Xiaolan Zhu, Lei Zhang, Lu Wang, Shiying Wang, Xuexi Wang, Gwanggil Jeon
{"title":"Classification of Tibetan Medical Syndrome Based on Class Association Rules","authors":"Xiaolan Zhu, Lei Zhang, Lu Wang, Shiying Wang, Xuexi Wang, Gwanggil Jeon","doi":"10.1109/SITIS.2018.00051","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00051","url":null,"abstract":"This paper put forward a classification model of Tibetan medical syndrome of common plateau disease (Chronic Atrophic Gastritis) based on the class association rules. Taking the clinical diagnosis and treatment data of Chronic Atrophic Gastritis provided by Qinghai Provincial Tibetan Hospital as the research object. Firstly, using the clustering algorithm to divide syndrome normalized. Secondly, the constraint-based Apriori algorithm is applied to mine the strong association rules between symptoms and syndrome after pruning and prioritizing these rules, and the classification model of the Tibetan medical syndrome is established by selecting a set with high-priority rules. Finally, the accuracy of the classification model is verified and compared with four traditional classification algorithms to prove the effectiveness of the proposed method. The experimental results showed that the proposed method outperformed most other traditional classification algorithms with an accuracy of 82.72%.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"234 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116465154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Impact of Gait Stabilization: A Study on How to Exploit it for User Recognition","authors":"Alessio Mecca","doi":"10.1109/SITIS.2018.00090","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00090","url":null,"abstract":"Biometrics are nowadays taking more and more space both in research institutions and industries. This trend is even increased during the last years due to the widespread of wearable devices, especially consumer smartphones containing several sensors that can be exploited for the collection of user data and their recognition. This study deals with gait recognition with data collected by wearable accelerometers. The main focus is to test the gait stabilization effect, i.e., the tendency of humans to produce more stable gait dynamics after a certain (very short) period of walking. We use a subset of one of the largest freely available dataset, the ZJU-gaitacc, in order to present comparable results. The achieved performances confirm the benefits in the use of the last steps of a reasonably long walk (about 20 meters) in order to recognize a user. Moreover, we observe that it is possible to identify the correct identity of a user within the first 5 ranks of the CMC curve with a rate of 99%. Results for Verification with single and multiple template(s) is also presented as well as the ones achieved in Open Set Identification, the most difficult yet realistic biometric modality.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117085218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Interactive Multimedia Base Mobile Learning for Health: The Creative Media Design of \"Acne is a Health Indicator\"","authors":"Chudanat Sudthongkhong, Thanannath Phattharachairawee, Sutharat Puangsing","doi":"10.1109/SITIS.2018.00059","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00059","url":null,"abstract":"Abstract This research studied media. The purposes were 1) to provide accurate information to those who had acne problems so that they could have proper acne treatment by themselves, 2) to help teenagers to have more understanding about acne and could give advice to others affected by the same problems. The research was advised, examined, and evaluated by advisors and experts in the relevant fields. The sample group was twenty seven undergraduate students of Medical Media and Science Programme, Media Arts Department. The research tools included lessons on acne issues, an achievement test, and a survey questionnaire on learners' satisfaction towards the lessons. The result of On visual and audio evaluation, the average scores given by the target group were equal at 3.88 with S.D. 0.62 (satisfactory level) The average score on the content aspect was the highest, The content is easy to understand score was 4.26 with S.D. = 0.71 (satisfactory level) The average score on the creative media design as the target group thought the media made them understand more of the benefits The study showed that the learners had more understanding about acne. The lessons' content was evaluated as 'satisfactory' by the expert for it was accurate and appropriate for the target group. The visuals and narration of the lessons were also evaluated as 'satisfactory' by the technical expert. The sample group gave good response to these media. The media can be used as informative source of acne issues and developed further.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129876406","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Konstantinos Konstantoudakis, Emmanouil Christakis, Petros Drakoulis, Alexandros Doumanoglou, N. Zioulis, D. Zarpalas, P. Daras
{"title":"Comparing CNNs and JPEG for Real-Time Multi-view Streaming in Tele-Immersive Scenarios","authors":"Konstantinos Konstantoudakis, Emmanouil Christakis, Petros Drakoulis, Alexandros Doumanoglou, N. Zioulis, D. Zarpalas, P. Daras","doi":"10.1109/SITIS.2018.00022","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00022","url":null,"abstract":"Deep learning-based codecs for lossy image compression have recently managed to surpass traditional codecs like JPEG and JPEG 2000 in terms of rate-distortion trade-off. However, they generally utilize architectures with large numbers of stacked layers, often making their inference execution prohibitively slow for time-sensitive applications. In this work, we assess the suitability of such compression techniques in real-time video streaming, and, more specifically, next-generation interactive tele-presence applications, which impose stringent latency requirements. To that end, we compare a recently published work on image compression based on convolutional neural networks which achieves state-of-the-art compression ratio using a relatively lightweight architecture, against a CPU and a GPU implementation of JPEG, measuring compression ratios and timings. With these results, we run a simulation of a tele-immersion pipeline for various networking conditions and examine the performance of the compared codecs, calculating framerates and latencies for different codec/network combinations.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127407415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Y. Kawasaki, Yoshitaka Sakurai, Eriko Sakurai, S. Tsuruta
{"title":"Predicting Unsubscription from Customer's E-Mail Using Deep Learning","authors":"Y. Kawasaki, Yoshitaka Sakurai, Eriko Sakurai, S. Tsuruta","doi":"10.1109/SITIS.2018.00081","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00081","url":null,"abstract":"In recent years, the scale of E-commerce web sites and the number of users have increased remarkably. Along with that, it is required to respond promptly to requests from customers via online. In this research, we identify costumers, who want to withdraw their order by analyzing their e-mail text sent to customer support for classification model to urge operators to respond. The classification model was carried out in a convolution neural network after embedding expressions of words. We tuned the parameters in the experiment and found it possible to classify with accuracy of 79.2%. In addition, we compared the accuracy with predictive model by customer status. As a result, we obtained high accuracy compared with logistic regression models and support vector machines. From these results, it was proven that the mail document contained information indicating to resign from EC site customers.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"116 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125394322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Retrieval of Facial Images Re-rendered with Natural Aging Effect using Child Facial Image and Age","authors":"Praveen Kumar Chandaliya, Preyas Garg, N. Nain","doi":"10.1109/SITIS.2018.00076","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00076","url":null,"abstract":"We represent face progression and face regression on the children face image dataset containing 8581 faces images in the age group [2 : 20] years. This dataset contains 4789 and 3792 images of boys and girls respectively. To generate the images we have used a generative approach such that we don't require pair models (more than 2 images of a person with age difference of 1 or more). In addition to regression and progression, we have compared the ground truth with the regressed or progressed images. These progressed or regressed images can be used to trace and identify children lost at the young age as a victim of child trafficking or abduction.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125562252","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Malak Saidi, Anis Tissaoui, D. Benslimane, Wehbi Benallal
{"title":"An Entropy-Based Uncertainty Measure of Configurable Process Models","authors":"Malak Saidi, Anis Tissaoui, D. Benslimane, Wehbi Benallal","doi":"10.1109/SITIS.2018.00014","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00014","url":null,"abstract":"Nowadays, the business environment is more and more evolved. It has become crucial in such a dynamic and an evolving environment to adopt an approach that is based on a paradigm called \"design by reuse\" in order to make the process of a given organization reusable. The idea of reuse of the model has emerged with the need to reduce the cost of development and design time. A new concept is born with this configuration; it's the concept of uncertainty since the configurable model means the restriction of the behavior represented by an existing model of the process so that it allows only the desired behavior of the model while all the unwanted behavior is eliminated from it. So, let's choose a path among many, but which one? In this paper, we will propose an entropy-based uncertainty measure based on entropy that enables us to take into account the dynamic aspect of the model at the design-time and to quantify this uncertainty in order to evaluate predictability and managerial efficiency of process models.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"289 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121330370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Building Quality Metrics for Green Computing Projects: A Model and a Case Study of Engineering a Green Computing Awareness Website","authors":"Amany Alnahdi, Faisal Bazarah","doi":"10.1109/SITIS.2018.00096","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00096","url":null,"abstract":"Green computing projects can improve sustainability of computing resources. As there can be several methodologies for developing green computing projects, assessing the quality of these projects can help in determining the feasibility of a project to a particular application. In addition, having a tool for measuring quality factors determined by the stakeholders of the domain can further support decision making when differentiating between multiple computing projects or determining quality features in a certain project. This paper presents a measuring model for assessing the quality of engineering projects in the domain of green computing. Also, a case study based on the proposed model is presented.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114238702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Towards Multi-modal Finger Presentation Attack Detection","authors":"M. Gomez-Barrero, Jascha Kolberg, C. Busch","doi":"10.1109/SITIS.2018.00089","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00089","url":null,"abstract":"The wide deployment of biometric verification systems has also unveiled security and privacy issues. Among other vulnerabilities, presentation attacks directed to the capture device pose a severe security threat. That is, a gummy finger (known as presentation attack instrument, PAI) can be used to impersonate another subject and thereby gain illegal access to the system. To prevent such attacks, presentation attack detection (PAD) techniques have been proposed in the last decade. For the particular case of fingerprints, most approaches are based on conventional optical or capacitive sensors, acquiring a single image, and which can thus detect only a limited number of PAIs. In this work, we present a new multi-modal PAD approach based on a recently developed capture device, which is able to acquire four different types of samples: i) finger photos, ii) finger vein samples, iii) multi-spectral short wave infrared images, and iv) laser speckle contrast image sequence samples. Different ad-hoc algorithms have been developed for each set of images. The experimental evaluation over 35 PAIs, part of them used only at the test stage, shows the efficiency of the proposed approach in a realistic scenario, with an APCER of 6.6% for a BPCER of 0.2%.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116258519","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Asymmetric Bilateral Phase Correlation for Optical Flow Estimation in the Frequency Domain","authors":"V. Argyriou","doi":"10.1109/SITIS.2018.00034","DOIUrl":"https://doi.org/10.1109/SITIS.2018.00034","url":null,"abstract":"We address the problem of motion estimation in images operating in the frequency domain. A method is presented which extends phase correlation to handle multiple motions present in an area. Our scheme is based on a novel Bilateral-Phase Correlation (BLPC) technique that incorporates the concept and principles of Bilateral Filters retaining the motion boundaries by taking into account the difference both in value and distance in a manner very similar to Gaussian convolution. The optical flow is obtained by applying the proposed method at certain locations selected based on the present motion differences and then performing non-uniform interpolation in a multi-scale iterative framework. Experiments with several well-known datasets with and without ground-truth show that our scheme outperforms recently proposed state-of-the-art phase correlation based optical flow methods.","PeriodicalId":267494,"journal":{"name":"2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128003561","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}