Real-time Information Acquisition Research Articles

A Monitoring System for the Segmentation and Grading of Broccoli Head Based on Deep Learning and Neural Networks.

Achieving the non-contact and non-destructive observation of broccoli head is the key step to realize the acquisition of high-throughput phenotyping information of broccoli. However, the rapid segmentation and grading of broccoli head remains difficult in many parts of the world due to low equipment development level. In this paper, we combined an advanced computer vision technique with a deep learning architecture to allow the acquisition of real-time and accurate information about broccoli head. By constructing a private image dataset with 100s of broccoli-head images (acquired using a self-developed imaging system) under controlled conditions, a deep convolutional neural network named “Improved ResNet” was trained to extract the broccoli pixels from the background. Then, a yield estimation model was built based on the number of extracted pixels and the corresponding pixel weight value. Additionally, the Particle Swarm Optimization Algorithm (PSOA) and the Otsu method were applied to grade the quality of each broccoli head according to our new standard. The trained model achieved an Accuracy of 0.896 on the test set for broccoli head segmentation, demonstrating the feasibility of this approach. When testing the model on a set of images with different light intensities or with some noise, the model still achieved satisfactory results. Overall, our approach of training a deep learning model using low-cost imaging devices represents a means to improve broccoli breeding and vegetable trade.

Key technologies of 3D scene construction for remote assisted driving of intelligent ships

Objectives In order to realize the shore-based remote monitoring and management of the whole life cycle of intelligent ship navigation, this paper studies a virtual reality (VR)-based remote assisted driving support system for ships. Methods Through the real-time acquisition and fusion of ship situation information regarding navigation, and the dynamic and static target information of the ship, VR technology is used to reconstruct and present a navigation scene in way of omni-direction and multiple angle of view, a ship collision risk prediction model is established and the three-dimensional dynamic display of the navigation risk relationship between surrounding ships is created. Results The system can accurately display the real scene and state information of the ships during voyage, and provide a three-dimensional and multi-perspective look-out function. It not only provides comprehensive navigation information for ship pilots, but also achieves shore-based remote assistance driving support. Conclusions The results of this study can provide technical support and guarantees for the construction of integrated ship-shore intelligent systems.

Edge and Cloud Collaborative Entity Recommendation Method towards the IoT Search.

There are massive entities with strong denaturation of state in the physical world, and users have urgent needs for real-time and intelligent acquisition of entity information, thus recommendation technologies that can actively provide instant and precise entity state information come into being. Existing IoT data recommendation methods ignore the characteristics of IoT data and user search behavior; thus the recommendation performances are relatively limited. Considering the time-varying characteristics of the IoT entity state and the characteristics of user search behavior, an edge-cloud collaborative entity recommendation method is proposed via combining the advantages of edge computing and cloud computing. First, an entity recommendation system architecture based on the collaboration between edge and cloud is designed. Then, an entity identification method suitable for edge is presented, which takes into account the feature information of entities and carries out effective entity identification based on the deep clustering model, so as to improve the real-time and accuracy of entity state information search. Furthermore, an interest group division method applied in cloud is devised, which fully considers user’s potential search needs and divides user interest groups based on clustering model for enhancing the quality of recommendation system. Simulation results demonstrate that the proposed recommendation method can effectively improve the real-time and accuracy performance of entity recommendation in comparison with traditional methods.

Channel Compression Optimization Oriented Bus Passenger Object Detection

Bus passenger flow information can facilitate scientific dispatching plans, which is essential to decision making and operation performance evaluation. Real-time acquisition of bus passenger flow information is an indispensable part for bus intellectualization. The method of passenger flow statistics in bus video monitoring scene based on deep convolution neural network can provide rich information for passenger flow statistics. In order to adapt to the real scenario of mobile and embedded devices on buses, and to consider the bandwidth limitation, this paper uses a lightweight network model M7, which is suitable for the vehicle system. Based on the classic network model tiny YOLO, the model is optimized by a depthwise separable convolution method. The optimized network model M7 reduces the number of parameters and improves the detection speed, while maintaining a low loss in detection accuracy. As such, the network model M7 is compressed and further optimized by removing redundant channels. The experimental results show that the detection speed of the network model target recognition after channel compression is 40%, which is faster than the precious channel compression on the premise of ensuring detection.

Research on integrated operation and maintenance acquisition and monitoring technology for new generation dispatching control system

Focusing on the intelligence demands of operation and maintenance for the new generation dispatching control system and the technical requirements of pre-monitoring, early warning and fault handling in the event, based on the architecture with the characteristics of physical distribution and logical integration, this paper designs a kind of integrated operation and maintenance acquisition and monitoring method. It first builds the full model of the automation equipment operation information, collects and summarizes the operation information such as resource pool, platform status, database, application and multi-activity consistency and data consistency, then achieves real-time data acquisition of various key indicators information for the operation of the new generation of control systems; Through the wide-area system service bus, the system operation information is gathered into the integrated operation and maintenance center to realize panoramic monitoring of the operation status for the multi-activity analysis decision center, the dual-active model data center and the dual-active monitoring system, and to comprehensively improve the intelligent level of operation and maintenance for the new generation dispatching control system.

Object spatial localization by fusing 3D point clouds and instance segmentation

Real-time detection and acquisition of localization information of instance targets in real three-dimensional space plays an important role in application scenarios such as virtual reality simulation and digital twinning. The existing spatial localization methods without the aid of lidar and other equipment often have problems in restoring the real scale. In order to overcome this problem and achieve more accurate object spatial localization, an object spatial localization by fusing 3D point clouds and instance segmentation is proposed. This method obtains sparse 3D point cloud data by binocular stereo matching, which is used to describe the real scale and spatial location information of the object. Then uses deep learning method to perform monocular instance segmentation on the specific category target of interest, and the segmentation result is used as the front/background prior information to complete the coordinate correction and densification of the 3D point cloud data inside and outside the object contour. Compared with the unsupervised depth estimation methods based on deep learning, our method can quickly and accurately achieve the three-dimensional precise localization of the instance target and its various components in real-world scenes, and the accuracy in the indoor scene is more than 90%.

Development of Welding Multi-Information Remote Wireless Monitoring System Based on STM32

A single sensor is used to obtain welding information in welding monitoring process, but this method has some shortcomings. In order to obtain more comprehensive and reliable welding information, this paper designed and built a welding multi-information wireless monitoring system with STM32-F407ZET6 as the control core and ALK8266 as the wireless transmission module. Real-time acquisition, transmission and display of electric arc signal and welding image information are realized in the monitoring system. This paper mainly introduces the hardware and software core of the monitoring system. At the same time, the signal collected by the monitoring system is compared with the original signal, and the accuracy of the remote monitoring system is tested. The monitoring system is used in welding test. The test results show that the accuracy of the monitoring system meets the requirements, and the on-line monitoring of electric arc signal and welding image can be realized in the welding process.

Incomplete Road Information Imputation Using Parallel Interpolation to Enhance the Safety of Autonomous Driving

Autonomous driving is the main application of Internet of Things (IoT) technology in the field of intelligent transportation. In autonomous driving, self-driving cars will avoid changing lanes in a short distance. When the self-driving car executes the follow-up instruction, the road smoothness in front of the car will affect the driving safety and comfort of the car. The real-time acquisition of road information in front of driving will help the self-driving car adjust driving behavior. However, other vehicles on the road will lead to the failure of Light Detection And Ranging (LiDAR) detectors to obtain complete road point cloud data. The incomplete road point cloud data need to be imputated to avoid potential misjudgements of the road conditions. Currently, little research work specifically focuses on imputating the incomplete road point cloud data that are caused by obstacle vehicles. In this paper, we propose a fast method to imputate the incomplete road point cloud data using a Graphics Processing Unit (GPU)-based parallel Inverse Distance Weighted (IDW) interpolation algorithm to enhance the safety of autonomous driving. To evaluate the performance of the proposed method, two groups of experiments are conducted. The experimental results indicate the following: (1) the known point cloud data within 5 meters around the obstacle vehicle are sufficient to guarantee the imputation accuracy; (2) when the weight parameter of the IDW interpolation is 4, the efficiency and accuracy of the imputation can be optimally balanced; and (3) it takes approximately 0.6 seconds to imputate the incomplete dataset consisting of 15 million points, while the imputation error is approximately 5 millimeters. The proposed method is capable of efficiently and effectively imputating the incomplete road point cloud data that are induced by obstacle vehicles and outperforms other interpolation algorithms and machine learning algorithms.

集成成像3D信息获取技术

As a novel auto-stereoscopic three-dimensional (3D) display technology, integral imaging is able to acquire complete 3D information of the 3D scene and reconstruct it. Thus, integral imaging is one of the most promising technologies of the glasses-free 3D displays. In the integral imaging 3D information acquisition process, different perspectives of the 3D scene are recorded to generate the elemental image array to be the 3D content for the integral imaging display. On the other hand, the integral imaging 3D acquisition can be a multi-dimensional information pickup approach applied to the detection and imaging of occluded scenes, target recognition, two-dimensional (2D) / 3D information encryption and microscopic 3D imaging fields. The basic principles, different types of the integral imaging 3D information acquisition approaches, and real-time 3D information acquisition technologies were reviewed in this paper. Some challenging problems and future development trend of the technology were also discussed.

RETRACTED ARTICLE: Data transmission and real-time information acquisition based on fine-grained algorithm and wireless network

With the advent of the 5G era, wireless network data transmission and real-time information acquisition face certain technical challenges. Simultaneously, how to ensure fast and safe information transmission becomes the research topic of the information age. The improvement of this research is based on the traditional fine-grained algorithm, and this study uses spatial constraints and evaluation scores to obtain the bounding box positions of objects and objects. Simultaneously, Part-based R-CNN is used to extract convolution features for each filtered bounding box and join the local features to form a feature representation vector. In addition, the research is based on the application of high-resolution acquisition of information entropy, abnormal signal detection and transient signal measurement methods and techniques in typical time domain test instruments, that is, digital oscilloscope, and this study is experimentally verified. The research indicates that the method proposed in this paper is scientific and can provide theoretical reference for subsequent related research.

Research and Exploration on the Practice Teaching Model of IOT Specialty—Taking the Practical Teaching Model of IOT Engineering Specialty of Shandong Agricultural University as an Example

Shandong Agricultural University attaches great importance to the cultivation of innovative practical ability of Engineering students. Combining with the orientation of the University and its own characteristics, Shandong Agricultural University has found a more distinctive way to cultivate students in the engineering practice teaching of Internet of Things specialty, and has formed an effective practical teaching mode of Internet of Things specialty. This mode can enhance the engineering of Internet of Things specialty students’ Practical ability, as well as improving students' ability to apply what they have learned, and has a good effect in promoting students' ability to combine theory with practice. The Internet of Things (IOT) refers to a huge network formed by real-time acquisition of various information about objects or processes through various information sensing devices and the combination with the Internet. The Internet of Things (IOT) has realized the connection between things and things, things and people and networks, so as to facilitate the identification, management and control of people or things. It is called the third wave of the development of the world information industry after computers and the Internet. Internet of Things (IOT) industry has become the top priority in fostering and developing strategic emerging industries in China, and has been officially listed as one of the key strategic emerging industries for national development. Personnel training of Internet of Things specialty is based on the cultivation of compound applied talents such as Internet of Things application market development and technology promotion. Its professional characteristics determine how to effectively cultivate students' theoretical and engineering practice ability, and how to cultivate professional compound application talents has become the core issue of professional training. As an important part of higher education in China, engineering education practice teaching is an effective way to enhance students' engineering practice ability, improve their comprehensive quality, and cultivate their innovative spirit and ability. It is also an indispensable important teaching link for students during their undergraduate study. Further strengthening the practical teaching of engineering education is an important measure to embody the characteristics of practical education in Colleges and universities in China. Shandong Agricultural University attaches great importance to the cultivation of innovative practical ability of Engineering students. Combining with the orientation of the University and its own characteristics, Shandong Agricultural University has found a more distinctive way to cultivate students in the field of engineering practical teaching of Internet of Things specialty, and has formed an effective practical teaching mode of Internet of Things specialty. Practice has proved that this model has a good effect on enhancing the engineering practice ability of students majoring in Internet of Things, improving students' ability to apply what they have learned, and promoting students' ability to combine theory with practice.

Integrated navigation for Mars final approach based on Doppler radar and X-ray pulsars with atomic clock error

Final approach phase has been recognized as one of the key phases in Mars landing progress. The performance of the navigation system in this phase determines the positioning accuracy of the atmospheric entry point, which further influences the actualization of Mars high-precision pinpoint landing. Regarding this phase, conventional navigation strategies rely on the Earth-based measurement whose time delay is serious due to the long distance between the spacecraft and the ground telemetering station. Therefore, an X-ray pulsars and Doppler radar integrated navigation algorithm is proposed in the current study to ensure the real-time measurement information acquisition and to enhance the reliability of the navigation system. The non-Gaussian bias error of the atomic clock is also considered in the measurement model to improve the accuracy of estimation results. Meanwhile, the augmented state rank Kalman filter (ARKF) is introduced to match the new nonlinear navigation model involving non-Gaussian noises. Numerical simulation results show that the proposed navigation algorithm can make full use of the navigation information provided by X-ray pulsars and Doppler radar, and can effectively reduce the influence of atomic clock errors and guarantee a better performance than traditional methods.

Compressive spectral feature sensing

To reduce the size of spectral data, compressive sensing imaging systems are developed to sample fewer measurements than the Nyquist-rate ones, from which the original data can be recovered by the optimisation model and algorithm. However, this is not a cheap option for the case where the real-time acquisition of spectral information is required. To solve this problem, the authors propose a novel sensing approach for spectral features by combining the sampling, recovery and feature extraction. Inspired by the spectral feature representation, the sampling (sensing) matrix is designed from the training spectral samples to sense the spectral features of the imaging scene, which can be utilised for classification and recognition directly. Besides, the physical realisation of the sensing matrix for compressive spectral imaging systems is demonstrated by designing new modulation patterns of the digital micro-mirror device. The experimental results on real spectral data show the feasibility of the proposed scheme and the robustness to the quantisation error and the measurement noise. Moreover, the proposed sensing approach can reduce the cost of computation and time greatly by removing the sparse recovery and feature extraction..

Monitoring and Protection of Forest Ecological Tourism Resources by Dynamic Monitoring System

Abstract Forest can adjust climate and provide resources for the development of the society and tourism as well as promote the progress of human civilization, which is of great significance to the survival and development of human beings. With the industrial development and the improvement of people’s living standard, the development strength on forest resources is becoming higher than ever before. As forest resources are important resources which can maintain the ecological balance of the earth, its monitoring and protection is necessary. Hence, remote sensing technology has been developed for monitoring the changes of forest resources, which has the quickness characteristics and real-time spatial information acquisition and analysis capacities. This paper firstly introduced the geographical location, geomorphology, climate status, soil and vegetation types of Zhangjiakou City, Hebei Province and the basic theory of remote sensing monitoring such as vegetation spectral reflectance and normalized differential vegetation index (NDVI). Then, the NDVI was used to analyse the vegetation coverage and area ratio of Zhangjiakou City in 2006, 2010 and 2016. It was found that the vegetation coverage during the ten years from 2006 to 2016 showed an overall trend of growth. Conclusions: It is concluded that dynamic monitoring can effectively monitor and protect forest vegetation, which provided ideas for the follow-up forestry planning and ecological tourism development in Zhangjiakou.

A SDR-based verification platform for 802.11 PHY layer security authentication

The WiFi security authentication mechanism combined with the PHY layer information has become a hot spot of WiFi security research. The PHY layer contains rich information such as wireless channel, device location, and signal quality. High performance WiFi verification that supports PHY layer programming has become an indispensable tool for WiFi security research. This paper designs and implements a verification platform TickSEC that supports the research of WiFi security authentication at the PHY layer. It supports real-time acquisition of PHY layer information, and offers the programmability within the PHY layer. We also give a case study of WiFi device identification using PHY layer information. Experimental results show that TickSEC can meet the needs of PHY layer WiFi authentication verification.

WSN Optimization Algorithm for Traffic Environmental Monitoring

In accordance with the features of variety and disparity of traffic information, using wireless sensor network to monitor traffic environment, this paper proposes an optimization algorithm of applying wireless sensor to monitor traffic environment. In this paper, to optimize the coverage, we analyze the irregularity of network sensing areas based on environmental factors and propose a wireless sensor network optimization algorithm. According to the irregularity of network node sensing areas, we build an irregular network coverage model, divide the node monitoring area to improve the network coverage and make corrections to the coverage according to the network coverage connectivity and other features. The simulation test proves that the method proposed in this paper can avoid too many redundant nodes - it only requires a reasonable number of network nodes. This will reduce network energy costs and increase network connectivity without affecting the coverage, thus improving the network performance. the algorithm can satisfy the requirements of real-time acquisition, processing and remote supervision of traffic information.

Interpersonal synchronization of inferior frontal cortices tracks social interactive learning of a song

Much of human learning emerges as a result of interaction with others. Yet, this interpersonal process has been poorly characterized from a neurophysiological perspective. This study investigated (i) whether Interpersonal Brain Synchronization (IBS) can reliably mark social interactive learning, and specifically (ii) during what kind of interactive behavior. We recorded brain activity from learner-instructor dyads using functional Near-Infrared Spectroscopy (fNIRS) during the acquisition of a music song. We made four fundamental observations. First, during the interactive learning task, brain activity recorded from the bilateral Inferior Frontal Cortex (IFC) synchronized across the learner and the instructor. Second, such IBS was observed in particular when the learner was observing the instructor's vocal behavior and when the learning experience entailed a turn-taking and more active mode of interaction. Third, this specific enhancement of IBS predicted learner's behavioral performance. Fourth, Granger causality analyses further disclosed that the signal recorded from the instructor's brain better predicted that recorded from the learner's brain than vice versa. Together, these results indicate that social interactive learning can be neurophysiologically characterized in terms of IBS. Furthermore, they suggest that the learner's involvement in the learning experience, alongside the instructor's modeling, are key factors driving the alignment of neural processes across learner and instructor. Such alignment impacts upon the real-time acquisition of new information and eventually upon the learning (behavioral) performance. Hence, besides providing a biological characterization of social interactive learning, our results hold relevance for clinical and pedagogical practices.

Design and implementation of wireless multimedia sensor network node based on FPGA and binocular vision

According to the actual demand of the wireless sensor network for multimedia information acquisition, the new multimedia wireless sensor node is designed and implemented with FPGA as the core and Zigbee wireless communication. On the multimedia nodes, sensors such as binocular camera and accelerometer are configured to realize real-time perception and acquisition of environmental information and image data, and the short distance wireless communication and detection ability is formed through Zigbee protocol. When the test distance is not more than 60 m, the measured data fluctuate around the theoretical curve, and the communication is reliable. When the distance of the node is within the 14 m, the data transmission has no error. In view of the fact that the mismatch rate of the traditional Census transform is high under the condition of accuracy and noise, an improved Census transform stereo matching algorithm is proposed, which is applied to the nodes of multimedia sensor network. The experimental results show that this scheme can realize the data transmission and processing of wireless sensor network nodes and has strong operation capability and visual matching precision while reducing power consumption.

Design of a Precision Agriculture Leakage Seeding System Based on Wireless Sensors

In light of the agricultural development in China, more attention has been paid to the studies about precision agriculture. The environmental factors such as temperature-humidity and soil humidity are the key influencing factors on crop growth, therefore, how to rapidly and accurately acquire the environmental information of crop growth and learn about their real-time growing environment is of vital importance. The wireless sensor networks (WSN) can make real-time environmental information acquisition as well as communication and processing of network environmental data. Based on this, the RSSI range-based positioning method was optimized in this paper in order to greatly improve its precision. To be specific, in this study, the particle swarm optimization (PSO) algorithm was firstly applied in the hybrid mutation strategy to make more accurate node positioning and significantly improve the evolutionary performance by enlarging the hunting zone; besides, through the use of WSN, the influencing parameters on crop growth such as soil humidity, and temperature-humidity etc. would be monitored; finally, to realize the precise location and derive the unseeded nodes, GPS was applied for accurate positioning, and the intelligence algorithm was adopted to determine the coordinate position of unknown nodes. At last, the actual field test indicates that the designed monitoring system in this paper satisfies the requirements for precise measurement, playing a positive role in promoting the development of precision agriculture.

Development and Application of Big Data Platform for “Bohai granary”

In order to effectively solve series of problems which affect grain production in implementation of the “Bohai granary” project, such as the wide varieties of factors (including soil fertility, soil salinity, pH, underground water level, water salinity, crop varieties and management etc.), the huge spatial and temporal variability, the difficulty of real-time information collection, the complexity of analysis and processing etc., a “Bohai granary” big data platform is developed. With the invention of “Shennong IOAT” series of sensing equipment, the acquisition of multi-site real-time synchronization field information is achieved. And by combining a variety of data collection methods, the collection of factors comprehensively affecting the grain production has been realized. Based on the Hadoop big data platform, it becomes a reality to store, analyze and apply the collected data efficiently. Through the big data platform, the precise management of grain production, the automatic warning of soil moisture content, the disaster and typical insect damage in crop growth, and the automatic control of typical link production are all achieved.