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.

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.

The purpose of computational phylogenetics is to assemble a branching diagram or tree that represents a hypothesis regarding the evolutionary relationships of an entity set. Phyletic trees and cladograms are well-known methods for expressing phyletic relationships. Although many estimating methods for cladograms have been proposed, few studies have examined automatic estimation of phyletic trees because, in our opinion, most biological entities do not have birth year information. On the other hand, targets in cultural phylogenetics may have birth year information. Therefore, we propose a method to estimate phyletic trees for cultural phylogenetics using estimated cladograms and birth order information. First, we define necessary conditions for estimating phyletic trees from cladograms and birth order. We then propose an algorithm for estimating phyletic trees that satisfy these conditions. We demonstrate that the phyletic trees estimated by the proposed algorithm satisfy the defined conditions. Our experimental results show that the proposed estimation method obtained approximately 70% estimation accuracy for some targets.

It is risky to invest to single or similar mutual funds because the variance of the return becomes large. Mutual funds are categorized based on the investment strategy by a company that rated funds based on performance, but the fund categories are different from its actual operations. While some previous studies have proposed methods to cluster mutual funds based on the historical performances, we cannot apply these methods to new mutual funds. In this paper, we clusters mutual funds based on the investment similarity instead of the historical performances. The contributions of this paper are: 1. To propose two new methods for classifying mutual funds based on the investment similarity, 2. To evaluate the proposed methods based on actual 551 Japanese mutual funds.

Nonindependent mate choice occurs when a female is in-fluenced in her choices of mate by the social environment. Frequency-dependent selection (FDS) is a typical example of a nonindependent mate choice and comes in two forms: positive or negative. In the positive form, any rare variant is at a disadvantage, whereas rare variants are favored in the negative form. Both forms of FDS have been confirmed in many species, and several mathematical and theoretical biol-ogy studies have reported the advantages of each. However, few studies have focused on the evolution of the two forms of FDS together. In this work, we simulated FDS using an agent-based model consisting of imported mating strategy as gene and female preference influenced by the social environ-ment as meme. Experimental results revealed a relation be-tween the operational sex ratio of males and the FDS strategy of females. A similar tendency was observed among real an-imals.

This paper investigates the effect of group work with the assumption of three motivators to make friends. Obeying the assumption we proposed twelve variation of methods for grouping students. The effects are evaluated by some measures from social network analysis and by the changes of real friendship networks, which are observed by a friendship prediction method. The proposed methods brought new friendship among students to classes and made rearrange of community structure.

Universities are expected to pay more effort to support students, which pushes the spread of student counseling. This has been gathering attention because many kinds of students and many ways of studies become common and because students meet many difficulties in their academic career and consideration of their future. We have been developing a recording system for student counseling. The system is expected to use in student counseling section in universities. The records should be analyzed to give answers for difficulties. In this paper we give an ontology for human relationship. Human relationship can be used as indexes for describing and analyzing records. We considered many types of relationships from the aspect of student counseling.

Anonymous mobile robots are often classified into synchronous, semi-synchronous, and asynchronous robots when discussing the pattern formation problem. For semi-synchronous robots, all patterns formable with memory are also formable without memory, with the single exception of forming a point (i.e., the gathering) by two robots. (All patterns formable with memory are formable without memory for synchronous robots, and little is known for asynchronous robots.) However, the gathering problem for two semi-synchronous robots without memory (called oblivious robots in this paper) is trivially solvable when their local coordinate systems are consistent, and the impossibility proof essentially uses the inconsistencies in their coordinate systems. Motivated by this, this paper investigates the magnitude of consistency between the local coordinate systems necessary and sufficient to solve the gathering problem for two oblivious robots under semi-synchronous and asynchronous models. To discuss the magnitude of consistency, we assume that each robot is equipped with an unreliable compass, the bearings of which may deviate from an absolute reference direction, and that the local coordinate system of each robot is determined by its compass. We consider two families of unreliable compasses, namely, static compasses with (possibly incorrect) constant bearings and dynamic compasses the bearings of which can change arbitrarily (immediately before a new look-compute-move cycle starts and after the last cycle ends). For each of the combinations of robot and compass models, we establish the condition on deviation $\phi$ that allows an algorithm to solve the gathering problem, where the deviation is measured by the largest angle formed between the x-axis of a compass and the reference direction of the global coordinate system: $\phi < \pi/2$ for semi-synchronous and asynchronous robots with static compasses, $\phi < \pi/4$ for semi-synchronous robots with dynamic compasses, and $\phi < \pi/6$ for asynchronous robots with dynamic compasses. Except for asynchronous robots with dynamic compasses, these sufficient conditions are also necessary.