Search

In order to solve the problems of loss of moving targets due to the flight status of the unmanned aerial vehicle (UAV) itself, the interference of the environment the randomness of the target and other reasons in the process of collecting moving target image information by the UAV platform, a deep deterministic policy gradient (DDPG) algorithm UAV following method based on moving target recognition was proposed. Facing the vehicle target on the highway, the relationship among the height, posture and high-speed vehicle motion of the UAV was analyzed. the velocity adaptive model of the target detection frame rate of the mobile platform was estab lished, and the flight attitude and speed of the UAV were corrected in real time according to the motion state of the target, so that the UAV could maintain the relative position and angle with the target. Then, based on the value network of DDPG algorithm, the value of UAV taking spe- cific actions in different states was estimated; the strategy network generates the strategy of UAV taking actions in a given state, and gives UAV flight altitude and speed control parameters for target tracking, so that the UAV could automatically adjust the flight state according to the movement change of the target, and realize the adaptive tracking of the moving target. Simulation experiments show that the DDPG algorithm can provide stable flight attitude data and a reliable control basis for the UAV following task, and the UAV can track the ground moving target in a circular area with a speed range of 0~33 m/s and a radius of 120 m in real time, and can achieve continuous and stable tracking within the endurance range. [ABSTRACT FROM AUTHOR]

The object detection based on video has the problem of poor recognition effect in bad weather, so it is necessary to make up for video defects and improve the robustness of detection framework. In view of this problem, this study designs an object detection framework based on radar and video fusion. YOLOv5 (You Only Look Once version 5) network is used to obtain image feature map and image detection frame, density-based clustering is used to obtain radar detection frame, and radar data is encoded to get object detection results based on radar information. Finally, the detection boxes of the two are superimposed to obtain a new ROI (Region of Interest), and the classification vector after fusion radar information is obtained, which improves the detection accuracy in extreme weather. The experimental results show that the mAP(mean Average Precision) of the framework reaches 60.07%, and the parameter number is only 7.64 x 10°, which indicates that the framework has the characteristics of lightweight, fast computing speed and high robustness, and can be widely used in embedded and mobile platforms. [ABSTRACT FROM AUTHOR]

The hub motor-driven mobile platform has gradually replaced the traditional centralized electric drive system. There is ever-increasing demand for flowers, fruits, vegetables, and tea horticulture for the new energy-powered operating equipment, particularly with high efficiency, energy saving, compact structure, independent and controllable advantages. Compared with direct-drive hub motors, the geared hub motors have been the mainstream of the drive unit for facility horticulture, due to the higher overload and torque output. The operational requirements of large load and torque can be fully met in the operation scenarios of facility horticulture. However, the geared hub motors are limited to the size of the space inside the hub. The high heat generation has seriously restricted the operational performance of electric drive mobile platforms. In this study, a decelerated inner-rotor axial flux hub motor was designed to meet the requirements of the low-speed and high-torque traction for electric-driven mobile platforms in facility horticulture operation scenarios. The electromagnetic finite element (FE) model was established to analyze the electromagnetic and loss features of the hub motor. Moreover, an improved magnetic-thermal coupling FE model of the hub motor was also constructed using the thermal network. The effect of temperature on the winding resistivity was considered to reduce the prediction accuracy of the simulation model, compared with the conventional magnetic-thermal bidirectional model. The prediction accuracy of the torque was improved by 5.33% using the improved model, compared with the bench tests. The correctness of the model was verified using the magnetic-thermal coupling FE model. A systematic investigation was made on the influence of the temperature and phase current on the torque of the motor. The experiments were also conducted on the external efficiency of the hub motor under peak operating conditions. The simulation results reveal that the average output torque of the motor decreased, as the steady-state temperature increased. The prediction value of torque was deviated by less than 1.56% from the measured at the motor speed of 800 r/min. The output torque of the motor also decreased with increasing motor temperature. The output torque of 15.23 N·m was reduced by 7.66% at the current of 32 A, compared with the conventional. The experimental results demonstrate that the power of the hub motor increased with the increase of the rotational speed in the middle and low-speed ranges. The peak power was up to 4.59 kW, while the torque almost remained constant. The output torque also decreased with the increase of motor temperature. The average output torque of the motor was linearly related to the phase current in the range of 0 to 20 A. The efficiency of the motor was up to 93.2% in the middle speed range with the torques in the range of 300 to 600 N·m. This finding can provide a direct guideline for the structural design of hub motors and the magnetic-thermal multi-physical field coupling performance analysis. [ABSTRACT FROM AUTHOR]

In order to develop the target object mobile platform for vehicle Automatic Emergency Braking (AEB) system test, this article studied the configuration design, strength analysis, fatigue life estimation and path tracking of test scene. Through the analysis of the test scenarios stipulated in C-NCAP Management Regulation (2024 Edition), the moving path of the target was extracted, and the expected trajectory was obtained according to the boundary conditions, then the trajectory tracking results were obtained through dynamic simulation. The comparison shows that the simulation results are basically consistent with the specified requirements, indicating that the designed mobile platform can meet the needs of AEB testing. [ABSTRACT FROM AUTHOR]

[Objective] Syntheticaperture radar (SAR) is an active observation technology distinguished by its all-time and all-weather monitoring capability. Consequently, SAR systems offer distinctive advantages in disaster monitoring, environmental surveillance, and mapping applications. However, given the intricacies of the SAR system, data acquisition is confined to mobile platforms, such as aircraftand satellites. This limitation poses challenges to the teaching of the SAR course as it requires hands-on experiments. To address this issue, an experimental platform for the virtual simulation of SAR high-resolution imaging was designed and developed. [Methods] This platform includes an experimental business, application presentation, logic control, and data analysis layers. The experimental business layer includes three modules: System design and data acquisition, signal processing, and evaluation and application. Each module includes 2--4 submodules. The progressive design according to the actual field experiment process of the SAR can restore the experimental design, equipment operation, data processing, and other processes. The application presentation layer provides students with an immersive experience and guarantees ateaching effect. The logic control layer provides convenience for human--computer interaction and enhances students' sense of participation in the experiment. The data analysis layer can analyze and reproduce experimental problems to consolidate basic knowledge. The virtual simulation experiment comprises system design, experiment planning, data acquisition, signal processing, and image evaluation. Through computer simulation, the entire SAR experiment is simulated with high display, fidelity, and interaction. At each simulation stage, students can emulate the characteristics of the simulation experiment, including high model reproducibility, repeatability, ease of interaction, and safety. In the system design and experiment planning stage, students can intuitively and swiftly adjust the installation position of system components and arrange the experiment scenes. In the signal processing stage, students can exercise control over the simulation process through modular programming on the simulation platform. In the evaluation stage, students can visually assess the experimental results using the built-in graphical programming of the simulation platform. Notably, a comprehensive process analysis and feedback mechanism have been devised to assist students in accurately identifying their shortcomings and promptly rectifying them. [Results] The outcomes of this experimental platform are outlined as follows: 1 The realistic simulation of the actual scene of the experiment is performed to deepen students' understanding of the basic knowledge of the SAR system. Concurrently, the mechanisms of step prompt, after-class feedback, and evaluation are established to help students understand their shortcomings and make improvements in a timely fashion. 2 The operation, design, and processing of the actual experiments are reproduced, providing students with opportunities to practice and explore that are not easily accessible in reality, helping students learn SAR technology and improve their professional and technical abilities. 3 The teaching method combining simulation and practical operation is established. This open experimental design can improve students' innovation ability and comprehension quality. [Conclusions] The platform has completed several rounds of service teaching and is open to the public online. After background information sorting and course feedback, the platform has been unanimously praised, which can significantly improve students' theoretical learning ability, innovation ability, and exploration consciousness. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Machine Tool & Hydraulics is the property of Guangzhou Mechanical Engineering Research Institute (GMERI) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of South China University of Technology (Natural Science Edition) is the property of South China University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to overcome the influence of shallow seas, low headroom and existing bridge structure on the construction of jet grouting piles, the construction technology of mobile working platform + jet grouting with connecting rods at sea was studied and put into practical application, based on the contraction practice of the East Artificial Island of Shenzhen-Zhongshan Link. Engineering practice shows that: 1) the construction technology of mobile working platform + jet grouting with connecting rods effectively solves the technical problems in jet grouting pile construction at sea and the working platform has a wider applicable range; 2) the dynamic speed control system based on theoretical calculation formulae can better ensure the quality of jet grouting pile construction, and the deviation rate of cement dosage is only 2.4% ; 3) the impact of the construction process on the existing bridge structure is mainly manifested in horizontal displacement in the down-bridge direction and the deformation value fluctuates in the range of -1.3 ~1.7 mm, which meets the high requirements for deformation control of extremely sensitive buildings (structures). [ABSTRACT FROM AUTHOR]

Copyright of Railway Construction Technology is the property of Railway Construction Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Power Generation Technology is the property of Power Generation Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Atomic Energy Science & Technology is the property of Editorial Board of Atomic Energy Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Experimental Technology & Management is the property of Experimental Technology & Management Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Henan University of Science & Technology, Natural Science is the property of Editorial Office of Journal of Henan University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Railway Science & Engineering is the property of Journal of Railway Science & Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Guangdong Architecture Civil Engineering is the property of Guangdong Architecture Civil Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Experimental Technology & Management is the property of Experimental Technology & Management Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Hydrographic Surveying & Charting / Haiyang Cehui is the property of Hydrographic Surveying & Charting Editorial Board and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Coal Science & Technology (0253-2336) is the property of Coal Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Stereo cultivation is usually used in plant factories for seedling and cultivation. Transportation of cultivation bed is an important part of the stereo cultivation automation. At present, cultivation bed is mostly handled manually, which has problems such as high labor intensity and low level of automation. To solve this problem, a multifunctional operation platform, which had the functions of autonomous tracking, automatic positioning, and automatic conveying of cultivation bed, was developed in this paper. The multifunctional operation platform mainly consists of navigation system, positioning system, communication system, walking system, lifting system, automatic docking system, and automatic conveying system. The working principle and technical parameters of the multifunctional work platform were introduced. During operation, the cultivation bed was transported from nursery workshop to greenhouse by the multifunctional operation platform firstly. Then， the multifunctional operation platform reached the target stereo cultivation rack through the road reserved in greenhouse and lifted the cultivation bed to the target height. The automatic conveying mechanism started to push cultivation bed to stereo cultivation rack by automatic docking mechanism. The cultivation bed was transported to stereo cultivation rack when the proximity switch installed on stereo cultivation rack detected the cultivation bed. Finally, the multifunctional operation platform stopped working and go back to the charger area. When the crops were mature, the multifunctional operation platform would automatically transport the cultivation bed to the picking area, so as the logistics automation of the crop production process was realized by the multifunctional operation platform. To meet the requirements of multi-layer cultivation of stereo cultivation rack, the lifting mechanism was designed based on principle of virtual displacement according to the weight of the cultivation bed and the height of the stereo cultivation rack. Single hydraulic cylinder driving and two scissor lift mechanisms were chosen. The maximum driving force of the hydraulic cylinder was about 15 443.9 N through theoretical analysis. The length, stroke, outer diameter and inner diameter of the hydraulic cylinder were determined to 940, 360, 63, and 35 mm respectively. The automatic docking and automatic conveying mechanism of the cultivation bed were studied. The automatic docking was realized between the multifunctional operation platform and stereo cultivation rack by automatic docking mechanism, and two-way transportation of the cultivation bed was realized by automatic conveying mechanism. Thus, the automatic loading and unloading of the cultivation bed was realized. The positioning system based on the RFID (Radio Frequency Identification) sensor was determined. Walking system and the lifting mechanism of the working platform would stop working when the RFID sensor detected the electronic labels on the ground and stereo cultivation rack.STM32 was used as the main controller of the automatic control system. The software and hardware of the control system were designed. A human-machine interaction interface was designed based on the Android. It was to monitor the motion status and operating parameters of the multifunctional operation platform in real time. To evaluate the operation performance of the multifunctional operation platform, the experiments were conducted. The test indexes were the height range of the lifting mechanism, the front and rear positioning deviation, the height positioning deviation, and the success rate of the platform and the stereo cultivation frame docking. The experiment results show that the height range and effective lift height of the multifunctional mobile platform was 833-2 460 mm and 1 627 mm. The front and rear positioning deviation is less than 9 mm, average value was 4.5 mm. The height positioning deviation was less than 5 mm, average value was 3.7 mm. And the docking success rate was not less than 96%, which meet the requirements of the operation. This study provides a reference for further improving the automation level of stereo cultivation of plant factories. [ABSTRACT FROM AUTHOR]

Aiming at the environmental characteristics of the wind turbine blades including variable cross-sections, large slopes, and multiple obstacles, a crawler-type pipeline endoscope robot with a 4-DOF joint was designed for internal inspection and maintenance, and the kinematic characteristics of the proposed robot were analyzed herein. The robot included three parts: front/rear crawler-type mobile platform and a middle 4-DOF joint. The 4-DOF joint consisted of a 2-DOF cross joint commonly used in a snake robot, and forward/backward rotation module. Through the cooperation of the four motors reside, functional movements such as head-up, turning, multi-angle roiling and climbing might be reaped. Firstly, the basic structure, dynamic system and connecting mechanism of the 4- DOF joint were introduced. Then, the forward and inverse kinematics of the robot were solved based on the D-H method. The working space of the robot was then obtained, and the overall dynamic simulaton of the robot was carted out using CoppeliaSim. Finally, the robot was assembled according to the proposed design scheme, and the realization of various functional movements of the robot was verified through experiments. [ABSTRACT FROM AUTHOR]

Mobile platforms and autonomous vehicles have widely been used for agricultural specific tasks to reduce soil compaction and power consumption, as well as labor saving, compared with traditional large tractors and machinery. In this study, a kind of self-propelled mobile platform was designed for wheat seeding with high precision, high intensity, and strong repeatability in agricultural production. The CAN bus, synchronous multi-motor, and steering control mode were also adopted to implement the movement of mobile chassis in the longitudinal and horizontal directions, concurrently combining differential steering and electromotive push rod. Four control modules of the microcontroller unit (MCU) were designed to realize the communication and motion between platform devices, including serial communication, data acquisition, motion execution, and motor drive module. A four-wheel steering (4WS) fuzzy controller was also proposed using the Ackerman principle and the dynamic model. The total driving power and steering torque of mobile platforms were all evaluated to determine the type selection of servo motor and electromotive push rod. The velocity measurement of the global navigation satellite system (GNSS) and seeding depth control technique were utilized to implement the automatic precision seeding of wheat. The precision seeding was characterized by the use of an electric motor to replace the land wheel. The seeding rate was still controlled when travelling at a non-uniform speed. The travelling speed of the mobile platform was obtained as the input signal, while, the matched motor speed was then settled using GNSS high-precision positioning module. The rotation speed of the seed metering device was constantly readjusted to guarantee the uniformity of seeding. A field experiment was carried out, indicating that the GNSS precision seeding system was stable and reliable. Specifically, the uniform coefficient of variation between rows was not more than 1.8%, and the stability coefficient of seeding depth was not less than 89%. The drive control system presented high response sensitivity. The actual speed gradually approached the target speed after starting the servo motors for 2.6s. The speed synchronization errors tended to be relatively stable, indicating that the mobile platform performed strong anti-interference capability and speed consistency under the condition of loading. The steering control system implemented the wheel deflection, where the bogie frame was driven to rotate through the stroke change of the electromotive push rod. The test results demonstrated that the mean absolute error (MAE) of steering angle was less than 0.7°, indicating that the control accuracy met the expected. This finding can be used to promote the development of intelligent equipment for wheat precision seeding and meet the demand for medium and high-level machinery equipment for agricultural modernization. [ABSTRACT FROM AUTHOR]

Copyright of China Mechanical Engineering is the property of Editorial Board of China Mechanical Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

: Aiming at the problems existing in the current simple cryogenic micro-abrasive air jet machining experimental equipment, we develop a micro-channel special machine tool for cryogenic micro-abrasive air jet machining. The machine tool is mainly composed of a micro-abrasive air jet generating part, a cooling part, a machining part, an abrasive recovery part and a control system part. Firstly, the overall design of the machine tool is performed to ensure it has reasonable layout and stable structure. Secondly, the overall design, theoretical calculation and simulation analysis of the core component cooler of the machine tool are carried out, and the rationality of the design is verified by temperature measurement experiment. The PLC controller and liquid nitrogen level monitor are used to realize the automatic temperature control of the cooler. Finally, the four-dimensional mobile platform is designed and controlled through the human-machine interaction interface. The verification experiment shows that the machine tool can achieve effective erosion removal of polydimethylsiloxane（PDMS）at low temperature, and the processing effect is significantly better than that at room temperature, which can meet the diversified application requirements of microfluidic chips. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The increase of pheasants has posed a threaten to crops as the advancement of ecology. However, most conventional methods of bird repellent have inherent deficiencies in terms of efficiency and danger. An efficiency monitoring method for pheasant is necessary to combine with artificial intelligence, in order to provide early warning and expulsion of pheasants. Normally, pheasant activities are mostly in the early morning and dusk under complex environment with protective color or habit of hiding. This behavior has made monitoring methods much more challenge. In this paper, a novel recognition method for pheasant has been proposed on the deployment of embedded computing platform, combined with the enhanced Tiny-YOLOV3 target detection network, particularly on considering the behavior of pheasant and specific living conditions. A lightweight network is required to ensure the accuracy and real-time monitoring due to the deployment on a mobile platform in the field environment. A real-time monitoring network ET-YOLO has also been established for the emergence of pheasants in a complex field environment, according to the basic structure of the Tiny-YOLOV3 lightweight target detection network. The feature extraction can deepen the net depth of Tiny-YOLOV3, and thereby increase the detection scale to improve the detection accuracy of original net target. CenterNet structure was used in the net detection layer to further enhance the detection accuracy and speed. The dataset of pheasant monitoring was produced after augmentation using the field collection of images in various environments, including 6000 high resolution images of pheasant in different distances, angles and environments. The indicators of experimental evaluation were mainly tested in terms of accuracy, real-time performance, and model size. Specifically, the average detection accuracy, average detection speed, and detection model size of the pheasant were used for evaluation. The experimental results showed that the average detection accuracy of ET-YOLO in the complex field environment was 86.5%, and the average detection speed was 62 frames/s, 15% higher than that of initial Tiny-YOLOV3. The average detection accuracy was higher than that of YOLOV3, Faster-RCNN and SSD_MobileNetV2 by 1.5%, 1.1% and 18%, respectively. The average detection speed was 38 frames /s, 47 frames /s and 1 frame/s higher than that of YOLOV3, Faster-RCNN and SSD_MobileNetV2, respectively, when the detection model size of 56 MB. The proposed method can be suitable for the deployment on embedded computing platforms equipped with agricultural robots and intelligent machines in terms of recognition accuracy, real-time performance, and model size, particularly recognizing pheasants in complex environments. [ABSTRACT FROM AUTHOR]

Aiming at the texture synthesis in new computer graphics technical conditions, this paper proposed a texture interpolation method to synthesize different resolution textures adaptively from a single real world texture. The synthesized texture's DPI was the same as the original texture example. Firstly, the proposed method used a high-dimensional interpolation algorithm to generate an intermediate guidance texture with target resolution by split the source texture. Secondly, it selected particular random patches to fill the gaps in the intermediate texture according to the self-similarity in the source texture. Finally, it seamlessly embedded these patches in the previous intermediate texture by the Poisson image-editing algorithm. Experimental results show that the proposed method can handle both stationary and non-stationary texture synthesis, and the synthetic results are more consistent in the visual properties of the source texture. In addition, the implement logic of the proposed method is enough simple to be programing and executing on a common mobile platform. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Guangdong University of Technology is the property of Journal of Guangdong University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Systems Engineering & Electronics is the property of Journal of Systems Engineering & Electronics Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

An intelligent mobile teaching platfonn is designed to meet the teaching needs of intelligent vehicle technology, so that students can truly participate in the relevant design of intelligent vehicles. This platform integrates the simulation development platform and the real vehicle automatic driving system. It uses SolidWorks to model the vehicle model, uses V-rep to build the simulation environment, and communicates with ROS(Robot Operating System). On this basis, the platform was verified by the algorithm, the experimental results and analyses were obtained. Teaching practice shows that the intelligent mobile teaching platfonn promotes students'understanding and learning of intelligent vehicle technologies to a certain extent. The intelligent mobile teaching platform provides a new method for the teaching of intelligent vehicle technology, it not only makes up the shortcomings that the real cars are too big to be used for teaching, but also makes up the shortcomings that the virtual experiment scene is too idealized. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Guangdong University of Technology is the property of Journal of Guangdong University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Forensic Science & Technology is the property of Institute of Forensic Science, Ministry of Public Security and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Shenzhen University Humanities & Social Sciences is the property of Journal of Shenzhen University (Humanities & Social Sciences) Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Since August 17, 2012, Tencent launched the "WeChat public platform", WeChatextension became the platform of both medium of communication, social, and the comprehensive properties of the new "Mobile Instant Information Medium ." In the WeChat space is filled with a variety of spread risk, or even cause damage to the credibility of the government agency situation, "Government WeChat" as the situation. Government WeChat not only greatly pulled into the communication distance between the government and the people, but also to expand the innovative thinking and service performance web3.0 era of mobile government, and has worked in emergency management, public opinion guidance, and other areas of social mobilization played out strong social function, resulting in a positive and practical influence. However, with the removal of WeChat version 5.0 upgrade and media functions, Government WeChat selection and breakthrough dilemma facing major development. [ABSTRACT FROM AUTHOR]

There are two major trends of smart phones. The first is close architecture, i.e., the handset and the operating system are dependent, for example, iOS is only for iPhone. The second is open architecture, i.e., the handset and the operating system are independent, like Android can for handsets of many manufacturers. This study adopted the switching costs proposed by Burnham, Frels, and Mahajan1 and integrated them with the switching intention as the research model. We mainly explored mediation effects between the switching costs and customer loyalty via switching intention. The first research result is the relationship between the switching costs negatively to the conversion intention. Second, we assessed the influence of switching intention on customer loyalty. According to the research finding of this study, we proposed the deign recommendations for the smart phone solution providers with the relevant operators in the field. Finally, the management implication and future direction of this research is proposed. [ABSTRACT FROM AUTHOR]