This paper presents a paradigm shift in natural language processing through the evolution of our Knowledge Matrix theory into a coordinate-based direct mapping system with flow-controlled slicing operations. Moving beyond traditional deep learning approaches based on attention mechanisms and contextual representations, we establish a foundational mathematical framework where tokens map to scalar identity values and texts unfold as temporal sequences in a five-dimensional Text Space defined by time (t), token identity (y), sentence identity (s), paragraph identity (p), and text unit identity (e). This representation enables both text analysis and generation through straightforward geometric operations controlled by hierarchical flow patterns, eliminating the need for neural networks, attention mechanisms, and complex training processes. Flow control operates through a hierarchical E→P→S→Y selection cascade where each dimensional choice constrains and guides subsequent selections, creating natural text generation through geometric constraint propagation. Through practical implementation, we demonstrate our method’s effectiveness in text generation while maintaining perfect reconstruction fidelity. Experimental results validate both the five-dimensional framework and large-scale conversational applications achieving ChatGPT-like functionality through coordinate operations alone. Our approach suggests a fundamental rethinking of natural language processing, emphasizing mathematical clarity and flow-controlled geometric operations over architectural complexity.

This paper introduces a novel neural architecture that significantly transforms how neural networks process information. While traditional neural networks rely on training to map inputs to predefined output values, our approach, derived from space mapping theory, establishes a framework that generates mathematically distinguishable scalar values through random space mapping. The architecture consists of neural units that function as random space mapping operators, progressively transforming high-dimensional inputs into scalar values while maintaining their discriminative properties. This approach is particularly advantageous in closed dataset environments—where all data items are known and finite—as it eliminates the computational overhead of traditional training while ensuring reliable pattern distinguishability. Instead of training networks to achieve specific output values, we establish a database-driven recognition mechanism that links these scalar values to desired outputs. Through implementations in both flower recognition and robot navigation tasks, we demonstrate how our architecture achieves effective high-dimensional data processing while offering significant interpretability and efficiency. The results suggest a new direction for neural architecture design, offering a training-free alternative that could significantly advance high-dimensional data processing tasks across various domains.

This paper proposes an innovative method for knowledge construction and application based on the concept of space mapping. Space mapping is a mathematical operation that maps a vector to a space, expressing the relationship between input and output information. By representing data as vectors and matrices, the method establishes a mathematical relationship between input and output using a “knowledge vector”. The “dark-matter matrix” transforms the input vector into the knowledge vector, mapping the input data onto the output space. The approach is extended to “parallel spaces”, allowing for independent knowledge vectors in each space. The paper defines concepts related to space mapping, such as space-time mapping, time-space mapping, chain mapping, and parallel spaces. It presents schemes and methods for knowledge construction and application based on space mapping processing, including vector construction techniques and knowledge modeling methods like chain mapping and parallel spaces. These techniques enable handling complex data and implementing efficient, scalable knowledge construction and application schemes. The method is illustrated with two application examples: robot navigation in a maze and image recognition using chain mapping. The results demonstrate the method’s ability to handle temporal, high-dimensional, and heterogeneous data aspects, create non-redundant knowledge vectors, and generate different output information based on application requirements.

This paper aims to analyze the phenomenon of inapplicability of experience, which means that sometimes we make mistakes when we use our past experience to solve current problems. We propose a knowledge model based on the concept of “dark-matter”, which is a term used to describe the time-related data that is hidden from our observation. We use a two-dimensional matrix to represent both time-related and non-time-related data, and we call it space. We also introduce the concept of parallel spaces, which are composed of several spaces that can explain different situations and outcomes. We use case studies to illustrate how knowledge is generated and expressed using “dark-matter” and parallel spaces. We also reveal the reason for the inapplicability of experience and suggest some solutions. The contribution of this paper is that we provide a new perspective and a new model to understand and process knowledge based on “dark-matter” and parallel spaces.

Research work on machine learning techniques has been going on since the invention of computers. With the development of machine learning techniques, researches on how knowledge is expressed in computers and the learning process of knowledge have become more important. Unlike other machine learning models such as artificial neural networks, in the previous work of this paper, a machine learning model based on the concept of “dark-matter” is presented. In this model, matrixes are used to represent temporal and non-temporal data. The term “matter” is used to denote non-temporal data. The term “dark-matter”, on the other hand, is used to represent temporal data. In this paper, an exploratory research on the expression of knowledge and its generation process based on the concept “dark-matter” is presented. A case study is used to illustrate how knowledge is generated and expressed. The contribution of this paper is that new methods of knowledge generation and expression are proposed based on the concept of “dark-matter”. In the paper, first, the concept of “dark-matter” is briefly reviewed. After that, the methods of knowledge generation and knowledge expression are illustrated with examples. The process of knowledge generation is also illustrated with examples. Finally, the relationship between knowledge and “dark-matter” is revealed.

It is highlighted for machine learning models implementing functions based on data training without program coding. Artificial neural network is one of the efficient machine learning models. Different from the other machine learning models like artificial neural network, we have presented semantic computing models which represent “meaning” of machine learning results. In our model, semantic spaces are created based on training data sets. Data calculations are performed on the space. Data are mapped to semantic spaces and presented as points in semantic spaces. The mapped positions of data represent the “meaning” of data. In this paper, we first present our new discovery in the formation of semantic spaces. We use the word “matter” to represent features of semantic spaces which are related to the non-temporal data. As the same time, we use the word “dark-matter” to represent the features of semantic spaces which are temporally changed. We use the word “energy” to represent matrixes which are used in the semantic computations to generate output data. We reveal that the “dark-matter” is the spatiotemporal matrix and present a mechanism of “memory” for implementing the semantic computation. The most important contribution of this paper is that we developed a new mechanism for implementing machine learning with “knowledge” in the “memory.” In the paper, we use case studies to illustrate the concepts and the mechanism. At the beginning, we present an example on creating a semantic space from a “chaotic state” to an “ordered state.” After that, we use examples to illustrate the mechanism of the “memory” and the semantic computation. The space expansion and the space division are also illustrated by examples.

The most important mechanism of the computer is that various functions are implemented based on programs stored in it. Programs are developed by program languages implementing functions of models. One of the efficient methods to construct a model is to construct it by semantic computation models. Using semantic computation models, we can construct a model in a semantic space. In this paper, we present a mechanism to execute models presented by the semantic spaces. We have presented a mechanism to implement combinational and sequential logic computations based on the semantic space model. The combinational and sequential logic computations are the basic functions in computer systems. However, we still need a control mechanism like that in computers. In this paper, we present a control mechanism based on the semantic space model and some of execution examples. The most important contribution of this paper is that we first present a concept for control and program based on the semantic space model. In order to demonstrate the efficiency of the proposed mechanism, we performed a demonstration experiment. In the experiment, an agent is constructed for unmanned ground vehicle control with the control mechanism. A video camera is used to determine the position of the vehicle and obstacles on the road. The control signals, including “turn left,” “turn right,” “go ahead” and “stop” outputted from the agent are used to demonstrate the efficiency of the mechanism.

Semantic computing is essentially significant for realizing the semantic interpretation of natural and social phenomena and analyzes the changes of various environmental situations. The 5D World Map (5DWM) System [4,6,8] has introduced the concept of “SPA (Sensing, Processing and Analytical Actuation Functions)” for global environmental system integrations [1–4], as a global environmental knowledge sharing, analysis and integration system. Environmental knowledge base creation with 5D World Map is realized for sharing, analyzing and visualizing various information resources to the map which can facilitate global phenomena-observations and knowledge discoveries with multi-dimensional axis control mechanisms. The 5DWM is globally utilized as a Global Environmental Semantic Computing System, in SDGs 9, 11, 14, United-Nations-ESCAP: (https://sdghelpdesk.unescap.org/toolboxes) for observing and analyzing disaster, natural phenomena, ocean-water situations with local and global multimedia data resources. This paper proposes a new semantic computing method as an important approach to semantic analysis for various environmental phenomena and changes in a real world. This method realizes “Self-Contained-Knowledge-Base-Image” & “Contextual-Semantic-Interpretation” as a new concept of “Coral-Health-level Analysis in Semantic-Space for Ocean-environment” for global ocean-environmental analysis [8,9,12,18]. This computing method is applied to automatic database creation with coral-health-level analysis sensors for interpreting environmental phenomena and changes occurring in the oceans in the world. We have focused on an experimental study for creating “Coral-Health-level Analysis Semantic-Space for Ocean-environment” [8,9,12,18]. This method realizes new semantic interpretation for coral health-level with “coral-images and coral-health-level knowledge-chart”.

Artificial intelligence systems require logic calculation to give true or false judgment. However, artificial intelligence systems cannot be simply implemented by basic Boolean logic calculation. Deep artificial neural networks implemented by multiple matrix calculation is one of the efficient methods to construct artificial intelligence systems. We have presented semantic computing models in which input data are mapped in to a semantic space and presented as points in semantic spaces. From the point view of our semantic computing model, the multiple matrix calculation like artificial neural networks is a data mapping operation. That is, input data are mapped into a semantic space by the multiple matrix calculation. In our method, the true or false logic judgement is transmitted into calculating Euclidean distances of those points in the semantic spaces. In order to apply the semantic computation model for developing artificial intelligence systems, it is important to understand the mechanism between the logic calculation and semantic space and the deep-learning mechanism. In this paper, we present logic calculation implemented by the multiple matrix calculation which is the basic calculation method to implement the artificial intelligence system. The most important contribution of this paper is that we first present the mechanism for implementing logic calculation with semantic space model and machine learning. In the paper, we use three example cases to illustrate the mechanism. We first present an example case on implementing combination logic calculations based on linear space mapping. After that, we present an example case where the semantic space is constructed based on principal component analysis. The third example case is on sequential logic operations. The concept of semantic space, subspace selection and learning mechanism utilized in the example cases are also illustrated.

The significant computation in global environmental analysis is "context-oriented semantic computing" to interpret the meanings of natural phenomena occurring in the nature. Our semantic computing method realizes the semantic interpretation of natural phenomena and analyzes the changes of various environmental situations. 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 global environments. Semantic computations contribute to make "appropriate and urgent solutions" to the changes of environmental situations. It is also significant to memorize those situations and compute environment changes in various aspects and contexts, in order to discover what are happening in the nature of our planet. We have various (almost infinite) aspects and contexts in environmental changes, and it is essential to realize a new analyzer for computing the meanings of those situations and making solutions for discovering actual aspects and contexts. We propose a new method for semantic computing in our Multi-dimensional World map. We utilize a multi-dimensional computing model, the Mathematical Model of Meaning (MMM) [1–3], and a multi-dimensional space with an adaptive axis adjustment mechanism. In semantic computing for environmental changes in multi-aspects and contexts, we present important functional pillars for analyzing natural environment situations. We also present a method to analyze and visualize the highlighted pillars using our Multi-dimensional World Map (5-Dimensional World Map) System. We 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 System. This concept is essential to design environmental systems with Physical-Cyber integration to detect environmental phenomena 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. This system currently realizes the integration and semantic-analysis for KEIO-MDBL-UN-ESCAP Joint system for global ocean-water analysis with image databases. We have implemented an actual space integration system for accessing environmental information resources and image analysis.

In order to realize an artificial intelligent system, a basic mechanism should be provided for expressing and processing the semantic. We have presented semantic computing models in which original data are mapped in to a semantic space and presented as points in semantic spaces. That is, we presented a method to process semantic information by calculating Euclidean distances of those points in the semantic spaces. In our continuous studies, we note that different mapping matrixes are required to map the original data in to the semantic space when this model is applied in different application areas. Therefore, it is an important research topic to develop methods to create the mapping matrixes applied in different areas. Many research works are presented on applying the model in the areas of semantic information retrieving, semantic information classifying, semantic information extracting, and semantic information analyzing on reason and results, etc. In these works, the mapping matrixes are created based on the analyzations in the application areas with human knowledge. In this paper, we present a new method to perform the semantic mapping through deep-learning computation. The most important feature of our method is that we implement semantic mapping through training data sets rather than the mapping matrix which is created based on the analyzations of human being. We first discuss five basic operations, the semantic space creation, semantic mapping, semantic mapping matrix, semantic space expansion and contraction. After that, we present our method. In order to present correlations of the semantic information correctly in Euclidean distances, the axes of a semantic space must be orthogonal to each other. Therefore, we also discuss how to implement semantic orthogonal mapping. We believe that our study will open new application areas on semantic computing and deep-learning.

Semantic computing integration with deep-learning realizes a new artificial brain-memory system. We have presented a concept of “MMM: Semantic Computing System” for analyzing and interpreting environmental phenomena and changes occurring in the oceans and rivers in the world. 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. This paper presents integration and semantic-analysis methods for KEIO-MDBL-UN-ESCAP Joint system for global ocean-water analysis with Coral-Image Analysis in two environmental-semantic spaces with water-quality and image databases. We have implemented an actual space integration system for accessing environmental information resources with water-quality and image analysis. We clarify the feasibility and effectiveness of our method and system by showing several experimental results for environmental medical document data Environmental-semantic space integration realizes deep analysis environmental phenomena and situations. The essential computation in environmental study is context-dependent-differential computation to analyze the changes of various situations (air, water, 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. In the design of environment-analysis systems, one of the most important issues is how to integrate several environmental aspects and analyze environmental data resources with semantic interpretations. In this paper, we present an environmental-semantic computing system. Our environmental-semantic computing system realizes integration and semantic-search among environmental-semantic spaces with waterquality and image databases.

Environmental-semantic space integration is a promising approach to realize deep analysis environmental phenomena and situations. The essential computation in environmental study is context-dependent-differential computation to analyze the changes of various situations (air, water, 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. In the design of environment-analysis systems, one of the most important issues is how to integrate several environmental aspects and analyze environmental data resources with semantic interpretations. In this paper, we present an environmental-semantic computing system. Our environmental-semantic computing system realizes integration and semantic-search among environmental-semantic spaces with water-quality and image databases. We have already presented a concept of “Semantic Computing System” for analyzing and interpreting environmental phenomena and changes occurring in the oceans and rivers in the world. 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. This paper presents integration and semantic-analysis methods for two environmental-semantic spaces with water-quality and image databases. We have implemented an actual space integration system for accessing environmental information resources with water-quality and image analysis. We clarify the feasibility and effectiveness of our method and system by showing several experimental results for environmental medical document databases.

In a world where taking photos has become a daily behavior to most people, it is deemed that a photo sharing service has the strong potential to recommend desirable sightseeing places for the majority of travelers. There is much research on location recommendations and route suggestions for sightseeing based on check-in frequency to extract the popularity of a location, which is used to infer a user's interest in a place. However, the popularity of a location is not sufficient for the location recommendation, and user's preferences in a place cannot be extracted using only the check-in frequency. In this study, we propose a recommendation system for sightseeing places based on user's photo-taking behavior, where a large amount of photo data can be classified into five genres: scenery, architecture, nature, activity, and food. These data are leveraged to recommend popular sightseeing places according to a user's preference that is extracted from the user's photo-taking behavior. In the experiment, we test the classification capability of CNN (Convolutional Neural Network) in deep learning for five genres of photo data that we collected using smartphones. The proposed system could be realized by incorporating CNN as a photo classifier into our photo sharing service to recommend sightseeing places.

In the design of multimedia data mining systems, one of the most important issues is how to search and analyze media data, according to contexts. We have introduced a semantic associative search method based on our “Mathematical Model of Meaning (MMM) [1, 2, 3]”. This model is applied to compute semantic correlations between keywords, images, music and documents dynamically in a context-dependent way.

Humankind faces a most crucial mission; we must endeavour, on a global scale, to restore and improve our natural and social environments. In this environmental study, we will use context-dependent differential computation to analyse changes in various factors (temperatures, colours, level of CO2, habitats, sea levels, coral areas, etc.). In this paper, we will discuss a global environmental computing methodology for analysing the diversity of nature and animals, using a large amount of information on global environments.

Semantic computing is an important and promising approach to semantic analysis for various environmental phenomena and changes in real world. This paper presents a new semantic computing method with multi-spectrum images for analyzing and interpreting environmental phenomena and changes occurring in the physical world.

Cloud computing is changing the utilization environments of computers in both enterprise and personal. Application development techniques and methodologies that are suitable to cloud environments are new challenging research topics. As demand for developing business applications is increasing rapidly and commercial profitability is dependent on decreasing the application development costs, it is essentially important to provide methods meeting the requirements of developing applications with low cost and short development time. Therefore, it is required to develop new methods facilitate the cloud application development based on easy-to-accomplish and end-user-composition. In this work, we compiled seven requirements of typical business application development such as data structure, database schema, page transition control, authorization, session management, programming, and input and output interface design. Furthermore we observe that none of current cloud development environments support a majority of these requested features. As a result, we present our own cloud application development platform, called FOCAPLAS that meets all of these requirements. A case study presenting a cloud application developing process is presented demonstrate how to use our FOCAPLAS. We believe that our requirements may serve as a valuable guide for cloud data modeling and our FOCAPLAS will be a useful platform for cloud application development.

In the natural environment research field, computer systems are widely utilized. The majority of computer systems are used to store observed data. Super computers are used to simulate environment changes, for example, the global climate change. Prior research has shown that computer systems make it possible to store and access huge amount of observed data based on database manage systems. The simulation accuracy of nature environment changes is also improved accompanied by the progress of computer technology. In this work, we propose a new method to discover what are happening in the nature of our planet utilizing differential computing in our Multi-dimensional World Map. 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 of our planet. By using Differential Computing, important factors that change natural environment are highlighted. Furthermore, the highlighted factors are visualized by using our Multi-dimensional World Map, which makes it possible to view the nature environment changes in the view of history, geographic, etc.

This paper points out that achievements in the field of multimedia analysis and retrieval represent an important opportunity for improvement of recommender system mechanisms. Online shopping systems use various recommender systems; however a study of different approaches has shown that they do not exploit the potential of information carried by multimedia product data for product recommendations. We demonstrate how this can be accomplished by a personalized recommender system framework that is based on a method of analysis of colour features of entity images. Colour-features are based on image colour histograms, psychological properties of colours and a learning mechanism. We have developed a service-oriented framework for a personalized recommender system that is based on incorporation of this method into a highly interactive business process model. The framework is designed in a generic way and can be applied to an arbitrary domain. It is based on service-oriented architecture in order to promote its flexibility and reuse, which is important when applying it to existing recommender system environments. An experimental study was performed for the domain of travel agency. The framework provides several important advantages, such as automatic creation of entity image meta-data which is based on colour-based image analysis and extraction of their semantic properties, user-interaction based learning, dynamic selection and presentation ordering of entity images, and feedback for creation of base image entity sets.

This paper presents a combined-image query creation method for expressing user's intentions by combining multiple digital images for image retrieval. This method uses image databases provided for query-creation and performs several set-operators to express user's imagination by combining user's imaginary images and real scenes. The user's intentions are expressed by the operation of subspace projection in the image feature space. This method makes it possible to create an imaginary image as the combined-image query for expressing user's intentions by combining several images and operators in the query creation process. The important feature of this method is to use shape and color features for expressing imaginations by extending our previously proposed method. This paper shows several experimental results to clarify the feasibility and effectiveness of our method.

Utilization of global information resources as a part of risk management is insufficient. The authorities are maintaining information systems mainly for their own purposes, without access to high quality public information sources in Internet and without interoperability between systems of different authorities. Beneficial use of all available information resources would provide an opportunity to create knowledge based on different pieces of information. However, powerful distributed knowledge management, mining of the information items, analysing the quality of them, is needed to create new information to be utilized. The distributed operations needs support of complex network architectures, models supporting mutual understanding over the cultures and language borders, and ability to recognize the context and adapt the results to the new context. This paper opens discussion from different viewpoints to the topic of global risk management. Architectural solutions supporting interoperability, quality of data in wide networks, ubiquity and mobility as well as time dimension of the information space are covered.

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 user's 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.

In the current World Wide Web (WWW) environment, it is important to realize intelligent and effective information acquisition mechanisms. We propose a semantic associative search method based on our mathematical model of meaning to realize intelligent and effective information acquisition. Our method provides a dynamic context recognition mechanism for information acquisition according to user's queries given as contexts. We integrate two application systems of our semantic associative search method to realize an intelligent and effective information acquisition environment for WWW information resources. We apply our method to information retrieval on WWW information resources, which are identified by Uniform Resource Locators (URLs). This application system makes it possible to dynamically obtain semantically related information resources on WWW, according to user's queries given as contexts. Furthermore, we have applied our method to queries and information resources described in multiple languages. We integrate those applications for supporting WWW information acquisition.