile distance statistic, providing robustness to sparse returns and partial occlusions. All intrinsic and extrinsic sensor parameters are resolved at runtime via ROS 2 topic introspection and the URDF transform tree, enabling platform-agnostic deployment. Detected entities are classified according to mobility semantics (dynamic, static, and minor) and persistently encoded in a GeoJSON-based semantic map, with these annotations subsequently propagated to navigation graph edges as additive penalties and velocity constraints. Route computation is performed by the Nav2 Route Server through the minimization of a composite cost functional combining geometric path length with semantic penalties. A reactive replanning module monitors semantic cost updates during execution and triggers route invalidation and re-computation when threshold violations occur. Experimental evaluation over 115 navigation segments (legs) on three heterogeneous robotic platforms (two single-board RPi5 configurations and one dual-board setup with inference offloading) yielded an overall success rate of 97% (baseline: 100%, adaptive: 94%), with 42 replanning events observed in 57% of adaptive trials. Navigation time distributions exhibited statistically significant departures from normality (Shapiro–Wilk, p < 0.005). While central tendency differences between the baseline and adaptive modes were not significant (Mann–Whitney U, p = 0.157), the adaptive planner reduced temporal variance substantially (σ = 11.0 s vs. 31.1 s; Levene’s test W = 3.14, p = 0.082), primarily by mitigating AMCL recovery-induced outliers. On-device YOLO26n inference, executed via the NCNN backend, achieved 5.5 ± 0.7 FPS (167 ± 21 ms latency), and distributed inference reduced the average system CPU load from 85% to 48%. The study further reports deployment-level observations relevant to the Nav2 ecosystem, including GeoJSON metadata persistence constraints, graph discontinuity (“path-gap”) artifacts, and practical Route Server configuration patterns for semantic cost integration. Full article

Human-to-robot (H2R) handovers are critical in human–robot interaction but are challenged by complex environments that impact robot perception. Traditional RGB-based perception methods exhibit severe performance degradation under harsh lighting (e.g., glare and darkness). Furthermore, H2R handovers occur in unstructured environments populated with fine-grained visual details, such as multi-angle hand configurations and novel object geometries, where conventional semantic segmentation and grasp generation approaches struggle to generalize. To overcome lighting disturbances, we present an H2R handover system with a dual-path perception pipeline. The system fuses perception data from a stereo RGB-D camera (eye-in-hand) and a time-of-flight (ToF) camera (fixed scene) under normal lighting, and switches to the ToF camera for reliable perception under glare and darkness. In parallel, to address the complex spatial and geometric features, we augment the Point Transformer v3 (PTv3) architecture by integrating a T-Net module and a self-attention mechanism to fuse the relative positional angle features between human and robot, enabling efficient real-time 3D semantic segmentation of both the object and the human hand. For grasp generation, we extend GraspNet with a grasp selection module optimized for H2R scenarios. We validate our approach through extensive experiments: (1) a semantic segmentation dataset with 7500 annotated point clouds covering 15 objects and 5 relative angles and tested on 750 point clouds from 15 unseen objects, where our method achieves 84.4% mIoU, outperforming Swin3D-L by 3.26 percentage points with 3.2× faster inference; (2) 250 real-world handover trials comparing our method with the baseline across 5 objects, 5 hand postures, and 5 angles, showing an improvement of 18.4 percentage points in success rate; (3) 450 trials under controlled adverse lighting (darkness and glare), where our dual-path perception method achieves 82.7% overall success, surpassing single-camera baselines by up to 39.4 percentage points; and (4) a comparative experiment against a state-of-the-art multimodal H2R handover method under identical adverse lighting, where our system achieves 75.0% success (15/20) versus the baseline’s 15.0% (3/20), further confirming the lighting robustness of our design. These results demonstrate the system’s robustness and generalization in challenging H2R handover scenarios. Full article

This paper proposes a novel, dual-output, hybrid-clamped, quasi-five-level inverter (DO-HC-FLI) topology, capable of providing two independent AC voltage outputs with adjustable frequency and amplitude. Derived from a dual-output, active, neutral-point-clamped, three-level inverter, the proposed topology introduces three additional switches per phase to create dynamic switching paths. This expands the available range of DC-side voltage outputs and significantly improves the utilization rate of the DC–link voltage. Additionally, by adopting an asymmetric DC–link voltage configuration, the output line voltage levels of the conventional four-level inverter are increased to a number comparable to that of a five-level inverter. The front-end stage employs a hybrid series-parallel architecture, integrating dual Buck circuits with DC power sources. This configuration supplies the subsequent inverter stage with DC voltage levels at an optimal asymmetric ratio. In conjunction with a dual-output space vector pulse width modulation (SVPWM) strategy, the proposed system can collaboratively optimize the output voltage level characteristics of the inverter stage. Furthermore, a comprehensive analysis and comparison with other multilevel inverters are presented to demonstrate the superiority of the proposed topology. Finally, simulations and experiments are conducted to validate the effectiveness and feasibility of the proposed topology and modulation strategy. Full article

The designs of lossless data compression architectures create a natural trade-off between throughput, power consumption, and compression efficiency, making it difficult for designers to identify an optimal configuration that satisfies all three criteria. This paper proposes a Configurable Dual-Path Huffman/Arithmetic Encoder (CDP-HAE), which offers an architecture that supports the use of shared preprocessing, parallel path encoding using Huffman and Arithmetic, as well as selectable output. The CDP-HAE’s design prevents the waste of excess bandwidth by sending only one selected bit stream at a time. This also enables adaptation to the dynamically changing statistical characteristics of the input data. CDP-HAE’s architecture underwent ASIC synthesis in 90 nm CMOS technology and is implemented on an Artix-7 (A7-100T) using the Vivado EDA tool, confirming the scalability of the architecture to both devices. Synthesis results show that CDP-HAE improves operating frequency by 28.6% and reduces critical path delay by 27.2% compared to reference designs. Additionally, the dual-path design has a slight increase in area; the area utilization remains within reasonable limits. Power analysis indicates that optimizing logic sharing and minimizing switching activity reduces total power consumption by 34.4%. Compression tests show that the CDP-HAE delivers performance comparable to that of a conventional Huffman Encoder using application-specific datasets. Furthermore, the proposed CDP-HAE achieves performance comparable to conventional Huffman encoders on application-specific datasets, while providing up to 10% improvement in compression ratio over Huffman-only encoding. Full article

To reveal how digital twin empowers electric vehicle supply chain resilience, this study first proposes a novel “Human–Machine–Material–Environment” system architecture. Then, it employs dynamic fsQCA on data from 27 electric vehicle companies to explore the underlying configurational mechanisms. The results reveal that digital twin empowers electric vehicle supply chain resilience not through singular factors, but through multiple, equally effective configurations of its core dimensions. This study identifies six types of high-resilience pathways, such as “dual-driven by twin and safety” and “comprehensive upgrade digital twin”. This demonstrates that no universal best pathway exists. This finding of equifinality is complemented by causal asymmetry, as the paths leading to non-high resilience are not mere opposites of the successful ones. Across time periods, data security management, human–machine collaboration, and digital twin applications consistently emerge as core prerequisites for improving supply chain resilience. By introducing digital twin, this study expands the theoretical boundaries of electric vehicle supply chain resilience research and provides new analytical perspectives and frameworks. Full article

Skeleton-based action recognition has achieved remarkable advances with graph convolutional networks (GCNs). However, most existing models process spatial and temporal information within a single coupled stream, which often obscures the distinct patterns of joint configuration and motion dynamics. This paper introduces the Dual-Path Cross-Attention Graph Convolutional Network (DPCA-GCN), an architecture that explicitly separates spatial and temporal modeling into two specialized pathways while maintaining rich bidirectional interaction between them. The spatial branch integrates graph convolution and spatial transformers to capture intra-frame joint relationships, whereas the temporal branch combines temporal convolution and temporal transformers to model inter-frame dependencies. A bidirectional cross-attention mechanism facilitates explicit information exchange between both paths, and an adaptive gating module balances their respective contributions according to the action context. Unlike traditional approaches that process spatial–temporal information sequentially, our dual-path design enables specialized processing while maintaining cross-modal coherence through memory-efficient chunked attention mechanisms. Extensive experiments on the NTU RGB+D 60 and NTU RGB+D 120 datasets demonstrate that DPCA-GCN achieves competitive joint-only accuracies of 88.72%/94.31% and 82.85%/83.65%, respectively, with exceptional top-5 scores of 96.97%/99.14% and 95.59%/95.96%, while maintaining significantly lower computational complexity compared to multi-modal approaches. Full article

A novel architectural design is proposed to optimize the thermal management of lithium-ion batteries (LiBs) through a software-enabled switching mechanism. This approach addresses critical challenges such as hot-spot generation, peak temperature rise, and uneven thermal distribution—issues commonly observed in conventional single-terminal battery modules (STBMs). The proposed dual-terminal configuration integrates an enhanced battery pack structure with a software-enabled switching algorithm that identifies the 50% depth of discharge (DoD) and toggles the current path between two terminals to supply the load. Correspondingly, the module also incorporates the division of four thermal zones and four regions concept in the battery module (BM). Experiments were conducted to evaluate the performance of the proposed model at five different C-rates: 0.5C, 0.75C, 1C, 1.25C, and 1.5C. The results demonstrate that the software-enabled dual-terminal switching (Se-DTS) consistently outperforms the STBM across three key aspects. First, in terms of peak temperature, Se-DTS achieved reductions of 19.33%, 17.83%, and 12.72% at C-rates of 1C, 1.25C, and 1.5C, respectively. Second, in thermal distribution, Se-DTS improved performance, with an 86.1% reduction at 1.25C. Third, regarding hot-spot reduction, improvements of 100% (regional level) and 72.22% (zonal level) were observed at 1.25C, while at 1.5C, an 80% improvement was achieved at the zonal level, without using a cooling system. Full article

The aircraft power supply system plays a crucial role in maintaining the stability and safety of airborne avionics. With the evolution toward more electric and all-electric aircraft, its architecture increasingly adopts symmetrical configurations, such as dual-redundant paths and three-phase balanced outputs. However, these symmetry-based designs are often disrupted by diverse fault mechanisms encountered in complex operational environments. This review contributes a comprehensive and structured analysis of how such fault events lead to symmetry-breaking phenomena across different subsystems, including generators, converters, controllers, and distribution networks. Unlike previous reviews that treat faults in isolation, this study emphasizes the underlying physical mechanisms and hierarchical fault propagation characteristics, revealing how structural coupling and multi-physics interactions give rise to failure modes. The paper concludes by outlining future research directions in symmetry-aware fault modeling and intelligent maintenance strategies, aiming to address the growing complexity and reliability demands of next-generation aircraft. Full article

This paper presents a novel harmonic-selective clocking scheme that facilitates concurrent downconversion of spectrally distant radio frequency (RF) signals using a single low-frequency local oscillator (LO) in an N-path receiver architecture. The proposed scheme selectively generates LO harmonics aligned with multiple RF bands, enabling simultaneous downconversion without modification of the passive mixer topology. The receiver employs a 4-path passive mixer configuration to enhance harmonic selectivity and provide flexible frequency planning.The architecture is implemented on a printed circuit board (PCB) and validated through comprehensive simulation and experimental measurements under continuous wave and modulated signal conditions. Measured results demonstrate a sensitivity of $-55\mathrm{dBm}$ and a conversion gain varying from $-2.5\mathrm{dB}$ to $-9\mathrm{dB}$ depending on the selected harmonic pair. The receiver’s performance is further corroborated by concurrent (dual band) reception of real-world signals, including a GPS signal centered at 1575 MHz and an LTE signal at 1179 MHz, both downconverted using a single 393 MHz LO. Signal fidelity is assessed via Normalized Mean Square Error (NMSE) and Error Vector Magnitude (EVM), confirming the proposed architecture’s effectiveness in maintaining high-quality signal reception under concurrent multiband operation. The results highlight the potential of harmonic-selective clocking to simplify multiband receiver design for wireless communication and global navigation satellite system (GNSS) applications. Full article

Solar-driven interfacial evaporation has emerged as a sustainable and highly efficient technology for seawater desalination, attracting considerable attention for its potential to address global water scarcity. However, challenges such as low evaporation rates and salt accumulation significantly hinder the performance and operational lifespan of evaporators. Here, we present an innovative Janus-structured evaporator featuring distinct operational mechanisms through the integration of a hydrophobic PVDF-HFP@PPy photothermal membrane and a hydrophilic PVA-CF@TA-Fe³⁺ hydrogel, coupled with a unidirectional flow configuration. Distinct from conventional Janus evaporators that depend on interfacial water transport through asymmetric layers, our design achieves two pivotal innovations: (1) the integration of a lateral fluid flow path with the Janus architecture to enable sustained brine replenishment and salt rejection and (2) the creation of dual vapor escape pathways (hydrophobic and hydrophilic layers) synergized with hydrogel-mediated water activation to elevate evaporation kinetics. Under 1 sun illumination, the evaporator achieves a maximum evaporation rate of 2.26 kg m⁻² h⁻¹ with a photothermal efficiency of 84.6%, in both unidirectional flow and suspension modes. Notably, the evaporation performance remains stable across a range of saline conditions, demonstrating remarkable resistance to salt accumulation. Even during continuous evaporation of highly saline water (10% brine), the evaporator maintains an evaporation rate of 2.10 kg m⁻² h⁻¹ without observable salt precipitation. The dual anti-salt strategies—enabled by the Janus structure and unidirectional flow design—underscore the evaporator’s capability for sustained high performance and long-term stability in saline environments. These findings provide valuable insights into the development of next-generation solar evaporators that deliver high performance, long-term stability, and robustness in saline and hypersaline environments. Full article

Traditional network architectures in smart ship communication systems struggle to efficiently manage the integration of heterogeneous sensor data. Additionally, conventional end-to-end transmission algorithms that rely on single-metric and single-path selection are inadequate in fulfilling the high reliability and real-time transmission requirements essential for high-priority service data. This inadequacy results in increased latency and packet loss for critical control information. To address these challenges, this study proposes an innovative ship network framework that synergistically integrates Software-Defined Networking (SDN) and Time-Sensitive Networking (TSN) technologies. Central to this framework is the introduction of a redundant multipath selection algorithm, which leverages Double Dueling Deep Q-Networks (D3QNs) in conjunction with Graph Convolutional Networks (GCNs). Initially, an optimization function encompassing transmission latency, bandwidth utilization, and packet loss rate is formulated within a software-defined time-sensitive network transmission framework tailored for smart ships. The proposed D3QN-GCN-based algorithm effectively identifies optimal working and redundant paths for TSN switches. These dual-path configurations are then disseminated by the SDN controller to the TSN switches, enabling the TSN’s inherent reliability redundancy mechanisms to facilitate the simultaneous transmission of critical service flows across multiple paths. Experimental evaluations demonstrate that the proposed algorithm exhibits robust convergence characteristics and significantly outperforms existing algorithms in terms of reducing network latency and packet loss rates. Furthermore, the algorithm enhances bandwidth utilization and promotes balanced network load distribution. This research offers a novel and effective solution for shipboard switch path selection, thereby advancing the reliability and efficiency of smart ship communication systems. Full article