We aim to evaluate the carcinogenic risk of low dose rate exposure to tritium using carcinogenic hypersensitive model mouse (Apc^{Min / +} mouse) and to clarify its carcinogenic mechanism. Tritiated water of 90 MBq was intraperitoneally injected to the Apc^{Min / +} mice (F1) which mice generated from C57BL / 6J-Apc^{Min / +} mice (♂) and C3H mice (wild type, ♀) at 2 weeks of age. The mice were kept for 25 weeks and the number of small intestine tumors were measured. As a result, mice injected tritiated water showed significant differences in the increase in the number of small intestine tumors, the increase in spleen weight and the decrease in hemoglobin levels. Currently, DNA is purified from cells taken from a part of a tumor, and LOH analysis is performed on chromosome 18 using a Mit marker.

Drug administration is performed by various treatments. Drug administration is not easy, and there is a high risk of side effects and sequelae if there are errors in the plans such as dosage and administration inter val. Therefore, it is important to estimate the blood drug concentration in advance. In previous studies, the use of neural networks has made it possible to exceed the prediction accuracy of drug motion analysis proposed in the field of pharmacy. However, the blood drug concentrations recorded in the data used are few and biased.

In this study, in order to estimate the blood drug concentration using a small number of data with a biased data distribution, a method to equalize the data by removing the data in the large part of the data distribution and A method is used to equalize the data by using GAN (Generative Adversarial Network) to generate pseudo data using the data in the area where the data distribution is small and adding the generated data as training data of the original data.

This paper describes the study of impressions of one minor music. The experiment invited two groups of healthy participants (one group has eight people and the other one has twenty-two), and one minor music (“Requiem (Mozart)”) is employed as the test piece. The experiment data are collected by using Visual Analog Scale (VAS) measure, and analyzed by using box-and-whisker plot, univariate scatter plot and cluster analysis. All participants are asked to listen to the minor music individually. In order to analyze their impression of the minor music, they are asked to answer the questionnaire on VAS (7 questions; “Bright-Dark”, “Happy-Sad”, and so on) individually. The results obtained from the two groups of participants are similar; they show that subjective evaluation values based on the impression of the minor music (“Sad”, “Dark”, and so on) have been obtained and visualized by the combination of box-and-whisker plot and univariate scatter plot, and it has been discovered that the questions based on the similar impression belong to the same cluster.

Our goal is to quantify the subtle differences in individual perceptions, and we explore the possibility of the VAS being able to represent indices other than pain. We consider that VAS's advantage should be contrasted with the Likert Scale and that the advantage of VAS is that it can be expressed in detail as a point on a linear number line, not as a stepped expression. We studied it was necessary to investigate the performance of the VAS. In this study, we compared the method of expressing subjectivity on a number line to express subjectivity directly on a number line, such as the NRS. However, we did not use the NRS, which expresses subjectivity on a scale of 11, as it is, but adopted a method of expressing subjectivity directly as a numerical value. For example, in the VAS, the distance between the straight line of 100 mm and the mark's left side is used as the measurement value. We convert this measurement into the value of the interval [0, 1] and use it. Therefore, we refer to the evaluation by the value of the interval [0, 1] as the Ex-NRS, which is directly inputted instead of the NRS that evaluates in 11 steps. In this paper, we report a comparison between a numerical representation of subjectivity and a direct numerical representation using Ex-NRS. We used grayscale images presented to subjective assessment subjects, and VAS and Ex-NRS measured the degree of subjectivity for comparison.

In this study, we proposed a new TRISS method, which improved the TRISS (Trauma and Injury Severity Score) method and incorporated the advantages of ASCOT (A Severity Characterization of Trauma). As a result, we proposed a new TRISS method, which is almost identical to the ASCOT method except for the cases of 55 years old at ISS 48 and 85 years old or older at ISS 48. In the future, we will improve the Revised Trauma Score (RTS) method and propose a more accurate method of survival assessment.

In recent years, the number of death due to lung cancer is increasing year by year worldwide. In Japan, the number of deaths by cancer site in 2018 was 1st for men and 2nd for women. Early detection and treatment of lung cancer are important, so it is necessary to detect the nodular shadow in visual screenig. A CT apparatus is used to detect lung cancer. Due to the high performance of the CT apparatus, the number of CT images increases, the burden on the interpreting doctor is heavy, and the diagnostic accuracy may decrease. From these reason, development of a CAD system is required. In this paper, we propose an image analysis method to detect abnormal shadows from chest CT images automatically. As a method, the initial lesion candidate areas are extracted by using temporal subtraction technique that emphasizes temporal change by subtracting from a current image to previous one which is obtained same subject. The image of the area is given as input and classification is performed by CNN (Convolutional Neural Network). In the classification experiment based on our proposed method, 92.33 % of true positive rates and 10.53 % of false positive rates are obtained from the 49 clinical cases.

Enormous number of panoramic X-ray images are checked by dentists every day. It needs much time for dentists and may cause interpretation errors. There are some studies on teeth detection with deep learning. However, object detection using deep learning provides multiple candidates, and it is not east to select one from the candidates. This paper proposes an automatic teeth recognition method, which refines the candidates by an optimization method with prior knowledge model. At first the proposed method detects teeth candidates by faster R-CNN, which is one of the deep learning-based techniques. Next, it determines the best candidate by optimizing an objective function. The objective function evaluates the relative position of the teeth based on prior knowledge model. With 1000 images, the accuracy of the proposed method was 0.94. It is higher than 0.92 that is without optimization. The proposed method performs the better recognition accuracy in comparison with the method without optimization step.

In emergency hospitals, the automatic fracture detection system is essential for doctors and patients to recover not only the injury but also the health status without their long hospitalization. Previous studies for the fracture detection system with CT images or deep-learning have difficulty in analyzing the internal structure or confirming predicted results easily. This study proposes a system for automatic detection of pelvic fractures from 3D CT images. Firstly, it defines the labeling work as a new 3D annotation method of fractures(called 3D surface annotation). 3D shape data of pelvic bone surfaces makes the burden of it light. The feature vector inside the pelvic surface is created from 3D shape data and CT images, and learned by 3D convolutional neural networks (CNN). The proposed method was validated by using 103 subjects. Eventually, the accuracy, precision, recall and specificity for the test data were 69.5%, 60.0%, 60.4% and 75.0%

In this study, we investigated the ideal training environment, requests, and prospects for improving the competitiveness of visually impaired athletes, targeting Blind Football leaders.The survey was conducted in a semi-structured interview, and the obtained data was immediately converted into text by the author himself, and then organized and aggregated according to the purpose of this study.The purpose is to obtain a material for improving the sports strengthening environment for the visually impaired, although the purpose is to strengthen the scene in Blind Football.

Among them, "a place where you can go with peace of mind and get used to", "a place where you can easily exchange information with athletes and staff", "a place where you can concentrate with peace of mind including how to move", "not only specialized knowledge" It was suggested that there is an urgent need to deal with and prepare for "reliable staff who can cooperate with athletes and staff" and "equipment that is effective and easy to handle with a simple program".

We are developing a walking support device for the visually impaired. Real-time detection based on camera images using 5G communication with the client server system. At this stage, it performs object recognition, deviation detection, step detection, and warns the user with voice output. We will investigate the recognition accuracy of the newly added deviation detection and step detection. Compare the 5G environment with 4G and examine the practicality of the development device.

著者は、大学4 回時の昭和57 年10 月25 日国立松籟荘病院（現 やまと精神医療センター）初受診、三原病院入院歴（病名 精神分裂病）を持つ、現在障害者（精神）2 級手帳保持者である。ただし、障害者認定は30 歳の広島大学工学部文部教官助手からで、それ以前の仕事、神戸大学大学院工学研究科工学修士号論文や奈良工業高等専門学校情報工学科文部教官助手時代の業績（論文1、国際会議論文3）は、健常者が行ったものとなっている。これらの業績が、30 年たった今、非常に問題になっている。つまり、主観を扱うファジィ理論と客観を重視するベイズ統計学の学問上の争いに巻き込まれた。この奈良工業高等専門学校文部教官助手時代の論文が非常に問題となり、ここでは写像の公式を発見したが、これは幻視からのもので、つまり、幻を見たことになる。しかしながら、幻に応用例を付加すれば、幻ではなくなり、日本ファジィ学会論文誌に掲載された。また、プロの査読者が審査して掲載されれば、学術的には精神的に異常はない。ここで、応用例も幻的であることに注意しよう。従って、この論文は、読者からは、幻の上の幻の様に捉えられていた。本稿では、著者の経験を交え、幻視体験談的原稿について言及する。

We proposed an automatic classification method for estimating sleep-wake state in neonates using body movements. We used Optical Flow to detect body movements, and then applied block separation to the frame images to create a histogram of the amount of movement in each direction. The histogram of each block was combined to create feature vectors, and classified into 6 classes using hierarchical SVM. We also proposed two methods to mitigate the differences in the direction of video capture in the dataset. The experimental results showed that the highest value of macro-F1 was 0.675, which was classified by the proposed method using the data expansion method. Furthermore, the percentage of correct answers for each State exceeded 50% by unifying the orientation of the newborns.

In recent years, the measurement and assessment of stress has become increasingly important, since it has been described as a stressed society in Japan. The electrocardiogram (ECG) is one of the indexes that can measure biological information on a daily life. For example, the ECG has been attracting attention as an index for stress assessment. A plantar ECG using fabric electrodes is suitable to daily monitoring. The plantar ECG is expected to reduce the burden of measurement on the subject and to provide a variety of measurement environments. However, stress estimation by plantar induction site has not been performed. The purpose of this preliminary study was to estimate the stress level using the plantar ECG. For our purpose, the plantar ECG was measured during the emotional image presentation. The subjects were three healthy males. The results showed that the stress level of two subjects was higher during the unpleasant image presentation than during the pleasant image presentation.

Respiratory disease is a serious illness that accounts for four of the world's top 10 causes of death in a year and accounts for more than 8 million deaths worldwide. Currently, the diagnosis of respiratory diseases is made by auscultation, however the diagnosis result depends on the proficiency of the doctor. Therefore, a computer-aided diagnosis system that quantitatively classifies breath sounds and outputs the results as a "second opinion" is required. In this paper, we describe the development of an algorithm for automatically classifying large-scale respiratory sound data sets used in the ICBHI 2017 Challenge. The proposed method consists of two stages. First, by preparing two types of window widths for short-time Fourier transform, two types of images, a spectrogram with high time resolution and a spectrogram with high frequency resolution, are generated. Second, T-CRNN that learns the series features in the time direction, F-CRNN that learns the series features in the frequency direction, and respiratory sounds were classified by inputting them into TF-CRNN, which is a composite model of them. In this paper, we apply our proposed method to 920 respiratory sound data, and average score of 64%, harmonic score of 62%, sensitivity of 54% and specificity of 73% are obtained.

On immune cells' analysis, analyst has hard working such as manual cell tracking to analyze in cell's movies. The aim of this study was reducing the load of theirs with automated tracking cells using the classifier. Cell's initial positions in the video was picked up from points of high recognized frequency in "Recognized Frequency Space". Recognized Frequency Space was generated from the positions that was recognized cells by the classifier. The classifier was trained by CNN which is one of deep learning methods. Then, cell's next positions were picked up using the cell's positions in the previous frame to track cells. As the result of used "Recognized Frequency Space" made by the classifier, 8 single cells were picked up from the frame image. And 5 of 8 cells could be tracked for 100 frames. This indicates that isolated immune cells can be tracked automatically if it is followed the method, and the method can reduce the load of cell's analyst.

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 pattern 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. However, the classification of unearthed coins is even difficult task for numismatics experts. The purpose of this study is to improve the accuracy of identification of unearthed coin images using deep learning. We use methods such as Data Augmentation to improve the identification accuracy.

The blending of scents in current aromatherapy depends on the experience and knowledge of aromatherapy specialists, such as the selection and mixing ratio of fragrance components according to the purpose of use. However, in the near future, there is no doubt that the introduction of artificial intelligence technology will establish a "rational design method for essential oils" that takes into account the aromatic components of essential oils, their actions, contraindications and precautions. As part of this, in order to understand the stress status of children who are closed due to COVID-19 and refraining from going out, we used AI technology to respond to stress from the measured values of saliva amylase and the reaction to the scent of four types of essential oils. Build a system to estimate "total difficulty (TDS)"

Molecular targeted therapies approved for the treatment of lung cancer have been recognized as having significantly higher response rates and less severe side effects in patients with driver gene mutations. However, genetic mutations are difficult to determine based on visual screening, and highly invasive bronchoscopy is recommended to patients. In this paper, we propose a method for detecting driver genetic information mutations from thoracic CT images with the aim of developing a CAD (Computer Aided Diagnosis) system to support physicians in making treatment decisions. This method uses clinical information of the patient and radiomics features extracted from two-dimensional tomographic CT images to perform supervised learning with SVM. After that, we perform two classes of mutation classifications and evaluation experiments to verify the effectiveness of the proposed method.

The attention has been focused in using assistive devices at the aging era of Japan. One of the devices is electric wheelchair, which enables physical disability people to easily operate it. However, accidents are occurring frequently with increasing demand by using electric wheelchair. Therefore, the development of an autonomous driving electric wheelchair is required to reduce accidents. In this paper, we propose a recognition of obstacles of panoramic images that obtained from a spherical camera. A spherical camera is equipped in an electric wheelchair, and images are cut out from the sequential images obtained by running. For obstacles recognition, we use YOLOv3. The proposed method considers the distortion of the image caused by using the spherical camera. The improvement of the model of YOLOv3 is examined, and the validity with the actual data is verified.

In this paper, (1) the extraction of the white line region, (2) the extraction of the relative location of the driving recorder on the traffic lane and (3) the parallelism of the car and the white lines are mentioned. To get the image of the road environment, the drive recorder DC-DR410 produced COMTEC Co. and a car named “Rush” produced Toyota Co. are used. The road used in order to get data is “TOMEI” highway. The maximum error of the distance between the white line and the drive recorder was less than about 2cm.

In recent years, aerial photography has been used to search for victims in the event of a disaster. Searching from the sky enables quick search activities in places that are difficult to enter. In this paper we propose a method of detecting a person fallen on the ground from images taken by a camera mounted on a UAV(multicopter). Unlike pedestrians, a fallen person takes various postures, and the orientation of the head in an image is not identical. Therefore, it is necessary to develop a method which is robust to various orientations of a fallen person. In the proposed method, Ri-HOG features and Ri-LBP features invariant to object orientation are employed for representing a fallen person, and the fallen person is detected by a classifier constructed using Random Forest. The effectiveness of the proposed method was verified by experiments.

An autocorrelated fuzzy time series model is an autoregressive model fuzzified by the author. This model uses fuzzy time series data and gives fuzzy outputs. In addition, although its prediction accuracy is good, the coefficients of the model can only be obtained by solving the two LP problems. Real time series data are easier to obtain than fuzzy time series data. Therefore, a fuzzy time series model using real time series data is proposed. The proposed model was applied to numerical examples and good results were obtained. The challenge of improving the width of the model was found, and this paper reports the results.

The autocorrelated fuzzy time series model uses fuzzy time series data to output fuzzy predictions. Since fuzzy operations are used to compute the fuzzy numbers, the vagueness of this model can be large. Therefore, a fuzzy autoregressive model using real time series data has been proposed. The proposed model was easy to use and the prediction accuracy was good in the numerical examples. A consumer price index was analyzed as an example of the application of the proposed model, the usefulness of the proposed model was confirmed. Then, the results are reported in this paper.

Prediction accuracy of time series and regression analyses can be important. Sometimes, however, we want to know only extents of a rise or fall using rough information. In this case, we want to get predictions easily. The models were tested to see if they could easily predict scale of variation using qualitative data. In this trial, the expected results were obtained. Therefore, this paper reports its prediction methods and results.

We are required to perform various tasks efficiently and with great concentration. This depends mainly on the environment in which the work is being done. This study aimed to investigate the effects of background music on work and cerebral blood flow during mental work. In this study, we tested the changes in cerebral blood flow among participants who listened to BGM while performing the calculation and memorization of English words. The block design was adopted as the experimental method. The task and the rest were performed for 5 sets of 30 seconds each. The maximum, minimum, mean, and variance values were calculated from the measurements' results, and the distribution of the sizes was represented in a box whisker diagram. The experimental results showed that the variance of cerebral blood flow between subjects was more significant during computational tasks than at rest, and the group that contained verbal information had higher overall cerebral blood flow than the group that did not. Besides, cerebral blood flow was lower during the task than during rest.

Some patients may be hospitalized without an agreement because there is not consciousness of their disease in the mind medical care. Even in these cases, psychiatric clinicians try to inform a patient with the mental disorder of that disease and its treatment method kindly. However, they usually reject some treatment such as medication or electro-convulsive therapy. Psychiatrists sometimes prescribe antipsychotic drugs for the patients informed of nothing. Psychiatrists are worried about doing it without the informed consents. There are medical ethical problems.

This paper describes Evaluation of stimulus on the venous stimulus induced PIVC by force measurement during penetration to the model of during penetration using a training model of vein blood sampling to elucidate the thrombosis formation mechanism during infusion of infants and stress analysis on it. As for the force measurement during penetration, CCD movie camera and spring scale were used by image processing. It was found that the maximum penetration force is increasing with penetration angle, and the duration time for penetration is also increasing due to the increment of the angle. As for the contact shear stress analysis on the vein wall, Ansys Mechanical was used to obtain the maximum stress. It was found that the maximum shear stress is approximately 100kPa when the force to move the PIVC is 2N. It is concluded that there is a risk of thrombus formation as the level of the shear stress is several kPa due to the prediction of the shear stress by FEM analysis.

The goals of this study are to examine the propulsion of neutrophils which move in water in the direction of high concentration of the cytokine and to apply it to DDS. Assuming that neutrophils move by the concentration Marangoni effect, we experimentally examined changes of cytokine concentration on the surrounding fluid and neutrophil membrane. But detailed propulsion mechanism is unknown. Especially, the effects of pseudopods which are used when neutrophils move on the inner wall of blood vessels on the underwater propulsion, and the effects of living neutrophils and dead ones on membrane properties are still unknown. Then, in this study, the observation using the microscope was carried out, and the moving speed of neutrophils and the concentration gradient on the membrane was quantified. Besides, the effect of the membrane properties on the propulsion mechanism was investigated by examining the difference of these values living status, dead status, with pseudopods and without pseudopods. The results show that there is a large difference of cytokine concentration on membrane, in case of pseudopods. It was concluded that both neutrophil’s velocity and concentration gradient on the membrane are greatly influenced by living status and dead status.

Standing on a different view point from Anderson we prove that the extended Wiener process defined by Anderson satisfies the definition of the Wiener process in standard analysis, for example the Wiener process at time t obeys the normal distribution N(0,t) by showing the central limit theorem. The essential theory used in the proof is the extended convolution property in nonstandard analysis which is shown in K., Nishiyama and Tchizawa and K. and Tchizawa.

The data of domestic Covid-19 and the data of international comparison of subjective view of health were analyzed by the significance method and the similarity method in the spherical SOM method. In the first data, which of the four groups of observation periods in 47 prefectures belonged was organized. In the latter data, nine seemingly similar health labels were still divided into groups A to C. Its rightfulness was proved by the plane SOM. In the following international comparison data of subjective health views, nine health-oriented labels are given in advance with three labels such as A: lifestyle, B: regular health consultation and exercise, and C: nutrition and rest. By this, the validity of the spherical SOM analysis was proved on the plane SOM.

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 su rvey data from doctors who became mothers and identified their motivation using the spherical SOM and DIM mode methods.

The computer vision involves many modeling problems with preventing noise caused by sensing units such as cameras. In order to improve computer vision system performance, a robust modeling technique must be developed for essential models in the system. The RANSAC and least median of squares (LMedS) algorithm have been widely applied for such issues. However, the performance deteriorates as the noise ratio increases and the modeling time for algorithms tends to increase in industrial applications. As an effective technique, we proposed a new fuzzy LMedS method based on reinforcement learning concept for robust modeling. In this study, we investigate an application of the fuzzy LMedS method to 3D shape reconstruction problem. Through numerical experiments using 3D measurement data, the performance was evaluated. Their results found the proposed method to be promising for 3D reconstruction.

The authors have defined a type-2 fuzzy contingency table for contingency analysis and proposed a fuzzy portfolio analysis method based on it. In the conventional fuzzy contingency table, the intersection of fuzzy sets is defined by min operation, but we replace it with t-norm and propose a new type-1 fuzzy contingency table. In this paper, we redefine fuzzy contingency table using t-norm, and furthermore, we introduce fuzzy portfolio analysis as an application of the technique.

We generalize the index to define the reliability of retest for the cases which have the time shift from the first test to the second test, where the test means questionnaire for a group. The old definition of the index assumes the stability, which means the answers to the test do not change from time to time. However, this assumption is not realistic. The answers of some of the group go up, and some go down. We define the rising point Pu and the descent point Pd, and verified the sum of Pu and Pd give the best expectation value of the time shift by using the least square method. We show the usefulness of the generalized reliability index for several typical examples.

We used the Crossroad Game in the Palliative care. The purpose was to educate nursing students about difficult problems of Palliative care, and the Crossroad Game were effective for this purpose. These effects were also recognized online simulation．We plan to evaluate the effectiveness of this simulation in the future．

This Paper describes a trial of environmental evaluation from medical staff's viewpoint using ThreeSeconds rule Intelligence. It reports that we build the trial system to try to evaluate the environment seen from medical staff’s viewpoint in the hospital. The purpose of this research is to find the conversion method from the data from many sensors and videos into human sense value. If we find the way of conversion from the data from many sensors into human sense, the artificial intelligence could be built to evaluate that a condition of patient is safe or not like Human sense. And if this artificial intelligence would be stablished it, A double watch of the machine and human will be achieved. Then the stress of medical staff's will be decreased and every work will be done safely in medicine.

We needed to investigate educational items of “Essential of Oriental Medicine” to increase the value of traditional Japanese Acupuncture and Moxibustion. We investigated teachers in an acupuncturist training facility about the importance of educational items and the degree of learning target in “Essential of Oriental Medicine”. In addition, we asked teachers for their opinions on the educational items of “Essential of Oriental Medicine” in the free description of the questionnaire. We considered that the results of the survey would serve as a reference for the development of the core curriculum of “Essential of Oriental Medicine”.