School of Advanced Technology

School of Advanced Technology
Xi'an Jiaotong-Liverpool University
111 Ren'ai Road Suzhou Dushu Lake Science and Education Innovation District , Suzhou Industrial Park
Suzhou,Jiangsu Province,P. R. China,215123
1. Preface


Source:ACM International Conference Proceeding Series,2020,Vol.

2. Exploring Haptic Feedback for Common Message Notification between Intimate Couples with Smartwatches

Author:Graham-Knight,John Brandon;Corbett,Jon Michael Robert;Lasserre,Patricia;Liang,Hai Ning;Hasan,Khalad

Source:ACM International Conference Proceeding Series,2020,Vol.

Abstract:In this paper, we explore haptic feedback for smartwatches (i.e., vibrations) as a means to transmit the conversational meaning of short text messages through a non-visual mode of communication between intimate people. The current use of smartwatch vibrations is limited to basic patterns to convey simple information such as notifying users on an incoming phone call or a text message. We envision the use of vibrations to notify commonly exchanged messages between intimate ones by providing discreet feedback on their wrist. This form of communication preserves the flow of users' primary activities without making them to look at the display, supporting unobtrusive interaction. We start our exploration by examining the common short text messages that intimate people, like couples, exchange in their daily life. We next investigate the vibration properties such as vibration duration and number of vibrations that are suitable to convey the meaning of these messages. We further examine users' accuracy of detecting and extracting the meaning of messages from vibrations where our results report an accuracy of 95%% while perceiving the correct meanings. We conclude with design recommendations for using such vibrational feedback for communicating information with intimate partners.
3. Protein image classification based on convolutional neural network and recurrent neural network

Author:Qu,Yuanying;Song,Haowei;Liang,Hai Ning;Ma,Jieming;Wang,Wei

Source:ACM International Conference Proceeding Series,2019,Vol.

Abstract:Proteins are an essential component in the cell where the functions are executed to enable life. At present, the manual evaluation and classification of protein images is not practical given the current situation for generated images on a large scale. Hence, the requirement of automating protein image classification can be quite useful. Until now, classical machine learning and convolutional neural network algorithms have achieved results in image classification without the desired level of accuracy. Under the circumstances, the research aims to propose an accurate classified model for protein image classification by combining a convolutional neural network with a recurrent neural network.
4. Anomaly detection for machinery by using Big Data Real-Time processing and clustering technique


Source:ACM International Conference Proceeding Series,2019,Vol.

Abstract:© 2019 Association for Computing Machinery. This paper aims to apply techniques of Big Data Analytics including K-Means Clustering to diagnose potential problems for offshore rotating machinery. The innovative methods are attempted in both Batch K-Means and Streaming K-Means. Their performances are compared with the conventional signal analysis method. Both KMeans models have a better performance on detecting significant mechanical faults as anomalies for offshore rotating machinery which can be considered as appropriate method for machine operational maintenance.
5. Topic-graph based recommendation on social tagging systems: A study on researchgate


Source:ACM International Conference Proceeding Series,2018,Vol.

Abstract:Social Tagging Systems (STSs), allowing users to annotate online resources with freely chosen key words, are an essential type of application in Web 2.0. Recommendation in STSs can prevent information overload and support users to locate relevant items for interaction. This article applies a Topic-Graph Based Recommendation approach. First, we discover semantics behind tags through topic inferencing with Latent Dirichlet Allocation (LDA). Second, we conduct Graph-Based Recommendation for tags and users. The approach is applied on a real-word representative data sample collected from the Academic Social Networking Site ResearchGate. The widely used Co-occurrence Based Graph Recommendation is implemented as a baseline approach. Our preliminary human evaluation shows that the Topic-Graph Based Recommendation can complement to the Co-occurrence baseline to provide more reliable results. Future studies are provided on leveraging future features and information for recommendation from researcher-generated social media data on a large scale.
6. Sentimental Analysis of Chinese New Social Media for stock market information

Author:Chen, GH;He, LL;Papangelis, K


Abstract:The popularity of social media provides a new platform to collect big social data. With the development of social sentiment analysis, high business value extracted from social data are applied to various fields. Asset price prediction, as an emerging topic based on the behavioral economics, is closely linked to social data analysis. This research aims to explore the effort of sentiment analysis data in the prediction of China composite index. Data from Sina Weibo and financial community is processed to get the useful sentiment information. A linear regression model and a multilayer neural network algorithm are used to prove the relationship between social data and price market prediction. The experiments show a strong relationship between the numbers of negative sentiment and a multilayer perceptron model is effectively built to predict the composite index.
7. Semi-unsupervised lifelong learning for sentiment classification Less manual data annotation and more self-studying

Author:Hong, Xianbin ; Pal, Gautam ; Guan, Sheng-Uei ; Wong, Prudence ; Liu, Dawei ; Man, Ka Lok ; Huang, Xin

Source:ACM International Conference Proceeding Series,2019,Vol.

Abstract:Lifelong machine learning is a novel machine learning paradigm which can continually accumulate knowledge during learning. The knowledge extracting and reusing abilities enable the lifelong machine learning to solve the related problems. The traditional approaches like Naïve Bayes and some neural network based approaches only aim to achieve the best performance upon a single task. Unlike them, the lifelong machine learning in this paper focus on how to accumulate knowledge during learning and leverage them for the further tasks. Meanwhile, the demand for labeled data for training also be significantly decreased with the knowledge reusing. This paper suggests that the aim of the lifelong learning is to use less labeled data and computational cost to achieve the performance as well as or even better than the supervised learning. © 2019 Association for Computing Machinery.
8. Mapping media and meaning Autoethnography as an approach to designing personal heritage soundscapes

Author:Chamberlain, Alan ; Bødker, Mads ; Papangelis, Konstantinos

Source:ACM International Conference Proceeding Series,2017,Vol.Part F131930

Abstract:The paper presents reflections on understanding the issues of designing of locative sonic memory-scapes. As physical space and digital media become ever more intertwined, together forming and augmenting meaning and experience, we need methods to further explore possible ways in which physical places and intangible personal content can be used to develop meaningful experiences. The paper explores the use of autoethnography as a method for soundscape design in the fields of personal heritage and locative media. Specifically, we explore possible connections between digital media, space and 'meaning making', suggesting how autoethnographies might help discover design opportunities for merging digital media and places. These are methods that are more personally relevant than those typically associated with a more system-based design approaches that we often find are less sensitive to the way that emotion, relationships, memory and meaning come together. As a way to expand upon these relationships we also reflect on relations between personal and community-based responses. © 2017 Association for Computing Machinery.
9. Assessing the Effects of a Full-body Motion-based Exergame in Virtual Reality

Author:Xu, WG;Liang, HN;Yu, YF;Monteiro, DO;Hasan, K;Fleming, C


Abstract:There is a growing number of commercial exergames tailored for virtual reality (VR) head-mounted displays (HMDs). However, empirical evaluations of the feasibility and effects of such games, especially those requiring full body motions, are still limited. This research investigates the effects of playing a full-body motion VR exergame. We have conducted a study with a game that has two modes, single- and multi-tasking, and with two types of displays, a VR HMD and a 50-inch Large Display, to collect data about users' game experience, simulator sickness, and brainwave responses. Our results indicate that (1) Participants have the same level of game experience and simulator sickness when playing the exergame in VR and Large Display; (2) VR has increased participants' Theta wave; (3) Participants believe multi-tasking is more challenging and show a higher level of simulator sickness than single-tasking; and (4) Participants have a worse game performance in multi-tasking than single-tasking.
10. GNU Radio Based Bandpass Sampling Radio Processor

Author:Wang, HM;Wang, FG;Li, SY;Lee, S;Yao, C;Balykbay, M


Abstract:Bandpass(1) sampling (BPS), which can directly down-convert and digitize RF signals, is widely used in software-defined radio (SDR). Recently, GNU Radio, a free software toolkit for building SDR, has become popular. Based on BPS and signal-processing techniques, a receiver architecture for a digital RF frontend was presented and an SDR system using GNU Radio was built. The low-cost platform design of the bandpass sampling radio processor (BPSRP) was focused on and a multiband receiver without modification of the RF hardware was realized. An SDR that simultaneously receives a DQPSK video signal, a 16QAM signal, and a WBMF signal were implemented to demonstrate our method.
11. Preface

Author:Guan, Steven

Source:ACM International Conference Proceeding Series,2019,Vol.Part F148152

12. MK-Pad: A Mouse+Keyboard input technique for distance interaction through a mobile tablet device

Author:Lv,Chunchuan;Yuan,Boyuan;Bi,Ran;Hai-Ning;Diniz,Nancy;Wong,M. L.Dennis

Source:ACM International Conference Proceeding Series,2013,Vol.

Abstract:We introduce MK-Pad (Mouse+Keyboard Pad), a technique for entering text and performing mouse operations using a tablet device for distance interaction. MK-Pad uses the screen of a 10.1" tablet touchscreen to host a soft keyboard and turns the screen into a large multi-touch trackpad. The multi-touch capabilities of the tablet make it possible to avoid the need for explicit mode switching between textentry and mouse operations. Similarly, because of the relatively large size of the tablet display, we are able to map the entire external screen onto the tablet display and this provides users with both absolute and relative cursor positioning: tapping causes the cursor to jump to the corresponding location, providing rapid movement across large distances, while clutching using relative mode supports fine positioning control. We conducted two studies. We use data from the first study to inform the design of MK-Pad. In the second study we compare MKPad against the standard mouse and keyboard. The results show that MK-Pad has potential and a good alternative to mouse and keyboard for distance interaction with large displays. Copyright 2013 ACM.
13. Experimental Analysis of the Facial Expression Recognition of Male and Female

Author:Huang, GM;Cui, J;Alam, M;Wong, KH


Abstract:With the development of deep learning, people have paid more and more attention to the research of facial expression recognition (FER), and obtained decent results in the laboratory. However, some studies have pointed out the defects of FER system itself based on the universal theory of expression and believed that human expression is specific. The purpose of this study is to analyze the influence of different gender data on the recognition rate of FER classification system. This study needs to prove that the recognition rate of different gender data in the existing FER system is different. In addition, it is necessary to confirm that there is a population recognition advantage between different gender groups in the experiment. Experiments construct a classification system by Inception V3 and transfer learning methods and design a comparative experiment. It was found that data sets with different gender ratios did influence the experimental results to some extent, and the recognition rate of female data was slightly higher than that of male data. Finally, it is concluded that models trained by male data have a higher rate of expression recognition for male group, as is the case with female data, which is similar to the situation of different cultural groups.
14. Security Risk Management Plan. Student Portal-Case Study

Author:Mogos, Gabriela

Source:ACM International Conference Proceeding Series,2020,Vol.

Abstract:A student portal is a regularly utilized expression to describe the login page where students can give a username and password to access an instruction association's projects and other learning related materials. For instance, a student who has taken a crack at an online program may utilize a university portal to get to online course materials, for example, articles, lectures and recordings, facilitated on the school's data bases. university portal might be utilized to give data about the school, unique activities and events, course information, schedules, scholarly resources and contact data. The paper presents several security issues that were detected at the Prince Sultan University, Riyadh, Saudi Arabia's portal. The Prince Sultan University (PSU) portal allows students to access the main website which is connected to PSU Moodle website and also connected to PSU Edugate website. Starting from the determined vulnerabilities, the paper presents a risk analysis of the sensitive data of a public institution, in cyberspace. © 2020 ACM.
15. Electrohydrodynamic Printing Process Monitoring for Diverse Microstructure Bioscaffold Fabrication

Author:Sun, Jie ; Jing, Linzhi ; Zhan, Ningpin ; Huang, Dejian ; Liang, Yung C.

Source:ACM International Conference Proceeding Series,2020,Vol.

Abstract:Electrohydrodynamic printing (EHDP) is able to precisely manipulate the position, size, and morphology of micro/nanofibers, and fabricate high resolution scaffolds using viscous biopolymer solutions. In order to ensure the reliable printing, it is very necessary to identify EHDP cone status during fabrication. In this work, we used a digital microscopic imaging technique to monitor EHDP cones during printing, with subsequent image processing. A convolutional neural network (CNN) is then developed to classify these EHDP cones. With the help of this monitoring and identification system, scaffolds with diverse triangular, hexagonal and coil-wall microstructures can be fabricated for tissue engineering applications. © 2020 ACM.
16. Preface

Author:Guan, Steven

Source:ACM International Conference Proceeding Series,2018,Vol.Part F137134

17. Lifelong Machine Learning: Outlook and Direction

Author:Hong, XB;Wong, P;Liu, DW;Guan, SU;Man, KL;Huang, X


Abstract:The Lifelong machine learning is an advanced machine learning paradigm and also is the key to the stronger AI. In this paper, we review the development history of the lifelong machine learning and evaluate the current stage. The aim, definition and main components of it is introduced. In addition, the bottleneck and possible solution also is discussed and the further development waypoint is proposed.
18. 4G-based Remote Manual Control for Unmanned Surface Vehicles

Author:Zhu, XH;Kong, SP;Yan, K;Yue, Y


Abstract:Remote manual control for USVs is essential when a USV fails to navigate or traps into a complicated river. Conventional transmitters and receivers are widely used to provide the utility of remote manual control for USVs. However, constrained by the power of transmitter, the communication distance between the USV and the user is limited. In this paper, a 4G-based remote control system for USVs is proposed. With the help of live video from a camera deployed on the USV, users can remotely control the USV using an Android APP and the 4G network. Compared to traditional remote control methods, our approach dramatically extends the control distance and improves the control flexibility of USVs. The approach is applied to a USV for water quality monitoring. Experimental results show that it has small communication delay and can remotely control the USV during the navigation.
Total 18 results found
Copyright 2006-2020 © Xi'an Jiaotong-Liverpool University 苏ICP备07016150号-1 京公网安备 11010102002019号