Pyke Tin
University of Miyazaki
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Pyke Tin.
ieee global conference on consumer electronics | 2016
Thi Thi Zin; Pyke Tin; Hiromitsu Hama
The Internet of Things in which things or objects are connected becomes important in modern society. It also reflects to our Consumer World in which objects or things such as cell phones, consumer products, smart homes, cars, TVs etc. are in the World Wide connections. One of the most challenging problems is concerned with the defining and computing of reliability and availability measures since an object or thing or device quality of service failures can lead to dangerous situations for people as well as physical infrastructures In this paper, we propose a probability based concept for measuring the reliability and availability of the devices and things connected in the Internet of Things. We will investigate the proposed model from the perspectives of consumer world by using things link analysis. For evaluation, some simulation results are presented.
international conference on genetic and evolutionary computing | 2016
Thi Thi Zin; Pyke Tin; Hiromitsu Hama
Now a day Deep Learning has become a promising and challenging research topic adaptable to almost all applications. On the other hand Social Media Networks such as Facebook, Twitter, Flickr and etc. become ubiquitous so that extracting knowledge from social networks has also become an important task. Since both ranking and clustering can provide overall views on social network data, and each has been a hot topic by itself. In this paper we explore some applications of deep learning in social networks for integration of clustering and ranking. It has been well recognized that ranking systems without taking cluster effects into account leads to dumb outcomes. For example ranking a database and deep learning papers together may not be useful. Similarly, clustering a large number of things for example thousands of users in social networks, in one large cluster without ranking is dull as well. Thus, in this paper, based on initial N clusters, ranking is applied separately. Then by using a deep learning model each object will be decomposed into K-dimensional vector. In which each component belongs to a cluster which is measured by Markov Chain Stationary Distribution. We then reassign the objects to the nearest cluster in order to improve the clustering process for better clusters and wiser ranking. Finally, some experimental results will be shown to confirm that the proposed new mutual enforcement deep learning model of clustering and ranking in social networks, which we now name DeepLCRank (Deep Learning Cluster Rank) can provide more informative views of data compared with traditional clustering.
international conference on computing measurement control and sensor network | 2016
Thi Thi Zin; Ikuo Kobayashi; Pyke Tin; Hiromitsu Hama
This paper proposes a general intelligent video surveillance monitoring system to explore and examine some problems in animal behavior analysis particularly in cow behaviors. In this concern, farmers, animal health professionals and researchers have well recognized that analysis of changes in the behavioral patterns of cattle is an important factor for an animal health and welfare management system. Also, in today dairy world, farm sizes are growing larger and larger, as a result the attention time limits for individual animals smaller and smaller. Thus, video based monitoring system will become an emerging technology approaching to an era of intelligent monitoring system. In this context, image processing is a promising technique for such challenging system because it is relatively low cost and simple enough to implement. One of important issues in the management of group-housed livestock is to make early detection of abnormal behaviors of a cow. Particularly failure in detecting estrus in timely and accurate manner can be a serious factor in achieving efficient reproductive performance. Another aspect is concerned with health management to identify unhealthy or poor health such as lameness through analysis of measured motion data. Lameness is a one of the biggest health and welfare issue in modern intensive dairy farming. Although there has been a tremendous amount of methods for detecting estrus, still it needs to improve for achieving a more accurate and practical. Thus in this paper, a general intelligent video surveillance system framework for animal behavior analysis is proposed to be by using (i) various types of Background Models for target or targets extraction, (ii) Markov and Hidden Markov models for detection of various types of behaviors among the targets, (iii) Dynamic Programming and Markov Decision Making Process for producing output results. As an illustration, a pilot experiment will be performed to confirm the feasibility and validity of the proposed framework.
international multiconference of engineers and computer scientists | 2017
Thi Thi Zin; Pyke Tin; Hiromitsu Hama
In these days the population of elderly people grows faster and faster and most of them are rather preferred independent living at their homes. Thus a new and better approaches are necessary for improving the life quality of the elderly with the help of modern technology. In this chapter we shall propose a video based monitoring system to analyze the daily activities of elderly people with independent living at their homes. This approach combines data provided by the video cameras with data provided by the multiple environmental data based on the type of activity. Only normal activity or behavior data are used to train the stochastic model. Then decisions are made based on the variations from the model results to detect the abnormal behaviors. Some experimental results are shown to confirm the validity of proposed method in this paper.
international conference on genetic and evolutionary computing | 2017
Thi Thi Zin; Pyke Tin; Hiromitsu Hama
In today world a new buzzword Internet of Things has been on the news nearly every day. Some researchers are even using Internet of Every Things. Its potentialities and applicability are now on the cutting edge technology. Also, all most all of business, health care, academic institutions are in one way or another, having to deal with the Internet of Things. So the Internet of Things reliability becomes an important factor. In this paper we proposed a Markov Queuing approach to analyze the Internet of Thing reliability. Since queuing theory investigates the delay and availability of functioning things and Markov concepts take the dependency of Things in the Internet, the combination of these two concepts will make the problem clear and soluble. For illustration, we present some experimental results.
international conference on genetic and evolutionary computing | 2017
Thi Thi Zin; Pyke Tin; Hiromitsu Hama
In today modern societies, everywhere has to deal in one way or another with Big Data. Academicians, researchers, industrialists and many others have developed and still developing variety of methods, approaches and solutions for such big in volume, fast in velocity, versatile in variety and value in vicinity known as Big Data problems. However much has to be done concerning with Big Data analysis. Therefore, in this paper we propose a new concept named as Big Data Reservoir which can be interpreted as Ocean in which all most all information is stored, transmitted, communicated and extracted to utilize in our daily life. As a starting point of our proposed new concept, in this paper we shall consider a stochastic model for input/output analysis of Big Data by using Water Storage Reservoir Model in the real world. Specifically, we shall investigate the Big Data information processing in terms of stochastic model in the theory of water storage or dam theory. Finally, we shall present some illustrations with simulation.
international conference on genetic and evolutionary computing | 2016
Thi Thi Zin; Pyke Tin; Hiromitsu Hama
In today world, various types of communication networks such as academic, social, technological, business and etc. come into front. All of the networks are continuously growing and expanding in volume, velocity and variety like popular platform Big Data. Among them, the academic networks such as Alumni, Research Gate, Student Network, Teacher Network and so on provide a powerful abstraction of the academic structure and dynamics of diverse kinds of inter personal academic activities and interaction. Generally, the academic network contents such as research findings and educational concepts are created and consumed by the influences of all different academic navigation paths that lead to the challenging research issues. Therefore, identifying important and researcher relevant refined structures such as new research topics information or academic communities become major factors in modern decision making world.. In this paper, we propose a novel research topic ranking system in academic networks by using the research data relational graphs from academic media platform jointly with educational data to improve the relevance between research topics and researchers intentions (i.e., academic relevance). Specifically, we propose a stochastic model based Academic-Research Topic Ranking algorithm by taking academic value into account. By using some extensive experiments, we demonstrated the significant and effectiveness of the proposed academic-research topic ranking method.
ieee global conference on consumer electronics | 2015
Thi Thi Zin; Pyke Tin; Hiromitsu Hama
In this paper, a novel method for ranking consumer product brands by using link structures among the consumers is presented. The proposed ranking system will be established according to importance, popularity, reliability and relevancy based on consumer communication network. Using a modified version of the PageRank algorithm, the proposed ranking system is enforced by assigning each of them an authoritative score. In addition, the scores with respect to producers are also calculated by taking a time factor into account. Some experimental works are carried out to confirm the effectiveness of the proposed system.
Archive | 2011
Hama Hiromitsu; Pyke Tin; Shibuya Kiichiro
Archive | 2011
Hama Hiromitsu; Pyke Tin; Shibuya Kiichiro