We developed a method to determine Heart Rate Variability (HRV) on a smartphone without any additional equipment or attachment. LF/HF is an index reflecting sympatho-vagal balance. In order to measure photoplethysmogram (PPG), we adopted smartphone white LED light as a light source and smartphone CMOS camera as a photo sensor. By means of a low sampling rate of smartphone (33Hz), we determined PPG and corresponding time-series heart beat intervals for 10 healthy subjects (22±0.8 years). From this time-series heart beat intervals, we determined HRV using fast Fourier Transform (FFT) through interpolating and resampling processes. LF and HF determined by a smartphone correlate significantly with those calculated from electrocardiogram (ECG) (LF: r=1.0, HF: r=0.99, p<0.05) under 0.2 to 15000 lux light conditions. Our method appears promising for future autonomic measurement method for daily stress monitoring using only a smartphone.

View full abstract

Our interest lies in the modeling of speech waveforms along a time axis, but not the spectral domain. According to information processing in the cochlea of the inner ear and/or the inferior colliculus in the midbrain, speech waveforms were divided into multiple spectral channels with one octave each; based on phase locking in the auditory nerve fibers, extrema in narrowband waveforms were sampled at an irregular timing. Because amplitude envelope plays a key role in auditory processing in the nerve nuclei and/or cerebral cortices, including the inferior colliculus central nucleus, the kernel function was designed with the linkage of less than seven cosine functions at duration of one term each. Although the linear estimation of angular velocity in the fine structure of amplitude envelope resulted in less than nine percent of phase error, suggesting that subjective roughness will not be caused, more than one hundred percent of quantization error was yielded for kernels at bandwidths of over 1,280 Hz. Contrary to high correlation among every short-term epoch in speech waveform synchronized with a pitch, 4.2 percent of kernels belong to the exception with large deviation, which will not be suitable for linear approximation.

View full abstract

The hammering test with artificial intelligence has recently been thrust into the spotlight because the simple as well as economical time-based-maintenance for the total area of at least 452km^2 should be executed without delay to prevent the lifted surface of domestic old buildings from falling. The test belongs to resonance recognition, which is caused by the degradation of stuck and/or bed mortar over time, suggesting not only external wall diagnosis but also wide range of non-destructive applications. Because both amplitude and frequency are altered by impact energy, we have proposed a robust index of resonance, in which half-life time is normalized for each impact, so that the index is independently verified by phase error of the fourth physical quantity based on auditory information processing in the brain. No more than ten trials of hammering were visualized by the histogram of resonance signals against spectral channel, accelerating the progress of automatic hammering test without a priori knowledge.

View full abstract

As common orthopedic diseases, there are rheumatoid arthritis (RA) and osteoporosis. Early detection and early treatment are important task for analyzing these diseases. Although visual screening is valid for diagnosis, some problem such as mass screening on data sets and different diagnostic accuracy in the subjective assessment by the physician are still remained. In order to respond necessity of computer aided diagnosis (CAD) system to solve these problems, reduce the burden to physicians and perform quantitative evaluation support from CR images of the hand, we carry out the development of a registration method of phalanges regions from CR images of the hand. In particular, phalanges regions are used automatic segmentation results from CR images of the hand of same subject. First, salient region are detected based on entropy from image of phalanges regions. Then, optimum deformation value is found from relationship between previous salient region features and current one. Finally, temporal changes are detected by registration of phalanges regions based on rigid deformation.

View full abstract

The aim of this study was to develop a remote height-monitoring system (henceforth, the system) to contribute to patient safety. We have developed and produced a system that can be operated by researchers and health care workers. To evaluate the system, an experiment was performed to measure the height resulting from an alarm (the distance measurement test). Results showed good linear correlation. In addition, in the alarm activation experiment, even the false alarm and loss report rates were low. Therefore, the system proves to be useful for reducing injuries resulting from accidental falls from beds.

View full abstract

In this research Markov decision processes are used in order to represent lectures. The best teaching strategy computed in previous research maximizes the effectiveness of a lecture. The best teaching strategy computed in this research maximizes the effectiveness of a subject which is composed of multiple lectures. We propose two computation methods based on statistical decision theory for teaching strategies. Dynamic programming algorithm is used in the proposed methods. The first proposed method selects teaching materials for a learner. The second proposed method selects teaching materials for multiple learners. A purpose of education is represented by the reward function of Markov decision processes. A teaching strategy is represented by the policy of Markov decision processes. The best teaching strategies computed by the proposed methods maximize the expected reward of Markov decision processes. We show the effectiveness of the proposed methods by some numerical calculation examples.

View full abstract

The present study focused on the shooting angles and distances in the blind football games of the top four countries in the London 2012 Paralympic Games in order to clarify the differences in shooting among the teams of each country. The study aimed to provide a material that would help improve the performance of the Japanese team. An analysis of the shooting area revealed that a greater number of shootings (33.8%) were made in the left side (31-60°). In terms of the shooting position (distance, angle), the attack from the left side was found to be more frequent than that from the right side. The teams of the top countries were found to have an attacking style of shooting from the left side. From these findings, it was suggested that in a blind football game, angular shooting was more effective than frontal shooting to the goal. Additionally, because a shorter distance to the goal corresponded to a higher probability of shooting into the goal net, shooting within six meters from the goal was deemed important.

View full abstract

Information technology is applied to many tasks in educational engineering. E-testing is one of important tasks in educational engineering. There are many previous studies on e-testing. An error rate in e-testing represents the probability of an event that an e-testing method computes wrong evaluations for understanding of students. In previous studies the error rate is not minimized theoretically. We propose an e-testing method based on statistical decision theory. The proposed method minimizes the error rate with respect to the Bayes criterion. Dynamic programming technique is used to solve the e-testing problem. We show the effectiveness of the proposed method by some numerical calculation examples. The proposed method is one of adaptive tests of hypotheses in statistics. The proposed method can be applied to many tasks in healthcare industry.

View full abstract