We are developing an indoor movement support machine to conduct livelihood support for people with lower limbs disabilities. A joystick is designed for users to manipulate this machine. However, it is inconvenient for users to operate the joystick and the same time conduce daily life activity. Therefore, we are aiming to develop a method to detect the movement intention by the movement of user's upper body. In this report, to try to determine the movement intention, we measured the activities of daily life by inertial sensors.
Smartphones are equipped with various personal authentication functions. Accordingly, in the previous experiment, we have tried to develop a security enhancement method for pattern authentication of smartphone. To discriminate individual users, we applied self-organizing maps (SOM) for the authentication, which is based on locus of figure drawing and angle of device holding. The result suggested the possibility to enhance the accuracy of pattern authentication. In this article, we propose an extended picture password method using behavioral profile and SOM for a biometrics authentication using previous results.
In this paper, in order to perform a walking neuro-rehabilitation of brain cognitive function, we developed a system that could analyze the brain activity during virtual walking and feedback the analysis result to subjects. The important thing in neuro-rehabilitation by virtual walking is that subjects should be informed with imagination situation to recall the sensation of walking. In this report, we measured the brain activity by a optical topography device. The imagination situation was feedbacked by image presentation when virtual walking was conducted and the effects of feedback information on brain activity was discovered.
Following amputation, patients often report severe pain in the vivid phantom awareness of their lost limbs, which is called as phantom limb pain (PLP). Some researchers have treated PLP with providing the visual images of the lost limbs to the patients by using a mirror. We extended this paradigm to the multimodal (visual, auditory and tactile) Virtual Reality (VR) system to provide more efficient images of the phantom limb. We applied this VR system to 4 PLP patients in two different tactile conditions for 5 minutes respectively. The following findings were obtained: 1) PLP improved immediately after the VR training; and 2) Affective pain characteristics ameliorated greater than sensory pain characteristics; and finally 3) Tactile feedbacks on the healthy limb had inverse effects for the acquisition of voluntary movements of the phantom limb. These preliminary results show that we have achieved a milestone toward the neurorehabilitation platform system for PLP.
Methods to evaluate venous blood collection models quantitatively have been investigated. The conventional puncture force method has been evaluated and the problems associated with the reproducibility of torque and puncture strength have been identified. Using a motorized test stand, quantitative evaluation has been applied to a puncture force measurement system that enables a constant speed at a predetermined angle. Compared with the conventional method, the assessed model has demonstrated detectable and advantageous characteristics.
In recent years, the walk support equipment for visually impaired persons has spread, and a studded paving block and a sound-type signal are installed on the sidewalk. However, there are still problems that the places of installation are few with the former, and the provided information becomes obscure with the latter in the noisy environment such as heavy traffic or heavy rain. In order to solve these difficulties, this paper proposes a method of detecting pedestrian signals and traffic signs at a pedestrian crossing from a self-wearable camera. Experimental results are shown and the method is evaluated.
In recent years, researches on pedestrians detection have grown actively. Also, technology on pedestrians detection can be used in many fields. This paper proposes a method of peculiar information extraction based on pedestrians detection from self-wearable camera images. This method is more effective in cost than using more cameras, and applicable to various fields. Also, not only pedestrians detection but also their peculiar information extraction extends the flexibility of pedestrians' information processing. Experimental results are shown and the performance of the proposed method is evaluated
This paper proposes a method of detecting salient regions from an image. Detection of salient regions is important, because it is expected to improve the precision and the processing speed of object recognition through image processing. The proposed method employs human visual characteristics, i.e., complementary color harmony and Purkinje phenomenon to detect salient regions from an image. Experimental results show the effectiveness of the spatial redundancy considering global redundancy and local redundancy, based on the human visual characteristics.
Detecting feature points from an image is an important technique in advanced image processing, and various feature point detection methods have been proposed to date. Attention is paid on the technique for detecting corner points in this paper. The proposed method detects corners of objects from an ILBP image by use of particular ILBP values and their spread patterns. The advantage of the proposed method is that, unlike Harris corner detector or FAST, it does not employ a threshold for the corner detection. Experimental results are shown with discussion.
The development of artificial intelligence is significant with the spread of a portable terminal including a smart phone in recent years. By progress of artificial intelligence, machine enabled to act like human beings. However machine has not been possible to take a smooth communication between humans yet. It can be considered as one of the causes, it is not considered emotions sufficiently. In this study, we propose a method of one of the facial expression recognition. First of all, we have developed a system for recognizing using feature point extraction of WebAPI called "detectface();". However, it was not possible to obtain sufficient accuracy in some emotion. It is considered that the accuracy of the feature point depends on situation of original image. Therefore, We have implemented a feature point extraction system in order to improve the accuracy. Finally we explain the experimental results and discuss future plans.
Young generation who are called internet generation are usually facing information written by close to a colloquial sentence such as a bulletin board and the blog. Increase of the number of young generation who can not understand or express sentences which has emotional expression is concerned. Meanwhile, conversation between human beings and the agent system has become general. However, because the system does not take into account the feelings of human beings, we feel uncomfortable with the conversation. To resolve this two issues, we propose an emotional expression support system for people who are weak in expressing feelings or understanding them from a sentence.
This study, focusing on the situation of speech, is to clarify which of the three levels (low, average and high, along with the indices of blood pressure and anxiety) is adequate for before speech conditions. Introducing the fuzzy evaluation values, calculated thorough the application of the fuzzy reasoning, the correlations between those values and self- and mutual-evaluations for speech are analyzed. The significant correlation was observed in the average level, while no significance was found in low and high levels respectively.
In order to synchronize the movement of omni-directional walking training robot to the walking motion of users, the walking training robot need to recognize the walking motion of user and move following the user s waking motion. The use's walking motion could be analyzed and identified based on the surface electromyogram (sEMG). In this report, the sEMG of muscles used in walking motion was measured, and a hierarchical neural network was proposed to identify the walking motion of users. The usefulness of the identification method was verified by experiment.
Transportation Problem (TP) is a well-known basic network model that can be defined as a problem to minimize the total delivery cost. But for some real-world applications, the TP model is often extended to satisfy other additional constraints or is performed in several stages. In addition, traditional TP model is not include the concept of opportunity loss. In traditional TP, customer demand is always satisfied. In the real world, there are many cases where customer demand is not satisfied, and opportunity loss occurs. In this paper, we formulate a two-stage transportation problem with opportunity loss and inventory cost. To solve the problem, we applied Differential Evolution (DE).
The main purpose of this research is to establish the estimation method of an antecedent using knowledge of probabilistic and linguistic. Traditional studies about estimation method of an antecedent roughly classified into two approaches. One is statistical approach and the other is rule-based approach. In recent years, research about integration of these two methods has begun, however it has not been possible to satisfy a sufficient accuracy yet. Therefore we propose a better integration method of the two approaches for improving the accuracy. We show the following two points as a specific method: (i) Using case markers consider the role of the noun phrase that constitute a sentence (Case Grammar) and (ii) Using conditional probability and simple probability to prioritize the antecedent candidates. We performed experiments to estimate the antecedent of the topic matter omitted for the sentence that is omitted it using our proposal methods. We finally show the experimental results and discuss about it.
Diagnosis Procedure Combination / Per-Diem Payment System (DPC/PDPS), which has been introduced since 2003, standardizes medical records. It is possible to collect analyzable clinical information nationwide as the uniform format (DPC formatted data) from medical centers and hospitals. In this paper, we describe a prediction method of a length of stay in the hospital from DPC data using Self-Organizing Maps (SOM) and its evaluation of predictability for different diseases. By the result of an experiment, it was confirmed that the proposed SOM prediction method was superior to the method using mean values of length of stay in hospital in 71 % of diseases to evaluate.
Recent years, speech recognition technique and voice authentication method is in progress to the field of the Internet technology. As a biometrics authentication method, our security applications with Self-Organizing Maps are currently in development. In this article, we described a method for speech recognition executed concurrently with voice authentication. And also we discussed the result of the experiment to evaluate our method with FAR (False Accept Rate) and FRR (False Reject Rate). We obtained that the best recognition accuracy of nouns is over 88% and the same of verbs is 83% in the experiment.
Time series are often sampled at different frequencies like month, quarter, etc. The classic fuzzy cluster analysis simply aggregates all data into the common lowest frequency and then computes a similarity matrix. Such temporal aggregation may yield inaccurate or misleading results due to information loss. Inspired by the growing literature of Mixed Data Sampling (MIDAS) regression technique, this paper proposes a way to construct a similarity matrix exploiting all data available whatever their sampling frequencies are. In empirical application on recent Japanese and U.S. macroeconomic indicators, the MIDAS approach and the classic low frequency approach produce different partition trees.
This paper proposes a new method for the detection of retina vessels in fundus images based on a new morphology operation and the anisotropic diffusion filter. The retina vessels detection in fundus images is needed for the diagnosis of an eye disease. However, it is an extremely exhausting and time consuming task for medical doctors, and therefore an automatic retina vessel detection method is strongly required. After the actual experiments on particular sets of fundus images, it has been found that the proposed method works better compared with the conventional detection methods.
The everyday environment is filled by the objects including the important information which is used as a guide of the behavior such as the traffic signs, a store sign, a price tag and so on. In this paper, we present a new system which extracts the salient object region including the important information and an experiment result applied to the database "Image-MSRA 5000".
In this paper, the authors discuss the instructional structure analysis. We describe the similarity structure graph and the connectivity structure graph scoring the quizzes in the classroom. Then, we show how to get the partition tree, the approximate structure graph, and the cognition structure graph from the similarity structure graph and the connectivity structure graph. Finally we discuss the case study concerning the teaching units on exponent and logarithm in high school mathematics education.
With development of the Internet, media lessons have also developed greatly. Recently, student's needs is increasing for media lessons, we have to satisfy student's needs. In this paper, we propose a needs analysis applying Kano model.
The "Napier's binary chessboard" is a calculating board introduced by John Napier in his book "Rabdologiae" . This Napier's binary chessboard can easily be basic four arithmetic operations of binary numbers. In this paper, we propose teaching materials as one of the applications to introductory education on information mathematics using the "Napier's binary chessboard board", and also show the result of the real introductory education using the teaching materials proposed above.
In elementary school, each teacher determines the materials to use that year. If the contents of teaching materials are qualitatively similar, teaching materials using the character are popular. Teachers choose teaching materials using the character that parents and children prefer to not just the taste of their own. Therefore, it is very important to determine the appropriate character to be used for teaching materials for materials company. They need to create teaching materials with a view to taste of the character required by the three attributes teachers, children, and parents. In this paper, I propose an analysis system for preference structure of teaching materials using the character arranging the fuzzy conjoint analysis.
We have done the experiment in JARI using human type robot which simulate the human accidental injury. The precise data of acceleration has been taken from the robot, then HIC has been calculated for the experiment of various conditions. We analyze the HIC of the protectors and conditions. Form the result, It is concluded that the increase of the cart and bicycle is similar. The effect of the helmet is amazing, which reduces HIC by 5903. On the other hand, the effect of the safety cap is not so large, the reduction is 1833 (about one third of helmet). We determine the reduction values of HIC using least square method. This values are valuable to predict or summarize the various effects of the situation.
Questionnaire using Likert Scale (LS) style has been used in order to confirm the relevance of affectiveness, feelings or emotions of subjects and its results of psychological tests or biometric test. However case studies and research that conducted a questionnaire by using the Visual Analog Scale (VAS) style instead of the LS has begun in recent years. There is no significant problem in many applications in the case of using LS, but it is believed that there may be distortion measurement results for some reason. There is a tendency that the subjects wants to agree to statements that are presented in the questionnaire. While there is a possibility that the case of using VAS can obtain the results which reflected in sensitivity of the subject more accurately than the case of using LS. However there is a problem that making tally sheet of values measured by VAS is done by manual and its burden is large. Our main purpose of this study is to solve this problem by VAS application. We have developed an VAS application which runs on iPad and conducted a verification experiment using this app. Finally we show the experimental results and discuss future plans.
We have been proposed the method of the neural network based on quantum theory (wave equation and path integrals) of polaritons, and made some relation's tools and descriptions for calculations for arbitrary neural circuits developed. The most important difference between the common (classical) neural network and quantum one existed in whether there were interferences between both systems. The quantum system had essentially many interference's relationships in its system, and so its probability was related to the probability amplitude, wave functions and propagators, which were commonly complex functions. On the other hand, the classical probability never contained any interferences since it had in the real number field. And concretely we showed how those quantum methods, whose system contained many interference, were applied to the Bayes' theory, entropy of information theory, and the two-step neural network of multi channels.
In our previous study, the silent reading time, the gaze duration and the saccade were measured using point-of-regard measurement for evaluating legibility. And, we reported that the silent reading time and the gaze duration were extended and the saccade was shortened, when the contrast between characters and a background decreased. This result showed that luminance contrast may influence perception and cognition process. In this report, the influence of perception and cognition process by luminance contrast of perception and cognition process by luminance contrast was measured using EOG and EEG analysis. As the result, P300 latency was extended, when the luminance contrast decreased. Therefore, it was shown that luminance contrast has influenced the perception and cognition process.
Research results suggest us that the social behavior of autistic disorder is associated with the neural networks in the prefrontal area and also so called mirror neuron systems. This paper describes the PA training system (prefrontal area training system) ,which was designed to enhance the concentration power of the subjects and boost the imaging ability of the target vanishing away gradually. This equipment seems to facilitate the subjects of autistic disorder to improve the social communication ability
In this study, We examined an exercise program for the purpose of lack of exercise measures in the support spot(1, Improvement of the exercise function, 2, Acquisition of the sense of accomplishment, 3, Breeding of the social nature). The participant was 13 persons with intellectual disabilities. As a result, joint ownership of the sense of accomplishment, preliminary imitation action and action restraint developed in a target person. By this exercise program, we were able to confirm not only the action transformation of the participant but also the change of the psychology.
A purpose of this study was to find the relation of ADL improvement to clinical practices and the situation at the time of hospitalization by using the DPC survey data and the decision tree analysis. The amount of ADL improvement was estimated from the difference of the value of ADL at the times of hosopitalization and leaving hopital. The ADL improvement was connected with age at the patient's hospitalization, the existence of re-hospitalization, of operation, and of emergency conveyance. In the cases with cerebral infarction, ADL improvers' percentage became high in the patients who performed nutrition management.
We are studying on the ubiquitous information communication system using electromagnetic wave, light, sound wave, and vibration wave. In this paper, we propose an emergency information Communication System (disaster information Communication System) by Sound Wave. Using the sound wave, the realization of the system which utilized a notebook PC, a tablet PC, a wearable PC effectively is possible and the realization of the system which utilized disaster prevention administration radio effectively is possible.
Existing general Personal Computers have PCM sound function to treat audio data, which are also available as information communication system by playback (transmitter) and recording (receiver) capabilities. In this paper, we propose an information communication method using sound wave, which detects digital wave pattern striding over threshold values. Our method has an advantage of lower CPU load than other digital signal processing methods that require signal-transformation, for information communication using sound wave.
We proposed information communication methods T-2DM, T-4DM, and T-S4DM that detects digital wave pattern striding over threshold values by using sound wave in our previous work. Our newest method T-S4DM has an advantage of lower CPU load than other digital signal processing methods that require signal-transformation, for information communication by sound wave. In this paper, we represent experiment results of sending and receiving sound wave patterns by our data communication programs.
This paper describes the development of microcapsules for shock wave drug delivery systems (DDS) by using chemotaxis. Especially, cytokine concentration gradient, which was obtained in our experiment, on neutrophil's membrane was investigated by numerical simulation for elucidating the mechanism of neutrophil's motion. As a result, the concentration gradient changes from negative value to positive by changing diffusion coefficient and adsorption-desorption coefficient of neutrophil's membrane. This result shows same trend as that in our previous experimental result.
The significance degree of each component was calculated only by once SOM learning where the Spherical Self-Organizing-Map (SSOM) was used for the demonstration. The method can also be used by the usual planar SOM. In the method, kinds of specimens of the data are inserted in each column as each specimen. The method is first demonstrated using the iris data.
The present metabolic syndrome judgment is as follows: It is judged as metabolic syndrome if checked values are exceeding standard values. It is identified by the non-metabolic digitally if checked values are not exceeding standard values. We established a non-ill area among the values, and the values are judged more finely. The method was applied to other items of the checkup judgment sheet, too. They are glucose metabolism, liver function, renal dysfunction, blood test, and inflammatory response. All these 6 items including the metabolic syndrome are included as the judgment items of Dr. Ningendock. In this paper, the further improvement of Dr. Ningendock is explained.
We propose a cluster analysis method using self-organizing feature maps (SOM). SOM-based cluster analysis methods are attracted among a lot of studies on the automatic cluster analysis methods. In most situations, a histogram, i.e. a density distribution of data, obtained from the learnt SOM involves more excessive peaks and valleys than we envisioned by the true number of clusters. In this paper, a method to smooth the histogram is proposed to make cluster analysis easier and to eliminate the unwanted extreme values. The effectiveness and the validity of the proposed method for the automatic clustering are examined for several artificially generated data.
Centered on fundus examination and intraocular pressure checkup examinees men, for data checkups of 66 items, analysis by significance of SOM has been made. As a result, the "vulnerability" of such abnormal inflammatory system and metabolic syndrome and obesity trend has been suggested may have a strong influence for depression of the optic nerve head and increased intraocular pressure. As an aid in the discussion of the origin of glaucoma, according to SOM the significance of the comparison of "yu-ido" value was shown.
From the perspective of general local residents of (consumers), using the official annual statistics for the 15 items medical examination results, lifestyle, medical environment, social environment, and lifestyle, the difference between the regional health by SOM were examined. As a result, the difference of modern Japan of "regional health force", to be dependent on day-to-day lifestyle and infrastructure development of the insurance environment and industrial structure of the region has been estimated. It is believed that it is possible by the calculating "Yuido" of SOM, will be discussed in detail the contents of these.