Papers by Taketoshi Ushiama
Lecture Notes in Computer Science, Dec 24, 2008
Recently, geographic information models for handling events have been proposed. However, the mode... more Recently, geographic information models for handling events have been proposed. However, the models are not always suitable to handle broadly spreading events, specifically in a distributed environment. This is because event data should be synchronized between geographic objects. In this paper, we propose a three-layered structure model with a view to handling events successfully in the distributed environment. In our model, event data and geographic objects are represented independently in the 1st layer, and they are associated dynamically according to a query in the 2nd layer. In the 3rd layer, data propagated from the 2nd layer are aggregated so as to be used in application systems. Based on this framework, event data and geographic objects could be represented independently, and event data computed in the 2nd layer would be shared and re-used.
IEEE Conference Proceedings, 2016
Mobile devices equipped with cameras, such as smartphones, have become extremely popular in recen... more Mobile devices equipped with cameras, such as smartphones, have become extremely popular in recent years, and have motivated users to capture an increasing number of digital photos in their daily lives. Users often invoke these photos during in-person interactions or conversations with others. In the context of a conversation between two people related to or involving reference to a photo, one of them might be inclined to show the photograph on his/her smartphone. However, it is difficult for users to search for a photo that they want to reference in the brief period during a conversation for which it might be relevant. Hence, in this study, we propose a system that shows users the photos relevant to the topic that they want to discuss in a given conversation according to their preferences. In the method of ranking photos used in our system, the index of the adequacy of a photo in the context of a conversation is defined as the degree of similarity to the photo that is used in the current conversation. Photos on each user's device are sorted by their degree of similarity with a given photo. We show that there is a strong relationship between our proposed ranking and those based on subjective assessment tasks, and confirmed the effectiveness of our system through experiments involving seven subjects.
IEICE Technical Report; IEICE Tech. Rep., Sep 6, 2016
IEICE Technical Report; IEICE Tech. Rep., Jun 25, 2007
아시아디지털아트앤디자인학회 학술대회 자료집, Dec 1, 2014
In recent years, according to wide spread of Internet usages, online shopping becomes very popula... more In recent years, according to wide spread of Internet usages, online shopping becomes very popular. Nowadays, many people use smartphones for online shopping instead of personal computers because many people use their smartphone in daily life and they provide enough functionality and usability for online shopping. On the other hand, many popular online shopping sites such as Amazon and Taobao employ collaborative filtering methods because they can recommend items to users effectively and efficiently. In order to recommend products successfully with collaborative filtering methods, large numbers of users’ evaluations on products are required, but it is very tedious for users to evaluate many items explicitly. In this paper, we propose a novel method to estimate the preference on a product based on users’ behaviors of browsing products on their smartphones. This method enables to recommend products to users based on their preferences without manually evaluations on products. The experimental results showed our method is effective for estimating the preferences of a user on products.
Intelligent Decision Technologies, Aug 12, 2010
Recently, the number of digital content objects is increasing rapidly with the progress of inform... more Recently, the number of digital content objects is increasing rapidly with the progress of information technology. It has become important how we manage enormous digital content objects effectively and utilize them efficiently. Up to now, a lot of researches on digital content management have been reported. One of the important objectives of conventional management techniques is to search digital content objects that satisfy an information request of a user. This is based on the assumption that a user has one or more information requests. However, a user may have no information request explicitly when the user uses some kinds of devices for presenting digital content such as a digital photoframe. Such devices are expected to provide a presentation of digital content that rouses user's interest. In this paper, we introduce an approach for composing photo slideshow that attracts user's interest automatically.
Springer eBooks, 2006
ABSTRACT This paper addresses a geographic information management to model various kinds of geogr... more ABSTRACT This paper addresses a geographic information management to model various kinds of geographic objects with respect to the space and time features. In this model, an event represents the geographic situation in which geographic objects change, and represented as a set of geographic objects which are concerned to the event. It is possible to easily divide an event into sub-events along space and time criteria. Using this model, our geographic information system can provide users with a capability to manipulate an event from various viewpoints.
2023 17th International Conference on Ubiquitous Information Management and Communication (IMCOM), Jan 3, 2023
When users selecting products on e-commerce sites, they always use reviews to guide their purchas... more When users selecting products on e-commerce sites, they always use reviews to guide their purchasing decisions. However, if several reviews are posted below one product, it might become difficult for users to select products efficiently. In this study, we propose two methods that use natural language processing technology, such as Word2vec and TF-IDF, to help users judge the reliability of features described in reviews effectively and efficiently. One method uses word embeddings and another method uses sentence embeddings. Finally, we evaluate the results of the two methods and find that the sentence embeddings method seams have a better performance.
IEICE Technical Report; IEICE Tech. Rep., Jun 14, 2014
Today, it has become difficult for people to find books that fulfill their preference because the... more Today, it has become difficult for people to find books that fulfill their preference because the number of books in the world has become very large. In order to select books to read, the reviews on candidate books are helpful. Therefore, the role of online review sites which are web sites storing reviews of books is important. One of the functions in the online review sites is the collaborative filtering (CF) with reviewers. In general, the user-based CF is based on the assumption that the preferences of users who select the same items will be similar. However, in many cases, each user would have different viewpoints for their evaluation of books. In this paper, we focused on the difference of viewpoints when each user evaluate a book. We propose a CF method based on the empathy with other reviewers. Our method utilizes the evaluation for a review as feedback. Experimental results show the effectiveness of the proposed method.
Record of Joint Conference of Electrical and Electronics Engineers in Kyushu, 2009
아시아디지털아트앤디자인학회 학술대회 자료집, Dec 1, 2012
Twitter is one of the most popular SNS services in the world. It has a large number of users and ... more Twitter is one of the most popular SNS services in the world. It has a large number of users and posts. One of the reasons why so many people uses Twitter is that they can use it easily and can obtain many kinds of information in real time. On Twitter, information is delivered via following networks. The following networks on Twitter are static and have to be specified manually by each user, so a user cannot share information that he/she wants if that was out of his/her following networks. In this paper, we propose a method for composing ad-hoc following networks automatically among users who are attending the same event for sharing information about it.
Lecture Notes in Computer Science, 2011
ABSTRACT Recently, electronic book(e-book) market is growing rapidly and people become able to ch... more ABSTRACT Recently, electronic book(e-book) market is growing rapidly and people become able to choice e-books that they would like to read from a large amount of e-books. Therefore, systems for finding efficiently one or more sufficient books that have something worth reading from vast numbers of e-books are demanded. In order to support users to select books, many techniques for searching and recommending books have been proposed. However the users would have to judge whether each book in candidates is worth reading. We think that stand reading is effective for the selecting actual books at bookstores in the real world. In this paper, we introduce a method for supporting stand reading on e-books on the Web. Our method recommends a user sentences which would attract and/or interest the user in a book. In our method, firstly, the attractiveness of each term in a book is calculated based on reviews about the book on the Web. Then, the attractiveness of each sentence in the book is calculated based on the attractiveness of the terms. Furthermore, this paper shows the experimental results of our method and discusses its effectiveness.
Springer eBooks, Sep 13, 2007
Recently the amount of personal contents which a person has to manage is increasing remarkably. W... more Recently the amount of personal contents which a person has to manage is increasing remarkably. We are working on Experience Web, which is a system for managing personal contents based on experiences of a user. Experience Web provides functions to integrate various types of personal contents in a unified manner, and enable a user to search them based on context. Personal contents represent activities of a user and are taken in an activity of a user. Personal contents are used more efficiently if they are shared in the users who attended the same activity. In this paper, we discuss the search that using personal contents of other users.
Lecture Notes in Computer Science, 2006
ABSTRACT
Uploads
Papers by Taketoshi Ushiama