In the rapidly changing world of smart technology, searching for documents has become more challenging due to the rise of advanced language models. These models sometimes face difficulties, like providing inaccurate information, commonly known as "hallucination." This research focuses on addressing this issue through Retrieval-Augmented Generation (RAG), a technique that guides models to give accurate responses based on real facts. To overcome scalability issues, the study explores connecting user queries with sophisticated language models such as BERT and Orca2, using an innovative query optimization process. The study unfolds in three scenarios: first, without RAG, second, without additional assistance, and finally, with extra help. Choosing the compact yet efficient Orca2 7B model demonstrates a smart use of computing resources. The empirical results, generated when we asked questions regarding schizophrenia, indicate a significant improvement in the initial language model’s performance under RAG, particularly when assisted with prompts augmenters. Consistency in document retrieval across different encodings highlights the effectiveness of using language model-generated queries. The introduction of UMAP for BERT further simplifies document retrieval while maintaining strong results.

In sports and traditional arts, skilled people have sensory knowledge obtained by repetitive training, called as implicit knowledge. Implicit knowledge is difficult to transfer systematically, therefore, efficient transfer is expected to improve competitiveness in sports and resolve the lack of successors in traditional arts. In addition, instructor evaluation is important when acquiring skills. However, there are limited opportunities to get advice from instructors. Therefore, in this research, our aim is to develop a system that reproduces instructor evaluations using acceleration that can be acquired with a smartphone. Yamanaka et al. developed a martial arts demonstration evaluation system using acceleration data. However, the entire movement was input regardless of the evaluation items and the points of focus in the actual evaluation were different from the points evaluated by the system. In this study, in order to reproduce actual evaluations, we proposed a machine learning model using only the focus points for each evaluation item. In experiments, the accuracy improved when the entire movement data was changed to the data of only the point of focus. We also obtained results suggesting that areas other than the focus area do not contribute to the evaluation.

Lexicon-based approaches to Document Classification are widely used, but the manual construction of lexicons can be time-consuming and resource-intensive. In this paper, we propose methods for automating the generation of lexicons later used for Document Classification. We explored diverse methods for generating lexicons, including semantic matches, frequency-based approaches, machine learning algorithms, and large language model techniques. We, later, used these lexicons to classify documents based on their content. By comparing our different lexicons results on a same task, based on criteria such as scalability and the F1 score, we determine optimized use-case for those methods. We show that our automated approaches are effective and efficient, producing accurate classifications with minimal human intervention. Some approaches have the potential to streamline the document classification process, reducing the time and resources required for manual lexicon generation, it also gives optimized use-case for the different methods. Thereafter, we discussed the obtained results.

Metric learning algorithms create distance metrics to capture the important relationships among features. These algorithms have been successful in low dimensional data. However, it is a challenge to handle high dimensional problems in real-world applications. This paper applies in high dimensional clustering problems a Reinforcement Learning (RL) based metric filtering approach in Evolutionary Distance Metric Learning (EDML), which relies on an evolutionary approach to optimize its distance metric. The proposed framework called High Dimensional Reinforced (HDR)-EDML has two novelties. The first is using a function approximation RL method called Least-Squares Policy Iteration (LSPI) to create a feature selection control strategy in high-dimensional input space to filter the metric. The second is adopting a two-way information exchange approach between LSPI and EDML Evolutionary Algorithm (EA) in metric learning. In the first way, LSPI will learn and send feedback that will affect the EDML metric creation. In the second way, the evolutionary feature prioritizing of EDML is utilized by LSPI in its learning process. These two novelties aim to reduce the number of selected features while maintaining the clustering performance. HDR-EDML is compared to conventional K-means, Information-Theoretic Metric Learning (ITML), normal EDML, and EDML with l1norm regularization for feature selection as baselines. Moreover, 3 different HDR-EDML approaches are examined to explore different ways of information exchange. Results show a significant decrease in the number of features while maintaining accuracy as well as reduced computational time and memory compared to another RL-based filtering method.

Data collection plays an important role in business agility; data can prove valuable and provide insights for important features. However, conventional data collection methods can be costly and time-consuming. This paper proposes a hybrid system R-EDML that combines a sequential feature selection performed by Reinforcement Learning (RL) with the evolutionary feature prioritization of Evolutionary Distance Metric Learning (EDML) in a clustering process. The goal is to reduce the features while maintaining or increasing the accuracy leading to less time complexity and future data collection time and cost reduction. In this method, features represented by the diagonal elements of EDML matrices are prioritized using a differential evolution algorithm. Further, a selection control strategy using RL is learned by sequentially inserting and evaluating the prioritized elements. The outcome offers the best accuracy R-EDML matrix with the least number of elements. Diagonal R-EDML focusing on the diagonal elements is compared with EDML and conventional feature selection. Full Matrix R-EDML focusing on the diagonal and non-diagonal elements is tested and compared with Information-Theoretic Metric Learning. Moreover, R-EDML policy is tested for each EDML generation and across all generations. Results show a significant decrease in the number of features while maintaining or increasing accuracy.

In daily life we perform various activities, such as walking and running. Even if we take an movement for a purpose, behaviors in the movement may differ according to physical/mental condition, background culture of the persons or other factors. If a device, such as a smart phone and a wearable device, can know the condition by observing behaviors, it may be able to use such information for appropriate service. In a previous research we proposed an algorithm which groups humans based on co-occurrence and exclusiveness of patterns between behaviors in Radio Gymnastic Exercises, which is a convenient benchmark for our purpose. In this work we focus on relation between human groups and physical/behavioral property of humans. After we revise the algorithm by introducing similarity among patterns, we characterize groups derived by the modified algorithm using various information by questionnaire and video data of the exercises. In our analysis we confirmed that the groups were characterized better by physical conditions than observed behaviors.

In our society, people engage in a variety of interactions. To analyze such interactions, we consider these interactions as a game and people as agents equipped with reinforcement learning algorithms. Reinforcement learning algorithms are widely studied with a goal of identifying strategies of gaining large payoffs in games; however, existing algorithms learn slowly because they require a large number of interactions. In this work, we constructed an algorithm that both learns quickly and maximizes payoffs in various repeated games. Our proposed algorithm combines two different algorithms that are used in the early and later stages of our algorithm. We conducted experiments in which our proposed agents played ten kinds of games in self-play and with other agents. Results showed that our proposed algorithm learned more quickly than existing algorithms and gained sufficiently large payoffs in nine games.

To gain a better understanding of how neural ensembles communicate and process information, neural decoding algorithms are used to extract information encoded in their spiking activity. Bayesian decoding is one of the most used neural population decoding approaches to extract information from the ensemble spiking activity of rat hippocampal neurons. Recently it has been shown how Bayesian decoding can be implemented without the intermediate step of sorting spike waveforms into groups of single units. Here we extend the approach in order to make it suitable for online encoding/decoding scenarios that require real-time decoding such as brain-machine interfaces. We propose an online algorithm for the Bayesian decoding that reduces the time required for decoding neural populations, resulting in a real-time capable decoding framework. More specifically, we improve the speed of the probability density estimation step, which is the most essential and the most expensive computation of the spike-sorting-less decoding process, by developing a kernel density compression algorithm. In contrary to existing online kernel compression techniques, rather than optimizing for the minimum estimation error caused by kernels compression, the proposed method compresses kernels on the basis of the distance between the merging component and its most similar neighbor. Thus, without costly optimization, the proposed method has very low compression latency with a small and manageable estimation error. In addition, the proposed bandwidth matching method for Gaussian kernels merging has an interesting mathematical property whereby optimization in the estimation of the probability density function can be performed efficiently, resulting in a faster decoding speed. We successfully applied the proposed kernel compression algorithm to the Bayesian decoding framework to reconstruct positions of a freely moving rat from hippocampal unsorted spikes, with significant improvements in the decoding speed and acceptable decoding error.

An upcoming trend of affective gaming is where a player's emotional state is used to manipulate game play. This is an interesting field to explore especially for the survival horror genre that is excellent at producing player's intense emotions. In this research, we analyzed different player affective states prior to (i.e., Neutral, Anxiety, Suspense) and after (i.e., Low-Fear, Mid-Fear, High-Fear) a scary event using an affect annotation tool to collect player self-reports of their affective states during the game. Brainwave signals, heart rate and keyboard-mouse activity were also collected for analyzing the potential of automatically detecting horror-related affect. Results indicated that players were more likely to experience fear from a scary event when they were in a suspense state compared to when they were in a neutral state. In this state, players only experienced fear after experiencing surprise. Heart rate data gave the best result in classifying player affect, which achieved up to 90% overall accuracy. This highlights the potential of using player affect in survival horror games to adapt a scary event to evoke more fear from players.

Self-reflection and self-evaluation are effective processes for identifying good learning behavior. These are essential in self-directed learning scenarios because students have to be responsible for their own learning. Although students benefit from doing fine-grained analysis of their own behavior, which we observed in our previous work, asking them to perform tasks such as analysis and making annotations are tedious and take significant amount of time and effort. In this paper, we present our work on the development of incremental affect models that can be used to minimize effort in analyzing and annotating behavior. Incremental models have an added benefit of adaptability to new information, which can be used by future systems to provide up-to-date affect-related feedback in real time.

In ambient information systems, not only extracting human behavior with a sensor network but also adaptive autonomous interaction between the environment and humans is an important function. In this paper, we propose a reinforcement learning methodology for acquiring suitable interaction for each person's daily behavior. This time, we used vital sensors to detect and classify a user's condition. In an experiment, we show the feasibility of the proposed methodology.

In recent years, highly-functional mobile devices such as smart phones and car navigation systems are widely used. These are important for our daily life because we use their applications anywhere and anytime. With the variety of applications available on these devices, however, it becomes more difficult to choose an appropriate application. Therefore we need a mechanism that recommends us suitable applications, which should depend on a user's context because he/she uses his/her devices differently in every context. This paper shows that it follows a power law what applications a user executes in daily life, and proposes a novel approach to find context-aware applications in the mobile devices. This approach is based on the term frequency - inverse document frequency (TF-IDF), which is used for extracting important keywords in a document. Moreover, we propose an application recommendation mechanism using this approach. Experimental results show that this recommendation mechanism is more effective than the mechanism using Naive Bayes.

This paper introduces a smart office chair, Owens Luis, whose pronunciation has a meaning of “an encouraging chair (****)” in Japanese. For most of the people, office environments are the place where they spend the longest time while awake. To improve the quality of life (QoL) in the office, Owens Luis monitors an office worker's mental and physiological states such as sleepiness and concentration, and controls the working environment by multi-modal displays including a motion chair, a variable color-temperature LED light and a hypersonic directional speaker.

In ambient information systems, not only extracting human behavior by sensor network but also adaptive autonomous interaction between the environment and humans is an important function. In this paper we propose a reinforcement learning framework to extract suitable interaction for each person from daily behavior. In the experiment, we show the feasibility of the proposed methodology.

We propose a smart office system that recognizes office workers' mental and physiological states to improve their quality of life at office. We integrated our systems into a single smart office environment. In this article we show the implementation of the smart office system and the details of each of its components such as I/O devices.

Data-centric affect modeling may render itself restrictive in practical applications for three reasons, namely, it falls short of feature optimization, infers discrete affect classes, and deals with relatively small to average sized datasets. Though it seems practical to use the feature combinations already associated to commonly investigated sensors, there may be other potentially optimal features that can lead to new relations. Secondly, although it seems more realistic to view affect as continuous, it requires using continuous labels that will increase the difficulty of modeling. Lastly, although a large scale dataset reflects a more precise range of values for any given feature, it severely hinders computational efficiency. We address these problems when inferring physiology-affect relations from datasets that contain 2-3 million feature vectors, each with 49 features and labelled with continuous affect values. We employ automatic feature selection to acquire near optimal feature subsets and a fast approximate kNN algorithm to solve the regression problem and cope with the challenge of a large scale dataset. Our results show that high estimation accuracy may be achieved even when the selected feature subset is only about 7% of the original features. May the results here motivate the HCI community to pursue affect modeling without being deterred by large datasets and further the discussions on acquiring optimal features for accurate continuous affect approximation.

This work deals with Q-learning in a multiagent environment. There are many multiagent Q-learning methods, and most of them aim to converge to a Nash equilibrium, which is not desirable in games like the Prisoner's Dilemma (PD). However, normal Q-lea

The consideration of human feelings in automated music generation by intelligent music systems, albeit a compelling theme, has received very little attention. This work aims to computationally specify a system's music compositional intelligence that tightly couples with the listener's affective perceptions. First, the system induces a model that describes the relationship between feelings and musical structures. The model is learned by applying the inductive logic programming paradigm of FOIL coupled with the Diverse Density weighting metric over a dataset that was constructed using musical score fragments that were hand-labeled by the listener according to a semantic differential scale that uses bipolar affective descriptor pairs. A genetic algorithm, whose fitness function is based on the acquired model and follows basic music theory, is then used to generate variants of the original musical structures. Lastly, the system creates chordal and non-chordal tones out of the GA-obtained variants. Empirical results show that the system is 80.6% accurate at the average in classifying the affective labels of the musical structures and that it is able to automatically generate musical pieces that stimulate four kinds of impressions, namely, favorable-unfavorable, bright-dark, happy-sad, and heartrending-not heartrending.

In order to meet the heterogeneous requirements from service providers and users simultaneously, there is an urgent need for a new information service system. After studying the characteristics of the user's access, it can be said that popularity of information utilization generally exists in information system. This paper introduces an access-based rating oriented distributed information system sustained by push/pull mobile agents for information service provision and utilization. In this environment, autonomous node adjustment technology is proposed to achieve load balance in the situation of changing users' preference. The effectiveness of our proposed technology is proved by simulation.

Video streaming services that provide heterogeneous video quality are required because the usage environments are diverse and changing dynamically. Considering the characteristics of the application, services must be distributed without stopping the service or deteriorating video quality. In order to achieve that, though the volume of the video data is too huge, it is necessary to reduce total storage volume and transmission quantity. In this paper, autonomous video-on-demand system architecture for heterogeneous quality levels and an evaluation method of service reliability are proposed. In this system, we employ layered video streaming data and distribute each layered video stream data in different servers. The system, streams the data from multiple sources to the users, assuring a reliable transmission. The evaluation shows the effectiveness of the proposal.

Under a dynamic and heterogenous environment, the need for adaptability and rapid response time to information service systems has become increasingly important. To cope with the continuously changing conditions of service provision and utilization, a faded information field (FIF) has been proposed, which is an agent-based distributed information service system architecture. In the case of a mono-service request, the system is designed to improve users' access time and preserve load balancing through the information structure. However, with interdependent requests of multi-service increasing, adaptability and timeliness have to be assured by the system. In this paper, the relationship that exists among the correlated services and the users' preferences for a separate and integrated service is clarified. Based on these factors, the autonomous network-based heterogeneous information services integration technology to provide one-stop service for users multi-service requests is proposed. We proved the effectiveness of the proposed technology through the simulation and the results show that the integrated service can reduce the total users access time compared with the conventional system.

To distinguish itself in today's competitive market, the service provider can offer the customer a service level agreement. User differentiation is required, appearing a need of a system able to assure the heterogeneous requirements of the users in such a mission-critical environment. In this paper, we propose an autonomous decentralized information service architecture; where he cooperation between the autonomous subsystems - mobile agents and nodes - helps the routing of the Pull-MA requests, leading to accomplish the heterogeneous service level objectives for real-time of each user in an ever-changing environment. The effectiveness of the proposed technology has been proved through simulation. The results show that the system is able to satisfy the different requirements of real-time required by each user.

Reinforcement learning is widely used to let an autonomous agent learn actions in an environment, and recently, it is used in a multi-agent context in which several agents share an environment. Most of multi-agent reinforcement learning algorithms aim to converge to a Nash equilibrium of game theory, but it does not necessarily mean a desirable result On the other hand, there are several methods aiming to depart from unfavorable Nash equilibria, but they use other agents' information for learning and the condition whether or not they work has not yet been analyzed and discussed in detail. In this paper, we first see the sufficient conditions of symmetric two-player two-action games that show whether or not reinforcement learning agents learn to bring the desirable result After that, we construct a new method that does not need any other agents' information for learning.

Autonomous community overlay network (CON) is a decentralized architecture that forms a community of individual end-users (community members) having the same interests and demands in somewhere, at specified time. It enables them to mutually cooperate and share information without loading up any single node excessively. For flexible and efficient communication among community members, an autonomous multilayer community overlay network (multilayer-CON) is proposed. This paper illustrates an approach to reconstruct the multilayer-CON on a top of a dynamic, unpredictable, and heterogeneous Internet environment by divide and integrate sub-communities. Furthermore, it evaluates the performance of the community communication over the multilayer-CON and gives evidence of the existence of the tradeoff relationship between the communication delay and construction overhead.

Information services in accordance with users' preference, utilization place and time are required more and more. Autonomous Decentralized Community System (ADCS) has been proposed to provide such services. ADCS consists of many autonomous stationary nodes and its network covers lands. In ADCS various services are provided on the network and their locations are unpredictable. To utilize these services, distributive service discovery technology is available. However, it has problem on response time. This paper proposes the Autonomous Service Search Technology which consists of two techniques. One is search area restriction technique that does not limit request propagation area, but broadcast reply message. The reply follows and catches up with request message propagation, and consequently request forwarding area is restricted. The other is termination detection technique that enables each node to detect termination autonomously by recursive judgment. The effectiveness of proposal on response time is shown by simulation.

Distributed applications typically interact with a number of heterogeneous and autonomous components that evolve independently. Methodical development of such applications can benefit from approaches based on domain-specific languages (DSLs). However, the evolution and customization of heterogeneous components introduces significant challenges to accommodating the syntax and semantics of a DSL in addition to the heterogeneous platforms on which they must run. In this paper, we address the challenge of implementing code generators for two such DSLs that are flexible (resilient to changes in generators or input formats), extensible (able to support multiple output targets and multiple input variants), and modular (generated code can be re-written). Our approach, Clearwater, leverages XML and XSLT standards: XML supports extensibility and mutability for in-progress specification formats, and XSLT provides flexibility and extensibility for multiple target languages. Modularity arises from using XML meta-tags in the code generator itself, which supports controlled addition, subtraction, or replacement to the generated code via XML-weaving. We discuss the use of our approach and show its advantages in two non-trivial code generators: the Infopipe Stub Generator (ISG) to support distributed flow applications, and the Automated Composable Code Translator to support automated distributed application deployment. As an example, the ISG accepts as input an XML description and generates output for C, C++, or Java using a number of communications platforms such as sockets and publish-subscribe.

We provide a performance comparison of generated Infopipes that have been translated and the Spi/XlP variant of Infopipe specification into executable code. Infopipes are abstractions to support information flow applications. These tools are evaluated through a realistic application: a continuous image streaming program. We implement the application in C and compare its performance to both a hand-written application and one that uses SunRPC.

Autonomous community information systems (ACIS) is a proposition made to contend with the extreme dynamism in the large-scale information system. ACIS is a decentralized bilateral-hierarchy architecture that forms a community of individual end-users (community members) having the same interests and demands in somewhere, at specified time. It allows the community members to mutually cooperate and share information without loading up any single node excessively. In this paper, an autonomous decentralized community communication technique is proposed to assure a flexible, scalable and a multilateral communication among the community members. The main ideas behind this communication technique are: content-code communication (communication service-based) for flexibility and multilateral benefits communication for scalable and productive cooperation among members. All members communicate productively for the satisfaction of all the community members. The scalability of the system's response time regardless of the number of the community members has been shown by simulation. Thus, the autonomous decentralized community communication technique reveals great results of the response time with continuous increasing in the total number of members.

This paper proposes a new strategy for manipulation of a rigid object by cooperation of multiple position-controlled manipulators using force control devices. The force control device consists of springs and a position-controlled micro-manipulator. Force control is achieved by controlling deflections of each spring by the micro-manipulator. A cooperative control algorithm considering the flexibility of macro/micro manipulators is proposed. After the differential equation of the error vector system is derived, a method of designing feedback gain matrices is shown for linearizing the system. To verify the efficiency of the algorithm, experiments are done on carrying an object by two industrial robots.