Shiori Sasaki

An Image-Query Creation Method for Representing Impression by Color-based Combination of Multiple Images

This paper presents a dynamic image-query creation and metadata extraction method with semantic correlation computation between color-combinations and impressions of multiple image data. The main features of our method are (1) to create an image-query which reflects users intention dynamically according to the color-based combinations of images with common features selected by a user as context, (2) to extract appropriate impression by each image collection which cannot be easily extracted from a single image, (3) to provide users an image retrieval environment reflecting historical and cultural semantics and impression of color especially for cultural properties, and (4) to enable an image retrieval environment for the collection of images by time, culture, author e.t.c.. The queries are created by the combination of multiple image sets and operations, which are intersection, accumulation, average, difference of color elements of sample images. First, a set of multiple images with common features is set as sample data for a query creation. Second, color histograms are extracted from the image sets for creating feature vector of a query. Third, the correlations between an image-query vector and target image vectors are calculated on a space which represents the relationship between color and the impression according to historical and cultural semantics of color. This image-query creation method representing impression of color makes it possible to expand the range of image retrieval for a large number of image data of cultural property in digital archives, such as electronic library and electronic museum, automatically.

Impression-Oriented Music Courseware and Its Application in Elementary Schools.

Purpose – The purpose of this paper is to present the design and implementation of music courseware that features a music search system that uses impression keywords. The paper applies the courseware to Kansei (sensibility) development for elementary and junior high school students. The objectives of this courseware are to cultivate childrens sensitivity to the mood of a music selection; an understanding of the effects of tonality on the mood of the music; and) an ability to appreciate and express music through activities such as searching, selecting, and listening while also utilizing information about musical impression. The courseware is also designed to support teachers who do not specialize in music education.Design/methodology/approach – Music courseware is designed containing the following three components: a semantic associative search engine that enables the retrieval of media data related to impression keywords selected by users; interfaces and tools for music retrieval and learning, which supp...

Design and development of a portable low-cost COTS-based water quality monitoring system

This paper presents a low-cost and portable water quality monitoring system for a researcher, consumer and also drinking water distribution systems. This system consists of main controller unit based on Commercial off-the-shelf (COTS) single board computer and equipped with LCD touch screen to display data information, the central measurement unit is interfaced to the multi-parameter sensor array to collect data from environment and communication unit that bring connection from the sensor device to The Internet. The dimension of portable water monitoring system are 38cm × 12.8cm × 8cm, and the weight is 658gr. The device also supports for modularity. From experiment we measured that the reliability delay for processing data is 1 second and delay for communication is only 2 seconds with 3.1Mbps Internet connection.

Ecological context-dependent analysis and prediction using MMM: A case of dengue fever disease

Dengue fever disease had threatens more than 4 billion people worldwide. Current studies in this disease focus on the relation between environmental data and dengue cases directly without considering the stage of the mosquitos life. In fact, dengue case is associated with different dominant stages under different circumstances. Therefore, it is important to analyze and select the dominant stage of mosquito for different situation to select an adequate strategy for disease-spreading prevention. In this research, we introduce the new system to select the stage based on context-dependency by using Mathematical Model of Meaning (MMM).The feature of this research is in calculating the similarity pattern analysis between environmental data with disease stage. The objective of the research is to build effective prevention system due to dominant mosquitos stage that possible to trigger dengue case. In this study, we focus on abiotic contexts with features such as rainfall, temperature, humidity, sunshine duration, CO2 and wind speed. This model consist of (a) subspace creation based on stage classification from ecological model of dynamic energy budget, (b) context-similarity calculation by using MMM, and (c) matching-prediction by Hilbert Transform. Through this system, we can determine an effective strategy to prevent dengue case in every different situation. Therefore, this system can contribute to reduce environmental damage and probability of health problem caused by an improper strategy of disease prevention. In this research, we employ real weather data of Surabaya from 2007 to 2011. The result shows that the dominant stage in wet season and dry season is different, also in specific case such as disaster, the dominant stage also different.

Context-Based Knowledge Creation and Sharing in Cross-Cultural Collaborative Communities

Virtual communities rely primarily on ICT to connect their members to work together, and to share knowledge and practices. The importance of virtual collaborative work is increasing not only because of its economical and environmental benefits, but also due to its flexibility for establishing dynamically new cross-organizational and cross-cultural innovative teams. Virtual collaborative spaces should support their joint activities. In order to design and realize such spaces, an understanding of the tasks to be carried out by the virtual community is necessary, as well as an understanding of the related processes, contexts, and knowledge. In our paper, we introduce a reference model of a Cross-Cultural Cyber Space (CCS) for context-based knowledge creation and sharing between the members of the cross-cultural collaborative community. We also describe the prototype implementation of the CCS, a 3D cross-cultural art museum system.

UAV-based multispectral image analysis system with semantic computing for agricultural health conditions monitoring and real-time management

Nowadays, UAV is widely used in several research and industrial fields. One of the highly beneficial features is that it is able to be utilized to capture aerial images in high-resolution for environmental study or detecting disaster phenomena quickly. This paper presents a multispectral image analysis system for aerial images that captured by multispectral camera, which are mounted on an unmanned autonomous vehicle (UAV) or Drone, and discusses an application of semantic computing system for agricultural health condition monitoring and analysis. In our experiments, we analyze multispectral images to detect healthy and unhealthy conditions of agricultural area and interpret the keyword of plant health conditions for user. We also propose the SPA process for real-time farming area management. As a case study, we conducted an experiment on rye fields in Latvia.

Space Creation and Evaluation Method Using Specialized and General Knowledge for Semantic Associative Search

In this paper, we present a new creation method of a semantic retrieval space for a specialized field of study, especially for the field of International Relations (IR), and new evaluation criteria for verifying practical effectiveness of the created space. This space creation method needs only a general dictionary and a lexicon of the technical terms for a specific field. Using the newly created space, we realized semantic associative search for documents which include various technical terms with general words, and also documents which include general words with technical terms. Furthermore, to verify practical effectiveness of the space creation method, that is, how much knowledge we can acquire from the created space newly, we present some evaluation criteria besides precision and recall rate.

UAV-based multispectral aerial image retrieval using spectral feature and semantic computing

This research proposes the multispectral image retrieval method by using spectral feature and semantic computing which is not many studies have focused. The main contributions are to enhance the effectiveness and advantageous of global environmental analysis system and realize semantic associative search and analysis. In this work, we study multispectral image retrieval using spectral feature computed in multispectral semantic-image space. The multispectral semantic-image space is supposing to realize the interpretation of substance (materials) on earth surface which can be provided the analyzed results as human-level interpretation. Our essential approach is utilizing the semantic computing to measure the similarity between multispectral image and the meaningful keywords which according to the users contexts. Our research results found that this method possible to acquire the spectral feature from the multispectral image and could be used in multispectral image retrieval. In this study, a multispectral image is used as the image query according to users query contexts. Moreover, the method performance of UAV-based multispectral aerial image retrieval using spectral feature and semantic computing is measured based on the queries with three contexts of multispectral image which is indicated by previous study on agricultural monitoring system and semantic interpretation model.

A realtime sensing-data-triggered news article provision system with 5D world map

The most important aim of our study is to realize a multi-database for social sciences and environmental sciences. Our system connects heterogeneous databases about historical phenomena by using common spatiotemporal information and visualize the connected results onto 5D World Map (a set of chronologically ordered global maps). To actualize that, we created a news articles provision system using real-time sensor data as a trigger and determined the effectiveness in the experiment. Here we found that we can get the information about the happening in the same atmospheric condition in the past by exhibiting news articles. These results provide new insight into our understanding of the relationship between real-time situation and past occurrence with news articles.

Event-based feature extraction for analyzing the first damage of coral under temperature and light intensity stressor

This paper deals with event-based feature extraction to analyze the incubation time of coral under two stressor: temperature and light intensity. The study is conducted in Kho Sichang Island, Thailand during hot season. The method for extracting the important events is Hilbert Huang Transform (HHT). The event as a result of Empirical Mode Decomposition (EMD) and Instantaneous Frequency (IF) are confirmed with the time duration of first symptom appearance in Acrophora Hummilis coral. The result shows variation of incubation time of coral disease under different event combination. The important finding in this research is incubation time of coral disease under different situation. It is important for early warning in coral damage.