tocauthor: Wei_Z* : Human-Computer Interaction Bibliography Search

Pmomo: Projection Mapping on Movable 3D Object Real Reality Interfaces / Zhou, Yi / Xiao, Shuangjiu / Tang, Ning / Wei, Zhiyong / Chen, Xu Proceedings of the ACM CHI'16 Conference on Human Factors in Computing Systems 2016-05-07 v.1 p.781-790

ACM Digital Library Link

Summary: We introduce Pmomo (acronym of projection mapping on movable object), a dynamic projection mapping system that tracks the 6-DOF position of real-world object, and shades it with virtual 3D contents by projection. The system can precisely lock the projection on the moving object in real-time, even the one with complex geometry. Based on depth camera, we developed a novel and robust tracking method that samples the structure of the object into low-density point cloud, then performs an adaptive searching scheme for the registration procedure. As a fully interactive system, our method can handle both internal and external complex occlusions, and can quickly track back the object even when losing track. In order to further improve the realism of the projected virtual textures, our system innovatively culls occlusions away from projection, which is achieved by a facet-covering method. As a result, the Pmomo system enables the possibility of new interactive Augmented Reality applications that require high-quality dynamic projection effect.

Automatic Accident Detection and Alarm System Videos/Demos 1: / Wei, Zhuo / Lo, Swee-Won / Liang, Yu / Li, Tieyan / Shen, Jialie / Deng, Robert H. Proceedings of the 2015 ACM International Conference on Multimedia 2015-10-26 p.781-784

ACM Digital Library Link

Summary: Accident detection and alarm system is very important to detect possible accidents or dangers for the peoples using their mobile devices while walking, i.e., distracted walking. In this paper, we introduce an automatic accident detection and alarm system, called AutoADAS, which is fully implemented and tested on the real mobile devices. The proposed system can be activated either manually or automatically when user walks. Under the manual mode, user activates the system before distracted walking while under the automatic mode, a "user behaviour profiling" module is used to recognize (distracted) walking behaviours and an "object detection" module is activated. Using image processing and camera field of view (FOV), the distance and angle between the user and detected objects are estimated and then applied to identify whether any potential accidents can happen. The "accident analysis and prediction" module includes: temporal alarm that inputs the user's walking speed and distance with respect to the detected objects and outputs temporal accident prediction; spatial alarm that inputs the user's walking direction and angle with respect to the detected objects and outputs spatial accident prediction. Once the proposed system positively predicts a potential accident, the "alarm and suggestion" module alerts the user with text, sound or vibration.

Large-scale Knowledge Base Completion: Inferring via Grounding Network Sampling over Selected Instances Session 6F: Knowledge Bases / Wei, Zhuoyu / Zhao, Jun / Liu, Kang / Qi, Zhenyu / Sun, Zhengya / Tian, Guanhua Proceedings of the 2015 ACM Conference on Information and Knowledge Management 2015-10-19 p.1331-1340

ACM Digital Library Link

Summary: Constructing large-scale knowledge bases has attracted much attention in recent years, for which Knowledge Base Completion (KBC) is a key technique. In general, inferring new facts in a large-scale knowledge base is not a trivial task. The large number of inferred candidate facts has resulted in the failure of the majority of previous approaches. Inference approaches can achieve high precision for formulas that are accurate, but they are required to infer candidate instances one by one, and extremely large candidate sets bog them down in expensive calculations. In contrast, the existing embedding-based methods can easily calculate similarity-based scores for each candidate instance as opposed to using inference, so they can handle large-scale data. However, this type of method does not consider explicit logical semantics and usually has unsatisfactory precision. To resolve the limitations of the above two types of methods, we propose an approach through Inferring via Grounding Network Sampling over Selected Instances. We first employ an embedding-based model to make the instance selection and generate much smaller candidate sets for subsequent fact inference, which not only narrows the candidate sets but also filters out part of the noise instances. Then, we only make inferences within these candidate sets by running a data-driven inference algorithm on the Markov Logic Network (MLN), which is called Inferring via Grounding Network Sampling (INS). In this process, we especially incorporate the similarity priori generated by embedding-based models into INS to promote the inference precision. The experimental results show that our approach improved Hits@1 from 32.911% to 71.692% on the FB15K dataset and achieved much better AP@n evaluations than state-of-the-art methods.

Detect Rumors Using Time Series of Social Context Information on Microblogging Websites Short Papers: Information Retrieval / Ma, Jing / Gao, Wei / Wei, Zhongyu / Lu, Yueming / Wong, Kam-Fai Proceedings of the 2015 ACM Conference on Information and Knowledge Management 2015-10-19 p.1751-1754

ACM Digital Library Link

Summary: Automatically identifying rumors from online social media especially microblogging websites is an important research issue. Most of existing work for rumor detection focuses on modeling features related to microblog contents, users and propagation patterns, but ignore the importance of the variation of these social context features during the message propagation over time. In this study, we propose a novel approach to capture the temporal characteristics of these features based on the time series of rumor's lifecycle, for which time series modeling technique is applied to incorporate various social context information. Our experiments using the events in two microblog datasets confirm that the method outperforms state-of-the-art rumor detection approaches by large margins. Moreover, our model demonstrates strong performance on detecting rumors at early stage after their initial broadcast.

Gibberish, Assistant, or Master?: Using Tweets Linking to News for Extractive Single-Document Summarization Short Papers / Wei, Zhongyu / Gao, Wei Proceedings of the 2015 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval 2015-08-09 p.1003-1006

ACM Digital Library Link

Summary: Single-document summarization is a challenging task. In this paper, we explore effective ways using the tweets linking to news for generating extractive summary of each document. We reveal the very basic value of tweets that can be utilized by regarding every tweet as a vote for candidate sentences. Base on such finding, we resort to unsupervised summarization models by leveraging the linking tweets to master the ranking of candidate extracts via random walk on a heterogeneous graph. The advantage is that we can use the linking tweets to opportunistically "supervise" the summarization with no need of reference summaries. Furthermore, we analyze the influence of the volume and latency of tweets on the quality of output summaries since tweets come after news release. Compared to truly supervised summarizer unaware of tweets, our method achieves significantly better results with reasonably small tradeoff on latency; compared to the same using tweets as auxiliary features, our method is comparable while needing less tweets and much shorter time to achieve significant outperformance.

How Your Portrait Impresses People?: Inferring Personality Impressions from Portrait Contents Posters 1 / Nie, Jie / Cui, Peng / Yan, Yan / Huang, Lei / Li, Zhen / Wei, Zhiqiang Proceedings of the 2014 ACM International Conference on Multimedia 2014-11-03 p.905-908

ACM Digital Library Link

Summary: Whenever looking at a stranger's portrait, besides observable appearance, we always build a personality impression implicitly in our subconscious. It is quite interesting to ask how a portrait impresses people. This paper presents a novel method to infer personality impression from portrait. Firstly, a questionnaire is applied to demonstrate the consistence of people's impression. And then personality-related features are explored through the statistical analysis method. Finally, features are trained using Support Vector Machine. Experimental results demonstrate our method could achieve a precision of 52.14% and a recall of 52.78% on inferring 4 personalities from 2,463 randomly selected portraits of people downloaded from "Google images". Improvements of 44.04% and 37.91% are reported compared to a baseline method. And features contribution analysis deeply unveils the correspondence between portrait contents and personality impressions. Demonstrations with respect to visual patterns in portrait collages of different personalities further prove the effectiveness of the proposed method. Furthermore, we apply our method to analyze portraits of Hillary Clinton and obtain an interesting multifaceted figure of this famous politics, which is another proof of both our concept and method.

A Theoretical Model of Mental Workload in Pilots Based on Multiple Experimental Measurements Mental Workload and Stress / Wei, Zongmin / Zhuang, Damin / Wanyan, Xiaoru / Zhang, Huan / Liu, Chen EPCE 2014: 11th International Conference on Engineering Psychology and Cognitive Ergonomics 2014-06-22 p.104-113

Keywords: Mental workload; Human-machine interaction; MMN; SDNN; Eye blink

Link to Digital Content at Springer

Summary: The present study attempted to establish an effective discrimination and prediction model that can be applied to evaluate mental workload changes in human-machine interaction processes on aircraft flight deck. By adopting a combined measure based on primary task measurement, subjective measurement and physiological measurement, this study developed both experimental measurement and theoretical modeling of mental workload under flight simulation task conditions. The experimental results showed that, as the mental workload increased, the peak amplitude of Mismatch negativity (MMN) was significantly increased, SDNN (the standard deviation of R-R intervals) was significantly decreased, the number of eye blink was decreased significantly. Finally, a comprehensive mental workload discrimination and prediction model for the aircraft flight deck display interface was constructed by the Bayesian Fisher discrimination and classification method. The model's accuracy was checked by original validation method. When comparing the prediction and discrimination results of this comprehensive model with that of single indices, the former showed much higher accuracy.

Mainstream media behavior analysis on Twitter: a case study on UK general election / Wei, Zhongyu / He, Yulan / Gao, Wei / Li, Binyang / Zhou, Lanjun / Wong, Kam-fai Proceedings of the 2013 ACM Conference on Hypertext and Social Media 2013-05-01 p.174-178

ACM Digital Library Link

Summary: With the development of social media tools such as Facebook and Twitter, mainstream media organizations including newspapers and TV media have played an active role in engaging with their audience and strengthening their influence on the recently emerged platforms. In this paper, we analyze the behavior of mainstream media on Twitter and study how they exert their influence to shape public opinion during the UK's 2010 General Election. We first propose an empirical measure to quantify mainstream media bias based on sentiment analysis and show that it correlates better with the actual political bias in the UK media than the pure quantitative measures based on media coverage of various political parties. We then compare the information diffusion patterns from different categories of sources. We found that while mainstream media is good at seeding prominent information cascades, its role in shaping public opinion is being challenged by journalists since tweets from them are more likely to be retweeted and they spread faster and have longer lifespan compared to tweets from mainstream media. Moreover, the political bias of the journalists is a good indicator of the actual election results.

An evaluation of learning analytics to identify exploratory dialogue in online discussions Discourse analytics / Ferguson, Rebecca / Wei, Zhongyu / He, Yulan / Shum, Simon Buckingham LAK'13: 2013 International Conference on Learning Analytics and Knowledge 2013-04-08 p.85-93

ACM Digital Library Link

Summary: Social learning analytics are concerned with the process of knowledge construction as learners build knowledge together in their social and cultural environments. One of the most important tools employed during this process is language. In this paper we take exploratory dialogue, a joint form of co-reasoning, to be an external indicator that learning is taking place. Using techniques developed within the field of computational linguistics, we build on previous work using cue phrases to identify exploratory dialogue within online discussion. Automatic detection of this type of dialogue is framed as a binary classification task that labels each contribution to an online discussion as exploratory or non-exploratory. We describe the development of a self-training framework that employs discourse features and topical features for classification by integrating both cue-phrase matching and k-nearest neighbour classification. Experiments with a corpus constructed from the archive of a two-day online conference show that our proposed framework outperforms other approaches. A classifier developed using the self-training framework is able to make useful distinctions between the learning dialogue taking place at different times within an online conference as well as between the contributions of individual participants.

Features and predictors of problematic internet use in Chinese college students / Huang, R. L. / Lu, Z. / Liu, J. J. / You, Y. M. / Pan, Z. Q. / Wei, Z. / He, Q. / Wang, Z. Z. Behaviour and Information Technology 2009 v.28 n.5 p.485-490

Link to Article at informaworld

Summary: This study was set to investigate the prevalence of problematic internet use (PIU) among college students and the possible factors related to this disorder. About 4400 college students, ranging from freshmen to juniors, from eight different universities in Wuhan, China were surveyed. Young's Diagnostic Questionnaire for Internet Addiction (YDQ) and the Zung Self-rating Depression Scale were used to define PIU and depression accordingly. Data was analysed with chi-squared testing and logistic regression. Out of the 3496 participants, 9.58% (male 13.54%, female 4.88%) met the criteria of PIU. Factors such as heavy internet use habits, poor academic achievement, lack of love from the family, etc. were found to be significantly associated with PIU. About 48.51% (1696) of the students were light internet users, who use the internet <5 h/week, while 16.36% (572) were heavy users who use it more than 15 h/week, though heavy users were more likely to develop PIU. Also, 25.53% of the students with depression developed PIU, in comparison with 8.91% of PIU among those without depression (p < 0.001). Being male, frequent internet use, poor academic achievement, poor family atmosphere and lack of love from parents were predictors of PIU among college students. The habit and purpose of using the internet is diverse, which influences the susceptibility of PIU as well. There was a correlation between depression and the development of PIU as well.

Service-oriented data denormalization for scalable web applications Performance and scalability / Wei, Zhou / Dejun, Jiang / Pierre, Guillaume / Chi, Chi-Hung / van Steen, Maarten Proceedings of the 2008 International Conference on the World Wide Web 2008-04-21 p.267-276

Keywords: data denormalization, scalability, web applications

ACM Digital Library Link

Summary: Many techniques have been proposed to scale web applications. However, the data interdependencies between the database queries and transactions issued by the applications limit their efficiency. We claim that major scalability improvements can be gained by restructuring the web application data into multiple independent data services with exclusive access to their private data store. While this restructuring does not provide performance gains by itself, the implied simplification of each database workload allows a much more efficient use of classical techniques. We illustrate the data denormalization process on three benchmark applications: TPC-W, RUBiS and RUBBoS. We deploy the resulting service-oriented implementation of TPC-W across an 85-node cluster and show that restructuring its data can provide at least an order of magnitude improvement in the maximum sustainable throughput compared to master-slave database replication, while preserving strong consistency and transactional properties.

Comparing Presentation Styles of Help for Shoppers on the Web Human-centred computing : cognitive, social and ergonomic aspects / Gao, Q. / Rau, P.-L. P. / Wei, Z. Proceedings of the Tenth International Conference on Human-Computer Interaction 2003-06-22 v.3 p.1238-1242