Search

Existing 3D object detection frameworks in sensor-based applications heavily rely on large-scale annotated data to achieve optimal performance. However, obtaining such annotations from sensor data-like LiDAR or image sensors-is both time-consuming and costly. Semi-supervised learning offers an efficient solution to this challenge and holds significant potential for sensor-driven artificial intelligence (AI) applications. While it reduces the need for labeled data, semi-supervised learning still depends on a small amount of labeled samples for training. In the initial stages, relying on such limited samples can adversely affect the effective training of student-teacher networks. In this paper, we propose PE-MCAT, a semi-supervised 3D object detection method that generates high-precision pseudo-labels. First, to address the challenges of insufficient local feature capture and poor robustness in point cloud data, we introduce a point enrichment module. This module incorporates information from image sensors and combines multiple feature fusion methods of local and self-features to directly enhance the quality of point clouds and pseudo-labels, compensating for the limitations posed by using only a few labeled samples. Second, we explore the relationship between the teacher network and the pseudo-labels it generates. We propose a multi-class adaptive threshold strategy to initially filter and create a high-quality pseudo-label set. Furthermore, a joint variable threshold strategy is introduced to refine this set further, enhancing the selection of superior pseudo-labels.Extensive experiments demonstrate that PE-MCAT consistently outperforms recent state-of-the-art methods across different datasets. Specifically, on the KITTI dataset and using only 2% of labeled samples, our method improved the mean Average Precision (mAP) by 0.7% for cars, 3.7% for pedestrians, and 3.0% for cyclists.

Non-rigid point cloud registration holds significant importance for human body pose analysis in the fields of sports, medicine, gaming, etc. In this paper, we propose a non-rigid point cloud registration algorithm based on geodesic distance measurement, which can improve the accuracy of the registration for matching point pairs during non-rigid deformations. Firstly, a graph is constructed for two sets of point clouds using geodesic distance measurement considering that geodesic distance changes minimally during non-rigid deformation of the human body, which can preserve the point cloud matching information between corresponding points. Furthermore, a maximal clique search is employed to find combinations of matching pairs between point clouds. Finally, by driving the human body model parameters, sparse matching pairs are overlapped as much as possible to achieve non-rigid point cloud registration of the human body. The accuracy of the proposed algorithm is verified with FAUST and CAPE datasets.

For the current wearable devices in the application of cross-diversified user groups, it is common to face the technical difficulties of static sign language recognition accuracy attenuation, weak anti-noise ability, and insufficient system robustness due to the differences in the use of users. This paper proposes a novel static sign language recognition method enhanced by a self-attention mechanism. The key features of sign language gesture classification are highlighted by the weight function, and then the self-attention mechanism is combined to pay more attention to the key features, and the convolutional neural network is used to extract the features and classify them, which realizes the accurate recognition of different types of static sign language under standard gestures and non-standard gestures. Experimental results reveal that the proposed method achieves an average accuracy of 99.52% in the standard static sign language recognition task when tested against the standard 36 static gestures selected within the reference American Sign Language dataset. By imposing random angular bias conditions of ±(0°-9°] and ±(9°-18°], the average recognition rates in this range were 98.63% and 86.33%. These findings indicate that, compared to existing methods, the proposed method not only maintains a high recognition rate for standard static gestures but also exhibits superior noise resistance and robustness, rendering it suitable for static sign language recognition among diverse user populations.

This paper presents a new type of phase-shifted Fiber Bragg Grating (FBG): the sliced-FBG (SFBG). The fabrication process involves cutting a standard FBG inside its grating region. As a result, the last grating pitch is shorter than the others. The optical output signal consists of the overlap between the FBG reflection and the reflection at the fiber-cleaved tip. This new fiber optic device has been studied as a vibration sensor, allowing for the characterization of this sensor in the frequency range of 150 Hz to 70 kHz. How the phase shift in the FBG can be controlled by changing the length of the last pitch is also shown. This device can be used as a filter and a sensing element. As a sensing element, we will demonstrate its application as a vibration sensor that can be utilized in various applications, particularly in monitoring mechanical structures.

Defects in photovoltaic (PV) panels can significantly reduce the power generation efficiency of the system and may cause localized overheating due to uneven current distribution. Therefore, adopting precise pixel-level defect detection, i.e., defect segmentation, technology is essential to ensuring stable operation. However, for effective defect segmentation, the feature extractor must adaptively determine the appropriate scale or receptive field for accurate defect localization, while the decoder must seamlessly fuse coarse-level semantics with fine-grained features to enhance high-level representations. In this paper, we propose a Progressive Deformable Transformer (PDeT) for defect segmentation in PV cells. This approach effectively learns spatial sampling offsets and refines features progressively through coarse-level semantic attention. Specifically, the network adaptively captures spatial offset positions and computes self-attention, expanding the model's receptive field and enabling feature extraction across objects of various shapes. Furthermore, we introduce a semantic aggregation module to refine semantic information, converting the fused feature map into a scale space and balancing contextual information. Extensive experiments demonstrate the effectiveness of our method, achieving an mIoU of 88.41% on our solar cell dataset, outperforming other methods. Additionally, to validate the PDeT's applicability across different domains, we trained and tested it on the MVTec-AD dataset. The experimental results demonstrate that the PDeT exhibits excellent recognition performance in various other scenarios as well.

Upper and lower limb rehabilitation training is essential for restoring patients' physical movement ability and enhancing muscle strength and coordination. However, traditional rehabilitation training methods have limitations, such as high costs, low patient participation, and lack of real-time feedback. The purpose of this study is to design and implement a rehabilitation training evaluation system based on virtual reality to improve the quality of patients' rehabilitation training. This paper proposes an upper and lower limb rehabilitation training evaluation system based on virtual reality technology, aiming to solve the problems existing in traditional rehabilitation training. The system provides patients with an immersive and interactive rehabilitation training environment through virtual reality technology, aiming to improve patients' participation and rehabilitation effects. This study used Kinect 2.0 and Leap Motion sensors to capture patients' motion data and transmit them to virtual training scenes. The system designed multiple virtual scenes specifically for different upper and lower limbs, with a focus on hand function training. Through these scenes, patients can perform various movement training, and the system will provide real-time feedback based on the accuracy of the patient's movements. The experimental results show that patients using the system show higher participation and better rehabilitation training effects. Compared with patients receiving traditional rehabilitation training, patients using the virtual reality system have significantly improved movement accuracy and training participation. The virtual reality rehabilitation training evaluation system developed in this study improves the quality of patients' rehabilitation and provides personalized treatment information to medical personnel through data collection and analysis, promoting the systematization and personalization of rehabilitation training. This system is innovative and has broad application potential in the field of rehabilitation medicine.

Identifying rice cultivation areas in a timely and accurate manner holds great significance in comprehending the overall distribution pattern of rice and formulating agricultural policies. The remote sensing observation technique provides a convenient means to monitor the distribution of rice cultivation areas on a large scale. Single-source or single-temporal remote sensing images are often used in many studies, which makes the information of rice in different types of images and different growth stages hard to be utilized, leading to unsatisfactory identification results. This paper presents a rice cultivation area identification method based on a deep learning model using multi-source and multi-temporal remote sensing images. Specifically, a U-Net based model is employed to identify the rice planting areas using both the Landsat-8 optical dataset and Sentinel-1 Polarimetric Synthetic Aperture Radar (PolSAR) dataset; to take full into account of the spectral reflectance traits and polarimetric scattering traits of rice in different periods, multiple image features from multi-temporal Landsat-8 and Sentinel-1 images are fed into the network to train the model. The experimental results on China's Sanjiang Plain demonstrate the high classification precisions of the proposed Multi-Source and Multi-Temporal Rice Identification U-Net (MSMTRIU-NET) and that inputting more information from multi-source and multi-temporal images into the network can indeed improve the classification performance; further, the classification map exhibits greater continuity, and the demarcations between rice cultivation regions and surrounding environments reflect reality more accurately., Competing Interests: The authors declare no conflicts of interest.

The hyperspectral image (HSI) classification task is widely used in remote sensing image analysis. The HSI classification methods based on convolutional neural networks (CNNs) have greatly improved the classification performance. However, they cannot well utilize the sequential properties of spectral features and face the challenge of increasing computational cost with the increase in network depth. To address these shortcomings, this paper proposes a novel network with a CNN-Mamba architecture, called DBMamba, which uses a bidirectional Mamba to process spectral feature sequences at a linear computational cost. In the DBMamba, principal component analysis (PCA) is first used to extract the main features of the data. Then, a dual-branch CNN structure, with the fused features from spectral-spatial features by 3D-CNN and spatial features by 2D-CNN, is used to extract shallow spectral-spatial features. Finally, a bidirectional Mamba is used to effectively capture global contextual information in features and significantly enhance the extraction of spectral features. Experimental results on the Indian Pines, Salinas, and Pavia University datasets demonstrate that the classification performance surpasses that of many cutting-edge methods, improving by 1.04%, 0.15%, and 0.09%, respectively, over the competing SSFTT method. The research in this paper enhances the existing knowledge on HSI classification and provides valuable insights for future research in this field.

In order to solve the problem that existing visible and infrared image fusion methods rely only on the original local or global information representation, which has the problem of edge blurring and non-protrusion of salient targets, this paper proposes a layered fusion method based on channel attention mechanism and improved Generative Adversarial Network (HFCA_GAN). Firstly, the infrared image and visible image are decomposed into a base layer and fine layer, respectively, by a guiding filter. Secondly, the visible light base layer is fused with the infrared image base layer by histogram mapping enhancement to improve the contour effect. Thirdly, the improved GAN algorithm is used to fuse the infrared and visible image refinement layer, and the depth transferable module and guided fusion network are added to enrich the detailed information of the fused image. Finally, the multilayer convolutional fusion network with channel attention mechanism is used to correlate the local information of the layered fusion image, and the final fusion image containing contour gradient information and useful details is obtained. TNO and RoadSence datasets are selected for training and testing. The results show that the proposed algorithm retains the global structure features of multilayer images and has obvious advantages in fusion performance, model generalization and computational efficiency.

Small object detection, which is frequently applied in defect detection, medical imaging, and security surveillance, often suffers from low accuracy due to limited feature information and blurred details. This paper proposes a small object detection method named YOLO-DHGC, which employs a two-stream structure with dense connections. Firstly, a novel backbone network, DenseHRNet, is introduced. It innovatively combines a dense connection mechanism with high-resolution feature map branches, effectively enhancing feature reuse and cross-layer fusion, thereby obtaining high-level semantic information from the image. Secondly, a two-stream structure based on an edge-gated branch is designed. It uses higher-level information from the regular detection stream to eliminate irrelevant interference remaining in the early processing stages of the edge-gated stream, allowing it to focus on processing information related to shape boundaries and accurately capture the morphological features of small objects. To assess the effectiveness of the proposed YOLO-DHGC method, we conducted experiments on several public datasets and a self-constructed dataset. Exceptionally, a defect detection accuracy of 96.3% was achieved on the Market-PCB public dataset, demonstrating the effectiveness of our method in detecting small object defects for industrial applications.

The stable flight of drones relies on Global Navigation Satellite Systems (GNSS). However, in complex environments, GNSS signals are prone to interference, leading to flight instability. Inspired by cross-view machine learning, this paper introduces the VDUAV dataset and designs the VRLM network architecture, opening new avenues for cross-view geolocation. First, to address the limitations of traditional datasets with limited scenarios, we propose the VDUAV dataset. By leveraging the virtual-real mapping of latitude and longitude coordinates, we establish a digital twin platform that incorporates 3D models of real-world environments. This platform facilitates the creation of the VDUAV dataset for cross-view drone localization, significantly reducing the cost of dataset production. Second, we introduce a new baseline model for cross-view matching, the Virtual Reality Localization Method (VRLM). The model uses FocalNet as its backbone and extracts multi-scale features from both drone and satellite images through two separate branches. These features are then fused using a Similarity Computation and Feature Fusion (SCFF) module. By applying a weighted fusion of multi-scale features, the model preserves critical distinguishing features in the images, leading to substantial improvements in both processing speed and localization accuracy. Experimental results demonstrate that the VRLM model outperforms FPI on the VDUAV dataset, achieving an accuracy increase to 83.35% on the MA@20 metric and a precision of 74.13% on the RDS metric.

The IEEE 802.11bf-based wireless fidelity (WiFi) indoor positioning system has gained significant attention recently. It is important to recognize that multi-user online positioning occurs in real wireless environments. This paper proposes an indoor positioning sensing strategy that includes an optimized preprocessing process and a new machine learning (ML) method called NKCK. The NKCK method can be broken down into three components: neighborhood component analysis (NCA) for dimensionality reduction, K-means clustering, and K-nearest neighbor (KNN) classification with cross-validation (CV). The KNN algorithm is particularly suitable for our dataset since it effectively classifies data based on proximity, relying on the spatial relationships between points. Experimental results indicate that the NKCK method outperforms traditional methods, achieving reductions in error rates of 82.4% compared to naive Bayes (NB), 85.0% compared to random forest (RF), 72.1% compared to support vector machine (SVM), 64.7% compared to multilayer perceptron (MLP), 50.0% compared to density-based spatial clustering of applications with noise (DBSCAN)-based methods, 42.0% compared to linear discriminant analysis (LDA)-based channel state information (CSI) amplitude fingerprinting, and 33.0% compared to principal component analysis (PCA)-based approaches. Due to the sensitivity of CSI, our multi-user online positioning system faces challenges in detecting dynamic human activities, such as human tracking, which requires further investigation in the future.

There have recently been rapid developments in smart healthcare systems, such as precision diagnosis, smart diet management, and drug discovery. These systems require the integration of the Internet of Things (IoT) for data acquisition, Digital Twins (DT) for data representation into a digital replica and Artificial Intelligence (AI) for decision-making. DT is a digital copy or replica of physical entities (e.g., patients), one of the emerging technologies that enable the advancement of smart healthcare systems. AI and Machine Learning (ML) offer great benefits to DT-based smart healthcare systems. They also pose certain risks, including security risks, and bring up issues of fairness, trustworthiness, explainability, and interpretability. One of the challenges that still make the full adaptation of AI/ML in healthcare questionable is the explainability of AI (XAI) and interpretability of ML (IML). Although the study of the explainability and interpretability of AI/ML is now a trend, there is a lack of research on the security of XAI-enabled DT for smart healthcare systems. Existing studies limit their focus to either the security of XAI or DT. This paper provides a brief overview of the research on the security of XAI-enabled DT for smart healthcare systems. It also explores potential adversarial attacks against XAI-enabled DT for smart healthcare systems. Additionally, it proposes a framework for designing XAI-enabled DT for smart healthcare systems that are secure and trusted.

The Yellow River, China's second-largest river, is renowned for its high sediment content. In response to the potential impacts of climate change on Yellow River water resources and water environmental management, an advanced monitoring and forecasting system for water and sediment throughout the entire Yellow River basin-from its source to the sea-is urgently needed. In this paper, based on the current status of water and sediment monitoring technologies, we proposed an integrated remote sensing monitoring network that combines satellite remote sensing, drone remote sensing, and ground-based wireless automatic monitoring networks, aiming to achieve the digital monitoring of water and sediment across the entire Yellow River basin, from its upper reaches to its estuary in the Bohai Sea. By utilizing ground-based in situ hyperspectral stations for sediment source areas in the upper reaches, such as the Qingshui River basin in Ningxia, and satellite remote sensing for midstream processes in the Xiaolangdi reservoir before the flood season in 2023, as well as downstream monitoring at the Yellow River estuary, this paper demonstrates the novelty and efficiency of the space-air-ground integrated remote sensing monitoring technology.

Security grids consisting of High-Definition (HD) Internet of Things (IoT) cameras are gaining popularity for organizational perimeter surveillance and security monitoring. Transmitting HD video data to cloud infrastructure requires high bandwidth and more storage space than text, audio, and image data. It becomes more challenging for large-scale organizations with massive security grids to minimize cloud network bandwidth and storage costs. This paper presents an application of Machine Vision at the IoT Edge (Mez) technology in association with a novel Grid Sensing (GRS) algorithm to optimize cloud Infrastructure as a Service (IaaS) resource allocation, leading to cost minimization. Experimental results demonstrated a 31.29% reduction in bandwidth and a 22.43% reduction in storage requirements. The Mez technology offers a network latency feedback module with knobs for transforming video frames to adjust to the latency sensitivity. The association of the GRS algorithm introduces its compatibility in the IoT camera-driven security grid by automatically ranking the existing bandwidth requirements by different IoT nodes. As a result, the proposed system minimizes the entire grid's throughput, contributing to significant cloud resource optimization.

With the continuous growth of urbanization, passenger flow in urban rail transit systems is steadily increasing, making accurate long-term forecasting essential for optimizing operational scheduling and enhancing service quality. However, passenger flow forecasting becomes increasingly complex due to the intricate structure of rail transit networks and external factors such as seasonal variations. To address these challenges, this paper introduces an optimized Informer model for long-term forecasting that incorporates the influences of other stations based on complex network theory. Compared to the ARIMA, LSTM, and Transformer models, this optimized Informer model excels in processing large-scale complex transit data, particularly in terms of long-term forecasting accuracy and capturing network dependencies. The results demonstrate that this forecasting approach, which integrates complex network theory with the Informer model, significantly improves the accuracy and efficiency of long-term passenger flow predictions, providing robust decision support for urban rail transit planning and management.

With the recent development of smart farms, researchers are very interested in such fields. In particular, the field of disease diagnosis is the most important factor. Disease diagnosis belongs to the field of anomaly detection and aims to distinguish whether plants or fruits are normal or abnormal. The problem can be solved by binary or multi-classification based on a Convolutional Neural Network (CNN), but it can also be solved by image reconstruction. However, due to the limitation of the performance of image generation, SOTA's methods propose a score calculation method using a latent vector error. In this paper, we propose a network that focuses on chili peppers and proceeds with background removal through GrabCut. It shows a high performance through an image-based score calculation method. Due to the difficulty of reconstructing the input image, the difference between the input and output images is large. However, the serial autoencoder proposed in this paper uses the difference between the two fake images, instead of the actual input, as a score. We propose a method of generating meaningful images using the GAN structure and classifying three results simultaneously by one discriminator. The proposed method showed a higher performance than previous research, and image-based scores showed the best performance.

In the field of medical imaging, microwave tomography (MWT) is based on the scattering and absorption characteristics of different tissues to microwaves and can reconstruct the electromagnetic property distribution of biological tissues non-invasively and without ionizing radiation. However, due to the inherently nonlinear and ill-posed characteristics of MWT calculations, actual imaging is prone to overfitting or artifacts. To address this, this paper proposes a two-step iterative imaging approach for rapid medical microwave tomography. This method establishes corresponding objective functions for microwave imaging across multiple frequencies and conducts iterative calculations on images at varying resolutions. This effectively enhances image clarity and accuracy while alleviating the issue of prolonged computational time associated with imaging complex structures at high resolution due to insufficient prior information during iterative processes. In the electromagnetic simulation section, we simulated a three-layer brain model and conducted imaging experiments. The results demonstrate that the algorithm significantly enhances imaging resolution, accurately pinpointing cerebral hemorrhages at different locations using an eight-antenna array and successfully reconstructs tomography images with a hemorrhage area radius of 1 cm. Lastly, experiments were conducted using a medical microwave tomography platform and four simplified human brain models, achieving millimeter-level accuracy in MWT.

This paper presents a comprehensive framework for mission planning and execution with a heterogeneous multi-robot system, specifically designed to coordinate unmanned ground vehicles (UGVs) and unmanned aerial vehicles (UAVs) in dynamic and unstructured environments. The proposed architecture evaluates the mission requirements, allocates tasks, and optimizes resource usage based on the capabilities of the available robots. It then executes the mission utilizing a decentralized control strategy that enables the robots to adapt to environmental changes and maintain formation stability in both 2D and 3D spaces. The framework's architecture supports loose coupling between its components, enhancing system scalability and maintainability. Key features include a robust task allocation algorithm, and a dynamic formation control mechanism, using a ROS 2 communication protocol that ensures reliable information exchange among robots. The effectiveness of this framework is demonstrated through a case study involving coordinated exploration and data collection tasks, showcasing its ability to manage missions while optimizing robot collaboration. This work advances the field of heterogeneous robotic systems by providing a scalable and adaptable solution for multi-robot coordination in challenging environments.

In the era of the Internet of Things (IoT), the demand for accurate positioning services has become increasingly critical, as location-based services (LBSs) depend on users' location data to deliver contextual functionalities. While the Global Positioning System (GPS) is widely regarded as the standard for outdoor localization due to its reliability and comprehensive coverage, its effectiveness in indoor positioning systems (IPSs) is limited by the inherent complexity of indoor environments. This paper examines the various measurement techniques and technological solutions that address the unique challenges posed by indoor environments. We specifically focus on three key aspects: (i) a comparative analysis of the different wireless technologies proposed for IPSs based on various methodologies, (ii) the challenges of IPSs, and (iii) forward-looking strategies for future research. In particular, we provide an in-depth evaluation of current IPSs, assessing them through multidimensional matrices that capture diverse architectural and design considerations, as well as evaluation metrics established in the literature. We further examine the challenges that impede the widespread deployment of IPSs and highlight the potential risk that these systems may not be recognized with a single, universally accepted standard method, unlike GPS for outdoor localization, which serves as the golden standard for positioning. Moreover, we outline several promising approaches that could address the existing challenges of IPSs. These include the application of transfer learning, feature engineering, data fusion, multisensory technologies, hybrid techniques, and ensemble learning methods, all of which hold the potential to significantly enhance the accuracy and reliability of IPSs. By leveraging these advanced methodologies, we aim to improve the overall performance of IPSs, thus paving the way for more robust and dependable LBSs in indoor environments.

This paper studies the performance of the communication link between a ground station and the satellites of a LEO constellation, employing code division multiplexing and a non-linear high-power amplifier. The analysis shows that the input power selection at the high-power amplifier of the ground station has a significant impact on overall system performance. The results concerning output power, the challenge of adjusting the back-off with a continuously changing number of satellites, and improved energy efficiency suggest operating in saturation. In this scenario, we can choose to transmit directly the sign of the sum of the signals directed to individual satellites. Analytical exact and simplified results are derived, enabling the estimation of performance as a function of the number of satellites being served when the amplifier operates at saturation. These analytic results are further validated through simulations. A formula to compute the loss across different numbers of satellites is also presented. The performance under saturated amplifier conditions is evaluated, compared, and discussed, providing valuable insights for simplifying the design and operation of satellite uplink communication systems under power amplifier constraints.

The multi-UAV target search problem is crucial in the field of autonomous Unmanned Aerial Vehicle (UAV) decision-making. The algorithm design of Multi-Agent Reinforcement Learning (MARL) methods has become integral to research on multi-UAV target search owing to its adaptability to the rapid online decision-making required by UAVs in complex, uncertain environments. In non-cooperative target search scenarios, targets may have the ability to escape. Target probability maps are used in many studies to characterize the likelihood of a target's existence, guiding the UAV to efficiently explore the task area and locate the target more quickly. However, the escape behavior of the target causes the target probability map to deviate from the actual target's position, thereby reducing its effectiveness in measuring the target's probability of existence and diminishing the efficiency of the UAV search. This paper investigates the multi-UAV target search problem in scenarios involving static obstacles and dynamic escape targets, modeling the problem within the framework of decentralized partially observable Markov decision process. Based on this model, a spatio-temporal efficient exploration network and a global convolutional local ascent mechanism are proposed. Subsequently, we introduce a multi-UAV Escape Target Search algorithm based on MAPPO (ETS-MAPPO) for addressing the escape target search difficulty problem. Simulation results demonstrate that the ETS-MAPPO algorithm outperforms five classic MARL algorithms in terms of the number of target searches, area coverage rate, and other metrics.

The deflection control of the main girder in suspension bridges, as flexible structures, is critically important during their operation. To predict the vertical deflection of existing suspension bridge girders under the combined effects of stochastic traffic loads and environmental temperature, this paper proposes an integrated deflection interval prediction method based on a Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), a probability density estimation layer, and bridge monitoring data. A time-series training dataset consisting of environmental temperature, vehicle load, and deflection monitoring data was built based on bridge health monitoring data. The CNN-LSTM combined layer is used to capture both local features and long-term dependencies in the time series. A Gaussian distribution (GD) is adopted as the probability density function, and its parameters are estimated using the maximum likelihood method, which outputs the optimal deflection prediction and probability intervals. Furthermore, this paper proposes a method for identifying abnormal deflections of the main girder in existing suspension bridges and establishes warning thresholds. This study indicates that, for short time scales, the CNN-LSTM-GD model achieves a 47.22% improvement in Root Mean Squared Error (RMSE) and a 12.37% increase in the coefficient of determination (R2) compared to the LSTM model. When compared to the CNN-LSTM model, it shows an improvement of 28.30% in RMSE and 6.55% in R2. For long time scales, the CNN-LSTM-GD model shows a 54.40% improvement in RMSE and a 10.22% increase in R2 compared to the LSTM model. Compared to the CNN-LSTM model, it improves RMSE by 38.43% and R2 by 5.31%. This model is instrumental in more accurately identifying abnormal deflections and determining deflection thresholds, making it applicable to bridge deflection early-warning systems.

At present, China's coal mine permanent tunneling support commonly uses mechanized drilling and anchoring equipment; there are low support efficiency, labor intensity, and other issues. In order to further improve the support efficiency and liberate productivity, this paper further researches the trajectory planning of the drilling and anchoring materials of the robotic arm for the drilling machine "grasping-carrying-loading-unloading" on the basis of the drilling and anchoring robotic system designed by the team in the previous stage. Firstly, the kinematic model of the robotic arm with material was established by improving the D-H parameter method. Then, the working space of the robotic arm with the material was analyzed using the Monte Carlo method. The singular bit-shaped region of the robotic arm was restricted, and obstacles were removed from the working space. The inverse kinematics was utilized to solve the feasible domain of the robotic arm with material. Secondly, in order to avoid blind searching, the guidance of the Bi-RRT algorithm was improved by adding the target guidance factor, and the two-way tree connection strategy for determining the feasible domain was combined with the Bi-RRT algorithm's feasible domain judgment bi-directional tree connection strategy to improve the convergence speed of the Bi-RRT algorithm. Then, in order to adapt to the dynamic environment and avoid the global planning algorithm from falling into the local minima, on the basis of the above planning methods, an improved Bi-RRT trajectory planning algorithm incorporating the artificial potential field was proposed, which takes the planned paths as the guiding potential field of the artificial potential field to make full use of the global information and avoid falling into the local minimization. Finally, a simulation environment was built in a ROS environment to compare and analyze the planning effect of different algorithms. The simulation results showed that the improved Bi-RRT trajectory planning algorithm incorporating the artificial potential field improved the optimization speed by 69.8% and shortened the trajectory length by 46.6% compared with the traditional RRT algorithm.

Photochromic inks have shown disadvantages, such as poor durability and high cost. Self-healable hydrogels have shown photostability and durability. Herein, a viologen-based covalent polymer was printed onto a paper surface toward the development of a multi-stimuli responsive chromogenic sheet with thermochromic, photochromic, and vapochromic properties. Viologen polymer was created by polymerizing a dialdehyde-based viologen with a hydroxyl-bearing dihydrazide in an acidic aqueous medium. The viologen polymer was well immobilized as a colorimetric agent into a polyvinyl alcohol (PVA)/tricarboxy cellulose (TCC)-based self-healable hydrogel. The viologen/hydrogel nanocomposite films were applied onto a paper surface. The coloration measurements showed that when exposed to ultraviolet light, the orange layer printed on the paper surface switched to green. The photochromic film was used to develop anti-counterfeiting prints using the organic hydrogel composed of a PVA/TCC composite and a viologen polymer. Reversible photochromism with strong photostability was observed when the printed papers were exposed to UV irradiation. A detection limit was monitored in the range of 0.5-300 ppm for NH 3(aq) . The exposure to heat (70 °C) was found to reversibly initiate a colorimetric change.

This paper presents a novel low-power low-voltage current differencing transconductance amplifier (CDTA). To achieve a low-voltage low-power CDTA, the BD-MOST (bulk-driven MOS transistor) technique operating in a subthreshold region is used. The proposed CDTA is designed in 0.18 µm CMOS technology, can operate with a supply voltage of 0.5 V, and consumes 1.05 μW of power. The proposed CDTA is used to realize a current-mode universal filter. The filter can realize five standard transfer functions of low-pass, band-pass, high-pass and band-stop, and all-pass from the same circuit. Neither component-matching conditions nor input signals of the inverse type are required to realize these filter functions. The current-mode filter offers low-input and high-output impedance and uses grounded capacitors. The natural frequency and quality factor of the filters can be orthogonally controlled. The proposed CDTA and its applications are simulated using SPICE to confirm the feasibility and functionality of the new circuits.

This paper addresses the inherent limitations in traditional color modeling techniques for measuring the flame equivalence ratio ( Φ ), particularly focusing on the subjectivity involved in threshold settings and the challenges posed by uneven 2D color distribution. To overcome these issues, this study introduces an attention-based convolutional neural network ( ACN ) model, a novel approach that transcends the conventional reliance on B/G color features ( T f ). The ACN model leverages adaptive feature extraction, augmented by a spatial attention mechanism, to more effectively analyze flame images. By amplifying key features, autonomously minimizing background noise, and standardizing variations in color distribution, the ACN model in this experiment achieved a prediction accuracy of 99%, with a 76% reduction in error rate compared to the original model, significantly improving the accuracy and objectivity of flame Φ measurement. This method marks a substantial development in the precision and reliability of flame analysis.

Medical image denoising is essential for improving the clarity and accuracy of diagnostic images. In this paper, we present an enhanced wavelet-based method for medical image denoising, aiming to effectively remove noise while preserving critical image details. After applying wavelet denoising, a bilateral filter is utilized as a post-processing step to further enhance image quality by reducing noise while maintaining edge sharpness. The bilateral filter's effectiveness heavily depends on its parameters, which must be carefully optimized. To achieve this, we employ Bayesian optimization, a powerful technique that efficiently identifies the optimal filter parameters, ensuring the best balance between noise reduction and detail preservation. The experimental results demonstrate a significant improvement in image denoising performance, validating the effectiveness of our approach.

This paper proposes a dual-band patch antenna with combined self-decoupling and filtering properties, designed to suppress mutual coupling between two antenna elements both within the same dual-band and across different dual-bands. Initially, a dual-band aperture-coupled filtering patch antenna is designed, featuring a forked short-circuited SIR feedline with a quarter-wavelength open-ended stub and a U-shaped patch with two U-slots, which generate three controllable radiation nulls while introducing two additional resonant modes. The design steps are also provided in detail. Subsequently, the low mutual coupling phenomenon of two vertically placed aperture-coupled patch antennas is investigated, successfully developing a high-isolated dual-band two-element MIMO array I. Furthermore, the other quad-band two-element MIMO array II is designed, which utilizes the filtering response to significantly reduce mutual coupling across four bands. Finally, a dual-band filtering patch antenna element and two two-element MIMO arrays are fabricated and measured. The measurements and simulations validate the antenna's low mutual coupling performance in multi-band MIMO arrays and demonstrate its strong potential for future wireless communication applications.

Wearables with photoplethysmography (PPG) sensors are being increasingly used in clinical research as a non-invasive, inexpensive method for remote monitoring of physiological health. Ensuring the accuracy and reliability of PPG-derived measurements is critical, as inaccuracies can impact research findings and clinical decisions. This paper systematically compares heart rate (HR) and heart rate variability (HRV) measures from PPG against an electrocardiogram (ECG) monitor in free-living settings. Two devices with PPG and one device with an ECG sensor were worn by 25 healthy volunteers for 10 days. PPG-derived HR and HRV showed reasonable accuracy and reliability, particularly during sleep, with mean absolute error < 1 beat for HR and 6-15 ms for HRV. The relative error of HRV estimated from PPG varied with activity type and was higher than during the resting state by 14-51%. The accuracy of HR/HRV was impacted by the proportion of usable data, body posture, and epoch length. The multi-scale peak and trough detection algorithm demonstrated superior performance in detecting beats from PPG signals, with an F1 score of 89% during sleep. The study demonstrates the trade-offs of utilizing PPG measurements for remote monitoring in daily life and identifies optimal use conditions by recommending enhancements.

In recent years, with the rapid construction of a safe, clean, efficient and sustainable modern energy system, the intelligence of coal mining has become the inevitable direction of the development of the coal mining industry. The intelligence of coal mining system and equipment is the core of intelligent mining, and the positioning technology of mining equipment is the key to underground intelligent mining. The strapdown inertial navigation system can make up for the shortcomings of traditional GPS positioning systems and laser positioning because of its strong anti-interference, high precision and real-time monitoring, and ability to carry out real-time dynamic positioning of mining equipment in underground coal mines. This paper briefly introduces the basic principle of the strapdown inertial navigation system, analyzes the application of the existing strapdown inertial navigation system in mining equipment, and lists and analyzes the research status of the improvement strategy of the inertial navigation system, such as zero speed correction and integrated navigation technology. Finally, by analyzing the application and future development trend of inertial navigation systems in mining equipment, this paper provides more data and method support for the positioning of mining equipment in the future.

Machine learning generative models have opened up a new perspective for automated machine diagnostics. These methods improve decision-making by extracting features, classifying, and creating new observations using deep neural networks. Generative modeling aims to determine the joint distribution of input data. This contrasts traditional methods used in diagnostics based on discriminative models and the conditional probability distribution of the target variable at known feature values. In the variational autoencoder (VAE) algorithms trained by the authors, the parameters of diagnostic features are random variables, the distributions of which can be approximated based on data, and the identification of probability distributions is based on variational inference. Variational inference is a tool that deals with difficult statistical problems and is usually faster than classical methods. VAEs can detect anomalies, predict failures, and optimize processes. This paper proposes an unsupervised approach to fault diagnosis using only healthy data with automatic feature extraction from the continuous probabilistic latent subspace of the VAE encoder and reduction in PCA or t-SNE. The solution, verified in the example of simulation data, is a response to a common problem related to the lack or difficulty of obtaining marked data in defected states of devices and mechanical structures.

In this paper, adaptive fault-tolerant control for multi-joint robot manipulators is proposed through the combination of synchronous techniques and neural networks. By using a synchronization technique, the position error at each joint simultaneously approaches zero during convergence due to the constraints imposed by the synchronization controller. This aspect is particularly important in fault-tolerant control, as it enables the robot to rapidly and effectively reduce the impact of faults, ensuring the performance of the robot when faults occur. Additionally, the neural network technique is used to compensate for uncertainty, disturbances, and faults in the system via online updating. Firstly, novel robust synchronous control for a robot manipulator based on terminal sliding mode control is presented. Subsequently, a combination of the novel synchronous control and neural network is proposed to enhance the fault tolerance of the robot manipulator. Finally, simulation results for a 3-DOF robot manipulator are presented to demonstrate the effectiveness of the proposed controller in comparison to traditional control techniques.

In many robotic applications, creating a map is crucial, and 3D maps provide a method for estimating the positions of other objects or obstacles. Most of the previous research processes 3D point clouds through projection-based or voxel-based models, but both approaches have certain limitations. This paper proposes a hybrid localization and mapping method using stereo vision and LiDAR. Unlike the traditional single-sensor systems, we construct a pose optimization model by matching ground information between LiDAR maps and visual images. We use stereo vision to extract ground information and fuse it with LiDAR tensor voting data to establish coplanarity constraints. Pose optimization is achieved through a graph-based optimization algorithm and a local window optimization method. The proposed method is evaluated using the KITTI dataset and compared against the ORB-SLAM3, F-LOAM, LOAM, and LeGO-LOAM methods. Additionally, we generate 3D point cloud maps for the corresponding sequences and high-definition point cloud maps of the streets in sequence 00. The experimental results demonstrate significant improvements in trajectory accuracy and robustness, enabling the construction of clear, dense 3D maps.

This paper presents the development of a novel eddy current array (ECA) system for real-time, layer-by-layer quality control in powder bed fusion (PBF) additive manufacturing. The system is integrated into the recoater of a PBF machine to provide spatially resolved electrical conductivity imaging of the manufactured part. The system features an array of 40 inductive sensors spaced at 1 mm pitch and is capable of performing a full array readout every 0.192 mm at 100 mm/s recoater speed. Array scalability was achieved through the careful selection of the electromagnetic configuration, miniaturized and seamlessly integrated sensor elements, and the use of advanced mixed signal processing techniques. Experimental validation was performed on stainless steel 316L parts, successfully detecting metallic structures and confirming system performance in both laboratory and real-time PBF environments. The prototype achieved a signal-to-noise ratio (SNR) of 26.5 dB, discriminating metal from air and thus demonstrating its potential for improving PBF part design, process optimization, and defect detection.

For any radio frequency (RF) sensor (receiver) to function optimally, the ambient noise field strength, converted to electrical power by the transducer (antenna), must be lower than the in-ternal noise of that sensor. Therefore, knowledge of the expected ambient noise level is essential for the design of sensors for earth observation, atmospheric research, radio astronomy or navigation. The International Telecommunication Union (ITU) provides a model that predicts ambient man-made noise levels, differentiated by frequency, origin and environment. This is entirely empirical model is based on data from the 1960's and 1970's. In recent years, 90,205 noise measurements have been collected to update the model. The analysis of that data set presented here is essential as it shows a pitfall to avoid: despite to size of the data set it is sparce over the parameter space, and unacceptable biases occur when a purely empirical model is based on them. The paper proposes another approach: to create a mathematical model based on physics that can be fine-tuned and validated using these collected measurements, without producing the biases. A revolutionary side effect of such a model would be the linking of two currently isolated domains, that of spectrum management and electromagnetic compatibility.

The Internet of Things (IoT) is a heterogeneous network composed of numerous dynamically connected devices. While it brings convenience, the IoT also faces serious challenges in data security. Ciphertext-policy attribute-based encryption (CP-ABE) is a promising cryptography method that supports fine-grained access control, offering a solution to the IoT's security issues. However, existing CP-ABE schemes are inefficient and unsuitable for IoT devices with limited computing resources. To address this problem, this paper proposes an efficient pairing-free CP-ABE scheme for the IoT. The scheme is based on lightweight elliptic curve scalar multiplication and supports multi-authority and verifiable outsourced decryption. The proposed scheme satisfies indistinguishability against chosen-plaintext attacks (CPA) under the elliptic curve decisional Diffie-Hellman (ECDDH) problem. Performance analysis shows that our proposed scheme is more efficient and better suited to the IoT environment compared to existing schemes.

This paper investigates the motion state estimation problem of the unmanned surface vehicle (USV) steering system in wireless sensor networks based on the binary coding scheme (BCS). In response to the presence of bandwidth constraints and mixed cyber-attacks in USV communication networks, this paper proposes an improved set-membership state estimation algorithm based on BCS. This algorithm partially addresses the problem of degraded performance in USV steering motion state estimation caused by mixed cyber-attacks and bandwidth constraints. Furthermore, this paper proposes a robust resilient filtering framework considering the possible occurrence of unknown but bounded (UBB) noises, model parameter uncertainties, and estimator gain perturbations in practical scenarios. The proposed framework can accurately estimate the sway velocity, yaw velocity, and roll velocity of the USV under the concurrent presence situation of mixed cyber-attacks, communication capacity constraints, UBB noises, model parameter uncertainties, and estimator gain perturbations. This paper first utilizes mathematical induction to provide the sufficient conditions for the existence of the desired estimator, and obtains the estimator gain by solving a set of linear matrix inequalities. Then, a recursive optimization algorithm is utilized to achieve optimal estimation performance. Finally, the effectiveness of the proposed estimation algorithm is verified through a simulation experiment.

Human action recognition (HAR) is a critical area in computer vision with wide-ranging applications, including video surveillance, healthcare monitoring, and abnormal behavior detection. Current HAR methods predominantly rely on full-body data, which can limit their effectiveness in real-world scenarios where occlusion is common. In such situations, the face often remains visible, providing valuable cues for action recognition. This paper introduces Face in Action (FIA), a novel two-stream method that leverages facial action cues for robust action recognition under conditions of significant occlusion. FIA consists of an RGB stream and a landmark stream. The RGB stream processes facial image sequences using a fine-spatio-multitemporal (FSM) 3D convolution module, which employs smaller spatial receptive fields to capture detailed local facial movements and larger temporal receptive fields to model broader temporal dynamics. The landmark stream processes facial landmark sequences using a normalized temporal attention (NTA) module within an NTA-GCN block, enhancing the detection of key facial frames and improving overall recognition accuracy. We validate the effectiveness of FIA using the NTU RGB+D and NTU RGB+D 120 datasets, focusing on action categories related to medical conditions. Our experiments demonstrate that FIA significantly outperforms existing methods in scenarios with extensive occlusion, highlighting its potential for practical applications in surveillance and healthcare settings.

This paper is devoted to the issue of using laser (lidar) sensing to determine wind speed and direction when solving practical problems during the analysis of meteorological conditions in the area around spaceports. This issue is relevant both for making decisions on the possibility of a safe launch of a launch vehicle and for conducting search and rescue operations using groups of manned and unmanned aerial vehicles. Based on numerical and experimental modeling, it is shown that lidars provide highly accurate measurements of wind speed profiles and allow for the determination of weak wind shear in vertical and horizontal directions. This paper proposes a method for determining the main parameters of lidar sensing (range, resolution, detectability, etc.), which allows for the capabilities of this technology in solving the practical problems of meteorological monitoring to be predicted. Of particular interest in this article are experimental modeling data verifying the proposed calculation methods and the experimental determination of the capabilities of lidar diagnostics. This paper summarizes the data from multi-month experiments measuring wind speed in clear weather conditions when other means of remote diagnostics are ineffective. As a result of the experiments, a statistical distribution of the maximum range of wind speed measurement in normal weather conditions with natural variation in the concentration of scattering particles in the atmosphere was obtained. This article also discusses the possibility of combining lidars and meteorological radars for the meteorological support of flights.

Piezoelectric transducers are commonly used in acoustic well logging. However, the low frequency and narrow range of the acoustic waves limit the achievable detection accuracy. In addition, the low amplitude of the waves causes useful information to be easily masked by noise during detection, which affects the accuracy of geological identification and makes it difficult to detect formations tens of meters away. This paper proposes a microporous liquid-electric transmission transducer, in which the microporous electrode structure generates a powerful shock wave through a high-energy instantaneous discharge. First, a model of the liquid-electric microporous transmitting transducer was constructed by combining simulations with numerical calculations, and its electro-acoustic characteristics were analyzed. Then, based on the survey requirements, two innovative optimization schemes for the microporous electrode structure were proposed, namely a triangular pyramid microporous electrode structure and a rectangular microporous electrode structure, and their performances were compared. The results show that the newly optimized triangular pyramid microporous electrode liquid-electric transducer generates acoustic waves with higher amplitude and a wider frequency range than conventional piezoelectric transducers and other microporous structures. It maintains high energy while achieving high frequencies, enabling detection at distances of up to hundreds of meters and the precise characterization of small geological bodies. This has significant implications for applications in marine exploration, land exploration, clean energy, and new energy fields.

Fault diagnosis plays a crucial role in maintaining the operational safety of mechanical systems. As intelligent data-driven approaches evolve, deep learning (DL) has emerged as a pivotal technique in fault diagnosis research. However, the collected vibrational signals from mechanical systems are usually corrupted by unrelated noises due to complicated transfer path modulations and component coupling. To solve the above problems, this paper proposed the dynamic temporal denoise neural network with multi-head attention (DTDNet). Firstly, this model transforms one-dimensional signals into two-dimensional tensors based on the periodic self-similarity of signals, employing multi-scale two-dimensional convolution kernels to extract signal features both within and across periods. Secondly, for the problem of lacking denoising structure in traditional convolutional neural networks, a temporal variable denoise (TVD) module with dynamic nonlinear processing is proposed to filter the noises. Lastly, a multi-head attention fusion (MAF) module is used to weight the denoted features of signals with different periods. Evaluation on two datasets, Case Western Reserve University bearing dataset (single sensor) and Real aircraft sensor dataset (multiple sensors), demonstrates that the DTDNet can reduce the useless noises in signals and achieve a remarkable improvement in classification performance compared with the state-of-the-art method. DTDNet provides a high-performance solution for potential noise that may occur in actual fault diagnosis tasks, which has important application value.

Modern mental fatigue detection methods include many parameters for evaluation. For example, many researchers use human subjective evaluation or driving parameters to assess this human condition. Development of a method for detecting the functional state of mental fatigue is an extremely important task. Despite the fact that human operator support systems are becoming more and more widespread, at the moment there is no open-source solution that can monitor this human state based on eye movement monitoring in real time and with high accuracy. Such a method allows the prevention of a large number of potential hazardous situations and accidents in critical industries (nuclear stations, transport systems, and air traffic control). This paper describes the developed method for mental fatigue detection based on human eye movements. We based our research on a developed earlier dataset that included captured eye-tracking data of human operators that implemented different tasks during the day. In the scope of the developed method, we propose a technique for the determination of the most relevant gaze characteristics for mental fatigue state detection. The developed method includes the following machine learning techniques for human state classification: random forest, decision tree, and multilayered perceptron. The experimental results showed that the most relevant characteristics are as follows: average velocity within the fixation area; average curvature of the gaze trajectory; minimum curvature of the gaze trajectory; minimum saccade length; percentage of fixations shorter than 150 ms; and proportion of time spent in fixations shorter than 150 milliseconds. The processing of eye movement data using the proposed method is performed in real time, with the maximum accuracy (0.85) and F1-score (0.80) reached using the random forest method.

Coverage control is a fundamental and critical issue in plentiful wireless sensor network (WSN) applications. Aiming at the high-dimensional optimization problem of sensor node deployment and the complexity of the monitoring area, an orthogonal learning multi-strategy bald eagle search (OLMBES) algorithm is proposed to optimize the location deployment of sensor nodes. This paper incorporates three kinds of strategies into the bald eagle search (BES) algorithm, including Lévy flight, quasi-reflection-based learning, and quadratic interpolation, which enhances the global exploration ability of the algorithm and accelerates the convergence speed. Furthermore, orthogonal learning is integrated into BES to improve the algorithm's robustness and premature convergence problem. By this way, population search information is fully utilized to generate a more superior position guidance vector, which helps the algorithm jump out of the local optimal solution. Simulation results on CEC2014 benchmark functions reveal that the optimization performance of the proposed approach is better than that of the existing method. On the WSN coverage optimization problem, the proposed method has greater network coverage ratio, node uniformity, and stronger optimization stability when compared to other state-of-the-art algorithms.

Accurate heart rate estimation using Doppler radar and Frequency Modulated Continuous Wave (FMCW) radar is highly valued for privacy protection and the ability to measure through clothing. Conventional methods struggle to isolate the heartbeat from respiration and body motion. This paper introduces a novel heart rate estimation method using Variational Mode Decomposition (VMD) via Multiple-Input Multiple-Output (MIMO) FMCW radar. The proposed method first estimates human positions within the radar's coverage, reducing noise by focusing on signals from these positions. The signal is then decomposed into multiple Intrinsic Mode Function (IMF) signals using VMD, and the heartbeat-specific IMF is extracted based on its center frequency. The heart rate signal is reconstructed using weighted addition of IMF signals for each radar cell, with cells defined by specific angles and distances within the coverage area. Peak detection is used to estimate heart rate from these reconstructed signals. To ensure accuracy, the method selects the heart rate estimate with the highest energy and periodicity for the first four time windows. From the fifth time window onward, it selects the estimate closest to the average of the previous four, minimizing extraneous variations. Experiments conducted with one and two subjects showed promising results. In case 1, with one subject, the method achieved a Mean Absolute Error (MAE) of 2.54 BPM and an exclusion rate of 0.94% using MIMO FMCW radar, compared to 4.72% with Doppler radar. In case 2, with two subjects, the method achieved an MAE of 2.28 BPM, confirming accurate simultaneous heart rate estimation.

This paper presents an innovative piezo-actuated fast-steering mirror (FSM) that integrates control design and system operation to improve the tracking performance of laser beam steering (LBS) systems. The proposed piezoelectric FSM is centered on two pairs of stacked actuators functioning in the tip-tilt direction via novel flexible hinges with strain-gauge sensors for position measurement. The suggested flexible hinge scheme allows the first fundamental resonance mode with the optical mirror to exceed 400 Hz while achieving an actuation range of ±5 mrad. Thus, the design offers a wider mechanical actuation range than conventional piezoelectric FSMs. Moreover, LBS systems that use fast-steering motion controllers should be robust against dynamic disturbances, such as periodic external vibrations. Such disturbances, inherently associated with the operating conditions for LBS systems, typically reduce the stability of the tip-tilt motion. To attenuate the effects of such disturbances, a high-precision control system is necessary for the tip-tilt motion. Therefore, a control method integrating a proportional-integral controller with an adaptive feedforward control (AFC) algorithm is outlined to enhance tip-tilt tracking performance during high-speed scanning, compared with conventional LBS systems. Based on experimental findings, the AFC algorithm boosted control performance under dynamic disturbances, such as sinusoidal vibrations with multiple frequencies.

This paper introduces a systematic approach to the design of Direct Current-to-Digital Converter (DIDC) specifically engineered to overcome the limitations of traditional current measurement methodologies in System-on-Chip (SoC) designs. The proposed DIDC addresses critical challenges such as high power consumption, large area requirements, and the need for intermediate analog signals. By incorporating a current mirror in a cascode topology and managing the current across multiple binary-sized branches with the Successive Approximation Register (SAR) logic, the design achieves precise current measurement. A simple comparator, coupled with an isolation circuit, ensures accurate and reliable sensing. Fabricated using the TSMC 180 nm process, the DIDC achieves 8-bit precision without the need for nonlinearity calibration, showcasing remarkable energy efficiency with an energy per conversion of 1.52 pJ, power consumption of 117 µW, and a compact area of 0.016 mm². This innovative approach not only reduces power consumption and area, but also provides a scalable and efficient solution for next-generation semiconductor technologies. The ability to conduct online measurements during both standard operations and in-field conditions significantly enhances the performance and reliability of SoCs, making this DIDC a promising advancement in the field.

The conventional method for detecting road defects relies heavily on manual inspections, which are often inefficient and struggle with precise defect localization. This paper introduces a novel approach for identifying and locating road defects based on an enhanced ML-YOLO algorithm. By refining the YOLOv8 object detection framework, we optimize both the traditional convolutional layers and the spatial pyramid pooling network. Additionally, we incorporate the Convolutional Block Attention to effectively capture channel and spatial features, along with the Selective Kernel Networks that dynamically adapt to feature extraction across varying scales. An optimized target localization algorithm is proposed to achieve high-precision identification and accurate positioning of road defects. Experimental results indicate that the detection accuracy of the improved ML-YOLO algorithm reaches 0.841, with a recall rate of 0.745 and an average precision of 0.817. Compared to the baseline YOLOv8 model, there is an increase in accuracy by 0.13, a rise in recall rate by 0.117, and an enhancement in average precision by 0.116. After the high detection accuracy of road defects was confirmed, generalization experiments were carried out on the improved ML-YOLO model in the public data set. The experimental results showed that compared with the original YOLOv8n, the average precision and recall rate of all types of ML-YOLO increased by 0.075, 0.121, and 0.035 respectively, indicating robust generalization capabilities. When applied to real-time road monitoring scenarios, this algorithm facilitates precise detection and localization of defects while significantly mitigating traffic accident risks and extending roadway service life. A high detection accuracy of road defects was achieved.

Automating pruning tasks entails overcoming several challenges, encompassing not only robotic manipulation but also environment perception and detection. To achieve efficient pruning, robotic systems must accurately identify the correct cutting points. A possible method to define these points is to choose the cutting location based on the number of nodes present on the targeted cane. For this purpose, in grapevine pruning, it is required to correctly identify the nodes present on the primary canes of the grapevines. In this paper, a novel method of node detection in grapevines is proposed with four distinct state-of-the-art versions of the YOLO detection model: YOLOv7, YOLOv8, YOLOv9 and YOLOv10. These models were trained on a public dataset with images containing artificial backgrounds and afterwards validated on different cultivars of grapevines from two distinct Portuguese viticulture regions with cluttered backgrounds. This allowed us to evaluate the robustness of the algorithms on the detection of nodes in diverse environments, compare the performance of the YOLO models used, as well as create a publicly available dataset of grapevines obtained in Portuguese vineyards for node detection. Overall, all used models were capable of achieving correct node detection in images of grapevines from the three distinct datasets. Considering the trade-off between accuracy and inference speed, the YOLOv7 model demonstrated to be the most robust in detecting nodes in 2D images of grapevines, achieving F1-Score values between 70% and 86.5% with inference times of around 89 ms for an input size of 1280 × 1280 px. Considering these results, this work contributes with an efficient approach for real-time node detection for further implementation on an autonomous robotic pruning system.

The bidirectional reflectance distribution function (BRDF) can effectively characterize the reflectance properties of a target, which can be used to correct infrared remote sensing data and improve the accuracy of remote sensing measurements. When the surface temperature changes, the reflectance characteristics of the target usually change, and it is necessary to carry out BRDF measurements under variable temperature conditions. In this paper, a variable-temperature infrared BRDF measurement system based on a robotic arm is developed to realize high-resolution wide-temperature region measurement of BRDF. To improve the measurement accuracy, the shaping optical path was used to expand the laser beam, combined with the laser level to accurately adjust the three-dimensional coordinates of the robotic arm, and the dichotomy method is used to calibrate the detector nonlinearly. A portable heater suitable for the mechanical arm corner mechanism is developed, and fast and high-precision temperature control is realized by proportional integral derivative (PID) control. The specular and diffuse BRDF distributions were measured at room temperature to verify the effectiveness of the system. The BRDF distribution of SUS314 stainless steel samples with different roughness is measured during two temperature increases from 20 °C to 1000 °C, and the changing rule of BRDF under variable temperature environment is summarized, which provides technical support for evaluating the optical properties of high-temperature materials and improving the measurement accuracy of remote sensing data.