[in Japanese]

View full abstract

Aims: The purpose of this study is to develop a quantitative and objective method of diagnosing uterine peristalsis by using AI technology, which is currently evaluated visually by experienced physicians.
Methods: The coordinates at which uterine peristalsis occurs were estimated using DeepLabCut, a marker-less coordinate estimation library, on Cine MRI images of the uterus of female infertility patients. Local maximum and local minimum values were calculated from the obtained coordinate changes to detect the occurrence of uterine peristalsis.
Results: We were able to track uterine peristalsis and mechanically measure the timing and frequency of its occurrence by manually labeling 19 frames out of 90 frames of the target video image.
Conclusion: The ability to quantitatively and objectively diagnose uterine peristalsis, which was previously subjective, may lead to the development of new diagnostic methods and a reduction in the burden on physicians.

View full abstract

Intracerebral hematoma (ICH) is a disease with high mortality and poor prognosis rate, accounting for approximately 10% of all cerebrovascular disease. Manual extraction of ICH regions lacks accuracy and speed, and a quantitative evaluation method is needed. In this study, we propose a method that divides the extraction of ICH regions into multiple stages and extracts the target using two-class classification based on convolutional neural network. The performance of the model is evaluated using 18 subjects with intraventricular hemorrhage, and it is shown that the proposed method is promising for the extraction of ICH regions in a region with high absorption rates.

View full abstract

CT imaging is used to diagnosis brain diseases in pediatric age 0-3 years. To assess the normal growth of the pediatric brain, there is a need for a quantitative method to evaluate the degree of brain development. This study proposes a method for estimating developmental age from CT brain images of children using convolutional neural networks (CNN). Pre-processing included extraction of the cranial region, posture and position calibration and normalization of the CT values. Since 3D data was used as input, the model (3D-AlexNet), which is an extension of AlexNet to 3D, was used for age prediction. 4-fold cross-validation with 204 people as training data and 60 people as evaluation data. Results showed a root mean square error (RMSE) of 6.37 months between the predicted age and the actual age of the patient, with a correlation coefficient of 0.88.

View full abstract

In recent years, the most widely used identity authentication is performed once at the time of login. This standard identity authentication method is not designed to detect identity impersonation login. In addition, a continuous identity authentication, which performed several times during working time, requires a method that does not interrupt the operator's thinking or work. As a solution to these problems, we have proposed a method to perform authentication based on keystroke information using a keyboard. In this paper, we describe experimental results and discussion of keystroke and keystroke sound authentication, with a particular focus on keystroke sound during keyboard operation.

View full abstract

In recent years, with the increase in the number of electric vehicles, considerable attention has been paid to the impact of vehicle noise, such as road and wind noises, on the comfort of car interiors. Studies have been conducted on reducing the noise annoyance of electric vehicles and evaluating its effect from a physiological perspective. However, no study has examined this from a neurophysiological perspective. Herein, we investigate selective attention to vehicle sound and the effects of subtle changes in vehicle sound on event-related potentials (ERPs) under driving conditions. As results, we observe ERPs with subtle changes in vehicle sound pressure level (SPL) while driving. Furthermore, we find that different attention mechanisms may be evoked when SPL increases and decreases. These results will help investigate practical approaches to reduce vehicle noise and improve comfort within car interiors.

View full abstract

An Optical wave microphone is proposed as a new sound detection method. The Optical wave microphone measures sound waves by observing the weak diffraction light generated when laser light is affected by sound waves. Therefore, it can be used in locations where laser light is transmitted without disturbing the sound field. In addition, since no objects are used in the sound-receiving part, it can be used near equipment that generates a lot of electromagnetic waves, such as MRIs, in environments with severe temperature and humidity, and in intense air currents. However, due to the characteristics of the Optical wave microphone, the noise level is high, and there is an urgent need to improve the signal-to-noise ratio for practical use. In previous studies, it has been confirmed that the use of a retroreflector amplifies diffracted light, and that independent component analysis (ICA) shows good results. In this study, we succeeded in improving the signal-to-noise ratio of an Optical wave microphone using a retroreflector by ICA with principal component analysis (PCA) as a pretreatment.

View full abstract

Movements that appear unconsciously are called involuntary movements. Especially, rhythmic involuntary movements are called tremors. Tremor interferes with daily life and is one of the characteristic symptoms of neurological disorders such as Parkinson's disease (PD) and essential tremor (ET). Symptoms and progression of PD patients are assessed by a neurologist through neurological examination and interview according to the revised Unified Parkinson's Disease Rating Scale (UPDRS) sponsored by the Movement Disorders Society (MDS). PD is associated with other symptoms such as bradykinesia, whereas ET is characterized by tremor alone. However, in the early onset of PD, other symptoms may not be noticeable, and even neurologists may find it difficult to differentiate it from ET. In this paper, to solve this issue of getting lost in this judgment, consider whether it is possible to distinguish between PD and ET two types of neurological disorders from two approaches, time domain and frequency domain which from observed tremor movement by using an RGB camera.

View full abstract

Tracking multiple objects that have the same color and texture features is a challenging task. The proposed system aims to track a group of black cows which are similar to each other with respect to colors and sizes by using the tracking-by-detection method. Before performing black cow tracking, the black cow’s regions with mask and bounding box are detected by using the robustness Detectron2 object detector. The Detectron2 outputs are then used as input of SORT based tracking algorithm to track the black cows by giving specific IDs. Although the traditional SORT tracking algorithm relies on bounding box information of the detection result, a fusion of mask and bounding box information from Detectron2 output is utilized in the SORT tracking algorithm for our proposed method.

View full abstract

Artificial Intelligence is exponentially evolving into a solution to many life science complex problems especially human and animal healthcare systems. On the other hand, Spectral Analysis tools are coming to the front lines in processing image signals. These days, researchers and the industry have focused on image signal processing techniques to support farmers in automatically finding lame cows in their dairy farms. Lameness in dairy cattle is the number one welfare issue in the dairy industry due to pain, suffering, and economic impact. Therefore, in this paper, we propose a spectral analysis embedded Artificial Intelligence approach to cattle lameness detection by investigating and analyzing the image depth signals taken on the individual dairy cows while they are walking in the pathways from the milking station to resting areas. Specifically, we shall first develop the frequency signal variation measures of the collected image depth signals of individual cows by using spectral analysis. Then some AI models will be used to analyze obtained frequency variation measures for detecting cattle lameness scores. Finally, we present some partial experimental results using self-collected real-life data.

View full abstract

In this research, we investigate the sensing of medical tubing conditions using a home-made flexible sensor and BLE (Bluetooth Low Energy). With the increasing introduction of medical tubing in the medical field, the number of self-extraction accidents is also increasing. It not only prevents patients from receiving necessary treatment, but also causes hospital readmission and complications due to bleeding from the extraction site. There have been implemented as solutions, frequent visits by nurses and physical restraint of patients, but the burden of this problem has been identified as problematic. In this study, we investigated the early detection and prevention of accidents by attached a flexible sensor to a medical tube to detect tension and detachment.

View full abstract

Reinforcement learning is a promising approach for various applications such as complicated task acquisition and game AI. In reinforcement learning for games, there are necessary issues of combinatorial explosion of agent states and learning speed deterioration caused by sparse distribution of states in the state space for reinforcement learning. In this paper, we address state expression for reinforcement learning in games. According to characteristics of games, a state expression model is structured considering rotation, mirror translation, and symmetric translation of game boards. Through numerical experiments of Othello game, we found the proposed model is promising for game AI.

View full abstract

PV power generation must operate at its optimum operating point because the generated power varies with changes in weather conditions. Therefore, in PV, MPPT (Maximum Power Point Tracking) is indispensable. However, conventional methods of MPPT require complex numerical computations, which tend to increase hardware and software costs. Also, it cannot cope with sudden changes in solar radiation and partial shadowing problems. To work out these problems, we investigated a method applying the SOM (self-organizing maps) to predict the power-voltage (P-V) characteristics of photovoltaic power generation in order to realize a high-performance MPPT. The SOM is a data analysis method that maps multidimensional data onto a 2D planar map. The P-V characteristics of a solar cells can be estimated by using the SOM. The maximum power point also can be predicted simply by measuring the current and voltage of the solar cell at the least number of points. In this study, an experimental apparatus was constructed to measure the output of solar cells. The method presumes maximum power point. As a result, the current-voltage (I-V) and P-V characteristics could be predicted to some extent. However, it was difficult to accurately predict the maximum power point due to the characteristics of the SOM and unexplained factors. Although in this study effectiveness of the simple method by using the SOM for the MPPT is confirmed.

View full abstract

In our research, we are attempting to predict Autism Spectrum Disorder (ASD) and the associated Autism Diagnostic Observation Schedule (ADOS) scores using data from the body skeleton, head movement, and eye gaze. To the best of our knowledge, no such prior work has been completed. ASD is a neurological and developmental disorder that affects how people interact with others, communicate, learn, and behave. Scores from the Autism Diagnostic Observation Schedule (ADOS) are regarded as a standard tool for making an early diagnosis of autism. Successful treatment of ASD requires proper diagnosis and methodical therapy plans. Conventional treatments of ASD usually involve diverse intervention techniques designed by professional therapists. Unfortunately, highly trained therapists are not always readily available. Accessible therapists may sometimes lack experience and observational skills, making it difficult to assist ASD children effectively. So the question is, can we find an alternative to Standard Human Therapy (SHT) in the form of Robot Assisted or Robot Enhanced Therapy (RET)? Our work contributes by proposing a RET system based on 3D body joints and gaze information. We investigated the publicly available "DREAM" dataset, having bio-marker information on 61 children diagnosed with ASD. We propose a feature vector that is based on traditional directly connected body joints as well as some unconventional non-attached body joints with close association. We attempted to predict the severity of the disorder based on our predicted ASD levels and ados scores. The goal of our developed system is to effectively assist RET in ASD diagnosis and therapy.

View full abstract

One of the challenges for walking support systems for the visually impaired people is to design appropriate routes without colliding with static (cars, bicycles, etc.) and dynamic (people) obstacles. Previous studies in path design have used first-person camera images and Transformer-based neural networks to generate appropriate paths for an autonomous mobile robot considering the dynamic environment. In this paper, we experiment and evaluate the applicability of this method in the outdoor walking assistant system.

View full abstract

In recent years, as the number of visually impaired people has increased, various walking assistance systems have been developed. One of the most important functions is to create a route to the destination and guide the user. However, visually impaired people are not always able to turn right or left or correct their path as instructed because they have difficulty in understanding their surroundings. Therefore, in this study, we considered it important to give instructions to the user at the appropriate timing and collected three types of data: the set route, his/her own trajectory, and the timing of giving instructions, with the aim of ensuring that the visually impaired person can walk on the proposed route. Using these data and a recurrent neural network (RNN), we developed a system that provides automatic voice guidance at the appropriate timing. The results of the verification showed that the system provided good straight-ahead guidance, but there is still room for improvement in the right/left turn guidance.

View full abstract

The visually impaired face a variety of practical problems when traveling outdoors as a pedestrian. In recent years, various systems have been researched and developed to help the visually impaired navigate more safely and independently. However, most of them focus on local scope navigation, such as obstacle avoidance guidance, without considering the comprehensive navigation from the current location to the destination. Existing navigation services are also designed for typical people, so the timing of instructions is not appropriate for the visually impaired. So, we created a directional navigation tool for the visually impaired. This tool outputs instructions at a time more suitable for the visually impaired by comparing the location information received by GPS with the transit point obtained from Google map API. In addition to directional navigation at corners, a countdown function to the corner and a directional navigation function for departures are also implemented. Future work is to combine this tool with local scope guidance techniques to create a comprehensive navigation system.

View full abstract

In this paper, we propose an image correction method to improve visions of individuals with refractive errors such as myopia, hyperopia, and astigmatism. Refractive errors can be corrected by eyeglasses or contact lenses. However, there are problems such as maintenance or cost. Our method corrects images so that the corrected images are perceived similarly to the original images without wearing eyeglasses. Two convolutional neural network models are employed in our system: blur simulation model and image correction model. Blur simulation model is trained to simulate optical blur using a blur-induced camera, and image correction model produces images that can be perceived similar to the original images through the blur simulation. In our method, blur simulation model learns how corrected images are perceived while training image correction model, in addition to pretraining of clean-to-blurry images conversion to avoid implausible blur simulation for corrected images. Our method is fully software-based on inference, thus we do not require any special equipment except for computers. The images produced by our model provide better vision without significant contrast loss.

View full abstract

In programming education, it is necessary to correctly assess the programming skills of learners. The authors have named the source editing operations during programming as time-series information "coding sequences" and have been studying programming skills estimation methods using the coding sequences. In this paper, we propose an automatic judgement method for programming skills by focusing on the following information that can be extracted from the coding sequences; (1)the number of characters in variable and function names in a program and their composition, (2) the time taken to perform editing operations, and (3) whether or not a program can be executed.

View full abstract

This research proposed a new method of grouping of people after principal component analysis. First, we show that the scale of the normalized principal component scores is dependent on the number of the variables so that it is difficult to compare many results with each other. We proposed to renormalize principal component scores by two ways in grouping of the members in two-dimensional map. One is grouping of individuality, the other is grouping of selecting specially outlier. The nine classified areas can be given meaning. This method is an excellent way to classify all people according to their tendencies or to select extreme people based on rules. The advantage of this method is that no one is left out in the classification, and the classification is calculated automatically. The meaning of the axis is absolute and the comparison can be made in various mapping of any data.

View full abstract

In this paper, we focus on the input of elements necessary for each component of a program, such as control structure descriptions and function definitions, and design interfaces to facilitate coding by using forms. Based on these interfaces, we developed a prototype of a programming support tool and report the results of experiments using it. The authors have been studying an online coding support system for beginners of C programming language using the "standard coding form", which designed in web application styles. The programming learners can enter and edit necessary items using the forms step by step with hints which presented by the support system. In our previous study, we proposed a system that provides (1) input points for program components, (2) messages for guidance, and (3) information on syntax and coding procedures for novice users, and built a prototype system equipped with the system.

View full abstract

This study examines the results of an interview survey on the experiences of student volunteers, examining the ideal form of collaboration between parasports and university volunteer training.The subjects were two university students who had volunteer experience, not limited to parasports.
From the interview survey, it was suggested that volunteers are involved in understanding and noticing the degree of relationship with athletes, the sense of distance, and the characteristics of disabilities. In addition, it is also necessary for volunteers to reflect on themselves and become aware of their own transformation, and it was suggested that in the future, it is necessary to consider a program of reflection that raises the awareness of volunteers to a higher level.

View full abstract

Psychiatry is one field of medicine and treat of mental illness. However it is very unclear to distinguish mental illness from normal mental state. DSM-V(which is released by the American Psychiatric association) classifies mental illness mainly on the basis of not cause but statistical evidence. Even now there is no consistent consequence about the cause of mental illness. Many researchers have argued for a long time about endogen, exogen and psychogenic cause.
 In this paper, we will discuss about the true nature of mental illness and what is the difference between mind spirit. On this occasion, we will consider what a diagnosis for psychiatry is.

View full abstract

 The introduction of home mechanical ventilation (HMV) or home oxygen therapy (HOT) for chronic obstructive pulmonary disease (COPD) has been shown to improve patient outcomes and shorten hospital stays. Despite this, COPD deaths continue to increase worldwide, and there is room for improvement in the treatment of COPD at home.
 Maintaining fraction of inspiratory oxygen (FiO₂) may increase the effectiveness of treatment. However, previous studies have shown when HOT was used in combination with HMV, FiO₂ decreased due to leakage from the gap between the patient's face and non-invasive positive pressure ventilation (NPPV) mask.
 The latest HMV model, VOCSN (Ventec Life Systems, Inc.), is now being used in clinical practice as the newest ventilator model with HOT in HMV. We report on basic experiments conducted to investigate whether the VOCSN can maintain FiO₂ without being affected by leaks or ventilation volume compared to previous studies.

View full abstract

Bone tumors can be malignant or benign, and malignant bone tumors are life-threatening and intractable. The number of patients is very small (0.3% of the population), and determining whether a tumor is malignant or not requires a great deal of effort even for specialists. Therefore, there is a need to develop a system that automatically extracts the region of bone tumors and estimates benign or malignant status. In this study, we conducted experiments to automatically segment tumor regions of bone tumors and classify them into benign and malignant classes.

View full abstract

[in Japanese]

View full abstract

Blind people cannot draw figures by themselves. However, a blind physics teacher working at a university, for example, deeply wants to produce figures for his lectures by himself. In order to support for blind people to draw figures by themselves, some of the assistive systems have been developed [1, 2, 3, 4], but they are not practically used by the visually impaired. This is because, the produced figures are not precise enough to share sighted people or it requires long time to complete a figure. Based on this background, we are now developing a formal language of vector graphics, which is available for the visually impaired. This paper introduces our vector graphics and explains how it is useful for the visually impaired.

View full abstract

The purpose of this research is to elucidate the neutrophil propulsion mechanism by cytokine. In this study, to investigate the relationship between the velocity and the rotation or its period, observation experiments with a microscopy was conducted. The period of rotation was obtained from the time history of the concentration gradient by frequency analysis. As a result, it was found that the velocity is high when the period of rotation is short. It is concluded that the neutrophil’s rotation is an important role in the neutrophil's propulsion mechanism.

View full abstract

Treatment and intervention for fundamental recovery from autism spectrum disorder (ASD) seem to be undeveloped at the current moment because ASD can be caused by many different generic abnormalities. Furthermore, ASD is usually associated with intercurrent diseases such as epilepsy, gastrointestinal tract disturbance (constipation, diarrhea, indigestion, malabsorption, food allergy, etc.) and sleep disorders. This paper describes the possibility of healing ASD and epilepsy with acupuncture treatment.

View full abstract

Japan is now facing problems in various fields considering the shortage of caregivers caused by the elderly society. Care robots as one of the possible solutions to the elderly society has been effectively investigated. However, in most research, robots can only produce clear commands rather than unclear physiological desires such as "hungry" and "thirst". In this paper by introducing the distance-type fuzzy reasoning method, we have been able to (i) describe and represent the physiological desires with fuzzy sets, and (ii) reason for the most reasonable service with fuzzy reasoning. The effectiveness of the proposed method has been evaluated in simulations.

View full abstract

To realize a super-smart society, it is necessary to aim for advanced integration of cyberspace and physical space (real society). AI analysis of big data will bring effective information that meets the needs of individuals and companies to the real society more quickly. On the other hand, to build a safe and secure society, it is important to develop AI analysis methods that protect the privacy of big data in cyberspace. However, there is no known method that satisfies both data confidentiality and usability of the learning method at a high level. Therefore, the authors have proposed a distributed AI method using secret decomposition data. This method has higher confidentiality and usability than conventional methods, but the increase in computational complexity due to distributed processing is a problem. In this paper, we propose a new learning method to solve this problem. In particular, we apply this method to the Neural-Gas(NG) algorithm, which is unsupervised learning, and show its effectiveness.

View full abstract

Recently, AI technology called deep learning has been attracting attention. Deep learning is a kind of neural network. It is a method of machine learning using a hierarchical neural network with a multi-layer structure. Deep learning has shown great results in image recognition. In this study, we consider the classification of unearthed coins using deep learning. There are many types of unearthed coins to be excavated from a ruin. One of the most famous coins is Kanei-tsuho coins. There are many subdivisions of Kanei-tsuho coins. However, the classification of unearthed coins is even difficult task for numismatics experts. In this research, we use the attention mechanism in deep learning to perform image recognition of excavated coins. We verified whether the accuracy of image recognition is improved by using the attention mechanism.

View full abstract

With the increase in farm size in Japan’s livestock industry, managing individual animals has become quite difficult. Under such circumstances, disease detection becomes complicated, and a delay in detection increases disease spread and severity. This study aimed to establish an early detection AI ear-tag system and identify respiratory diseases in pigs using body-conducted sounds. An AI ear tag was used for physical robustness and classification algorithms in the pigpen. Additionally, using Pasteurella pneumonia model in pigs, we confirmed the feasibility of using an AI ear-tag system for detection. Finally, it was suggested that early detection of respiratory diseases could be achieved by assessing acoustic features and classification methods.

View full abstract

According to the livestock statics of the Ministry of Agriculture, Forestry, and Fisheries, the number of animals per household has increased since its peak in 1962, indicating the recent trend toward large-scale farming in the livestock industry. If a livestock epidemic were to spend under such circumstances, it would likely cause significant damage. Therefore, this study aimed to detect the disease in livestock early; machine learning based on time-frequency parameters obtained from the body-conduced sound of pigs confirms the effectiveness of this method. Specifically, LSTM using spectrograms and real-signal wavelet transforms as the input received a high decision rate in morbidity determination. This achievement is significant because it automates the management of livestock health and the early detection of disease.

View full abstract

In the Traveling Salesman Problem (TSP), when the number of cities is several hundred to several thousand, the number of trials itself is limited due to the increase in computation time, and it becomes impossible to even reach the correct answer. In SOM method, the computation time increases on the order of N². This N² factor defines the limit of SOM. N² factors are hard to change, so to shorten the computation time or increase the number of trials, it is necessary to reduce the number of learning cycles. In this study, we considered the properties of SOM parameters and observed convergence process of SOM as the learning cycle proceeded, and tried to decrease the number of learning cycles.

View full abstract

In recent years, Japan's population has been aging, and the "increase in the number of people requiring nursing care" has been cited as a social problem due to the aging of the society. Injuries such as fractures due to falls account for approximately 12.5% of all injuries, making it the fourth most common cause of care needs. Falls are a major cause of injury for the elderly, and even in the absence of trauma, fear of falling may cause gait disturbance called post-fall syndrome. Therefore, we thought that falls could be prevented by studying the causes and countermeasures of falls among the elderly. In this research, we used a plate-type distributed pressure system to obtain load data and basic data from elderly and healthy subjects, and analyzed and compared the data using a Self-Organizing Maps (SOM), which is used to group data with similar characteristics. In the previous year's research, we compared the data for each foot, but this year we analyzed how the load changes during the flow of walking, such as the first and second steps. The SOM created as a result of the analysis showed that the load data and basic data were divided into four groups, and by examining these groups, we were able to understand where the load data and basic data were located for each characteristic, and we also found that gait was improved before and after exercise.

View full abstract

Anaaalyses using contingency tables are very useful for finding interactions between two variables. The authors have extended contingency tables by applying fuzzy set theory and defined fuzzy contingency tables (type-1/type-2 fuzzy contingency tables). This allows us to fuzzify similarity indices in typical set theory. In this paper, we introduce typical similarity coefficients using the contingency table and propose a similarity evaluation method for scientific and mathematical texts as an application of the table.

View full abstract

The authors established Fuzzy Core Index Analysis, which is the method to transform a semi-ordered structure of nodes in serialization analysis into the linear-ordered structure, based on the idea of AHP. AHP has an index called the C.I. that measures the consistency of a pairwise comparison matrix. In this presentation, we propose “Fuzzy Consistency Index”, an index similar to C.I. in AHP, for a fuzzy core index matrix. Moreover, we check the validity of this new index via some examples in instruction structure analysis.

View full abstract

Genetic testing confirms the mutation in driver gene information involved in cancer cell growth. If the mutation is identified, molecularly targeted drugs with significantly higher response rates and milder side effects are expected to play an active role, but due to the difficulty of identification by imaging findings, testing is performed by invasive biopsy. However, due to the difficulty of identification by image findings, the examination is performed by invasive biopsy. Therefore, CAD (Computer Aided Diagnosis) system is highly applicable to detect mutations non-invasively by applying the analysis results obtained from images. In recent years, the correlation between radiomics features and cancer has been confirmed, and the prediction, classification, and detection of lesions in unknown data by machine learning using these features have shown high performance. Therefore, with the goal of developing a non-invasive genetic testing CAD system, we propose a method for detecting driver gene information mutations from chest CT (Computed Tomography) images using Ensemble Learning. In this method, the radiomics features extracted from the chest CT images are used for supervised learning by ensemble learning. Then, the effectiveness of the proposed method is verified by classifying the images into different classes and performing evaluation experiments.

View full abstract

This Paper describes a trial of environmental evaluation from medical staff's viewpoint using Three-Seconds rule Intelligence. This study proposes three-second rule intelligence that simulates the human behavior selection. Three-Seconds rule Intelligence first calculates the appearance probability of an action candidate using Bayesian network, and it selects an action that has appearance probability exceeds the preset threshold. By sequentially calculating and evaluating the time-series appearance probabilities of action candidates, it may be possible to give an empirical explanation for the "fluctuations" hidden in human behavior selection. This study applied this method to patient wait-and-see behavior of medical staff in radiation therapy, and by subdividing the factors to be observed and evaluating the appearance probability of action candidates by three-second rule intelligence, it clinically showed this method was effective.

View full abstract

[in Japanese]

View full abstract

Tongue diagnosis is one of the most important diagnostic methods of East Asian Traditional Medicine (Oriental medicine). In recent years, tongue imaging systems have been developed because tongue findings can be analyzed with tongue images. We surveyed research papers and other sources in Japan for the 10-year period 2012-2021 to determine the current state of the tongue diagnosis system. As a result, 35 references were identified from certain search criteria. In Japan, it was found that the development of systems for automatic tongue detection and photography is in progress, and the practical application of the tongue diagnosis system is an issue.

View full abstract

 Some characteristics of the mental map were investigated using the in-vehicle cameras and the following results were obtained. 1 The correct memory of the branch points by the left camera was about 55.6% and it by the forward one was about 84.1%, 2 The memory of the locations by the left camera was about 69.7% and it by the forward one was 74.5%.

View full abstract

Map in the brain, which is composed of 1 the route map from the point of departure to the destination, 2 the azimuth θ , 3 the direct distance D and 4the total moving distance are examined using the drive recorder set up at the front part of the car. Six target locations departed about a few kilometers from the starting location. The results showed that the accuracy of the survey map which composed of the direction θ and the direct distance D are considerably high.

View full abstract

This study aims to show an analysis of International Journal of Biomedical Soft Computing and Human Sciences (IJBSCHS) publications from the amount, author countries, and research topics from 2017 to 2021. It shows that publication number in each issue is stable with 4 to 5 papers, that the papers with international collaboration account for 26%, and that research topics are focused on recognition, data analysis, image processing, and welfare instrument. After an overview of what is happening in the journal in the past 5 years, this study finds the major challenge in the future is to get registered in some leading indexes like Scopus to increase its visibility.

View full abstract

One of the great goals in biology is to unravel the DNA sequence, which is the blueprint of an organism. Recently, it has become possible to obtain large amounts of DNA sequence information with the development of DNA sequencers. Especially in the field of metagenomics, it is necessary to distinguish each species from DNA sequence fragments obtained from multiple species. For this purpose, analysis method of DNA sequence fragment information using the combination of DNABERT which is a method based on natural language processing, Self Organizing Map, and Convolutional Neural Network is proposed, and the performance is confirmed in some experiments.

View full abstract

The significance method was applied to the analysis of corona data. The significance method was analyzed by the spherical SOM method. It was applied to the analysis of 17 elements in 47 prefectures.

View full abstract

The professional career of female medical doctors is influenced by various life events that can lead to early retirement: marriage, childbirth, childcare, nursing, mammy track etc. In recent years, efforts have been launched to have female doctors resume their clinical practice. In order to find clues to solve the problem, we used survey data from doctors who became mothers and identified their motivation using the spherical SOM, Residual Sum of Squares(RSS) and Significant degree.

View full abstract