Mobile users can open program in new tab for better viewing.

Open program in new tab

Day 1 11/07/2020
Room #1

Opening session 09:00 - 09:05

Opening speech by General Chair: Prof. Baoqi Huang (Inner Mongolia University, China)

Welcome message by EAI Conference Manager 09:05 - 09:10

Welcome message by EAI Community Manager 09:10 - 09:15

Keynote speech by Winston K.G. Seah 09:15 - 09:35

Professor of Network Engineering in the School of Engineering and Computer Science, Victoria University of Wellington, New Zealand

Keynote speech by Celimuge Wu 09:35 - 10:00

Associate Professor, The University of Electro-Communications, Japan

Keynote speech by Zheli Liu 10:00 - 10:25

Vice dean of College of Computer Science, Vice dean of College of Cyber Science, Nankai University, China

Coffee break (10 minutes) 10:25 - 10:35

Session 1 10:35 - 12:00

09:00 - 09:00
Measuring the impact of public transit on the transmission of epidemics.

In many developing countries, public transit plays an important role in daily life. However, few existing methods have considered the influence of public transit in their models. In this work, we present a dual-perspective view of the epidemic spreading process of the individual that involves both contamination in places (such as work places and homes) and public transit (such as buses and trains). In more detail, we consider a group of individuals who travel to some places using public transit, and introduce public transit into the epidemic spreading process. Our simulation results suggest that individuals with a high public transit trip contribution rate will increase the volume of infectious people when an infectious disease outbreak occurs by affecting the social network through the public transit trip contribution rate.
Authors: Yuan Bai (Department of Integrative Biology, University of Texas at Austin, Austin, 78705,The United States), Qiuyang Huang (College of Computer Science and Technology, Jilin University, Changchun 130117,China), Zhanwei Du (Department of Integrative Biology, University of Texas at Austin, Austin, 78705,The United States),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
The spatiotemporal traffic accident risk analysis in urban traffic network.

Traffic accidents seriously threaten people's lives and property all over the world. Therefore, it is of great significance to human society to have a long-term traffic accidents data with detail temporal and geographic information in a specific space, which can be used for traffic accident hotspots identification to reduce the incidence of traffic accidents. Here, we obtain a one-year dataset of traffic accidents of the city center in Changchun, Northeast China, in 2017. In this paper, we analyze the risk of traffic accident in urban area, and then discover the characteristics of traffic accidents at the temporal and spatial aspect. We construct a traffic network, which takes crossings as nodes and road sections as edges and weighted by the total number of traffic accidents. In addition, we integrate road structure data and meteorological data to explore the characteristics of the traffic network.
Authors: Chijun Zhang (Jilin University of Finance and Economics), Jing jin (Jilin University of Finance and Economics), Qiuyang Huang (Jilin University), Zhanwei Du (Key Laboratory of Urban Land Resources Monitoring and Simulation, MNR), Zhilu Yuan (Shenzhen University, Research Institute for Smart Cities.), Shengjun Tang (Shenzhen University, Research Institute for Smart Cities.), Yang Liu (Jilin University of Finance and Economics),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Enhanced WPA2/PSK for Preventing Authentication Cracking

With the popularization of mobile phones and Wi-Fi hotspots, the diversification of wireless communication applications has rapidly growing. Wi-Fi Protected Access (WPA), offered by network user authentication and communication encryption, is the most generally used mechanism to protect users in wireless networks. This paper has discussed the weakness of 4-way handshake procedure in Wi-Fi Protected Access 2/Pre-Shared Key (WPA2/PSK) and proposed an enhance WPA2/PSK by adding timestamp parameter to prevent authentication cracking. The experiments have compared WPA2/PSK with Enhanced WPA2/PSK cracking using Kali Linux tool and the result is given.
Authors: Chin-Ling Chen (Department of Information Management, National Pingtung University, Taiwan), Supaporn Punya (Department of Computer Science, RMUTT, Thailand),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
A Study on the Error Characteristics of Smartphone Inertial Sensors

The inertial sensors embedded in current smartphones are being used in a variety of applications, including motion monitoring, safe driving, panoramic roaming, Pedestrian Dead Reckoning (PDR), etc. Since the performance of these sensors has significant influences on these applications, it is of great value to comprehensively understand how the measurements returned by these sensors are statistically distributed. Most existing studies assume white Gaussian noises in sensor measurements, which is not experimentally confirmed in realistic and dynamic scenarios with commercial off-the-shelf (COTS) smartphones. In this paper, we study the statistical error characteristics of sensor measurements through extensive experiments in practice. The experimental results reveal that, when the device is stationary, the sensor measurement errors fully obey the standard Gaussian distribution; when the speed of smartphones increases, the sensor measurement errors begin rising, and the discrepancy between its distribution and the Gaussian distribution is enlarged. This paper establishes foundation for studying the statistical characteristics of the measurement errors of smartphone inertial sensors.
Authors: Huifeng Li (School of Computer, HulunBuir University, HulunBuir, China),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Design the tunable wideband filter for DDS+PLL hybrid frequency synthesizer

In this paper, the tunable wideband bandpass filter is designed, which is used in hybrid frequency synthesizer of PLL+DDS mixing in the outside of the feedback loop. The channels of tunable wideband bandpass filter is chosen by two ADGM1304 single-pole, four-throw (SP4T) MEMS switch. And they are integrated on a high-frequency board with a substrate of Ro4350B.The central frequency of bandpass filter is 2.32 GHz, 2.38 GHz, 2.44 GHz and 2.5 GHz respectively. A wideband filter with adjustable center frequency is designed and the bandwidth is up to 240MHz. Finally, physical tests show the spurious components and unwanted spectral components, especially near-end spurs at the center frequency are removed basically by the tunable broadband bandpass filter.
Authors: Yuxin Zhou (College of Electronic Information Engineering, Inner Mongolia University), Shaoting Cheng (College of Electronic Information Engineering, Inner Mongolia University), Xuemei Lei (College of Electronic Information Engineering, Inner Mongolia University),
Hide Authors & Abstract

Show Authors & Abstract

Session 2 12:00 - 13:00

09:00 - 09:00
Research on Community-Based Opportunistic Network Routing Protocol

The opportunity network is realized through the internode movement to achieve inter-network communication. There is not a complete communication path between the source node and the destination node in the network. This paper studies the opportunity network routing protocol based on the community. First, comparing the advantages and disadvantages of GN and K-means two community partition algorithm, Select the algorithm with high accuracy, high data transmission rate, and delay of the small GN algorithm. Then the GN algorithm is applied to the and Spray and Wait routing protocol. Regardless of the size of the network, the node density, The protocol is scalable and can maintain good performance.
Authors: Zhanwei Liu (Inner Mongolia Electronic Information Vocational Technical College), Wenbo Yuan (Inner Mongolia Electronic Information Vocational Technical College), Na Su (Inner Mongolia Electronic Information Vocational Technical College), Hui Wang (Inner Mongolia Electronic Information Vocational Technical College),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Performance analysis of MPTCP under high load based on SDN environment

Multipath Transmission Control Protocol (MPTCP) is in a rapid development process. MPTCP allows a network node to utilize multiple network interfaces and IP paths at the same time. It can take full advantage of network resources and provide reliable transmission, which brings advantages to users in terms of performance and reliability. In order to study the performance of MPTCP under high load, this paper uses Mininet to create an SDN environment and compare the performance differences between MPTCP and TCP under high load, and simulates a common Web application network architecture. The performance of MPTCP under this architecture is tested and analyzed. The test results show that MPTCP performs better than traditional TCP under high load. Besides, its performance can be optimized furtherly by adjusting related parameters.
Authors: Jiahui Hou (Changchun University of Science and Technology), Dinghui Hou (Changchun University of Science and Technology), Bixin Tao (Changchun University of Science and Technology), Hui Qi (Changchun University of Science and Technology), Xiaoqiang Di (Changchun University of Science and Technology), Weiwu Ren (Changchun University of Science and Technology), Ligang Cong (Changchun University of Science and Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Performance Analysis of QUIC-UDP Protocol under High Load

The QUIC protocol is currently recognized as a network pro- tocol that is expected to replace TCP. It is characterized by encryption, multiplexing, and low latency.It was proposed by Google in 2013 and aims to improve the transmission performance of HTTPS traffic and achieve rapid deployment and continuous development of transmission mechanisms.QUIC has gone through many versions since its release, and previous researchers have compared the transmission performance of QUIC and TCP. In this paper, the pressure test tool vegeta is modified,and the modified vegeta is used to test the TCP and QUIC protocols in a high load environment and collect the results to evaluate the performance of different protocols. Experiments show that under high load network conditions, the TCP protocol has better performance than the QUIC protocol; IQUIC (IETF QUIC) performs better than GQUIC (Google QUIC) at lower attack frequencies; as the attack frequency increases, IQUIC Performance decreases faster than GQUIC performance.
Authors: Lin Qi (Changchun University of Science and Technology), Zhihong Qiao (Changchun University of Science and Technology, Changchun), Aowei Zhang (Changchun University of Science and Technology), Hui Qi (Changchun University of Science and Technology), Weiwu Ren (Changchun University of Science and Technology), Xiaoqiang Di (Changchun University of Science and Technology), Rui Wang (Changchun University of Science and Technology),
Hide Authors & Abstract

Show Authors & Abstract

Lunch Break (30 minutes) 13:00 - 13:30

Session 3 13:30 - 15:30

09:00 - 09:00
Study on Ruminant Recognition of Cows Based on Activity Data and Long Short-Term Memory Network

In this paper, the collected activity data with ruminating status label is used as the data set, based on the long short-term memory network in the recurrent neural network, in order to identify and judge the ruminating process of dairy cows. This paper analyzes the advantages of selecting activity data as input data and long short-term memory network as core algorithm, introduces the hardware design and composition of the self-developed activity data acquisition system, and describes the characteristics of long short-term memory network structure. It is innovative to combine cow activity data with long short-term memory network to identify ruminating in the time period of cow activity data. The experimental results show that the long short-term memory network has different recognition effects on dairy cows of different individuals through the learning of activity data, and the accuracy of ruminating recognition of the whole data is 0.78. This method is effective and feasible. It can provide ideas for the related research of intelligent animal husbandry.
Authors: Shuai Hou (College of Electronic Information Engineering, Inner Mongolia University), Xiaodong Cheng (College of Electronic Information Engineering, Inner Mongolia University), Mingshu Han (College of Electronic Information Engineering, Inner Mongolia University),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Evaluation Method for Water Network Connectivity Based on Graph Theory

Water network connectivity plays a pivotal role in water security and ecological civilization, which also has been viewed as an important part for wa-ter comprehensive improvement. Using graph theory, the water network can be modeled as an undirected graph with multiple interconnected elements which represent rivers by edges and junctions by nodes. In this paper, the weight on edge represents the simplified river cross-section area which can be equivalent to flow capacity between two adjacent nodes. In order to obtain the flow capaci-ty between any two nodes, a maximum flow evaluation scheme is designed by using Boykov-Kolmogorov algorithm. Then by using the maximum flow be-tween nodes before and after dredging based on node degree features, a solution is assayed for average flow capacity of each node and water network connectiv-ity. The proposed approach has been tested on the river network of Xiacheng District in Hangzhou with dredging data in year 2016. The result shows that the water network connectivity is improved by 7.89% over the whole area and more than 40% in part region by dredging, and significant influenced by intersect density and dredging extent.
Authors: Yujia Zhou (Zhejiang Institute of Hydraulics & Estuary), Yannan Shi (Zhejiang Institute of Hydraulics & Estuary), Hui Wu (Zhejiang Institute of Hydraulics & Estuary), Yifan Chen (Zhejiang Institute of Hydraulics & Estuary), Qiong Yang (Zhejiang Institute of Hydraulics & Estuary), Zhongshuai Fang (Zhejiang Institute of Hydraulics & Estuary),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
A cross-domain secure deduplication scheme based on threshold blind signature

In the cloud storage environment, client-side deduplication can perform file repetitive detection locally. However, client-side deduplication still faces many security challenges. First, if the file hash value is used as evidence for repetitive detection, the attacker is likely to obtain the entire file information through the hash value of the file. Secondly, in order to protect data privacy, convergence encryption is widely used in the data deduplication scheme. Since the data itself is predictable, convergence encryption is still vulnerable to brute force attacks. In order to solve the above problems, this paper proposes to construct a secure deduplication scheme by using the threshold blind signature method. The generation of the convergence key is coordinated by multiple key servers, ensuring the confidentiality of the convergence key and effectively solving the violent dictionary attack problem. At the same time, since the key center is introduced to centrally manage the keys, the interaction between the key servers is reduced, and the key generation efficiency is improved. In addition, since the key server in this paper can be distributed in multiple independent network domains and interact with the key center through the Internet, the problem of cross-domain deduplication is solved. The experimental results show that the performance of this scheme is greatly improved in terms of system initialization and key generation.
Authors: Jinlei Du (Changchun University of Science and Technology), Jide Deng (Changchun University of Science and Technology), Hui Qi (Changchun University of Science and Technology), Xiaoqiang Di (Changchun University of Science and Technology), Zhengang Jiang (Changchun University of Science and Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Reinforcement Learning for Rack-Level Cooling

In recent years, %with the popularity of the Internet and the rapid development of the big data and cloud computing industry, the number and scale of data centers have increased rapidly. We have seen a rapid growth in big data and cloud computing industry, because of the rapid development in Internet technology. That's why the number and scale of data center have increased rapidly.A data center is a warehouse-level IT facility that hosts many servers. Because of the uneven heat production and heat dissipation of the servers in a rack, the hot spots emerges. In order to maintain the CPU temperature hence the computing performance,the server cooling is very critical. A common solution is to increase the speed of the Computer Room Air Handler (CRAH) blower and increase the flow of cold air. Nevertheless, this solution can only partially address the issue and raise the cooling energy consumption.
Authors: Yanduo Duan Yanduo Duan (Inner Mongolia University of Technology), Jianxiong Wan Jianxiong Wan (Inner Mongolia University of Technology), Jie Zhou Jie Zhou (Inner Mongolia University of Technology), Gaoxiang Cong Gaoxiang Cong (Inner Mongolia University of Technology), Zeeshan Rasheed Zeeshan Rasheed (Inner Mongolia University of Technology), Tianyang Hua Tianyang Hua (Inner Mongolia University of Technology),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
A Comprehensive Cellular Learning Automata Based Routing Algorithm in Opportunistic Networks

A distinctive cellular learning automata based routing algorithm is proposed which exploits the ambient nodes feature to polish up the performance of oppor-tunistic networks. The factors of each phase in the routing procedure of store-carry-forward are taken into account. Messages would be dropped on the basis of the dropping probability when congestion occurs during the store phase. Energy consumption would be balanced according to the threshold set by the node itself which is used to accept messages in the carry phase. Connection duration be-tween nodes has been estimated to reduce the energy waste caused by fragment messages transmission during the forwarding process. To evaluate the validity of our proposed algorithm, we conduct comprehensive simulation experiments on the ONE platform. The results show that the proposed routing algorithm achieves higher delivery ratio and less overhead ratio. In addition, it gains a balance of en-ergy consumption and an enhancement of the whole network performances.
Authors: Feng Zhang (School of Computer and Information Technology, Shanxi University, Shanxi 030006, China),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Research on The Application of Personalized Course Recommendation of Learn to Rank Based on Knowledge Graph

Aiming at the problem that the computer technology level of most non computer major students in Colleges and universities is not even, which can not be effectively aimed at teaching,Use the evaluation data of students for each course chapter to integrate the Knowledge Graph,Build a mixed model of Learn to Rank,student user migration and basic characteristics,Finally,the top-N recommended courses are sorted.In general,the recommendation algorithm is only applied to the recommendation service of e-commerce platform, The personalized recommendation algorithm proposed in this paper is mainly used to serve students to improve the quality of course teaching.
Authors: Hao Wu (Inner Mongolia Normal University, Hohhot, Inner Mongolia, 010020, China), FanJun Meng (Inner Mongolia Normal University, Hohhot, Inner Mongolia, 010020, China),
Hide Authors & Abstract

Show Authors & Abstract

Coffee break (20 minutes) 15:30 - 15:50

Workshop session 15:50 - 17:00

09:00 - 09:00
IoT-oriented designated verifier signature scheme

In order to reduce the computational cost of digital signature scheme in internet of things and improve the security of signature, based on analyzing the security requirement of Internet of things and SM2 Algorithm, a secure digital signature scheme in internet of things is proposed. The elliptic curve is used to construct the scheme, which improves the computing efficiency and meets the lightweight requirement in IoT environment. Specifies the verifier feature that meets the security requirements of a particular environment. The analysis shows that the scheme has the characteristics of message integrity, anti-repudiation, designated verification and anti-forgery.
Authors: Min Li (School of Computer Engineering, Jingchu university of technology, Jinmeng Hubei, 448000 China),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Remote sensing image recognition using deep belief network

How to acquire high-dimensional data such as remote sensing image efficiently and accurately has become a research hotpot recent years. Deep learning is a kind of learning method which uses many kinds of simple layers to learn the mapping relation of complex layers. The authors will attempt to apply the deep belief network model (DBN), which is important in deep learning, to remote sensing image recognition. Using the new large-scale remote sensing image data set with abundant changes as the research object, the hierarchical training mechanism of DBNs is studied and compared with CNNS, the results show that the accuracy and speed of DBNs is better than that of CNNS, and more effective information can be obtained.
Authors: Min Li (School of Computer Engineering,Jingchu university of technology,Jinmeng,Hubei,448000,China),
Hide Authors & Abstract

Show Authors & Abstract
09:00 - 09:00
Traffic Sign Recognition Algorithm Model Based on Machine Learning

At present, the development of our country is getting better and better, the vehicles running on the road are also increasing, so the traffic problems are becoming more and more obvious. This kind of problem will also set up the development of the modern city. At this time, the intelligent transportation technology has also developed, and the above problems are gradually treated by new methods. It has become one of the hot topics in the field of an intelligent transportation system to use the advantages of machine learning technology to deal with traffic congestion and improve the traffic efficiency of the road network. It has high theoretical and practical significance to detect road traffic signs in the actual scene. A method based on directional gradient histogram features combined with a support vector machine classifier is proposed. Each type of traffic sign has its own characteristics. By classifying its appearance and color, many recognition methods are produced, and the target area is retained by a unique method, thus the feature can be extracted and identified. Make the paving. The main work is to obtain a training sample, and then add the direction gradient histogram of the sample library into the SVM for training, to get a one to many classifiers to be tuned continuously, it can realize the rapid and accurate judgment of multiple traffic signs.
Authors: Hui Li (Inner Mongolia Electronic Information Vocational Technical College), Jun Feng (Inner Mongolia Electronic Information Vocational Technical College), Jialing Liu (Inner Mongolia Electronic Information Vocational Technical College), Yanli Gong (Inner Mongolia Electronic Information Vocational Technical College),
Hide Authors & Abstract

Show Authors & Abstract

Closing session 17:00 - 17:15

Day 2 12/07/2020