Skip to main content
Top

2021 | Book

Human Centered Computing

6th International Conference, HCC 2020, Virtual Event, December 14–15, 2020, Revised Selected Papers

insite
SEARCH

About this book

This book constitutes thoroughly reviewed, revised and selected papers from the 6th International Conference on Human Centered Computing, HCC 2020, held in virtually, due to COVID- 19, in December 2020. The 28 full and 20 short papers presented in this volume were carefully reviewed and selected from a total of 133 submissions.

The conference focuses on the following three main themes as follows: Data such as Data Visualization, Big Data, Data Security, Hyper connectivity such as Internet of Things, Cloud Computing, Mobile Network and Collaboration such as Collective Intelligence, Peer Production, Context Awareness and much more.

Table of Contents

Frontmatter
Dynamic Pick and Place Trajectory of Delta Parallel Manipulator

Based on the high-speed and stable demand of the dynamic pick-and-place of a Delta parallel manipulator in industrial production, a 5-3-5° multi-segment polynomial is used to design the speed laws of the joints of the manipulator, combined with the constraint of motion, the shortest period, and vibration control to construct a multi-target and multi-constrain. The nonlinear motion trajectory planning model is obtained, and the optimal solution of trajectory planning is obtained by using the optimized gravitational search algorithm. The results show that the speed and acceleration of the motion trajectory reach extreme values, and the motion trajectory is continuously smooth, meeting the expected planning requirements. The effectiveness of the motion trajectory model in shortening the operation cycle and the vibration of the control mechanism is verified, and the effectiveness of the optimized gravity search algorithm in the convergence control and global optimization is verified.

Qiaohong Zu, Qinyi Liu, Jiangming Wu
Design of Aquatic Product Traceability Coding Scheme Based on EPC Label

Aiming at the existing quality and safety issues in the aquatic product industry, with famous and excellent fresh aquatic products as the research object, the traceability coding of its supply chain is discussed. This paper analyzes the main links and elements information involved in the circulation of famous and excellent aquatic products, and uses EPC coding technology and RFID anti-counterfeiting encryption technology to design the traceability code of famous and excellent aquatic products, and builds the traceability system of aquatic products. Users can track and query famous and excellent aquatic products in breeding base, logistics center, sales center and other links, realizing the information transparency of aquatic products in the supply process, which has theoretical and practical significance for improving the quality and safety of aquatic products.

Qiaohong Zu, Ping Zhou, Xiaomin Zhang
DEVS-Based Modeling and Simulation of Wireless Sensor Network

A modeling and simulation method for wireless sensor network (WSN) using discrete event system specification (DEVS) is proposed in this paper considering that the existing simulators cannot fully satisfy the requirements of WSN simulation. The method is for multi-layer and multi-aspect modeling which contains the component layer in sensor nodes, the sensor node layer, the wireless sensor net-work layer and the external environment where a WSN is exposed, and modules in lower layer are integrated into superior models through coupling relation and model reuse. Minimum Hop Count (MHC) protocol is chosen as the routing protocol of the WSN in the simulation experiment. It is finally demonstrated through the performance analysis of WSN using MHC that the proposed DEVS-based modeling and simulation method is feasible for WSN simulation.

Songyuan Gu, Chen Wu, Yuanyuan Qin
Spatial Reciprocity Aided CSI Acquirement for HST Massive MIMO

This paper proposes a channel estimation scheme for large-scale multiple-input multiple-output (MIMO) systems in high-speed train (HST) scenarios. On the premise that the priori velocity is accurate, we introduce fuzzy prior spatial knowledge and design a sparse received signal model with dynamic grids. After reconstructing the channel estimation into a sparse Bayesian learning (SBL) parameter estimation problem, the maximization-minimization (MM) algorithm is adopted to solve the problem, and a fast searching algorithm based on significant gradient is proposed to solve the multi-peak optimization problem of the surrogate function. Finally, the simulation verifies that the scheme can converge quickly and has accurate estimation results.

Kaihang Zheng, Yinglei Teng, An Liu, Mei Song
A Flexible Film Thermocouple Temperature Sensor

This article introduces a thin-film thermocouple temperature sensor with symmetrical electrode structure. It uses PI film as a flexible substrate. Cu film and CuNi film made by MEMS manufacturing process as positive and negative electrodes. The device itself has the advantages of miniature, bendable and fast response speed. In order to reduce the resistance value of the film, an experiment was conducted to optimize the thickness of the metal film and the temperature of the sputtering substrate. The critical dimensions of Cu/CuNi film are 650 nm and 400 nm respectively. The best sputtering substrate temperature for Cu/CuNi films are 100 ℃ and 150 ℃. Testing the adhesion of thin film thermocouples using the peel-off method. The test result is 9.4 N. Finally, the film thermocouple temperature sensor is subjected to a temperature static calibration experiment. The result shows that the actual potential difference error is within ± 1 ℃. It belongs to the second class standard in the formulation of thermocouple standards in China. Through curve fitting, the corresponding relationship between temperature and potential difference is more accurate.

Yulong Bao, Bin Xu, Huang Wang, Dandan Yuan, Xiaoxiao Yan, Haoxin Shu, Gang Tang
Design of a Morphing Surface Using Auxetic Lattice Skin for Space-Reconfigurable Reflectors

The effect of Poisson’s ratio to the reflector reshaping is investigated through mechanical study of reconfigurable reflectors in this paper. The value of Poisson’s ratio corresponding to the minimum deforming stress is given and an auxetic lattice is proposed for the reflector surface. The parameters of the auxetic lattice are investigated for vary Poisson’s ratio. A case of reconfigurable reflector is studied, the curvature change and strain are calculated by surface geometry analyse, and the negative Poisson’s ratio is established for vary thickness. According to RMS calculation by the FEM structure analyse, the thickness can finally be established.

Bin Xu, Houfei Fang, Yangqin He, Shuidong Jiang, Lan Lan
The Method of User Information Fusion Oriented to Manufacturing Service Value Net

Based on the business system users of manufacturing enterprises, building a value net platform including multi-enterprise and social service resources needs to integrate the user information and explore more value-added services. This paper proposed a method of user information fusion for manufacturing service value net. First, based on the request of the multi-party value net fusion, we researched the user information representation method and designed the data structure. And then, considering the protection of sensitive fields, the study of privacy fields protection methods based on homomorphic encryption methods should be carried out to ensure the utility of data. The last step was researching the multi-platform user information transmission based on the RESTful interface specification. The value net case system shows that the user information fusion method is realizable and can ensure the system users’ security.

Wenjia Wu, Lin Shi, Jiaojiao Xiao, Changyou Zhang
Image Fusion Method for Transformer Substation Based on NSCT and Visual Saliency

To solve the problems of the existing infrared and visible image fusion algorithms, such as the decrease of the contrast of the fusion image, the lack of the visual target, and the lack of the detail texture, an image fusion algorithm based on the visual saliency is proposed. Firstly, NSCT is used to decompose the two source images to obtain the corresponding low-frequency sub-band and a series of high-frequency sub-band; secondly, an improved FT algorithm is used to detect the visual saliency region of the low-frequency sub-band of different sources; Thirdly, according to the size of visual saliency, different weights are assigned to low-frequency sub-band of different sources, based on which fusion is carried out; fourthly, the high-frequency sub-band weight map is obtained by screening methods, and then the weighted image is used for fusion; finally, the final fusion image is obtained by inverse NSCT transform. The experimental results show that our method has a better visual effect and higher objective indicators than other classical image fusion methods.

Fang Zhang, Xin Dong, Minghui Liu, Chengchang Liu
Permission Dispatching Mechanism Inside and Outside of the Warranty Period for Equipment Maintenance Service System

It is a vital service process for equipment maintenance to ensure regular operation. The equipment transitions from inside of the warranty period to outside of the warranty period and the staff involved in the maintenance service will transform from manufacturer personnel to a mixed team of user teams and third-party companies. The permissions will change with their responsibilities in the equipment maintenance service system. In this paper, we take the maintenance service system of shield tunneling machine equipment as a case, which design the personnel structure of the mixed maintenance team and establish an authorization mechanism to support the multi-team work process of equipment maintenance. We design a user group-based hierarchical control strategy that combines the equipment maintenance service system’s resource structure. At the end of this paper, though the simulation-based on Colored Petri Net CPN Tools, we verify the correctness and effectiveness of the permission dispatching mechanism.

Yujie Liu, Wenjia Wu, Wen Bo, Chen Han, Quanxin Zhang, Changyou Zhang
New Technology Development and Application Trends Based on Monitoring of Patent Data

As an important manifestation of science and technology, patents contain many aspects of information. The combination of multiple patents can dig out the development trend of a technology. Therefore, it is very important to understand them for mastering the trend of a technology and the decision-making and deployment of future development of the enterprise. Existing methods cannot provide enough analysis and forecast information. Therefore, a domain technology analysis model based on patent data is proposed in this paper. The visualization diagram constructed by this model can vividly display the multi-dimensional characteristics of the technology in the patent data, including the provincial and municipal distribution of technology domains in the patent, the development trend of sub-domains, the main technology composition of the patent, etc. which helps the enterprises quickly understand the status quo of technology development behind patent data. At the same time, the comprehensive analysis diagram generated can help us understand the relationship between the main team composition and technology in the technology domain, and make better decisions in future research. Finally, patents in the deep learning domain are researched in this paper.

Ce Peng, Tie Bao, Ming Sun
A K-means Clustering Optimization Algorithm for Spatiotemporal Trajectory Data

It is a hotspot problem to quickly extract valuable information and knowledge hidden in the complex, different types, fuzzy and huge amount of space-time trajectory data. In the space-time trajectory data clustering method, according to the existing deficiencies of the classical K-means algorithm, the mathematical distance method and effective iteration method are used to select the initial clustering center to optimize the K-means algorithm, which improves the accuracy and efficiency of the algorithm. Based on MATLAB experimental simulation platform, the comparison experiments between the classical algorithm and the optimized algorithm, the applicability test of the performance test, and the comparison test with the classical algorithm were designed. The experimental results show that the optimized K-means randomly selected initial clustering center is more accurate, which can avoid the drawbacks caused by randomly selected initial clustering center to a certain extent and has better clustering effect on sample data, and at the same time avoid the K-means clustering algorithm falling into the dilemma of local optimal solution in the clustering process.

Yanling Lu, Jingshan Wei, Shunyan Li, Junfen Zhou, Jingwen Li, Jianwu Jiang, Zhipeng Su
Temporal and Spatial Changes of Ecosystem Health in Guangdong Province in Recent 11 Years

As a coastal province in southern China, the economy of Guangdong has been rapidly developed after the implementation of the reform and opening up. In the past decades, the authority of Guangdong has emphasized ecological health construction while paying attention to economic development. Meanwhile, the construction of “the Belt and Road Initiatives” has posed great challenges to the health of the local ecosystem. Based on the Vigour -Organization-Resilience Model (VOR), the ecological health assessment system was established to evaluate and analyze the ecosystem health from 2009 to 2019 of Guangdong. Results showed that the ecosystem health of Guangdong showed a slight improvement for the study period, The areas with greater than level 2 had decreased by 8.42%. The overall ecological system health varied from general to good. The ecosystem health of the study area exhibited obvious spatial heterogeneity. The level of the ecosystem health in the northern part was better than the southern part. The ecosystem health of the study area decreased slightly at the beginning and then increased significantly, and the ecosystem health showed a stable and positive trend.

Nan Zhang, Yong Xu, Shiqing Dou, Juanli Jing, Hanbo Zhang
Salient Attention Model and Classes Imbalance Remission for Video Anomaly Analysis with Weak Label

Recently, weakly supervised anomaly detection has got more and more attention. In several security fields, realizing what kind of anomaly happened may be beneficial for security person who have preparation to deal with. However, lots of studies use global features aggregation or topK mean, and it exists feature dilution for anomaly. An attention model is proposed to generate the segment scores, i.e. we propose a salient selection way based on attention model to efficiently detect and classify the anomaly event. With these selected highlighted features, graphs are constructed. Graph convolutional network (GCN) is powerful to learn the embedding features, anomaly event can be expressed more strongly to classify with GCN. Because normal events are common and easy to collect, there is a problem that the normal and abnormal data are imbalance. An abnormal-focal loss is adapted to reduce influence of large normal data, and augment the margin of normal and different anomaly events. The experiments on UCF-Crime show that proposed methods can achieve the best performance. The AUC score is 81.54%, and 0.46% higher than state-of-the-art method. We obtain 58.26% accuracy for classification, and the normal and anomalies are separated better.

Hang Zhou, Huifen Xia, Yongzhao Zhan, Qirong Mao
A Data Fusion Model Based on Multi-source Non-real-Time Intelligence

In order to solve the problem of target fusion in complex battle environment, a data fusion model based on multi-source intelligence is established. Weight quantification analysis and fusion of non-real-time intelligence source are realized based on this model, the evidence reasoning method is used to solve the uncertainty in decision-making, and the accuracy of data fusion is improved by integrating non-real-time and real-time intelligence source. In general, this model considers more sufficient and comprehensive influencing factors, and the computational process of this model is intelligent.

Yuanyuan Qin, Songyuan Gu
Ancient Chinese Lexicon Construction Based on Unsupervised Algorithm of Minimum Entropy and CBDB Optimization

Ancient Chinese text segmentation is the basic work of the intelligentization of ancient books. In this paper, an unsupervised lexicon construction algorithm based on the minimum entropy model is applied to a large-scale ancient text corpus, and a dictionary composed of high-frequency co-occurring neighbor characters is extracted. Two experiments were performed on this lexicon. Firstly, the experimental results of ancient text segmentation are compared before and after the lexicon is imported into the word segmentation tool. Secondly, the words such as person’s name, place name, official name and person relationship in CDBD are added to the lexicon, and then the experimental results of ancient text segmentation before and after the optimized lexicon is imported into the word segmentation tool are compared. The above two experimental results show that the lexicon has different enhancement effects on the segmentation effect of ancient texts in different periods, and the optimization effect of CDBD data is not obvious. This article is one of the few works that applies monolingual word segmentation to ancient Chinese word segmentation. The work of this paper enriches the research in related fields.

Yuyao Li, Jinhao Liang, Xiujuan Huang
Availability Analysis of GNSS RAIM Based on Maximum Undetectable Position Bias

The combined use of multiple constellations of the Global Navigation Satellite System (GNSS) provides a great possibility to improve the integrity of the satellite navigation; however, with the increase of the number of satellites, the probability of multiple outliers increases. Although a number of studies analyzed the performance of the combined GNSS Receiver Autonomous Integrity Monitoring (RAIM), the analysis of the case of multiple outliers is still lacking. In this paper, a Maximum Undetectable Position Bias (MUPB) scheme, which is based on Bias Integrity Threat (BIT), is used to analyze the horizontal availability of RAIM with multiple outliers. We have analyzed the theoretical background for BIT and MUPB. Next, detailed simulations and analyses with single or combined GPS/BDS (BeiDou Satellite Navigation System)/GLONASS constellations were conducted to evaluate the performance of RAIM. In the simulated scenarios with three constellations (GPS  +  BDS  +  GLONASS) and 2 or 3 outliers occurring simultaneously, we compared the MUPB and the Horizontal Alert Level (HAL) of different aviation approach phases and analyzed the results.

Shitai Wang, Min Yin
Psychological Semantic Differences of Zhang Juzheng Before and After DuoQing Event

After the death of his father, Zhang Juzheng did not follow the rule to mourn his father for 27 months, but continued to work, known as Zhang’s DuoQing event. Because the event had a huge influence on the imperial court and Zhang Juzheng himself, the present paper analyzed the differences in written expressions of Zhang Juzheng before and after DuoQing event from a psychological semantic perspective. This paper used a classic Chinese dictionary, CC-LIWC, to analyze Zhang’s work (Memorials & letters), and obtained the word frequency of LIWC keywords, then compared their differences. We selected psychological semantically related CC-LIWC keywords for further analysis, including Functional-Personal pronouns, Affective processes, Social process, Cognitive process, Drives process, Personal concerns. The results indicated that only five dimensions of the Third person singular words, the Third person plural words, the Sadness words, the Female words and the Difference words were significantly different among the above keywords. This paper found that Zhang Juzheng was an efficient manager who loved power and work, the development of DuoQing event was beyond Zhang Juzheng’s expectation, and the incomprehension and impeachment from his close people made him sad. This paper provides a new method for analyzing one’s psychological changes before and after one major event, also provides some reference for modern leaders in terms of psychology and dealing with people.

Shuting Li, Miaorong Fan, Fugui Xing, Tingshao Zhu
Digital Rights Management Platform Based on Blockchain Technology

Traditional copyright protection technologies are unable to adapt to the current digital era of the Internet, and some problems such as difficult in digital works confirmation copyright, complex copyright transactions, copyright protection and infringement monitoring. Although Digital Rights Management (DRM) can provide certain security for digital copyrights, it still cannot effectively solve these problems. The decentralization, non-tampering, traceability and other characteristics of the blockchain are of great help to address the above problems. This paper proposes a scheme combining blockchain technology with digital rights management, and builds a digital rights management platform based on blockchain. In this paper, we propose platform system architecture based on blockchain technology by using the open source Hyperledger Fabric framework as the underlying blockchain development platform and combining smart contracts, IPFS systems, timestamps and other technologies, and have implemented the functions of the four core modules of the platform, which brings new breakthroughs for digital copyright protection technology.

Wenan Tan, Xiao Zhang, Xiaojuan Cai
A Deep Hybrid Neural Network Forecasting for Multivariate Non-stationary Time Series

In the field of financial time series prediction, multivariate time series is increasingly considered as the input of the prediction model and non-stationary time series have always been the most common data sets. However, the processing efficiency is low but the cost is high whenthe traditional methods is used for modeling non-stationary time series. This paper is aimed at providing the methodological guidance for building low-cost models for modeling multivariate non-stationary time series. By building a univariate CNN, a multivariate CNN, a nonpooling CNN (NPCNN), a CNN-LSTM and a NPCNN-LSTM, we conducted a series of comparative experiments. We found that multivariate non-stationary time series is not complex enough, the pooling operation will lose the useful information and the LSTM layer can weaken this negative effect. Meanwhile, convolutional layers and LSTM layers can improve the prediction accuracy. Adding the LSTM to prediction models can make models have better performance in short-term prediction.

Xiaojian Yang, Xiyu Liu
Risk Assessment of Flood Disasters in Hechi City Based on GIS

Flood disasters are one of the meteorological disasters that occur frequently and cause heavy losses. Hechi City is located in a low-latitude zone with a typical subtropical monsoon climate. Water resources are unevenly distributed in time and space, and floods often occur. The flood risk assessment of Hechi City has strong practical significance. This paper collects three phases of remote sensing image data and many years of meteorological and attribute data, builds a flood disaster risk assessment model based on the flood formation mechanism, uses Analytic Hierarchy Process (AHP) to determine the weight of each index factor, and calculates each evaluation index data with GIS technology Analyze, through the GIS spatial analysis function, superimpose the analysis results of flood hazard, disaster-generating environment sensitivity, and disaster-bearing body vulnerability in Hechi City to obtain the comprehensive risk distribution of flood disaster in Hechi City, showing Hechi City The flood disaster risk of the northeast region and the southwest region is gradually reduced to the central region. It is necessary to strengthen the actual disaster prevention and mitigation work in high-risk areas in the northeast region.

Min Yin, Chengcheng Wei, Juanli Jing, Xiaoqian Huang
Cultural Symbol Recognition Algorithm Based on CTPN + CRNN

This paper proposes a cultural symbol recognition algorithm based on CTPN + CRNN. The algorithm uses the improved VGG16 + BLSTM network to extract the depth features and sequence features of the text image, and uses the Anchor to locate the text position. Finally, the task of cultural symbol recognition is carried out through the CNN + BLSTM + CTC deep network, The algorithm is an ideal cultural symbol recognition scheme in terms of the recognition efficiency and accuracy.

Yanru Wang
Spatial-Temporal Variation and Future Changing Trend of NDVI in the Pearl River Basin from 1982 to 2015

Based on the GIMMS NDVI3g data from 1982 to 2015, this paper uses trend analysis, Mann-Kendall test and R/S analysis methods to explore the spatial- temporal variation and future trends of NDVI in the Pearl River Basin, in order to provide basis for the improvement of ecological problems in the area. The results show that: (1) In terms of time, the NDVI of the Pearl River Basin showed a fluctuating upward trend as a whole from 1982 to 2015, and it was extremely significant (P < 0.01); (2) In terms of space, the vegetation coverage was generally better in 34 years; the low and medium vegetation coverage areas (NDVI < 0.6) only accounted for 2.78% of the study area, which were concentrated in the Pearl River Delta region in the lower reaches of the Pearl River Basin; (3) In the trend analysis, NDVI showed an increasing trend in 34 years, and it accounted for 81.44% of the study area, mainly distributed in the upper reaches of the Yunnan-Guizhou Plateau and the middle reaches of the area; (4) In the future trend, the area with H > 0.75 accounts for 51.71%, indicating that the vegetation coverage will continue to increase in the future.

Caixia He, Bingxin Ma, Juanli Jing, Yong Xu, Shiqing Dou
An Improved Collaborative Filtering Algorithm Based on Filling Missing Data

At present, most of the literature uses error metrics to evaluate the performance of recommendation algorithms. However, especially in Top-N recommendation tasks, the accuracy metrics can better show the pros and cons of the recommendation algorithm. Researching traditional recommendation algorithms have a big problem is that the data of recommendation system is always sparse. In order to solve the problem and improve the accuracy metrics, we add a filling matrix when predicting the rating. And then, we considering that different users have different scoring preferences, the user and item biases are added to the loss function. Finally, we use the improved alternating least square method as the optimization method to update the filling matrix in the iterative process. The experiment compared four recommendation algorithms and the results show that, in terms of accuracy metrics, the accuracy of the improved algorithm has been improved many times. In addition, since the filling of the rating matrix needs to consider both the item and the user, we compared the algorithm that considers both and only considers one. The improved algorithm that considered both has an improvement of about 1%.

Xin Zhou, Wenan Tan
Diagnosis Method of Alzheimer’s Disease in PET Image Based on CNN Multi-mode Network

Developing a correct diagnosis of Alzheimer’s disease (AD) is a challenging task. Positron emission tomography (PET) is a good method to help doctors assist in the diagnosis of AD. In recent years, artificial intelligence methods such as machine learning have been widely used in image analysis and judgment and medical auxiliary diagnosis. The current methods are mainly to manually extract image features from medical images and then train classifiers to judge AD, or use deep learning, neural networks for end-to-end AD classification, most methods only use a single-mode method, and the classification effect is limited. This paper proposes a multi-mode network structure based on CNN to classify and diagnose AD. The network is mainly divided into three parts: CNN-based multi-scale deep-level feature extraction module, image texture feature extraction module, and SVM-based feature integration classification module. The network fully combines the advantages of the two modes of manual feature extraction and neural network. Compared with single mode feature extraction, this method has higher accuracy and has a good performance on the classification and diagnosis of AD.

Shupei Wu, He Huang
Research on Multi-floor Path Planning Based on Recommendation Factors

This paper proposes a path planning method for indoor multi-floor. By combining the Dijkstra algorithm, using intelligent recommendation predicted value as the weight of multi-floor path node, we give a multi-floor path plan based on the recommended factor. Compared with the traditional indoor path planning method, the method not only solves the problem of multi-floor planning in the interior, but also has the characteristics of personalized recommendation.

Yanru Wang, Haoyang Yu
E-commerce Review Classification Based on SVM

In order to classify the massive historical review information of e-commerce platforms, efficiently extract review information and visualize it, this paper establishes an SVM-based e-commerce review classification model (using the combination of word frequency and information gain for feature selection), using the SVM classification model effectively classifies the review text, and uses J2EE as the developed technical framework to realize the B/S mode of the e-commerce review information system, combined with the JFreeChart plug-in to realize the visual display of review data classification, and provide conciseness for merchants and consumers Intuitive reference. This paper compares the two algorithm classification models of random forest and SVM. By comparing the results of classification experiments, it is verified that SVM can solve the small sample data classification problem in this paper more efficiently and accurately.

Qiaohong Zu, Yang Zhou, Wei Zhu
Experimental Research of Galfenol Composite Cantilever

In order to research the output characteristics of Galfenol composite cantilever beam, an experimental platform is built for the experiment of beam. The influence of external magnetic field, load and substrate thickness on the strain of Galfenol surface and substrate surface is deeply analyzed, and the magnetostrictive mechanism of composite cantilever beam is discussed. The conclusion that Galfenol alloy is subjected to the coupling effect of tension and bending in the cantilever beam can provide reference for further exploring the application of the cantilever beam.

Qinghua Cao, Xiaoxing Zhang, Nannan Wu, Zhifeng Zhou, Jinming Zang
A Capacitive Flexible Tactile Sensor

In this paper, a capacitive flexible tactile sensor was designed to measure the pressure of objects based on MEMS technology. This sensor is a structure of a 4 × 4 array, with metal Ag as the capacitive electrode, which forms the tactile sensing unit of the sensor. The structure of capacitive flexible tactile sensor was designed and an experimental platform was established to test the performance. The tests show that when the thickness of the intermediate layer is 2 mm and the density is medium, the sensor’s sensitivity is the best while the time of both the response and the rebound is fast.

Dandan Yuan, Haoxin Shu, Yulong Bao, Bin Xu, Huan Wang
Multi-objective Optimization of E-commerce Logistics Warehouse Layout Based on Genetic Algorithm

With the support of Internet technology and infrastructure construction, fast and convenient online shopping has become an important part of urban consumption. E-commerce has a wide variety of products, large demand, short consumption cycles, and consumers have relatively high time requirements for online shopping services. A good warehouse layout strategy and inventory allocation strategy can help companies shorten inventory and pick-up time, reduce labor costs, and optimize the quality of delivery services. Therefore, studying the layout and distribution of e-commerce logistics warehouses is of inestimable value for improving the market competitiveness of e-commerce enterprises. This paper takes a E-commerce company’s storage center as the object, considers goods’ turnover rate and shelves’ stability as principles to construct a multi-objective optimization mathematical model. By setting up random goal weights to improve traditional genetic algorithm, and to use MATLAB software platform to optimize the solution with mixed multitargets genetic algorithm on basis of the background of a specific warehouse position distribution. The result shows that this model is practical and effective. It can realize the reasonable distribution of the layout problem and reduce handling loss, as well as improve warehouse’s space utilization.

Qiaohong Zu, Yanchang Liu
Magnetic Circuit Design of Galfenol Composite Cantilever

The magnetic circuit design is one of the most important factors in the design of giant magnetostrictive materials. In order to improve the uniformity of magnetic field, the composite cantilever beam is placed in the center of the hollow coil, the analytical solution of the driving magnetic field is solved, the basic parameters of the coil are determined, and the magnetic leakage reason is analyzed by finite element method. At the same time, the magnetic circuit design method is optimized by using finite element method. After optimization, the uniformity of magnetic induction intensity is improved, which provides reference for the magnetic circuit design of giant magnetostrictive material devices.

Qinghua Cao, Jinming Zang, Nannan Wu, Zhifeng Zhou
A MEMS-Based Piezoelectric Pump with a Low Frequency and High Flow

This paper mainly presents a piezoelectric pump based on a single piezoelectric vibrator under MEMS technology. The piezoelectric vibrator of the piezoelectric pump is made by MEMS technology, and the pump body is completed by 3D printing. Driven by a low-frequency AC voltage of 220 V 50 Hz, the center displacement of the piezoelectric vibrator of the pump can reach 136 μm with high output characteristic. Finally, the piezoelectric pump was used to perform a cooling test on the heating sheet PTC under the condition of 26 °C. It was found that the temperature of the PTC could be reduced by about 20 °C under the condition of the maximum output flow of 159 ml/min. Therefore, the piezoelectric pump has important practical significance in many aspects such as micro flow control and computer CPU cooling.

Dehui Liu, Zhen Wang, Liang Huang, Shaojie Wu, Dandan Yuan
Micro-video Learning Resource Portrait and Its Application

The emergence of a large number of online learning platforms changes the learners' demands and learning styles, thus the society puts forward higher requirements for the personalization, intelligentization and adaptability of learning resource platforms. For large-scale, multi-source and fragmented micro-video learning resources and personalized education problems, based on micro-video online learning resources data, the paper studies the accurate, comprehensive and usable micro-video learning resources portrait method. And through the application of deep learning technology, it studies the theory and method of micro-video learning resource data analysis and personalized learning resource recommendation. It explores and forms the basic theories and methods of data-driven micro-video learning resources analysis to support the research of personalized education theories and methods.

Jinjiao Lin, Yanze Zhao, Tianqi Gao, Chunfang Liu, Haitao Pu
Research on Downscaling and Correction of TRMM Data in Central China

The Central China has abundant rainfall, and rainfall is unevenly distributed in space and time, which can easily cause floods and soil erosion. It is of great significance to obtain precipitation information accurately and quickly. At present, remote sensing precipitation data has been widely used, but its spatial resolution and data accuracy still cannot meet actual application requirements. Therefore, this paper fully considers the applicability of TRMM 3B43 data from 2001 to 2019 in the Central China, based on a geographically weighted regression model, combined with NDVI, EVI, elevation, slope and aspect data. Different combinations were selected to downscale $$TRMM_{EVI}$$ T R M M EVI data, and perform GDA and GRA corrections on the optimized TRMM data, and finally perform accuracy evaluation and result analysis on annual, quarterly, and monthly scales. The research results showed that: (1) The accuracy of the $$TRMM_{EVI}$$ T R M M EVI data is better than the $$TRMM_{NDVI}$$ T R M M NDVI data when the spatial resolution is increased from 0.25° to 1 km, (2) The GDA correction result is more satisfactory than the GRA correction result and the data stability is better, so it is more suitable for TRMM data correction in the Central China. (3) The R2 of $$TRMM_{NDVI}^{GDA}$$ T R M M NDVI GDA data and the measured data of the site has high accuracy on the annual (0.91–0.986), quarter (0.704–0.88), and monthly (0.625–0.89) scales, and its detailed characteristics are better than TRMM data. (4) The better the downscaling and correction effect will be in the months with greater precipitation. Through downscaling and correction of TRMM data, it can better reflect the real precipitation information in the Central China, and provide reliable data support for agricultural production, optimal allocation of water resources, and flood prevention and disaster reduction.

Hanbo Zhang, Shiqing Dou, Yong Xu, Nan Zhang
Research on the Knowledge Map of Combat Simulation Domain Based on Relational Database

The analysis and evaluation of simulation data, especially the selection of assessment indexes and the establishment of index system, need the knowledge base or knowledge map of simulation application field as the expert knowledge support. The relational database of the existing combat simulation application system provides a reliable and easy to obtain data source for the construction of combat simulation domain knowledge map. This paper proposes an effective method to construct the knowledge map of simulation data based on relational database, which lays a foundation for the construction of combat simulation domain knowledge map and the analysis of simulation data based on knowledge map.

Li Guo, Boao Xu, Hao Li, Dongmei Zhao, Shengxiao Zhang, Wenyuan Xu
Scale-Aware Network with Attentional Selection for Human Pose Estimation

Human pose estimation is a fundamental yet challenging task in computer vision. Human pose estimation from a single image is a challenging problem due to the limited information of 2D images and the large variations in configuration and appearance of body parts. Recent works has largely improved the result of human pose estimation because of the development of convolutional neural network. However, there still exists many difficult cases, such as occluded keypoints, complex background and scale variations of human body keypoints, which cannot be well dealt with. In this paper, we design a novel scale-aware network with attentional selection that extracts multi-scale semantic information and meaningful features. Specifically, we propose a Feature Pyramid Supervision Module (FPSM), which can improve the estimation accuracy of scale variations. Meanwhile, a Spatial and Channel Attention Module (SCAM) is designed for recalibrating the spatial and channel features. Based on the proposed algorithm, we achieve state-of-the-art result on LSP dataset and make competitive performance on MPII Human Pose dataset.

Tianqi Lv, Lingrui Wu, Junhua Zhou, Zhonghua Liao, Xiang Zhai
Short-Term Traffic Flow Prediction Based on SVR and LSTM

To alleviate traffic congestion and support the development of real-time traffic and public transport, this paper conducts research on adopting support vector regression (SVR) and long short term memory (LSTM) to predict traffic flow of the lane, and then compares the results with that using the quadratic exponential smoothing. The consequence shows that SVR and LSTM have better prediction accuracy, about 1%–3% in terms of MAPE, than quadratic exponential smoothing, and SVR is slightly better than LSTM. Furthermore, in order to improve the predictive accuracy of model, we compare the performance of grid search, whale optimization algorithm (WOA) and genetic algorithm (GA) respectively in the respect of optimizing models’ parameters. The optimization effect of WOA-SVR and WOA-LSTM is better than the other two models respectively, about 0.9% and 2.52% better than GA-SVR and GA-LSTM while 0.29% and 2.32% better than GridSearch-SVR and GridSearch-LSTM considering MAPE.

Yi Wang, Jiahao Xu, Xianwu Cao, Ruiguan He, Jixiang Cao
A Logging Overhead Optimization Method Based on Anomaly Detection Model

Logs play an important role in system anomaly detection. However, in today’s large-scale software development and production, the cost of logging is non-negligible, and intensive logging in actual production processes will generate a large amount of redundant logs which are useless for anomaly detection. However, the current method of solving related problems is not ideal, and it is only applied when the overhead of the logging has affected the quality of service. Therefore, this paper proposes a method for optimizing logging records for this problem. Under a given budget (defined as the maximum volume of logs allowed to be output in a time interval), using an anomaly detection model based on deep learning and a two-phase filtering mechanism, the method determines whether to log according to the utility score of the log for anomaly detection to save useful logs and discard less useful logs during the system running process. The experimental results show that the proposed method alleviates the logging overhead problem without reducing the logging effectiveness.

Yun Wang, Qianhuizhi Zheng
Multi-objective Collaborative Optimization of Multi-level Inventory: A Model Driven by After-Sales Service

To improve the quality of after-sale service that is a new aspect for all manufacturing enterprises, the allocation of inventory reserves as well as reasonable dispatch between inventories have become the key to meet customer demand and reduce inventory cost. In this paper, a multi-stage safety inventory optimization model is constructed for after-sales service demand. The order quantity of inventory in the model is set to consider the changes of customer demand and fault loss under the influence of different quarters and regions. The cost and transportation time are also optimized by using multi-objective particle swarm optimization algorithm at the same time. Simulational results show that the proposed model can not only respond to the demand changes in different regions and different quarters timely, but also reduce the cost and time loss to meet customer demand. Compared with the methods that merely considers time and cost respectively, the proposed model is more suitable to solve the multi-stage inventory optimization problem across regions.

Mingxuan Ma, Yiping Lang, Xia Liu, Wendao Mao, Lilin Fan, Chunhong Liu
The Research About Spatial Distribution of Urban Functions Based on POI Data

The distribution of urban functional space is an important factor to measure the development of a city. Its reasonable layout plays an important role in the development of urban economy and the optimization of urban spatial pattern. This paper is based on the third ring road of Nanning city Based on POI data, the functional land is divided into five categories: life service, business and finance, public service, leisure and entertainment, and residence. By using kernel density analysis, frequency density analysis and standard deviation ellipse analysis, the urban function and distribution characteristics of the Third Ring Road area in Nanning city are identified and analyzed. The results show that: 1. The overall spatial layout is affected by traffic and urban master plan Under the influence of other factors, the spatial pattern of “circle layer” appears. Taking one ring as the core, it has obvious central agglomeration. 2. The trend of urban development shows an obvious pattern of prosperity in the West and decline in the East.

Jingwen Li, Yuan Ma, Jianwu Jiang, Wenda Chen, Na Yu, Shuo Pan
The Psychological Characteristics Changes Analysis of Su Shi Before and After the Wutai Poetry Case ——Based on the CC-LIWC

Su Shi(hereinafter referred to as Su) is a well-known historical celebrity in China, the Wutai Poetry Case(WPC) was a famous literary inquisition in Chinese history, and was a turning point in Su's life. Pevious studies on the influence of WPC were based on Su’s literatures, and there was a lack of empirical researches. In this paper, we conducted the Word Count Verbal Text Analysis on Su's literary works. [Methods] We firstly identified the writing year of Su's complete works, selected essays of five years before and after WPC, and used CC-LIWC(Classical Chinese version of Linguistic Inquiry and Word Count) to calculate the word frequency. Then, non-parametric tests were performed, and the CC-LIWC word categories with significant differences were obtained. Finally, the trend of word frequency changes of these categories were also reported. [Results] Before and after WPC, there are 9 categories with significant differences, which are the Third-person singular, Third-person plural, Tensem words, Focus present words, Negative Emotion words, Differentiation words, Perceptual Process words, See words and Time words. [Discussion] From the trend of the word frequency of the 9 categories, Su’s psychological characteristics were consistent with the Buddhist pursuit of being free from foreign objects, paying attention to the present, practicing non-differentiation, and getting out of worries after WPC. This result indicated that Su has been more advocating Buddhism practice after experiencing the political blow, and prove that the method of quantitative analysis is feasible.

Rui Ma, Fugui Xing, Miaorong Fan, Tingshao Zhu
A Conference Publishing System Based on Academic Social Network

Scholars and researchers participate in various academic conferences to share the latest research results and academic ideas. As more and more conferences are held, conference organizers need to promote their conference by setting up conference website. Therefore, conference organizers need a convenient and trusted tool to help them build a conference website. In addition, with the rapid growth of the Internet and the explosion of conference information, recommend conferences to scholars that interest them becomes important. For this consideration, we designed and implemented an academic conference publishing system, which can publish conference information quickly, implements multi-level management and recommends conferences that they are interested in for system users. In addition, by associating with SCHOLAT, our system presents conference members’ personal academic information and provide an online communication platform. We simulate the actual use environment to deploy and verify the system, and it is proved that the system has excellent performance in security, availability, authority and other aspects.

Jiongsheng Guo, Jianguo Li, Yong Tang, Weisheng Li
Software Component Library Management Mechanism for Equipment Parts Service Value-Net

Software reuse realizes the sharing of software resources, and component-based reuse is the main form of software reuse. The classification, storage, retrieval, and release of a large number of component resources require efficient component library management methods. This paper proposes an open software component library management mechanism based on microservices. Taking manufacturing product service life cycle value chain collaboration as a case, it realizes a domain-oriented microservice granularity division mechanism and forms a domain-oriented software component representation, warehousing, discovery, selection, arrangement, filing, and other compatible open software component library management mechanisms; realization of the design of an open software component management system for manufacturing product operation and maintenance reengineering value chain collaboration, The simulation verifies the open ability and management efficiency of the management mechanism.

Zhuo Tian, Changyou Zhang, Xiaofeng Cai, Jiaojiao Xiao
No-Reference Quality Assessment for UAV Patrol Images of Transmission Line

Uav patrol has gradually become the main operation mode of transmission line patrol task, however, due to the influence of the shooting mode and weather, the patrol images are inevitably distorted, resulting in quality degradation. In order to effectively evaluate the patrol image quality, this paper proposes a no-reference quality assessment method. Specifically, we first construct a dedicated patrol image quality assessment database, and then propose a no-referenced quality assessment model based on structure, texture and exposure. The experimental result shows that the method surpasses existing methods and is highly consistent with the quality labels.

Xujuan Fan, Xiancong Zhang, Jinqiang He, Yongli Liao, Dengjie Zhu
An Inclusive Finance Consortium Blockchain Platform for Secure Data Storage and Value Analysis for Small and Medium-Sized Enterprises

In the era of big data, people pay more and more attention to user privacy and data security. The market size of Small and Medium-sized Enterprises (SMEs) in China is sizable. Nevertheless, due to problems of data dispersion and lack of data features, it is very difficult to make use of the massive data of SMEs scattered in various institutions effectively, which leads to the inability to reflect the value of data. One of the problems is how to credit for SMEs better. Supported by federated learning for such scenarios, we present an inclusive Finance Consortium Blockchain platform in this paper. On the one hand, the platform combines decentralized identity and Blockchain as the underlying architecture, which guarantees authenticity of the data source and safe storage of user data on the chain. The smart contract mechanism provided by Blockchain can also assist secure storage and incentive mechanism of federated learning models effectively. On the other hand, we have innovatively introduced an asynchronous Federated Learning mode based on transfer learning, which encrypts the well-designed pre-training model and transfers it to each participant to guide training of the participant's local model. In the model reasoning stage, all the participants participate in a joint evaluation according to the local model and push the reasoning results on the Blockchain. The smart contract takes the weighted sum of the reasoning results provided by all the participants as the final result of shared model reasoning.

Jiaxi Liu, Peihang Liu, Zhonghong Ou, Guangwei Zhang, Meina Song
An Under-Sampling Method of Unbalanced Data Classification Based on Support Vector

To address the problem of unbalanced class distribution of power grid transmission line fault data, the number of fault classes is relatively smaller compared to the number of normal classes, an algorithm based on support vector under-sampling is proposed for transmission line fault classification. The method obtains the support vector on the original data, calculates the distance from the majority of the classes to the $$k$$ k nearest neighbor support vector, then calculates the class bit statistics to measure the local density information according to the distance, and finally under-samples based on the size of the sample class bit statistics. The bird nest dataset and insulator dataset are selected for performance evaluation, and the results show that this method has a good classification effect on unbalanced data, provides a theoretical reference for unbalanced data classification research, and has a certain practical value in the problem of grid transmission line fault classification.

Jinqiang He, Yongli Liao, Dengjie Zhu, Xujuan Fan, Xiancong Zhang
Image Classification Algorithm for Transmission Line Defects Based on Dual-Channel Feature Fusion

The power system is of great significance to the normal production of society and the daily life of the people, so regular inspection of transmission lines is essential. However, transmission lines are usually exposed to the outdoors, and the surrounding terrain and environment are complex, which may lead to problems such as structural aging and mechanical strength reduction, which in turn may lead to large area power outages and cause huge economic losses. In this paper, a two-channel feature fusion classification method is proposed to address the transmission line image classification problem. Using a two-channel parallel network structure, a neural network model is constructed to fuse the overall and local feature information, and then determine whether there are defects in the transmission line images. The experimental results show that the classification accuracy of the two-channel parallel convolutional neural network based on ResNet32 is 82.24% and 77.87% for the bird’s nest defect and insulator burst defect, respectively, on the actual transmission line image dataset, which exceeds the classification accuracy of other CNN models. This indicates that the classification accuracy can be effectively improved by fusing feature information.

Yongli Liao, Jinqiang He, Dengjie Zhu, Xujuan Fan, Xiancong Zhang
Research on Alarm Causality Filtering Based on Association Mining

Mining the association rules in the alarm data generated by network is an important method for operations to monitor and manage the network equipment. Analyzing the correlation of alarms through association rule mining algorithms can effectively simplify alarms and help locate network faults. Since the network alarm data has an obvious chronological relationship, it needs to be processed by the association rule mining algorithm based on time series. Through investigation, it is found that current association rule algorithms based on time series lack the determination of the realistic cause-and-effect relationship between successive alarms. Therefore, in order to improve the effectiveness of the association algorithm, this paper adopts an association mining algorithm based on the existing time series, which supports filtering the useless sequential associated items that have no causal relationship in the results. The experimental and analytical results show that the proposed method is effective.

Yuan Liu, Yi Man, Jianuo Cui
Exploring Psycholinguistic Differences Between Song and Ming Emperors Bases on Literary Edicts

Imperial edicts in ancient China were with strong political preference and practicality. It is very meaningful to interpret the psychological meaning of the emperors and necessary to analyze the sociality and individuality of emperors based on their imperial edicts. This paper analyzed the differences of psycholinguistic features in imperial edicts of Song and Ming dynasties via Classic Chinese LIWC (CC-LIWC) to obtain word frequency results for each word category in the edicts and used statistical tests to compare the differences of functional words-personal pronouns, emotional process words, cognitive insight words, physiological process words and motivational level words - in the edicts of Song and Ming dynasties. The result indicates the differences in CC-LIWC lexical frequencies between Ming and Song dynasties had an impact on the intensity of the emperors’work and their mentality in dealing with state issues.

Shuangyu Liu, Tingshao Zhu
The Influence of the Reform of Entrance Examination on University Development

The university entrance examination application is a very important last step for university entrance examination students. It is not only related to the future academic career and career development of candidates, but also affects the future direction of professional construction in universities. Shandong Province has been implementing the “university + major” application filling and filing admission mode, starting from 2020, will be changed to a new mode of “major (category) + university”. In order to explore the influence of the reform of university entrance examination on the development of universities, this article starts from the collection of questionnaires and analyzes the data, showing the relevant impact and reasons of the reform of university entrance examination, and puts forward constructive suggestions on the major construction and enrollment publicity of universities.

Dongfang Wan, Chenglin Zheng, Yue Wang, Wenjia Hu, Xinyi Ma, Jinjiao Lin
Backmatter
Metadata
Title
Human Centered Computing
Editors
Qiaohong Zu
Yong Tang
Vladimir Mladenović
Copyright Year
2021
Electronic ISBN
978-3-030-70626-5
Print ISBN
978-3-030-70625-8
DOI
https://doi.org/10.1007/978-3-030-70626-5

Premium Partner