Search Results (1,570)

The rapid development of Internet of Things technologies has accelerated the deployment of smart home systems. However, perception solutions based on visual sensors remain constrained by illumination sensitivity, occlusion, and privacy concerns. Frequency-modulated continuous-wave (FMCW) millimeter-wave radar provides a promising alternative because it operates independently of lighting conditions, is robust to environmental changes, and preserves user privacy. To address multiple-extended-target tracking in cluttered indoor environments, this paper proposes a high-accuracy tracking algorithm that combines an improved Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, an optimized Nearest-Neighbor Data Association (NNDA) scheme, and an Extended Kalman Filter (EKF). The improved DBSCAN algorithm introduces spatial-extent constraints, velocity-consistency checks, and candidate-cluster validation to cluster raw radar point clouds and convert extended targets into representative point targets with little additional computational cost. The optimized NNDA scheme then integrates clustering information into the association process, improving the matching accuracy between existing tracks and current measurements. Finally, the EKF estimates the state of each target from the associated measurements. Real-world experiments show that the proposed algorithm achieves tracking errors below 0.4 m in typical motion scenarios, maintains continuous tracking in two-person crossing scenarios, and reaches 93.3% counting accuracy in five-person scenarios. These results outperform the tracking system based on the commercial Texas Instruments (TI) IWR6843ISK millimeter-wave radar evaluation board. The proposed method offers a reliable and privacy-preserving sensing solution for smart homes, elderly care, and intelligent building applications. Full article

To address the critical challenge of excessive junction temperature caused by ultra-high heat flux densities (>100 W/cm²) in deep-sea LED Fish-Attracting Lamp (FAL) arrays, this study proposes a hybrid thermal management scheme integrating interfacial micro-texturing, chimney-effect convection, and heat pipe phase-change heat transfer, achieving the unification of passive high-efficiency heat dissipation and pressure-resistant sealing. The FAL housing structure is reconfigured using topology optimization to construct chimney-effect enhanced flow channels integrated with heat pipe bundle arrays, thereby establishing efficient heat conduction pathways from the Phenolic Resin Substrate (PRS) to the structural periphery. Micro-Element Texture (MET) arrays are fabricated at the PRS thermal interface to enhance interfacial thermal conductance. Based on multi-physics coupled numerical simulation, a parametric mapping model correlating geometric topology with thermal performance is established through response interface methodology, enabling the parametric optimization of micro-texture configurations. A thermal interface performance testing platform is constructed to validate the accuracy and reliability of the numerical model. Experimental results demonstrate that the integrated heat pipe technology effectively suppresses LED junction temperature rise; moreover, groove-type MET arrays oriented perpendicular to the gravity direction not only significantly increase the effective heat dissipation area but also optimize the dynamic characteristics of natural convection. This proposed solution reduces the maximum operating temperature of deep-sea FALs by 6.70% compared with conventional structures, providing an effective engineering solution for thermal structural design of high-power illumination systems. Full article

Background: Chronic exposure to artificial light at night (light pollution) causes circadian desynchronosis and melatonin deficiency, which is considered an independent driver of metabolic disorders and accelerated aging. However, the long-term effects of chronic desynchronosis on systemic metabolism and liver structure throughout the life cycle, as well as the potential of preventive melatonin administration, remain poorly understood. Objective: To evaluate the effects of chronic dark deprivation and prevention of metabolic disorders by exogenous melatonin on plasma melatonin levels, metabolic profile, liver function, and morphological changes in rats over a 24-month experiment. Methods: A 24-month experiment was conducted on 360 male Wistar rats divided into three groups: control (standard 10:14 h light/dark photoperiod), dark deprivation (DD, constant illumination), and correction (DD+Mel, constant illumination + melatonin 10 mg/kg five times per week). Animals were sacrificed at 6, 12, 18, and 24 months. Plasma melatonin was assessed by ELISA. Biochemical parameters (ALT, AST, LDH, total protein, albumin, bilirubin, glucose, triglycerides, and cholesterol), body weight, liver weight, relative liver weight, and histological parameters (steatosis, fibrosis, nuclear area, nuclear/cytoplasmic ratio, and binucleated hepatocytes) were analyzed. Results: In the DD group, a persistent progressive melatonin deficiency was detected (5.1-fold decrease by 6 months, p < 0.0005), accompanied by hypertriglyceridemia (Cohen’s d = 6.40), hypercholesterolemia (d = 4.59), biphasic dysglycemia (hypoglycemia followed by hyperglycemia), elevated ALT and AST activity (d = 2.60 and 2.46, respectively), hypoproteinemia (d = 5.33), hypoalbuminemia (d = 3.34), and hyperbilirubinemia (d = 3.22–4.37), as well as progressive steatosis (2.8 ± 0.3 points, d = 7.20) and pericellular fibrosis (1.8 ± 0.4 points, d = 4.50). In the DD group, a decrease in relative liver weight during the first 12 months was observed (metabolic disproportion, d = 2.31), reflecting disproportionate body weight gain. In the DD+Mel group, exogenous melatonin restored the biochemical parameters to values that did not differ statistically from the control values (Cohen’s d < 0.2 for most parameters), prevented steatosis (0.8 ± 0.3 points, d = 0.80) and fibrosis (0 points), increased relative liver weight by 24 months (3.83 ± 0.49 vs. 3.27 ± 0.029 in the control, d = 1.60), and increased the hepatocyte nuclear area (58.4 ± 4.1 vs. 48.6 ± 3.8 μm², d = 2.32). Conclusions: Chronic desynchronosis induced by constant illumination leads to persistent melatonin deficiency and complex metabolic and structural liver disturbances modeling accelerated aging. Exogenous melatonin (10 mg/kg five times per week) exhibits pronounced geroprotective, hepatoprotective, and antifibrotic effects, normalizing all biochemical parameters and preventing age-related liver involution. Full article

Accurate pest recognition is an important foundation for intelligent plant protection, precision pesticide application, and sustainable agricultural management. However, in real field environments, pest targets are often small in scale, severely occluded, and embedded in complex backgrounds, which limits the performance of existing supervised learning methods under low-annotation and cross-scenario conditions. To address these issues, a multimodal self-supervised pretraining framework is proposed for pest recognition, in which field pest images and environmental sensor data are integrated to construct pest representations with environmental awareness. In this framework, image features, including pest morphology, leaf texture, and damaged regions, are first extracted through a visual encoding branch, while temporal variation features of ecological factors, including temperature, humidity, illumination, soil moisture, rainfall, and wind speed, are modeled through an environmental encoding branch. On this basis, a cross-modal contrastive consistency module is designed to align visual and environmental representations, a temporal consistency self-supervised module is introduced to characterize the continuous evolutionary relationship between pest occurrence and environmental changes, and a multimodal collaborative representation fusion module is constructed to adaptively integrate information from different modalities. The experimental results show that the proposed method achieves favorable performance in the pest recognition task, with Accuracy, Precision, Recall, and F1-score reaching $94.37\%$, $93.96\%$, $93.42\%$, and $93.69\%$, respectively, outperforming ConvNeXtV2-T, ViT-B/16, Swin-T, SimCLR, MAE, and the conventional Image + Sensor fusion method. The ablation experiments further show that, after removing the cross-modal contrastive consistency module, the temporal consistency self-supervised module, and the multimodal collaborative fusion module, the F1-score decreases to $91.00\%$, $91.36\%$, and $90.49\%$, respectively, thereby demonstrating the contribution of each module. This study provides a viable multimodal self-supervised learning approach for AI-driven intelligent pest recognition, early warning, and precision control in agriculture. Full article

Autonomous driving, as a core component of intelligent transportation systems, relies highly on precise environmental perception capabilities. Vehicle target detection is the fundamental task of environmental perception. However, complex factors in real scenarios (such as target occlusion, illumination changes, and dense traffic flow) often lead to feature misjudgments, missed detections, target positioning deviations, and category confusions in existing methods. To address these challenges, this paper proposes the MLRP-YOLOv8n model that integrates Mixed Local Channel Attention (MLCA) and large kernel separable attention (LSKA). Three complementary attention mechanisms as well as improved regression loss are integrated into the lightweight YOLOv8n architecture to improve the accuracy of vehicle detection while maintaining computational efficiency. Firstly, MLCA is embedded in the C2f feature extraction module to enhance local feature focus; the SPPF module integrates LSKA optimize multi-scale feature fusion; RFCBAMConv convolution is used to replace the original convolution in the neck to enhance cross-level feature correlation; the PIoUv2 loss function is introduced instead of Complete Intersection over Union (CIoU) to accelerate model convergence and reduce regression errors. Experiments on the KITTI Detection dataset subset and UA-DETRAC datasets show that MLRP-YOLOv8n improves the mean average precision (mAP) by 1.9% and 3.2% respectively on the KITTI Detection dataset subset and UA-DETRAC datasets. This model achieves a balance between detection accuracy, tracking robustness, and computational efficiency, providing a reliable solution for autonomous driving environment perception. Full article

Visual fatigue is a serious issue among Chinese secondary school students owing to prolonged daily exposure (8–10 h) to visual display terminals (VDTs) in widely equipped multimedia classrooms. To mitigate such effects, this exploratory study identifies promising lighting parameters by evaluating the influence of blackboard reflection coefficients, the ratio of desktop illumination to blackboard illumination, and correlated color temperature (CCT) in a simulated multimedia classroom environment. Thirteen participants performed visual tasks (Landolt ring visual acuity tests and Anfimov’s Chart Task) under various conditions. Visual fatigue scale (VFS-10), index of mental capacity (IMC), and eye movement parameters (EMP) were used to assess visual fatigue and efficiency. Results suggest that higher blackboard reflection coefficients improved efficiency and reduced fatigue. Increased blackboard illumination alleviated fatigue at constant CCT, whereas changes in desktop illumination showed no significant effect. The highest efficiency among the tested CCT values was observed at 4700 K, while visual fatigue was minimized at 4000 K. The findings provide preliminary practical applications for minimizing visual fatigue and improving performance efficiency in secondary school multimedia classroom environments equipped with VDTs. Full article

This study presents the design and performance evaluation of a hybrid solar-driven system (SOLIVE) that integrates tubular daylighting and buoyancy-driven natural ventilation within a single architectural component for industrial and large-scale buildings. While solar tubes and solar chimneys have been widely studied as independent passive technologies, their combined use in a unified system capable of delivering both daylight and ventilation remains largely unexplored. The proposed system utilizes solar tubes not only for transmitting natural daylight but also as thermal drivers that induce airflow through the stack effect generated by solar heating along the tube surface. A mathematical framework combining photometric daylight modeling and buoyancy-driven airflow analysis was developed to evaluate the system performance. Numerical simulations were conducted for three representative solar reference days (Equinox, Summer Solstice, and Winter Solstice). The influence of the key design parameters, including illuminated surface area (5–15 m²), solar tube diameter (0.1–0.3 m), and ventilated space volume (20–60 m³), was systematically analyzed. The results show that, under the adopted modelling assumptions, the system provides peak illuminance between 376 and 502 lux and ventilation rates up to 20.5 air changes per hour (ACH). These values are discussed as indicative benchmarks with respect to ISO 8995-1 and ASHRAE 62.1, rather than as proof of full real-building compliance, since glare, illuminance uniformity, thermal comfort, occupancy, wind effects and HVAC integration were not fully modelled. These findings demonstrate the potential of the proposed system as an effective passive solution for improving indoor environmental quality and reducing building energy demand in sunny climates. Full article

Digital systems are ordinarily evaluated in terms of speed, throughput, efficiency, and optimization. Such evaluations are indispensable, but they remain philosophically incomplete because they treat latency as a merely technical property of systems rather than as a condition of mediated action. This article argues that latency should be understood as a phenomenological condition of technological mediation because the interval between human initiative and technical response influences how action is experienced, how continuity is sustained, and how agency is lived and distributed across human and technical components. The article argues that latency is a constitutive condition of mediated agency and that changes in temporal coupling reorganize how technology appears in experience. On this basis, it distinguishes delayed mediation, immediate mediation, and anticipatory mediation as three regimes through which the temporal structure of response alters the phenomenological status of action. When delay is perceptible, technology tends to appear as obstacle, procedure, or object of attention; when delay withdraws, mediation can recede into the continuity of action and be incorporated into embodied practice; when responsiveness gives way to prediction, mediation begins to pre-structure the field of action before initiative is fully articulated. The argument reinterprets Heidegger, Merleau-Ponty, postphenomenology, Stiegler, and Rosa through the lens of latency, while selected findings from human–computer interaction and agency research are used as a limited scientific dialogue concerning continuity, disruption, direct manipulation, presence, and the sense of agency. The article argues that existing literature has illuminated mediation, embodiment, interface responsiveness, acceleration, and anticipation, but has not systematically theorized latency itself as a temporal condition of agency. Anticipation is therefore treated not as a competing topic but as the limiting case at which latency analysis opens toward the use of the future in present action, as discussed by Rosen and Poli. The conclusion argues that the philosophical problem raised by digital speed is not simply acceleration as such, but the preservation of the human interval of hesitation, interpretation, judgment, and responsibility within increasingly responsive technical worlds. Full article

Plants perceive light signals through photoreceptors such as CRY1 to regulate growth and development. It is well-known that Arabidopsis CRY1 is a nucleocytoplasmic protein that mediates light inhibition of hypocotyl elongation in the nucleus, but the mechanisms by which CRY1 regulates root growth and functions in the cytoplasm remain poorly understood. Here, we identified eIF3G1, a subunit of the eukaryotic translation initiation factor 3 (eIF3) complex, as a CRY1-interacting protein associated with light-regulated root development. Under blue light, eif3g1 mutants showed longer primary roots, whereas eIF3G1 overexpression reduced root elongation, accompanied by corresponding changes in root apical meristem size. Differential irradiation experiments indicated that shoot illumination is required for eIF3G1-dependent root phenotypes. Transcriptome analysis revealed changes in translation-related and light-responsive genes in response to eIF3G1 perturbation. Comparison with the cry1 transcriptome revealed overlapping differentially expressed genes, including BIC1 and BIC2, and the bic1 bic2 double mutant showed reduced root elongation. Together, these findings identify eIF3G1 as a CRY1-interacting factor that contributes to the shoot-dependent regulation of root growth under blue light, suggesting that eIF3G1 may be associated with the CRY1-dependent shoot-to-root regulation of root growth. Full article

To address the decline in detection accuracy caused by the degradation of grayscale features under environmental interference, a lightweight detection model driven by grayscale characterization, YOLOv8n-CoalGangue, is proposed based on an in-depth analysis of the dynamic variations exhibited by grayscale features. First, grayscale histograms are used to quantitatively evaluate the effects of illumination changes and moisture conditions on feature distributions, revealing that global grayscale aliasing and local texture degradation are the key visual feature bottlenecks. Guided by these unique findings, targeted technological innovations are integrated into the developed architecture. HGNetV2-G, which incorporates the GhostNet principle, is used as the backbone to reduce the incurred computational cost while preserving the core feature extraction ability of the model. A mixed local channel attention (MLCA) mechanism is introduced in the neck to filter background noise and focus on local high-frequency features, which helps overcome global grayscale aliasing issues. In addition, a DGFPN-based feature fusion network is constructed by combining RepGFPN and DySample, together with lightweight shared convolution detection (LSCD), which compensates for the loss of multiscale grayscale details without increasing the imposed parameter burden. Furthermore, the PIoUv2 loss function improves the bounding-box regression process in dense overlapping scenarios. Experimental results show that the proposed model achieves an mAP@50 of 97.2% with a 32% reduction in the number of parameters required (only 2.1 M). It also demonstrates strong robustness under six extreme industrial conditions, such as low illumination and coal dust occlusion, confirming the effectiveness of the design driven by grayscale characterization for practical green mining applications. Full article

Intelligent perception systems are essential for precision agriculture, yet their deployment in agricultural field environments is significantly challenged by dense target occlusion and strict resource constraints on edge devices. To address this issue, this paper reviews lightweight object detection technologies from a problem-driven perspective, focusing on the interaction between occlusion-induced feature degradation and limited model capacity under real-world conditions. Unlike existing surveys that mainly summarize model evolution or application scenarios, this work presents a systematic review based on a unified analytical framework to examine how lightweight models compensate for feature loss caused by complex physical factors. Specifically, we analyze the mechanisms underlying feature degradation arising from morphological similarity, extreme scale variation, and dynamic environmental disturbances such as illumination changes and non-rigid deformation. Based on this analysis, recent advances in lightweight detection architectures are comparatively reviewed, including the YOLO series, real-time Transformers, and State Space Models, with an emphasis on their design trade-offs between computational efficiency and representation capability. In addition, key optimization strategies are discussed, such as multi-scale attention mechanisms and dynamic routing for adaptive computation allocation, as well as distribution-aware loss functions for improving localization robustness in densely occluded scenarios. The role of large vision models is also explored, highlighting their lightweight adaptation through knowledge distillation and parameter-efficient fine-tuning. Overall, by synthesizing empirical findings and comparative evidence from the recent literature, this review provides a structured understanding of collaborative optimization pathways and offers evidence-based strategic insights into achieving an effective balance between detection accuracy and computational efficiency for agricultural edge deployment. Full article

Global climate change and extreme precipitation events increasingly challenge urban infrastructure resilience, particularly in topographically vulnerable regions like Taiwan. Traditional flood monitoring relies heavily on the manual visual interpretation of extensive surveillance networks, a process that imposes high cognitive loads and risks delayed emergency responses. This study presents a comprehensive Cyber-Physical System (CPS) architecture for an automated Water Image Monitoring Platform. Integrating approximately 10,000 cameras and multi-modal data—including precipitation records and spatial alerts—the platform leverages advanced semantic segmentation (DeepLabV3+ with Xception71) to delineate inundation boundaries. To ensure robustness under adverse conditions such as low illumination, fog, and specular glare, we implemented targeted optimizations, including HSV pre-processing, Deblur GAN architectures, and attention mechanisms. Results demonstrate a significant performance evolution, with the event recall rate rising from 88% in 2022 to 99.7% by 2025. A key driver of this success is the synergy between stationary nodes and vehicle-mounted CCTV units, which provide critical dynamic geographic coverage. Furthermore, the deployment of edge computing reduced warning latency 10 times—from 19.2 to 2 s—while virtual water level gauges maintained a mean error within ±10 cm. Despite these gains, a Human-in-the-Loop (HITL) architecture remains strategically necessary for ethical accountability and error filtering. This CPS provides a foundational model for autonomous, resilient urban disaster management. Full article

Bi-temporal change detection (CD) in remote sensing (RS) aims to map image pairs at different times into a shared feature space to discriminate variant regions effectively. However, factors such as cloud interference may disrupt the feature distribution of RS images and cause pseudo-change problems. Existing public change detection datasets also pay less attention to such pseudo-change phenomena. To address the pseudo-change problems of CD applications, we propose a Domain Adversarial Anti-Interference Change Detection Network (DAAINet), which uses ResNet to extract multi-scale features from the original input images. Semantic features are then obtained and fed into a subsequent graph convolution module after soft clustering, by introducing a domain adversarial structure to align the feature space in RS images. In the graph convolution module, the association of node context is utilized to predict the adjacency relationship between objects. We collected data and constructed a real-world dataset called “Cloud Interference Change Detection” (CICD), which focuses on real bi-temporal remote sensing image data containing cloud interference and includes pseudo-changes caused by factors such as the presence of temporary objects and illumination changes. Experimental results demonstrate that our method is more robust and efficient compared to other state-of-the-art methods on two public CD datasets, and achieves state-of-the-art performance on the noise-corrupted CICD dataset, surpassing prior methods by up to 5.67%p in IoU and 1.42%p in recall. Full article

Artificial intelligence is transforming agriculture from a mechanized, labor-intensive sector into a data-driven, perception-enabled, and increasingly autonomous production system. In this review, AI serves as an umbrella term encompassing machine learning, computer vision, and robotic control, among other technologies. We synthesize recent advances across the tillage–sowing–management–harvesting (TSMH) workflow, covering intelligent tillage, precision sowing, field management, and robotic harvesting. The literature shows that AI has significantly improved agricultural perception, prediction, and task-level decision-making. However, large-scale adoption remains constrained by data heterogeneity, limited cross-scene generalization, environmental uncertainty, and insufficient integration across operational stages. Future progress will depend on multimodal data fusion, lightweight and interpretable models, cloud-edge collaboration, and full-chain decision architectures. By framing current research within the TSMH pipeline, this review highlights both technical advances and the critical bottlenecks that must be addressed to move smart agriculture from stage-specific intelligence toward system-level autonomy. Representative studies indicate that AI models can improve soil-property prediction and reduce sowing miss-detection rates to below 3% under controlled or bench-top conditions. However, field deployment may be affected by environmental variability, including illumination changes, dust, vibration, occlusion, and hardware constraints. These limitations highlight the need for robust and edge-compatible architectures. Full article

Real automotive inspection lines need robust defect detection under cluttered backgrounds, fluctuating illumination, and operator-introduced clutter, conditions under which fully supervised pipelines are rarely feasible because defective samples are scarce and heterogeneous. We address this gap with a deployment-oriented study of unsupervised anomaly detection (UAD) on AutoVI, a public automotive benchmark, and we go beyond running existing detectors in three ways. First, we establish unified RGB and pseudo-depth baselines for seven UAD models under a single calibration and evaluation policy that combines threshold-agnostic metrics (AUROC, AP), operational metrics (TPR at fixed TNR), and pixel-level sPRO/AUsPRO under a 5% false-positive budget. Second, we show that a plug-and-play late fusion of independently calibrated RGB detectors consistently recovers pixel-level localization that no single model achieves, with no extra training and no architectural change; effects are large (Cohen’s $d>2$ on every flagged improvement) and statistically significant across three seeds. Third, we report an actionable negative result: combining RGB with monocular pseudo-depth through the same fusion scheme degrades rather than improves localization, and we trace the failure to the relative nature of estimated depth interacting with a parameter-free aggregator. Ablations on the fusion operator, ensemble size, and calibration support these findings, and the released calibrated artifacts make the comparison reproducible on other MVTec-style benchmarks. Full article