Search

Abstract Background Residual low back and leg pain can occur after percutaneous endoscopic interlaminar discectomy (PEID) and compromise early surgical outcomes. This study aimed to determine the efficacy of combining dexamethasone with vitamin B12 (VB12) via epidural injection in improving the symptoms of low back and leg pain after PEID, and the underlying mechanism of action. Methods Patients who underwent PEID for lumbar disc herniation (LDH) were enrolled and randomly assigned to the single surgery (SS) group, where disc removal was performed via PEID alone, or the combined treatment (CT) group, which received epidural injections of dexamethasone and VB12 alongside surgery. The outcome measures were the Visual Analog Scale (VAS), Japanese Orthopaedic Association (JOA) score, Oswestry Disability Index (ODI), serum inflammatory factor expression, adverse surgical events, duration of postoperative hospitalization, and modified MacNab criteria. Results Compared with the SS group, the CT group exhibited lower VAS scores for low back and leg pain at 1, 3, and 7 days post-surgery (P

Abstract Effective monitoring and early warning of overhead power lines are critical for ensuring power supply stability and personnel safety. However, existing methods that rely solely on single vision or light detection and ranging (LiDAR) have limitations such as numerous invalid alarms, hardware equipment constraints, and lack of real‐time monitoring capabilities. This article proposes an intelligent monitoring method for safety distance of the powerline corridor based on heterogeneous sensor information. Firstly, an optimised single‐stage detector is designed to detect safety hazard objects. In the detector, the backbone network and the sample matching strategy are improved; in addition, the learning strategy is adjusted. Next, the pose transformation relationship is obtained through the visual matching of prior LiDAR information and images. The back projection transformation of 2D–3D is achieved according to the relationship. Finally, a monocular camera‐based end‐to‐end distance measurement scheme is proposed by combining 2D object information with coordinate transformation relationships. The scheme is applied to the distance measurements from hazard objects to powerlines. The experimental results show that the optimisation method improves the detection accuracy and reduces the computational complexity of the model. Also, case experiments with continuous frame data verify the effectiveness of the safety distance monitoring scheme.

Abstract Background To explore and compare the values of 3.0T magnetic resonance imaging (MRI) T2 mapping in evaluating the degree of acetabular cartilage degeneration in hip replacement surgery. Methods A total of 26 elderly patients with femoral neck fractures who were scanned in 3.0T MRI T2 mapping quantification technique were included. Basing on MRI images, the degree of acetabular cartilage degeneration was classified into Grade 0, 1, 2, 3 and 4, according to the International Cartilage Repair Society (ICRS) scores. In addition, 8 healthy volunteers were included for control group. Results By comparison with health population, T2 relaxation values in the anterior, superior, and posterior regions of acetabular cartilage in patients with femoral neck fracture were obviously increased (P 0.05). Importantly, acetabular cartilage degeneration can be detected through signal changes of T2 mapping pseudo-color images. Conclusion 3.0T MRI T2 mapping technology can be used to determine the degree of acetabular cartilage degeneration, which can effectively monitor the disease course.

Abstract Using the principles of density functional theory (DFT) and nonequilibrium Green’s function (NEGF), We thoroughly researched carbon-doped zigzag boron nitride nanoribbons (ZBNNRs) to understand their electronic behavior and transport properties. Intriguingly, we discovered that careful doping can transform carbon-doped ZBNNRs into a spintronic nanodevice with distinct transport features. Our model showed a giant magnetoresistance (GMR) up to a whopping 10 $$^5$$ 5 under mild bias conditions. Plus, we spotted a spin rectifier having a significant rectification ratio (RR) of 10 $$^4$$ 4 . Our calculated transmission spectra have nicely explained why there’s a GMR up to 10 $$^5$$ 5 for spin-up current at biases of $$-1.2$$ - 1.2 V, $$-1.1$$ - 1.1 V, and $$-1.0$$ - 1.0 V, and also accounted for a GMR up to 10 $$^3$$ 3 –10 $$^5$$ 5 for spin-down current at biases of 1.0 V, 1.1 V, and 1.2 V. Similarly, the transmission spectra elucidate that at biases of 1.0 V, 1.1 V, and 1.2 V for spin-up, and at biases of 1.1 V and 1.2 V for spin-down in APMO, the RRs reach 10 $$^4$$ 4 . Our research shines a light on a promising route to push forward the high-performance spintronics technology of ZBNNRs using carbon atom doping. These insights hint that our models could be game-changers in the sphere of nanoscale spintronic devices.

The electric meter box is a terminal device with a large number in the power grid. It may cause electrical hazards and property loss if damaged. Inspection of electricity meter boxes still relies on manual inspection with low efficiency and low automation. But image-based automated inspection is also limited by equipment battery and insufficient computing power, which makes the inspection system in urgent need of efficient model. However, lightweight model may reduce model robustness and be susceptible to interference from complex backgrounds due to insufficient feature extraction. Meanwhile, there are no publicly available datasets for electric meter boxes at present. To address the above issues, we firstly constructed a dataset, named EMB-11. After that, we improved the YOLOv7-tiny to design a novel model for electric meter box defect detection, named EMB-YOLO. In EMB-YOLO, we proposed the Big Kernel ShuffleBlock which can increase the effective receptive field and reduce the model parameters. Additionally, we proposed ELAN-CBAM to enhance the robustness of the model and reduce the interference of background noise. Finally, we constructed RepBSB based on the idea of structural reparameterization to reduce the size of the trained model. Compared to YOLOv7-tiny, the size of EMB-YOLO is only 4.82 Mb, which is reduced by 20.3 %. The detection speed is 343 frames/s, which is increased by 14.3 %. Most importantly, mAP can reach 82.8 %, which is increased by 3.5 %, reaching the SOTA level.

Abstract Purpose 3D printing techniques guide precision medicine and show great development potential in clinical applications. The purpose of this study was to compare the clinical outcomes of 3D-printed navigation templates versus free-hand in tension band wiring (TBW) procedures for olecranon fractures. Methods Patients who underwent TBW due to Mayo type II olecranon fractures between January 2019 and December 2021 in our hospital were prospectively enrolled in the study. The patients were divided into the 3D printed navigation template guiding TBW group (3D printed group) and the free-hand TBW group (free-hand group). The primary endpoint of this study was the success rate of the bicortical placement of Kirschner wires (K-wires). Times of intraoperative fluoroscopy, operation times, complications, VAS scores, and Mayo Elbow Performance Scores (MEPS) were analyzed as the secondary outcomes measure. Results The success rate of the bicortical placement of K-wires was 85.7% in the 3D Printed group was significantly higher than the free-hand group (60%). There were fewer times of intraoperative fluoroscopy in the 3D Printed group (1.43 ± 0.51) than that in the free-hand group (2.60 ± 1.00) with statistical significance (P

This paper reviewed the clinical data of a patient with postherpetic neuralgia, summarized the intervention effect of five-element music therapy and acupoint massage and related nursing measures. Five-element music theory was conducted under the guidance of traditional Chinese medicine, combined with manipulation massage on selected acupoints. Comprehensive nursing interventions such as dietary guidance and emotional care were carried out to improve treatment efficacy of pain relief in patients with postherpetic neuralgia. (本文总结1例五行音乐联合穴位按摩治疗带状疱疹后遗神经痛(PHN)患者的护理经验, 通过辨证施乐, 给予患者聆听音乐, 并选取相关穴位进行手法按摩, 同时配合饮食护理、情志护理等综合干预措施, 有效改善PHN患者疼痛症状。)

Key objects’ semantic segmentation and power line extraction from the electric power corridor point cloud are critical steps in power line inspection. However, the massive amount of point cloud data and missing power line points pose a challenge to the object extraction. To complete the extraction of power lines and other essential objects, a method called SS-IPLE is proposed, which is based on a pointwise multilayer-perceptron semantic segmentation network. The method consists of two main parts: electric power corridor semantic segmentation and individual power line extraction. In the segmentation step, SCF-Net is employed as our primary segmentation network, and the network can process large-scale point clouds. To further improve the segmentation ability of SCF-Net in the corridor, a local coding module is designed to construct the SCFL-Net. In the individual power line extraction step, individual power lines are extracted by flexible grid filtering, effectively overcoming the point-missing problem. The corridor point cloud semantic segmentation and individual power line extraction experiments are conducted in different corridors collected from suburban areas. Promising results are obtained for both semantic segmentation and individual power line extraction, with an mIou of point cloud semantic segmentation and a mean extraction rate of 96.70% and 96.56%, respectively.

Abstract Background Previous studies have demonstrated that by injecting uPA into the lumbar facet joints (LFJ) of normal rats, a rat LFJOA animal model can be successfully established. However, there is no evidence that intraarticular injection of uPA can induce or much serious osteoarthritis in bipedal rats, which biomechanics is much more similar to human than normal rats. To investigate whether intraarticular injection of urinary plasminogen activator (uPA) can induce LFJOA and low back pain symptoms in bipedal rats. Methods An experimental study on the construction of a modified animal model of lumbar facet joints osteoarthritis (LFJOA) which biomechanics is similar to human. Sprague–Dawley rats were treated with intraarticular injection of uPA in the L5–L6 facet joints (uPA group, n = 15) or saline (saline group, n = 15). The forelimbs of both two group rats were amputated. Mechanical and thermal hyperalgesia in the ipsilateral hind paws were evaluated using von Frey hairs and a thermoalgesia instrument, respectively. Toluidine blue staining, hematoxylin–eosin staining, and immunohistochemical examination of the LFJ was performed. Results The saline group rats have not demonstrated significant osteoarthritis in rats LFJ after surgery. The uPA group has not been induced significantly higher mechanical and thermal hyperalgesia in comparison with the saline group. But intraarticular injection of uPA in biped rats induced significantly stronger articular cartilage damage, synovitis, and proliferation of synovial cells in the LFJ. Inflammatory factors such as iNOS, IL-1β, and TNF-a were more significantly expressed in bipedal rat injected with uPA (p

Abstract 6D pose estimation has been pervasively applied to various robotic applications, such as service robots, collaborative robots, and unmanned warehouses. However, accurate 6D pose estimation is still a challenge problem due to the complexity of application scenarios caused by illumination changes, occlusion and even truncation between objects, and additional refinement is required for accurate 6D object pose estimation in prior work. Aiming at the efficiency and accuracy of 6D object pose estimation in these complex scenes, this paper presents a novel end‐to‐end network, which effectively utilises the contextual information within a neighbourhood region of each pixel to estimate the 6D object pose from RGB‐D images. Specifically, our network first applies the attention mechanism to extract effective pixel‐wise dense multimodal features, which are then expanded to multi‐scale dense features by integrating pixel‐wise features at different scales for pose estimation. The proposed method is evaluated extensively on the LineMOD and YCB‐Video datasets, and the experimental results show that the proposed method is superior to several state‐of‐the‐art baselines in terms of average point distance and average closest point distance.

Abstract Point cloud data in the real world is often affected by occlusion and light reflection, leading to incompleteness of the data. Large‐region missing point clouds will cause great deviations in downstream tasks. A dual feature fusion network (DFF‐Net) is proposed to improve the accuracy of the completion of a large missing region of the point cloud. First, a dual feature encoder is designed to extract and fuse the global and local features of the input point cloud. Subsequently, a decoder is used to directly generate a point cloud of missing region that retains local details. In order to make the generated point cloud more detailed, a loss function with multiple terms is employed to emphasise the distribution density and visual quality of the generated point cloud. A large number of experiments show that the authors’ DFF‐Net is better than the previous state‐of‐the‐art methods in the aspect of point cloud completion.

Visual perception equips unmanned aerial vehicles (UAVs) with increasingly comprehensive and instant environmental perception, rendering it a crucial technology in intelligent UAV obstacle avoidance. However, the rapid movements of UAVs cause significant changes in the field of view, affecting the algorithms’ ability to extract the visual features of collisions accurately. As a result, algorithms suffer from a high rate of false alarms and a delay in warning time. During the study of visual field angle curves of different orders, it was found that the peak times of the curves of higher-order information on the angular size of looming objects are linearly related to the time to collision (TTC) and occur before collisions. This discovery implies that encoding higher-order information on the angular size could resolve the issue of response lag. Furthermore, the fact that the image of a looming object adjusts to meet several looming visual cues compared to the background interference implies that integrating various field-of-view characteristics will likely enhance the model’s resistance to motion interference. Therefore, this paper presents a concise A-LGMD model for detecting looming objects. The model is based on image angular acceleration and addresses problems related to imprecise feature extraction and insufficient time series modeling to enhance the model’s ability to rapidly and precisely detect looming objects during the rapid self-motion of UAVs. The model draws inspiration from the lobula giant movement detector (LGMD), which shows high sensitivity to acceleration information. In the proposed model, higher-order information on the angular size is abstracted by the network and fused with multiple visual field angle characteristics to promote the selective response to looming objects. Experiments carried out on synthetic and real-world datasets reveal that the model can efficiently detect the angular acceleration of an image, filter out insignificant background motion, and provide early warnings. These findings indicate that the model could have significant potential in embedded collision detection systems of micro or small UAVs.

Hemiarthroplasty is a surgical choice for super-aged patients with a high surgical risk and a sedentary lifestyle. The direct superior approach (DSA), a minimally invasive modification of the posterior approach, is rarely studied in hemiarthroplasty. The aim of the present study was to compare the clinical outcomes in elderly patients with displaced femoral neck fractures undergoing hemiarthroplasty via DSA with the conventional posterolateral approach (PLA). A total of 48 elderly patients with displaced femoral neck fractures who underwent hemiarthroplasty between February 2020 and March 2021 were retrospectively included in the study. Of them, 24 patients (mean age 84.54 ± 2.11 years) were treated with hemiarthroplasty via DSA (DSA group), while the other 24 patients (mean age 84.92 ± 2.15 years) were treated with hemiarthroplasty via PLA (PLA group). Clinical outcomes, perioperative data, and complications were recorded. There were no obvious differences in the baseline characteristics between the DSA and PLA groups, including age, gender, body mass index, Garden type, American Society of Anesthesiologists score, and hematocrit. Perioperative data showed that the length of the incision in the DSA group was smaller than that in the PLA group (p 0.05). DSA is less invasive and has better clinical outcomes, which can allow an early return to daily living activities in elderly patients with displaced femoral neck fractures undergoing hemiarthroplasty.

The influences of different initial water contents, cold end temperatures and dry densities on water migration in sand were studied using the self-developed water migration and frost heaving testing equipment. The variations of frost heaving force and frost heaving amount subjected to aforementioned three factors were analyzed and the position of freezing front was determined. The results show that the initial water content and cold end temperature had significant influence on the soil water migration and frost heaving effect. When the initial water content increased from 0% to 10%, the peak water content increased by 6.00 times, the horizontal frost heaving force and frost heaving amount increased gradually, and the freezing front moved up to the position of 2.5 cm in height. When the cold end temperature decreased from -5 ℃ to -15 ℃, the peak water content increased by 4.38 times, the horizontal frost heaving force and frost heaving amount increased gradually, and the freezing front moved up to the position of 2.6 cm in height. Dry density has relatively insignificant influence on water migration and freezing characteristics of samples. Under low dry density, there was an overall trend of slightly larger increases in sample’s water content, horizontal frost heaving force and frost heaving amount, and the position of freezing front was concentrated at the position of 2.2-2.5 cm in height. The prediction formulae of frost heaving force and frost heaving amount were put forward for different influencing factors, and they can provide a reference for understanding the water migration law in sand under water vapor recharge and reasonably preventing frost heave.

Aiming at the low efficiency of vector control system caused by unreasonable current allocation, an improved energy saving control strategy based on weighted average current method is proposed in this paper, and the research is carried out on the background of interior permanent magnet synchronous motor vector control system. This method does not add new parameters, but achieves the goal of reducing motor loss and improving current utilization rate. Firstly, according to the mathematical model of permanent magnet synchronous motor considering iron loss resistance, the relationship between motor torque and d-q axis current is deduced. Then, by introducing the weighted average current factor, the minimum copper loss current and the minimum iron loss current are calculated analytically. Finally, the simulation analysis shows that the energy saving strategy proposed in this paper can further reduce the electrical loss of permanent magnet motor compared with the traditional energy saving control method, which proves the feasibility of this method in improving the energy efficiency of the vector control system of permanent magnet motor.

Due to the low efficiency and safety of a manual insulator inspection, research on intelligent insulator inspections has gained wide attention. However, most existing defect recognition methods extract abstract features of the entire image directly by convolutional neural networks (CNNs), which lack multi-granularity feature information, rendering the network insensitive to small defects. To address this problem, we propose a multi-granularity fusion network (MGFNet) to diagnose the health status of the insulator. An MGFNet includes a traversal clipping module (TC), progressive multi-granularity learning strategy (PMGL), and region relationship attention module (RRA). A TC effectively resolves the issue of distortion in insulator images and can provide a more detailed diagnosis for the local areas of insulators. A PMGL acquires the multi-granularity features of insulators and combines them to produce more resilient features. An RRA utilizes non-local interactions to better learn the difference between normal features and defect features. To eliminate the interference of the UAV images’ background, an MGFNet can be flexibly combined with object detection algorithms to form a two-stage object detection algorithm, which can accurately identify insulator defects in UAV images. The experimental results show that an MGFNet achieves 91.27% accuracy, outperforming other advanced methods. Furthermore, the successful deployment on a drone platform has enabled the real-time diagnosis of insulators, further confirming the practical applications value of an MGFNet.

Low-cost uncooled infrared thermal cameras show a large application potential for the rapid diagnosis of pig diseases. However, with the increase in ambient temperature and absorbing infrared radiation, almost all of them produce severe thermal drift and provide poor accuracy of temperature measurement. In addition, the unknown surface emissivity on a pig’s body can also bring measuring errors. In this article, an uncooled infrared thermal camera with an accuracy of 3°C was used to develop a smartphone-based sensor for measuring the pig’s temperature. Based on this sensor, we proposed a system combined with internal calibration for real-time compensation of the thermal drift and altering spectrum for eliminating the influence of unknown surface emissivity to improve the accuracy of temperature measurement. After calibration, the accuracy of this sensor was improved from 3 to 0.3°C without knowing the emissivity. We used this sensor to successfully identify pigs with abnormal temperatures on a livestock farm, which indicated that our proposed methods may be widely employed for rapid temperature screening and diagnosis of pig diseases.

To improve the robustness of UAVs in rotating and motion scenes, we propose a stereo simultaneous localization and mapping (SLAM) for UAVs with a new keyframe strategy that differs from current SLAM systems. Moreover, it has two strategies. 1) In the dominant strategy based on image quality, we filter and retain the strong feature points in each image frame by our own defined rules; this leads to longer survival time and attribute invariance in image tracking, and we save the image frames containing more strong feature points as keyframes. 2) In the secondary strategy based on motion state, we quantify the motion state during the UAV’s motion (called the compound rotation amount), and characterize the intensity of the motion. Since we want the UAV to have better robustness in the rotating scene, this strategy generates keyframes when the compound rotation amount meets the threshold. These two strategies are used to cope with gentle motion scenes and rotational motion scenes, respectively. Thus, the insertion of our keyframes is determined by the motion state; our SLAM system is proposed based on the motion state (MS-SLAM). In the back-end part of the system we construct a new weighted cost function to optimize the pose. Finally, through comparison experiments on the public dataset EuRoc, we demonstrate that our algorithm is more advantageous than some current mainstream algorithms. In difficult sequences, our algorithm compares the absolute trajectory error with ORB-SLAM2, SVO+gtsam, and VINS-Mono, the absolute trajectory error of our algorithm can be reduced by 87%.

Power line inspection is an important part of the smart grid. Efficient real-time detection of power devices on the power line is a challenging problem for power line inspection. In recent years, deep learning methods have achieved remarkable results in image classification and object detection. However, in the power line inspection based on computer vision, datasets have a significant impact on deep learning. The lack of public high-quality power scene data hinders the application of deep learning. To address this problem, we built a dataset for power line inspection scenes, named RSIn-Dataset. RSIn-Dataset contains 4 categories and 1887 images, with abundant backgrounds. Then, we used mainstream object detection methods to build a benchmark, providing reference for insulator detection. In addition, to address the problem of detection inefficiency caused by large model parameters, an improved YoloV4 is proposed, named YoloV4++. It uses a lightweight network, i.e., MobileNetv1, as the backbone, and employs the depthwise separable convolution to replace the standard convolution. Meanwhile, the focal loss is implemented in the loss function to solve the impact of sample imbalance. The experimental results show the effectiveness of YoloV4++. The mAP and FPS can reach 94.24% and 53.82 FPS, respectively.

The accuracy with which a neural network interprets a point cloud depends on the quality of the features expressed by the network. Addressing this issue, we propose a multi-level feature extraction layer (MFEL) which collects local contextual feature and global information by modeling point clouds at different levels. The MFEL is mainly composed of three independent modules, including the aggregated GAPLayer, the spatial position perceptron, and the RBFLayer, which learn point cloud features from three different scales. The aggregated GAPLayer aggregates the geometry features of neighboring points in a local coordinate system to centroid by graph convolution. Then, the spatial position perceptron independently learns the position features of each point in the world coordinate system. Finally, the RBFLayer aggregates points into pointsets according to the correlation between features, and extracts features from the pointset scale through the quantization layer. Based on the MFEL, an end-to-end classification and segmentation network, namely the MFNet and MFNet-S, is proposed. In the proposed network, the channel-attention mechanism is employed to better aggregate multi-level features. We conduct classification and semantic segmentation experiments on four standard datasets. The results show that the proposed method outperforms the compared methods on the multiple datasets, resulting in 93.1% classification accuracy in ModelNet40. Furthermore, the mIoU of part semantic segmentation in ShapeNet is 85.4%, and the mIoU for semantic segmentation in S3DIS and Semantic3D is 62.9% and 71.9%, respectively.

Voltage sag is one of the most common power quality disturbance in industry, which causes huge inrush current and inrush torque of induction motors, and has serious impacts on the safe and stable operation of induction motor. To further study the detailed transient characteristics of induction motors during sag events, an improved 2-D multi-slice field-circuit-motion coupling time-stepping finite element method (FEM) is proposed. Then, taking a 5.5 kW, a 55 kW and a 135 kW induction motors as examples, the influence of phase-angle jumps and initial point-on-wave on the stator current peak, torque peak, speed loss and critical clearing time of the induction motor are discussed by using the proposed model. The simulation results show that stator current peak and torque peak increase obviously, while speed and critical clearing time decrease apparently, when considering the phase angle jump. And different initial points have little influence on these operation indicators. Finally, the proposed method is verified by comparing the measured and calculation data of the 5.5 kW three-phase squirrel-cage motor, respectively. The results show that the proposed method can reach higher precision with considering nonlinear characteristics.

In recent years, garbage classification has become a hot topic in China, and legislation on garbage classification has been proposed. Proper garbage classification and improving the recycling rate of garbage can protect the environment and save resources. In order to effectively achieve garbage classification, a lightweight garbage object detection model based on deep learning techniques was designed and developed in this study, which can locate and classify garbage objects in real-time using embedded devices. Focusing on the problems of low accuracy and poor real-time performances in garbage classification, we proposed a lightweight garbage object detection model, YOLOG (YOLO for garbage detection), which is based on accurate local receptive field dilation and can run on embedded devices at high speed and with high performance. YOLOG improves on YOLOv4 in three key ways, including the design of DCSPResNet with accurate local receptive field expansion based on dilated–deformable convolution, network structure simplification, and the use of new activation functions. We collected the domestic garbage image dataset, then trained and tested the model on it. Finally, in order to compare the performance difference between YOLOG and existing state-of-the-art algorithms, we conducted comparison experiments using a uniform data set training model. The experimental results showed that YOLOG achieved AP0.5 of 94.58% and computation of 6.05 Gflops, thus outperformed YOLOv3, YOLOv4, YOLOv4-Tiny, and YOLOv5s in terms of comprehensive performance indicators. The network proposed in this paper can detect domestic garbage accurately and rapidly, provide a foundation for future academic research and engineering applications.

Large-scale 3D point clouds are rich in geometric shape and scale information but they are also scattered, disordered and unevenly distributed. These characteristics lead to difficulties in learning point cloud semantic segmentations. Although many works have performed well in this task, most of them lack research on spatial information, which limits the ability to learn and understand the complex geometric structure of point cloud scenes. To this end, we propose the multispatial information and dual adaptive (MSIDA) module, which consists of a multispatial information encoding (MSI) block and dual adaptive (DA) blocks. The MSI block transforms the information of the relative position of each centre point and its neighbouring points into a cylindrical coordinate system and spherical coordinate system. Then the spatial information among the points can be re-represented and encoded. The DA blocks include a Coordinate System Attention Pooling Fusion (CSAPF) block and a Local Aggregated Feature Attention (LAFA) block. The CSAPF block weights and fuses the local features in the three coordinate systems to further learn local features, while the LAFA block weights the local aggregated features in the three coordinate systems to better understand the scene in the local region. To test the performance of the proposed method, we conducted experiments on the S3DIS, Semantic3D and SemanticKITTI datasets and compared the proposed method with other networks. The proposed method achieved 73%, 77.8% and 59.8% mean Intersection over Union (mIoU) on the S3DIS, Semantic3D and SemanticKITTI datasets, respectively.

To investigate the seismic performance of underground structures under the action of the structure-soil interface, in this study, experiments were performed using plexiglass structures (two pieces) and a concrete structure (one piece) as the research objects. The surface of one plexiglass structure was prepainted with a layer of cement mortar as the contact surface between the structure and soil, and the other plexiglass structure was not treated and used for comparison. A rigid model box measuring 2.25 m × 2.25 m × 1.5 m was placed on a 3 m × 3 m shaking table, and the box was filled with the configured model soil and the underground structure prepared in advance. Input transverse uniform excitation was imparted to the whole system. A shaking table model test was performed on the underground structures to analyse the acceleration response, stress strain, and earth pressure changes in the underground structure, and the influence of the contact surface on the seismic dynamics of the underground structure was evaluated. The test results showed that under uniform excitation, the dynamic characteristics of the underground structures were greatly affected by the intensity and depth of the seismic waves. (1) When the soil-structure contact was considered, the stress and strain of the structures increased significantly, and the stress-strain value was significantly greater than the stress-strain value of the soil-structure interface in a fully bonded state. (2) There were inconsistencies between the acceleration peak curve of the plexiglass structure considering the contact effect and the acceleration peak curve of the plexiglass structure without considering the contact effect. The difference between the two lies mainly in the corresponding maximum peak acceleration and the Fourier spectrum amplitude. With respect to the value and frequency composition, regardless of whether the input acceleration intensity was 0.2 g or 0.5 g, the peak acceleration of the organic structure was greater when the contact surface effect was considered than without the contact surface effect. Therefore, the structure-soil interface needs to be considered in actual engineering. The presence of the contact surface improves the safety of the structure and is helpful for seismic design. The results of this study provide a basis for further research on the influence of soil-pipe contact on the seismic response of underground structures.

Intelligent drones or flying robots play a significant role in serving our society in applications such as rescue, inspection, agriculture, etc. Understanding the scene of the surroundings is an essential capability for further autonomous tasks. Intuitively, knowing the self-location of the UAV and creating a semantic 3D map is significant for fully autonomous tasks. However, integrating simultaneous localization, 3D reconstruction, and semantic segmentation together is a huge challenge for power-limited systems such as UAVs. To address this, we propose a real-time semantic mapping system that can help a power-limited UAV system to understand its location and surroundings. The proposed approach includes a modified visual SLAM with the direct method to accelerate the computationally intensive feature matching process and a real-time semantic segmentation module at the back end. The semantic module runs a lightweight network, BiSeNetV2, and performs segmentation only at key frames from the front-end SLAM task. Considering fast navigation and the on-board memory resources, we provide a real-time dense-map-building module to generate an OctoMap with the segmented semantic map. The proposed system is verified in real-time experiments on a UAV platform with a Jetson TX2 as the computation unit. A frame rate of around 12 Hz, with a semantic segmentation accuracy of around 89% demonstrates that our proposed system is computationally efficient while providing sufficient information for fully autonomous tasks such as rescue, inspection, etc.

The point clouds scanned by lidar are generally sparse, which can result in fewer sampling points of objects. To perform precise and effective 3D object detection, it is necessary to improve the feature representation ability to extract more feature information of the object points. Therefore, we propose an adaptive feature enhanced 3D object detection network based on point clouds (AFE-RCNN). AFE-RCNN is a point-voxel integrated network. We first voxelize the raw point clouds and obtain the voxel features through the 3D voxel convolutional neural network. Then, the 3D feature vectors are projected to the 2D bird’s eye view (BEV), and the relationship between the features in both spatial dimension and channel dimension is learned by the proposed residual of dual attention proposal generation module. The high-quality 3D box proposals are generated based on the BEV features and anchor-based approach. Next, we sample key points from raw point clouds to summarize the information of the voxel features, and obtain the key point features by the multi-scale feature extraction module based on adaptive feature adjustment. The neighboring contextual information is integrated into each key point through this module, and the robustness of feature processing is also guaranteed. Lastly, we aggregate the features of the BEV, voxels, and point clouds as the key point features that are used for proposal refinement. In addition, to ensure the correlation among the vertices of the bounding box, we propose a refinement loss function module with vertex associativity. Our AFE-RCNN exhibits comparable performance on the KITTI dataset and Waymo open dataset to state-of-the-art methods. On the KITTI 3D detection benchmark, for the moderate difficulty level of the car and the cyclist classes, the 3D detection mean average precisions of AFE-RCNN can reach 81.53% and 67.50%, respectively.

In China’s hot summer and cold winter zone, there are cold and humid in winter. If there is no heating measure, the human body will feel less comfortable in the cold environment. The traditional HVAC system consumes a lot of energy, and it is difficult to meet the thermal comfort needs of everyone. By creating a local thermal environment around the human body, the personalized heating system can significantly improve the thermal comfort level of the human body with lower energy consumption. In this paper, it is mainly analyzing the heating effect of the heating panel on the legs of the human body by theoretically analyzing the indoor temperature of 12 °C in the hot summer and cold winter zone. For the following two working conditions: the heating panel is placed vertically on the side of the human leg and the heating panel is placed horizontally under the feet. It is calculated that when the human body feels comfortable, the heat loss is about 45 W/m2∼50 W/m2. The conclusions are as follows: (1) When the heating panel is placed vertically on the side of the human leg, the thermal comfort needs are only met when the heating panel temperature is 70 °C and the distance between the heating panel and the leg is 5 cm or 10 cm. (2) When the heating panel is placed horizontally under the feet and the temperature of the heating panel is 70 °C, the local heat loss of the human body is less than 45W/m2, and the human body feels slightly warmer.

This paper introduces the structural characteristics of a 6-D force sensor based on an E-type membrane, analyzes the calibration results of each bridge, and determines the coupling relationship between bridges of a sensor. In the case that a sensor has no fault in its bridges, a decoupling matrix is calculated by identifying a linear decoupling model. In the case that the fault happens, a linear neural network method is used to discard the faulty bridge to calculate the reduced-dimensional decoupling matrix, and the BP neural network nonlinear method is used to compensate the faulty bridge signal for fault-tolerant decoupling. Simulation results indicate that the reliability of the sensor under the fault condition has been significantly improved.

Point cloud classification is a key technology for point cloud applications and point cloud feature extraction is a key step towards achieving point cloud classification. Although there are many point cloud feature extraction and classification methods, and the acquisition of colored point cloud data has become easier in recent years, most point cloud processing algorithms do not consider the color information associated with the point cloud or do not make full use of the color information. Therefore, we propose a voxel-based local feature descriptor according to the voxel-based local binary pattern (VLBP) and fuses point cloud RGB information and geometric structure features using a random forest classifier to build a color point cloud classification algorithm. The proposed algorithm voxelizes the point cloud; divides the neighborhood of the center point into cubes (i.e., multiple adjacent sub-voxels); compares the gray information of the voxel center and adjacent sub-voxels; performs voxel global thresholding to convert it into a binary code; and uses a local difference sign–magnitude transform (LDSMT) to decompose the local difference of an entire voxel into two complementary components of sign and magnitude. Then, the VLBP feature of each point is extracted. To obtain more structural information about the point cloud, the proposed method extracts the normal vector of each point and the corresponding fast point feature histogram (FPFH) based on the normal vector. Finally, the geometric mechanism features (normal vector and FPFH) and color features (RGB and VLBP features) of the point cloud are fused, and a random forest classifier is used to classify the color laser point cloud. The experimental results show that the proposed algorithm can achieve effective point cloud classification for point cloud data from different indoor and outdoor scenes, and the proposed VLBP features can improve the accuracy of point cloud classification.

In power inspection tasks, the insulator and spacer are important inspection objects. UAV (unmanned aerial vehicle) power inspection is becoming more and more popular. However, due to the limited computing resources carried by a UAV, a lighter model with small model size, high detection accuracy, and fast detection speed is needed to achieve online detection. In order to realize the online detection of power inspection objects, we propose an improved SSD (single shot multibox detector) insulator and spacer detection algorithm using the power inspection images collected by a UAV. In the proposed algorithm, the lightweight network MnasNet is used as the feature extraction network to generate feature maps. Then, two multiscale feature fusion methods are used to fuse multiple feature maps. Lastly, a power inspection object dataset containing insulators and spacers based on aerial images is built, and the performance of the proposed algorithm is tested on real aerial images and videos. Experimental results show that the proposed algorithm can efficiently detect insulators and spacers. Compared with existing algorithms, the proposed algorithm has the advantages of small model size and fast detection speed. The detection accuracy can achieve 93.8%. The detection time of a single image on TX2 (NVIDIA Jetson TX2) is 154 ms and the capture rate on TX2 is 8.27 fps, which allows realizing online detection.

Abstract: Along with China′s economic development, the dissolution of heavy metals in port minerals stockyard has became important contamination sources of soil and water, which can't be ignored. The amount of heavy metal dissolution is related to the species of heavy metals. Through the static soaking test, according to the leaching of heavy metals to determine the typical mineral products and the typical heavy metal factor to study the influence of time, pH and temperature on release of heavy metals in typical products at Tianjin port stockyard. The results showed that the amounts of heavy metals released from lead ore and copper ore were the greatest. Zn, Pb and Cd in the lead ore and Ni in the copper ore were the typical heavy metal factor, and were found to be 1-3 orders of magnitude higher than other heavy metal ions. The concentration of Zn, Pb, and Cd in lead ore increased with time, and the concentration of Ni in the copper ore basically remained stable. The concentration of Zn, Pb and Cd in the lead ore and Ni in the copper ore had no significant differences with the change of pH (3.5 to 7.5). The concentration of Zn, Pb, and Cd in the lead ore increased with temperature (20-40℃). The concentration of Ni in the copper ore showed a downward trend above 30℃. This study preliminarily investigated the basic rule of dissolution of heavy metals in minerals and provides data to support and control the dissolution of heavy metals in the port stockyard.

An improved hybrid homotopy method is proposed to decouple the multi-input model of tactile sensors. The time-embedded homotopy algorithm is proved to be very suitable for solving the problem. Three tracking factors that control the efficiency of the algorithm are studied: tracking operator, stepsize, and accuracy. Trust region methods are applied to track the zero paths instead of the traditional differential algorithm, and a periodic sampling method is proposed to improve the efficiency of the algorithm. Numerical experiments show that both the robustness and accuracy have received a huge boost after the hybrid algorithm is applied.

PurposeA comprehensive review of the literature in order to analyze data about the success rate of percutaneous resolution of the lumbar facet joint cysts as a conservative management strategy.MethodsA systematic search for relevant articles published during 1980 to May 2014 was performed in several electronic databases by using the specific MeSH terms and keywords. Most relevant data was captured and pooled for the meta-analysis to achieve overall effect size of treatment along with 95% confidence intervals.Results29 studies were included in the meta-analysis. Follow-up duration as mean ± sd (range) was 16±10.2 (5 days to 5.7 years). Overall the satisfactory results (after short- or long-term follow-up) were achieved in 55.8 [49.5, 62.08] % (pooled mean and 95% CI) of the 544 patients subjected to percutaneous lumbar facet joint cyst resolution procedures. 38.67 [33.3, 43.95] % of this population underwent surgery subsequently to achieve durable relief. There existed no linear relationship between the increasing average duration of follow-up period of individual studies and percent satisfaction from the percutaneous resolutions procedure.ConclusionResults shows that the percutaneous cyst resolution procedures have potential to be an alternative to surgical interventions but identification of suitable subjects requires further research.

The semantic correlation is a very important research direction in Natural Language Processing, and the semantic relatedness is different from the semantic similarity . At present, the semantic correlation algorithm, which is based on the similarity of the semantic meaning, and it can’t achieve the desired results in a certain extent. In this paper, byusing the large-scale corpus and How Net words’ concepts to dig out the hidden semantic relations between the words, finally, according to the semantic relations of the words in the text, the text correlation algorithm is proposed . Experimental results show that the use of How Net calculation of the text relevance which use less time than the use of large-scale corpus and Tongyici Cilin calculation of the text relevance, and in terms of accuracy of the calculation results also have to upgrade.