A metadatabase system for semantic image search by a mathematical model of meaning

Kiyoki, Yasushi; Kitagawa, Takashi; Hayama, Takanari

doi:10.1145/190627.190639

Cited by 127 publications

(69 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The essential difference is that our method provides the important function for semantic projections, which realizes the dynamic recognition of user's needs from their context. The mathematical model of meaning (MMM) [10] was proposed as the machinary with a function of semantic projection, and our method is applying the MMM to similarity calculations between user's contexts and services in railway-stations. Our method can dynamically change the information ranking according to the user's needs estimated using the user context.…”

Section: Information-ranking Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Similarity-Ranking Method on Semantic Computing for Providing Information-Services in Station-Concierge System

Yokoyama

Kiyoki

Mita

2017

emitter

Self Cite

View full text Add to dashboard Cite

The prevalence of smartphones and wireless broadband networks have been progressing as a new Railway infomration environment. According to the spread of such devices and information technology, various types of information can be obtained from databases connected to the Internet. One scenario of obtaining such a wide variety of information resources is in the phase of user's transportation. This paper proposes an information provision system, named the Station Concierge System that matches the situation and intention of passengers. The purpose of this system is to estimate the needs of passengers like station staff or hotel concierge and to provide information resources that satisfy user's expectations dynamically. The most important module of the system is constructed based on a new information ranking method for passenger intention prediction and service recommendation. This method has three main features, which are (1) projecting a user to semantic vector space by using her current context, (2) predicting the intention of a user based on selecting a semantic vector subspace, and (3) ranking the services by a descending order of relevant scores to the user' intention. By comparing the predicted results of our method with those of two straightforward computation methods, the experimental studies show the effectiveness and efficiency of the proposed method. Using this system, users can obtain transit information and service map that dynamically matches their context. INTRODUCTIONThe prevalence of smartphones and wireless broadband networks have been progressing as a new Railway infomration environment. According to the spread of such devices and information technology, various types of information can be obtained from databases connected to the Internet. One scenario of obtaining such a wide variety of information is when the users use transportation [1]. In general, information that passengers need are transfer guides, facility information, and tourist information, etc. but they are separately provided and managed by each service provider. Thus, passengers must look for information from each service provider contents and summarize/merge them. Obviously, this is a challenge in enhancing the convenience of transportation service [2]. One additional aspect to the challenge is the wide spreading diversity of passengers with increasing number of them needed special care such as tourists, baby carriage users, handicapped people, etc. and their respective demands. To address these challenges, JR East has provided smartphone users with the smartphone app "JR East App" [3] and has studied information services that reflect the needs of individual passengers by interactive communication [4]. With the available of information providing systems such as the JR East app, passengers can more easily obtain the information. Since the display of these systems is restricted to the displayable area, their screens are created for each category of information. Thus, the passengers struggle to find the information that they n...

show abstract

Section: Information-ranking Methodsmentioning

confidence: 99%

“…To understand user's needs from context, the vector space model determines the information depending on the context [10]. In this method, the similarity of the information dynamically changes with the context of the user for the vector subspace selection.…”

Section: Related Workmentioning

confidence: 99%

A Similarity-Ranking Method on Semantic Computing for Providing Information-Services in Station-Concierge System

Yokoyama

Kiyoki

Mita

2017

emitter

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the Mathematical Model of Meaning (MMM) [1,2,7], an orthogonal semantic space is created for semantic associative search. Retrieval candidates and queries are mapped onto the semantic space.…”

Section: Semantic Computing In MMMmentioning

confidence: 99%

“…The other methods do not provide the context dependent interpretation, that is, their space is fixed and static. The outline of MMM [1,2,7] is summarized as the following:…”

Section: Semantic Computing In MMMmentioning

confidence: 99%

A Global Environment Analysis and Visualization System with Semantic Computing for Multi-Dimensional World Map

Kiyoki

2016

Self Cite

View full text Add to dashboard Cite

Abstract. Humankind, the dominant species on Earth, faces the most essential and indispensable mission; we must endeavor on a global scale to perpetually restore and improve our natural and social environments. The essential computation in environmental study is context-dependent-differential computation to analyze the changes of various situations (temperature, color, CO2, places of livings, sea level, coral area, etc.). It is important to realize global environmental computing methodology for analyzing difference and diversity of nature and livings in a context dependent way with a large amount of information resources in terms of global environments. It is also significant to memorize those situations and compute environment change in various aspects and contexts, in order to discover what is happening in the nature of our planet. We have various (almost infinite) aspects and contexts in environmental changes in our planet, and it is essential to realize a new analyzer for computing differences in those situations for discovering actual aspects and contexts existing in the nature. We propose a new method for Differential Computing in our Multi-dimensional World map. We utilize a multi-dimensional computing model, the Mathematical Model of Meaning (MMM), and a multi-dimensional space filtering method with an adaptive axis adjustment mechanism to implement differential computing. Computing environmental changes in multi-aspects and contexts using differential computing, important factors that change natural environment are highlighted. We also present a method to analyze and visualize the highlighted factors using our Multi-dimensional World Map (5-Dimensional World Map) System. We also introduce the concept of "SPA (Sensing, Processing and Analytical Actuation Functions)" for realizing a global environmental system, to apply it to Multi-dimensional World Map (5-Dimensional World Map) System. This concept is effective and advantageous to design environmental systems with Physical-Cyber integration to detect environmental phenomena as real data resources in a physical-space (real space), map them to cyber-space to make analytical and semantic computing, and actuate the analytically computed results to the real space with visualization for expressing environmental phenomena, causalities and influences.

show abstract

“…This system has two sections representing (a) relations between story scenes and musical images and (b) relations between features of variations and musical impressions. Since human feeling of stories and music is different among people [6] and the difference is important in multimedia content creation, it is necessary to consider the above relations depending on each user. Although in [5] these relations are obtained by questionnaire data, that is, off line, in the present paper a method, which adjusts the relations for each user on line, is proposed.…”

Section: Introductionmentioning

confidence: 99%

Generation of Variations on Theme Music Based on Impressions of Story ScenesConsidering Human′s Feeling of Music and Stories

Ishizuka

Onisawa

2007

International Journal of Computer Games Technology

View full text Add to dashboard Cite

This paper describes a system which generates variations on theme music fitting to story scenes represented by texts and/or pictures. Inputs to the present system are original theme music and numerical information on given story scenes. The present system varies melodies, tempos, tones, tonalities, and accompaniments of given theme music based on impressions of story scenes. Genetic algorithms (GAs) using modular neural network (MNN) models as fitness functions are applied to music generation in order to reflect user's feeling of music and stories. The present system adjusts MNN models for each user on line. This paper also describes the evaluation experiments to confirm whether the generated variations on theme music reflect impressions of story scenes appropriately or not.

show abstract

A metadatabase system for semantic image search by a mathematical model of meaning

Cited by 127 publications

References 3 publications

A Similarity-Ranking Method on Semantic Computing for Providing Information-Services in Station-Concierge System

A Similarity-Ranking Method on Semantic Computing for Providing Information-Services in Station-Concierge System

A Global Environment Analysis and Visualization System with Semantic Computing for Multi-Dimensional World Map

Generation of Variations on Theme Music Based on Impressions of Story ScenesConsidering Human′s Feeling of Music and Stories

Contact Info

Product

Resources

About