Search Results (5,266)

Grain security is a fundamental guarantee for social stability and sustainable development. Accurate monitoring and prediction of overall granary temperature are essential for reducing storage losses and improving warehouse management efficiency. As an integrated system, the temperature evolution of the grain pile is deeply affected by its inherent physical structure and heat transfer pathways. Therefore, a multi-level warehouse–surface–line–point (WSLP) structural modeling approach driven by the physical properties of the grain pile is proposed to extract the joint environmental and spatial characteristics. Building upon the WSLP framework, a dual-channel time-series prediction architecture integrating both long short-term memory (LSTM) and iTransformer through a mutual verification fusion mechanism is developed to enable synchronized temperature forecasting across different regions of the grain piles. Experiments are conducted using real granary data from Shandong, China. The results demonstrate that the proposed model achieves more than 30% improvement over baseline methods in terms of MAE and RMSE. Moreover, the WSLP-LSTM–iTransformer framework significantly improves prediction accuracy in complex warehouse environments and enhances the interpretability and applicability of deep learning models for grain condition forecasting by incorporating real environmental characteristics. Full article

Deep learning models have advanced rapidly, leading to claims that they now match or exceed human performance. However, such claims are often based on closed-set conditions with fixed labels, extensive supervised training, and do not considering differences between the two systems. Recent findings also indicate that some models align more closely with human categorisation behaviour, whereas other studies argue that even highly accurate models diverge from human behaviour. Following principles from comparative psychology and imposing similar constraints on both systems, this study investigates whether these models can achieve human-level accuracy and human-like categorisation through three experiments using subsets of the ObjectNet dataset. Experiment 1 examined performance under varying presentation times and task complexities, showing that while recent models can match or exceed humans under conditions optimised for machines, they struggle to generalise to certain real-world categories without fine-tuning or task-specific zero-shot classification. Experiment 2 tested whether human performance remains stable when shifting from N-way categorisation to a free-naming task, while machine performance declines without fine-tuning; the results supported this prediction. Additional analyses separated detection from classification, showing that object isolation improved performance for both humans and machines. Experiment 3 investigated individual differences in human performance and whether models capture the qualitative ordinal relationships characterising human categorisation behaviour; only the multimodal CoCa model achieved this. These findings clarify the extent to which current models approximate human categorisation behaviour beyond mere accuracy and highlight the importance of incorporating principles from comparative psychology while considering individual differences. Full article

Monitoring wildlife has become increasingly important for understanding the evolution of species and ecosystem health. Acoustic monitoring offers several advantages over video-based approaches, enabling continuous 24/7 observation and robust detection under challenging environmental conditions. Deep learning models have demonstrated strong performance in audio classification. However, their computational complexity poses significant challenges for deployment on low-power embedded platforms. This paper presents a low-power embedded system for real-time bird audio detection. A hybrid CNN–RNN architecture is adopted, redesigned, and quantized to significantly reduce model complexity while preserving classification accuracy. To support efficient execution, a custom hardware accelerator was developed and integrated into a Zynq UltraScale+ ZU3CG FPGA. The proposed system achieves an accuracy of 87.4%, processes up to 5 audio samples per second, and operates at only 1.4 W, demonstrating its suitability for autonomous, energy-efficient wildlife monitoring applications. Full article

The deterioration of civil infrastructure poses a significant threat to public safety, yet conventional manual inspections remain subjective, labor-intensive, and constrained by accessibility. To address these challenges, this paper presents a real-time robotic inspection system that integrates deep learning perception and autonomous navigation. The proposed framework employs a two-stage neural network: a U-Net for initial segmentation followed by a Pix2Pix conditional generative adversarial network (GAN) that utilizes adversarial residual learning to refine boundary accuracy and suppress false positives. When deployed on an Unmanned Ground Vehicle (UGV) equipped with an RGB-D camera and LiDAR, this framework enables simultaneous automated crack detection and collision-free autonomous navigation. Evaluated on the CrackSeg9k dataset, the two-stage model achieved a mean Intersection over Union (mIoU) of 73.9 ± 0.6% and an F1-score of 76.4 ± 0.3%. Beyond benchmark testing, the robotic system was further validated through simulation, laboratory experiments, and real-world campus hallway tests, successfully detecting micro-cracks as narrow as 0.3 mm. Collectively, these results demonstrate the system’s potential for robust, autonomous, and field-deployable infrastructure inspection. Full article

Efficient route planning technology is the core support for ensuring the successful execution of unmanned aerial vehicle (UAV) flight missions. In this paper, the coordination issue of global route planning and local real-time obstacle avoidance in complex mountainous environments is studied. To deal with this issue, a hierarchical route planning framework is designed, including global route planning and AI-based local route re-planning using deep reinforcement learning, exhibiting both flexible versatility and practical coordination and deployment efficiency. Throughout the entire flight, the local route re-planning task triggered by dynamic threats can be executed in real time. Meanwhile, a multi-model DQN (MMDQN) agent with a Monte Carlo traversal iterative learning (MCTIL) strategy is designed for local route re-planning. Compared to existing methods, this agent can be directly used to generate local obstacle avoidance routes in various scenarios at any time during the flight, which simplifies the complicated structure and training process of conventional deep reinforcement learning (DRL) agents in dynamic, complex environments. Using the framework structure and MMDQN agent for local route re-planning ensures the safety and efficiency of the mission, as well as local obstacle avoidance during global flights. These performances are verified through simulations based on actual terrain data. Full article

The deployment of Advanced Driver-Assistance Systems (ADAS) in economically constrained markets frequently relies on hardware architectures that lack dedicated graphics processing units. Within such environments, the integration of deep neural networks faces significant hurdles, primarily stemming from strict limitations on energy consumption, the absolute necessity for deterministic real-time response, and the rigorous demands of safety certification protocols. Meanwhile, traditional geometry-based lane detection pipelines continue to exhibit limited robustness under adverse illumination conditions, including intense backlighting, low-contrast nighttime scenes, and heavy rainfall. Motivated by these constraints, this work re-examines geometry-based lane perception from a sensor-level viewpoint and introduces a Binary Line Segment Filter (BLSF) that leverages the inherent structural regularity of lane markings in bird’s-eye-view (BEV) imagery within a computationally lightweight framework. The proposed BLSF is integrated into a complete pipeline consisting of inverse perspective mapping, median local thresholding, line-segment detection, and a simplified Hough-style sliding-window fitting scheme combined with RANSAC. Experiments on a self-collected dataset of 297 challenging frames show that the inclusion of BLSF significantly improves robustness over an ablated baseline while sustaining real-time performance on a 2 GHz ARM CPU-only platform. Additional evaluations on the Dazzling Light and Night subsets of the CULane and LLAMAS benchmarks further confirm consistent gains of approximately 6–7% in F₁-score, together with corresponding improvements in IoU. These results demonstrate that interpretable, geometry-driven lane feature extraction remains a practical and complementary alternative to lightweight learning-based approaches for cost- and safety-critical ADAS applications. Full article

Artificial intelligence (AI) is rapidly reshaping thoracic surgery, advancing from decision support to the threshold of autonomous intervention. AI-driven technologies—including machine learning (ML), deep learning (DL), and computer vision—have demonstrated significant improvements in diagnostic accuracy, surgical planning, intraoperative navigation, and postoperative outcome prediction. In lung cancer and thoracic oncology, AI enhances imaging analysis, histopathological classification, and risk stratification, supporting multidisciplinary decision-making and personalized therapy. Robotic-assisted and AI-guided systems are optimizing surgical precision and workflow efficiency, while real-time decision-support tools and augmented reality are improving intraoperative safety. Despite these advances, widespread adoption is limited by challenges in algorithmic bias, data integration, regulatory approval, and ethical transparency. The literature emphasizes the need for multicenter validation, explainable AI, and robust governance frameworks to ensure safe and effective clinical integration. Future research should focus on digital twin technology, federated learning, and transparent AI outputs to further enhance reliability and accessibility. AI is poised to transform thoracic surgery, but responsible implementation and ongoing evaluation are essential for realizing its full potential. The aim of this review is to evaluate and synthesize the current landscape of artificial intelligence (AI) applications across the thoracic surgical pathway, from preoperative decision-support to intraoperative guidance and emerging autonomous interventions. Full article

Global Navigation Satellite Systems (GNSS) have become essential tools in geomatics engineering for precise positioning, cadastral surveys, topographic mapping, and deformation monitoring. Recent advances integrate GNSS with emerging technologies such as artificial intelligence (AI), machine learning (ML), cloud computing, and unmanned aerial systems (UAS), which have greatly improved accuracy, efficiency, and analytical capabilities in managing geospatial big data. In this study, we propose a hybrid Convolutional Neural Network–Long Short Term Memory (CNN-LSTM) architecture for seismic detection using high-rate (5 Hz) GNSS velocity time series. The model is trained on a large synthetic dataset generated by and real high-rate GNSS non-event data. Model performance was evaluated using real event and non-event data through an event-based approach. The results demonstrate that a hybrid deep-learning architecture can provide a reliable framework for seismic detection with high-rate GNSS velocity time series. Full article

Pest detection in the field is crucial for realizing smart agriculture. Deep learning-based target detection algorithms have become an important pest identification method due to their high detection accuracy, but the existing methods still suffer from misdetection and omission when detecting small-targeted pests and small-targeted pests in more complex backgrounds. For this reason, this study improves on YOLO11 and proposes a new model called MSDS-YOLO for enhanced detection of small-target pests. First, a new dynamic multi-scale feature extraction module (C3k2_DMSFE) is introduced, which can be adaptively adjusted according to different input features and thus effectively capture multi-scale and diverse feature information. Next, a novel Dimensional Selective Feature Pyramid Network (DSFPN) is proposed, which employs adaptive feature selection and multi-dimensional fusion mechanisms to enhance small-target saliency. Finally, the ability to fit small targets was enhanced by adding 160 × 160 detection heads removing 20 × 20 detection heads and using Normalized Gaussian Wasserstein Distance (NWD) combined with CIoU as a position loss function to measure the prediction error. In addition, a real small-target pest dataset, Cottonpest2, is constructed for validating the proposed model. The experimental results showed that a mAP50 of 86.7% was achieved on the self-constructed dataset Cottonpest2, which was improved by 3.0% compared to the baseline. At the same time, MSDS-YOLO has achieved better detection accuracy than other YOLO models on public datasets. Model evaluation on these three datasets shows that the MSDS-YOLO model has excellent robustness and model generalization ability. Full article

Thermal comfort and energy efficiency are two main goals of heating, ventilation, and air conditioning (HVAC) systems, which use about 40% of the total energy in buildings. This paper aims to predict optimal room temperature, enhance comfort, and reduce energy consumption while avoiding extra energy use from overheating or overcooling. Six Machine Learning (ML) models were tested to predict the optimal temperature in the classroom based on the occupancy characteristic detected by a Deep Learning (DL) model, You Only Look Once (YOLO). The decision tree achieved the highest accuracy at 97.36%, demonstrating its effectiveness in predicting the preferred temperature. To measure energy savings, the study used RETScreen software version 9.4 to compare intelligent temperature control with traditional operation of HVAC. Genetic algorithm (GA) was further employed to optimize HVAC energy consumption while keeping the thermal comfort level by adjusting set-points based on real-time occupancy. The GA showed how to balance comfort and efficiency, leading to better system performance. The results show that adjusting from default HVAC settings to preferred thermal comfort levels as well controlling the HVAC to work only if the room is occupied can reduce energy consumption and costs by approximately 76%, highlighting the substantial impact of even simple operational adjustments. Further improvements achieved through GA-optimized temperature settings provide additional savings of around 7% relative to preferred comfort levels, demonstrating the value of computational optimization techniques in fine-tuning building performance. These results show that intelligent, data-driven HVAC control can improve comfort, save energy, lower costs, and support sustainability in buildings. Full article

Amid the increasing demand to reduce carbon emissions, replacing diesel buses with electric buses has become a key development direction in public transportation. However, a significant challenge in this transition lies in developing efficient charging strategies and accurately determining the required fleet size, as existing research often fails to adequately account for the impact of real-time traffic congestion on energy consumption. To address this gap, in this study, an optimized charging strategy is proposed, and the necessary fleet size is calculated using a deep reinforcement learning (DRL) approach, which integrates actual route characteristics and dynamic traffic congestion patterns into an electric bus operation model. Modeling is conducted based on Beijing Bus Route 400 to ensure the practical applicability of the proposed method. The results demonstrate that the proposed DRL method ensures operational completion while minimizing charging time, with the algorithm showing rapid and stable convergence. In the multi-route scenarios investigated in this study, the DRL-based charging strategy requires 40% more electric buses, with this figure decreasing to 24% when fast-charging technology is adopted. This study provides bus companies with valuable electric bus procurement and route operation references. Full article

Short-term traffic prediction is vital for intelligent transportation systems, enabling adaptive congestion control, real-time signal management, and dynamic route planning for autonomous vehicles (AVs). This study introduces a custom Transformer-based deep learning framework for joint forecasting of traffic flow and vehicle speed, leveraging handcrafted positional encoding and stacked multi-head attention layers to model multivariate traffic patterns. Evaluated against baselines including Long Short-Term Memory (LSTM), Support Vector Machine (SVM), Random Tree, and Random Forest on the Next-Generation Simulation (NGSIM) dataset, the model achieves 94.2% accuracy (Root Mean Squared Error (RMSE) 0.16) for flow and 92.1% accuracy for speed, outperforming traditional and deep learning approaches. A hybrid evaluation metric, integrating RMSE and threshold-based accuracy tailored to AV operational needs, enhances its practical relevance. With its parallel processing capability, this framework offers a scalable, real-time solution, advancing AV ecosystems and smart mobility infrastructure. Full article

Cassava remains a critical food-security crop across Africa and Southeast Asia but is highly vulnerable to diseases such as cassava mosaic disease (CMD) and cassava brown streak disease (CBSD). Traditional diagnostic approaches are slow, labor-intensive, and inconsistent under field conditions. This review synthesizes current advances in combining unmanned aerial vehicles (UAVs) with deep learning (DL) to enable scalable, data-driven cassava disease detection. It examines UAV platforms, sensor technologies, flight protocols, image preprocessing pipelines, DL architectures, and existing datasets, and it evaluates how these components interact within UAV–DL disease-monitoring frameworks. The review also compares model performance across convolutional neural network-based and Transformer-based architectures, highlighting metrics such as accuracy, recall, F1-score, inference speed, and deployment feasibility. Persistent challenges—such as limited UAV-acquired datasets, annotation inconsistencies, geographic model bias, and inadequate real-time deployment—are identified and discussed. Finally, the paper proposes a structured research agenda including lightweight edge-deployable models, UAV-ready benchmarking protocols, and multimodal data fusion. This review provides a consolidated reference for researchers and practitioners seeking to develop practical and scalable cassava-disease detection systems. Full article

Early detection of small-scale fires is crucial for minimizing damage and enabling rapid emergency response. While recent deep learning-based fire detection systems have achieved high accuracy, they still face three key challenges: (1) limited deployability in resource-constrained edge environments due to high computational costs, (2) performance degradation caused by feature interference when jointly learning flame and smoke features in a single backbone, and (3) low sensitivity to small flames and thin smoke in the initial stages. To address these issues, we propose a lightweight dual-stream fire detection architecture based on YOLOv5n, which learns flame and smoke features separately to improve both accuracy and efficiency under strict edge constraints. The proposed method integrates two specialized attention modules: ESCFM++, which enhances spatial and channel discrimination for sharp boundaries and local flame structures (flame), and ESCFM-RS, which captures low-contrast, diffuse smoke patterns through depthwise convolutions and residual scaling (smoke). On the D-Fire dataset, the flame detector achieved 74.5% mAP@50 with only 1.89 M parameters, while the smoke detector achieved 89.2% mAP@50. When deployed on an NVIDIA Jetson Xavier NX(NVIDIA Corporation, Santa Clara, CA, USA)., the system achieved 59.7 FPS (single-stream) and 28.3 FPS (dual-tream) with GPU utilization below 90% and power consumption under 17 W. Under identical on-device conditions, it outperforms YOLOv9t and YOLOv12n by 36–62% in FPS and 0.7–2.0% in detection accuracy. We further validate deployment via outdoor day/night long-range live-stream tests on Jetson using our flame detector , showing reliable capture of small, distant flames that appear as tiny cues on the screen, particularly in challenging daytime scenes. These results demonstrate overall that modality-specific stream specialization and ESCFM attention reduce feature interference while improving detection accuracy and computational efficiency for real-time edge-device fire monitoring. Full article

To address the dual demands of accuracy and real-time performance in power quality disturbance (PQD) recognition for new power system, this paper proposes a lightweight model named the Cross-Channel Attention Three-Layer Convolutional Model (1D-CCANet-3), specifically designed for edge deployment. Based on the one-dimensional convolutional neural network (1D-CNN), the model features an ultra-compact architecture with only three convolutional layers and one fully connected layer. By incorporating a set of cross-channel attention (CCA) mechanisms in the final convolutional layer, the model further enhances disturbance recognition accuracy. Compared to other deep learning models, 1D-CCANet-3 significantly reduces computational and storage requirements for edge devices while achieving accurate and efficient PQD recognition. The model demonstrates robust performance in recognizing 10 types of PQD under varying signal-to-noise ratio (SNR) conditions. Furthermore, the model has been successfully deployed on the FPGA platform and exhibits high recognition accuracy and efficiency in real-world data validation. This work provides a feasible and effective solution for accurate and real-time PQD monitoring on edge devices in new power systems. Full article