S. Riyadi, Siti Mayanti, Cahya Damarjati, Sartika Puspita
{"title":"Deep Learning for Pixel-based Edge Models Classification of Tertiary Dentine Images","authors":"S. Riyadi, Siti Mayanti, Cahya Damarjati, Sartika Puspita","doi":"10.1145/3388176.3388197","DOIUrl":"https://doi.org/10.1145/3388176.3388197","url":null,"abstract":"Prevalence of dental caries remains significant clinical problems. The dental caries disease is treated by doing pulp capping. The treatment is evaluated by visually observing the tertiary dentine on x-ray images. This conventional evaluation is not accurate and subjective among the doctors. In order to assist doctor, this research proposed implementation of deep learning method to classify pixel-based edge images of tertiary dentine. The method involves x-ray image data collection, edge modelling, edge training and testing. Eleven pixel-based edge models were defined which consist of eight edge models and three non-edge models. A total number of 660 edge images were extracted from tertiary dentine images and used Convolutional Neural Network deep learning for training and testing. The overall classification of edge images was validated using cross validation method and performed 91% of classification accuracy.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116963847","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":"Legal Judgement Prediction for UK Courts","authors":"Benjamin Strickson, B. Iglesia","doi":"10.1145/3388176.3388183","DOIUrl":"https://doi.org/10.1145/3388176.3388183","url":null,"abstract":"Legal Judgement Prediction (LJP) is the task of automatically predicting the outcome of a court case given only the case document. During the last five years researchers have successfully attempted this task for the supreme courts of three jurisdictions: the European Union, France, and China. Motivation includes the many real world applications including: a prediction system that can be used at the judgement drafting stage, and the identification of the most important words and phrases within a judgement. The aim of our research was to build, for the first time, an LJP model for UK court cases. This required the creation of a labelled data set of UK court judgements and the subsequent application of machine learning models. We evaluated different feature representations and different algorithms. Our best performing model achieved: 69.05% accuracy and 69.02 F1 score. We demonstrate that LJP is a promising area of further research for UK courts by achieving high model performance and the ability to easily extract useful features.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131062644","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":"Adaptive Height Table and Chair System Based On Face Recognition","authors":"Zhifeng He, Xinran Shao, Yuanyuan Xiao","doi":"10.1145/3388176.3388214","DOIUrl":"https://doi.org/10.1145/3388176.3388214","url":null,"abstract":"This paper designs an intelligent study desk and chair for home education. It can detect the height of the human body, control the height of the table according to the height of the person, record each user's data, and automatically adjust the state of the table and chair when the user uses it twice. It can also use a clever way to correct the user's sitting posture and remind the user to take a reasonable rest after the user has worked for a long time.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"55 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122092876","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":"Genetic Ant Colony Algorithm Improves Resource Scheduling in Cloud Computing","authors":"AoFeng Zhou","doi":"10.1145/3388176.3388213","DOIUrl":"https://doi.org/10.1145/3388176.3388213","url":null,"abstract":"When a large number of users request cloud computing resource services, rational organization of resources and task scheduling is one of the key technologies of cloud computing. Aiming at the problems of low efficiency and slow convergence speed of existing cloud computing resource scheduling algorithms, combined with the characteristics of global search ability of genetic algorithm and positive feedback convergence of ant colony algorithm, a resource scheduling algorithm is proposed. The initial pheromone distribution is generated by the genetic operator, and the exact solution is obtained by the bidirectional convergence ant colony operator. The experimental results show that the proposed algorithm is superior in solving accuracy and convergence speed, and it is an effective cloud computing resource scheduling algorithm.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127493858","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":"A Mixed-Method Approach to Understand and Improve Individual Participation Behaviour in Online Health Communities","authors":"Tenuche S. Bashir","doi":"10.1145/3388176.3388190","DOIUrl":"https://doi.org/10.1145/3388176.3388190","url":null,"abstract":"With the expansion of online communities, extant research in multiple disciplines have attempted to investigate its adoption and use among individuals. However, the biggest challenge encountered by managers of these communities is supplying knowledge, particularly, the willingness to share knowledge among the members. Cancers figure among the leading causes of morbidity and mortality worldwide, with approximately 14 million new cases and 8.2 million cancer related deaths up till 2012. The number of new cases is expected to rise by about 70% over the next two decades. For this reason, there is an ever-increasing need to establish communities to offer empathic support to patients. To achieve its objectives, this study mainly adopts the Social cognitive theory and two components of the social influence theory. The study aims to provide insights on how and why patients diagnosed with cancer (and their relatives) seek social support using the Internet and social media. In particular, we seek to understand the motivation for joining and participating within these groups and the values derived from the community for the users both active and non-active.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133382555","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":"Mapping and Generating Adaptive Ontology of Decision Experiences","authors":"Yuan Zhou, S. Khatibi","doi":"10.1145/3388176.3388200","DOIUrl":"https://doi.org/10.1145/3388176.3388200","url":null,"abstract":"Decision-making is shared by many disciplines. In computer science decision-making systems aim to substitute or support people for making decisions. The systems generally need to acquire as many as possible data to provide possible options for any decision-making. The possible options are usually obtained by modeling situations data. However, situation data is becoming tremendous along with daily life changes and it is becoming more and more difficult to model and restore those situation data. However as human, when the situation data is lacking, we still can make appropriate decisions based on our \"decision experiences\". To learn how decisions are made adaptively by humans, this paper propose a method to characterize a decision-making process for a finite number of people only based on individual's actions without modeling any situation data. Then the characterization problem is formulated as a one-dimensional decision-making process and experimented as a number guessing game. The experimental results show the feasibility of the proposed method in mapping and generation of an adaptive ontology structure of decision experiences for experimental participants.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125169507","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":"Plant Leaf Image Recognition using Multiple-grid Based Local Descriptor and Dimensionality Reduction Approach","authors":"Thipwimon Chompookham, Sarayut Gonwirat, Siriwiwat Lata, Sirawan Phiphiphatphaisit, Olarik Surinta","doi":"10.1145/3388176.3388180","DOIUrl":"https://doi.org/10.1145/3388176.3388180","url":null,"abstract":"The identification process of plant species is one of the significant and challenging problems. In this research area, many researchers have focused on identifying the plant leaf images because the leaves of a plant are found almost all year round. The achieve method of the plant leaf image recognition is based on unique extraction features from the plant leaf and using the well-known machine learnings as a classification method. As a result, recognition accuracy was often not very high. In order to improve recognition accuracy, we proposed a multiple grids technique based on the local descriptors and dimensionality reduction. Firstly, we divided the plant leaf image according to grid size and calculated the local descriptors from each grid. Secondly, the dimensionality reduction is proposed to transform and decrease the correlated variables of the feature vector. Finally, the feature vector with a relatively low-dimensional is transferred to the machine learning techniques, which are the support vector machine and multi-layer perceptron algorithms. We have evaluated and compared the proposed algorithm with the bag of visual words method and the deep convolutional neural network (including AlexNet and GoogLeNet architectures) on the Folio leaf image dataset. The experiments show that the proposed algorithm has improved and obtained very high accuracy on plant leaf image recognition.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124943578","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":"A Novel Optimized Design of Energy Efficient Lights for Producing Uniform Illumination by Harnessing Photoluminescent Properties of 'Strontium Aluminate'","authors":"Vijay A. Kanade","doi":"10.1145/3388176.3388198","DOIUrl":"https://doi.org/10.1145/3388176.3388198","url":null,"abstract":"Electrical energy consumed worldwide today amounts to about 22,500 terawatt-hour (TWh). A larger chunk of this electrical energy is used to produce light energy. Excessive production of light energy (termed as 'light pollution') causes a disturbance in the natural environment that living beings live in. The very light energy when produced above a threshold poses certain drawbacks such as disrupting ecosystems, in particular affecting nocturnal wildlife, adverse health effects such as sleep disorders, increased headaches, etc. Hence, there seems to be a stronger need for developing a substitute for electrical form energy used for producing light energy. The research proposal discloses a portable lighting device that harnesses the properties of photo luminescent pigment 'Strontium Aluminate' for producing light energy by utilizing a free source of energy. The lighting device uses a portion of 'Strontium aluminate' mixed with freely available 'water' resource to produce light energy in the presence of black light.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131512184","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":"An Educational Smart Desk Control System for the Whole Family","authors":"Xinran Shao, Zhifeng He, Yutong Kang","doi":"10.1145/3388176.3388215","DOIUrl":"https://doi.org/10.1145/3388176.3388215","url":null,"abstract":"With the rapid development of wireless communication technology and mobile network technology, the Internet of Things technology is also constantly being updated, and the number of people entering smart homes has exploded. Noticing the family of small-sized houses, placing too many desks and chairs in the home will take up too much space. If there are children in the family, as the children grow up, the inappropriate table will face multiple eliminations. To meet the height requirements of family members of different heights and help children achieve more efficient, intelligent learning to make up for the disadvantages of traditional learning methods, this paper uses a combination of sensors, hardware, software and servers to design and implement an educational smart desk control system for the whole family.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133246638","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":"A Pedestrian Path-planning Model in Accordance with Obstacle's Danger with Reinforcement Learning","authors":"Thanh-Trung Trinh, Dinh-Minh Vu, M. Kimura","doi":"10.1145/3388176.3388187","DOIUrl":"https://doi.org/10.1145/3388176.3388187","url":null,"abstract":"Most microscopic pedestrian navigation models use the concept of \"forces\" applied to the pedestrian agents to replicate the navigation environment. While the approach could provide believable results in regular situations, it does not always resemble natural pedestrian navigation behaviour in many typical settings. In our research, we proposed a novel approach using reinforcement learning for simulation of pedestrian agent path planning and collision avoidance problem. The primary focus of this approach is using human perception of the environment and danger awareness of interferences. The implementation of our model has shown that the path planned by the agent shares many similarities with a human pedestrian in several aspects such as following common walking conventions and human behaviours.","PeriodicalId":187568,"journal":{"name":"Proceedings of the 3rd International Conference on Information Science and Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129396341","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}