|
Improving Manufacturing Technology Methods based on the Data Mining of a Microdrill Catalog Database |
|
Yoshito Nohara, Toshiki Hirogaki, Eiichi Aoyama(Doshisha University, Japan), Hiroyuki Kodama(Okyayama University, Japan) |
| Recently, as electrical products have become smaller and more sophisticated, the holes in PCBs have become smaller in diameter, thereby complicating the setting of hole processing conditions. In this study, we applied data-mining methods to tool catalogs of PCBs (defined as catalog mining) that contain a wealth of information on machining to search for machining conditions, formulate hypotheses, and ultimately discover and construct new knowledge useful for drilling holes in PCBs. In particular, this paper focuses on classification by clustering among the data-mining methods, introduces the C-means method, which was developed recently, and discusses the setting of machining conditions. |
|
|
Chatbots and Conversational Agents in Mental Health: A Literature Review |
|
Sergazy Narynov, Zhandos Zhumanov, Aidana Gumar, Mariyam Khassanova(Alem Research, Kazakhstan), Batyrkhan Omarov(Al-Farabi Kazakh National University, Kazakhstan) |
| In this study, we looked at chatbots, conversational agents, technologies for creating conversational agents, perspectives, and ethical issues in this direction. Also examples of therapy that are used by psychologists, psychotherapists, and the prospects of using them in a chatbot are explored in this review. As a result of the review, we considered the chatbot concepts for ourselves and identified technologies and methods for further development of the chatbot for mental health. We came to the conclusion to develop a chatbot for psychological help with the use of cognitive behavioral therapy. |
|
|
Differentiative Feature-based Fall Detection System |
|
Supannada Chotipant, Pornsuree Jamsri(King Mongkut's Institute of Technology Ladkrabang, Thailand) |
| Elderly people are dealing with falling down on a daily basis. This incident can happen anytime at any place. There is high risk of falling not only the elder but also the caregiver. Although there are numbers of applications and devices in the market for the user, the cutting-edge technology as a machine learning-based algorithm can increase effectiveness of fall detection model into device’s effectiveness. This paper proposed a novel method of 4 binary classification--Decision Tree, SVM, K-Nearest Neighbors, and Gradient Boosting. The focusing on acceleration magnitude, angular velocity magnitude, and difference between pre-current, current-post values are taken into account in the study. |
|
|
Evaluation Metrics for Automatically Constructed Concept Maps |
|
Aliya Nugumanova, Yerzhan Baiburin(Sarsen Amanzholov East Kazakhstan University, Kazakhstan) |
| Concept maps are knowledge visualization tools that allow representing the text or domain at a conceptual level. They contribute to a deeper understanding of the text, save time spent on reading and analysis. However, the process of creating concept maps is laborious and time-consuming.In this paper, we discuss popular evaluation metrics for automatically created concept maps and propose a metric based on network centrality. Experiments show that our proposed metrics complements existing ones by providing information about significance degrees of concepts and relations. |
|
|
Distracted Driver Recognizer with Simple and Efficient Convolutional Neural Network for Real-time System |
|
Duy-Linh Nguyen, Muhamad Dwisnanto Putro, Kang-Hyun Jo(University of Ulsan, Korea) |
| The traffic accident is a big problem in the world and it is happening every day. One of the main causes is distracted driving. Those are the actions of the driver when they are not focusing on driving on the road such as using the cellphone, drinking, makeup, talking to others, etc. For driver warning purpose, this paper proposes a distracted driver recognizer with a simple and efficient Convolutional Neural Network (CNN). The evaluation results on the State Farm Distracted Driver Detection dataset with ten activities achieved an accuracy of 99.51% and on video with the latency allowed for deployment in the real-time system based on a low-computation device. |
| |