SOSatoki Ogiso

Satoki Ogiso

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Satoki Ogiso has a total of 30 co-authors. Here are the top co-authors by number of shared publications:

  • Naoto Wakatsuki

    Univ Tsukuba, Grad Sch Syst & Informat Engn, Tsukuba, Ibaraki 3058573, Japan

    13 shared publications
  • Keiichi Zempo

    Faculty of Engineering, Information and Systems, University of Tsukuba, Japan

    9 shared publications
  • Koichi Mizutani

    Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Ibaraki 305-8573 Japan and Faculty of Engineering, Information and Systems, University of Tsukuba, Tsukuba, Ibaraki 305-8573 Japan

    8 shared publications
  • Koichi Mizutani

    Institute of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan

    7 shared publications
  • Tadashi Ebihara

    Univ Tsukuba, Grad Sch Syst & Informat Engn, Tsukuba, Ibaraki 3058573, Japan

    3 shared publications
  • Takashi Okuma

    National Institute of Advanced Industrial Science and Technology

    3 shared publications

Latest Publications

  • Open Access

    Comparison of Trajectory-Integrated, Stationary, and Wearable Methods for Estimating Thermal Exposure of Factory Workers: Associations Among Thermal Exposure, Fatigue, Thermal Sensation, and Workload

    by Satoshi Nakae, Satoki Ogiso, Ikue Mori, Takahiro Miura, Takanori Sugi, Yasunori Haga, Eri Nakano, Atsushi Kimura, Takeshi Kurata

    We compared three approaches for assigning individual air-temperature and humidity exposure in a thermally heterogeneous factory: a trajectory-integrated method combining worker location with spatially distributed environmental measurements, a stationary representative-point method, and a wearable-sensor method. Forty-eight workers were monitored during two summer measurement periods in an approximately 15,000 m2 manufacturing area. Thermal sensation and current fatigue were assessed twice per shift, and workload-related indicators were derived from worker trajectories and Fitbit data. Period- and shift-related outcomes were analyzed using aligned rank transform mixed-effects models. For descriptive analysis of thermal sensation, exposure temperatures were grouped into integer-degree bins and correlated with mean thermal-sensation ratings. Positive monotonic associations were observed for all three methods, but the relative magnitudes of the Spearman coefficients differed between periods. Fatigue was further examined using regression-tree analyses with worker-grouped five-fold cross-validation and cost-complexity pruning; cross-validation favored very simple models, whereas the displayed trees were exploratory. The trajectory-integrated approach provides a practical means of assigning spatially varying air-temperature and humidity exposure to moving workers, but the present study does not establish absolute measurement accuracy, causal relationships with fatigue, or comprehensive heat-stress or physiological strain.

  • Open Access

    Datasets, Machine Learning Recognition Performance, and Key Issues in Nursing Care Activity Recognition: A Systematic Review

    by Yasuyuki Yoshida, Hiroyasu Miwa, Satoshi Nakae, Satoki Ogiso, Ryosuke Ichikari, Takashi Okuma

    Countries experiencing rapid aging face severe caregiver shortages, necessitating effective workforce optimization. Nursing care activity recognition (NCAR) offers a promising solution by automatically detecting caregiving tasks over time and visualizing workflows. Based on this information, NCAR can facilitate improvements in caregiving processes. This review systematically assessed 32 studies following PRISMA guidelines, analyzing dataset characteristics and recognition performance of algorithms in NCAR to identify factors influencing recognition accuracy. The review revealed significant challenges, including a lack of publicly available datasets, class imbalance, and decreased recognition accuracy in real-world environments. Additionally, sensor configuration and annotation quality were found to significantly impact recognition performance. The limited availability of field data restricts model generalization, highlighting the need for novel algorithms and efficient data collection methods. Expanding datasets, designing appropriate classes, and improving algorithms are critical steps for advancing NCAR research and practical applications. The findings of this study demonstrate the potential of NCAR in optimizing caregiving workflows and mitigating workforce shortages.


  • Infrastructure-less Localization from Indoor Environmental Sounds Based on Spectral Decomposition and Spatial Likelihood Model

    by Satoki Ogiso, Yoshiaki Bando, Takeshi Kurata, Takashi Okuma

    Human and/or asset tracking using an attached sensor units helps understand their activities. Most common indoor localization methods for human tracking technologies require expensive infrastructures, deployment and maintenance. To overcome this problem, environmental sounds have been used for infrastructure-free localization. While they achieve room-level classification, they suffer from two problems: low signal-to-noise-ratio (SNR) condition and non-uniqueness of sound over the coverage area. A microphone localization method was proposed using supervised spectral decomposition and spatial likelihood to solve these problems. The proposed method was evaluated with actual recordings in an experimental room with a size of $12\times 30\ \mathrm{m}$ . The results showed that the proposed method with supervised NMF was robust under low-SNR condition compared to a simple feature (mel frequency cepstrum coefficient: MFCC). Additionally, the proposed method could be easily integrated with prior distribution, which is available from other Bayesian localizations. The proposed method can be used to evaluate the spatial likelihood from environmental sounds.

  • Technologies for Improving “Quality of Working”

    by Takashi Okuma, Masakatsu Kourogi, Ryosuke Ichikari, Mai Otsuki, Satoki Ogiso

    Proceedings of the International Display Workshops Volume 28 (IDW '21),Search for presentations


  • Open Access

    Robust Indoor Localization in a Reverberant Environment Using Microphone Pairs and Asynchronous Acoustic Beacons

    by Satoki Ogiso, Koichi Mizutani, Naoto Wakatsuki, Tadashi Ebihara

    In this paper, a robust indoor localization method using microphone pairs and asynchronous acoustic beacons was proposed. The proposed method is applicable even with a two-channel microphone pair, which is the minimal configuration of a microphone array. The proposed method estimates location by using the cross-correlation functions of the measured signals as location likelihoods. Three experiments were conducted to evaluate the proposed method. Four beacons were located at the corners of a localizing area of 4 m by 4 m and emitted signals with a bandwidth of 2 kHz. The localization results were compared to the previous method with deterministic direction-of-arrival estimation. The 90th percentiles of the localization error were 0.23 m for the proposed method with two microphones, 0.19 m for the proposed method with four microphones, and 0.30 m for the previous method under conditions without significant reverberation. Under a condition with reflective walls, the 90th percentile of the localization error of the previous method increased to 0.49 m, while that of the proposed method was only increased to 0.23 m for two microphones and 0.19 mfor four microphones. The proposed method contributes to a robust localization in indoor environments and relieves the constraints of receiver configuration.


  • Open Access

    Estimation of no-line-of-sight sound source using ratio of peak and root mean square values of cross correlation function

    by Taichi Hayashi, Satoki Ogiso, Takanobu Kuroyama

    Estimation of no-line-of-sight (NLOS) condition is a key technology for practical indoor localization. In this paper, a novel method to estimate the NLOS sound source using ratio of peak and root mean square values of cross correlation function is proposed. The proposed method is evalueted with experiment in a room and compared with previously proposed method using assumption of Rice distribution. The estimated result of NLOS of the previous method do not show a monotonic increasing with degree of the NLOS, because of the existance of non-deniable reflective waves. On the other hand, the proposed method is possible to estimate the value which show monotonic increase with degree of NLOS. The proposed method may contribute to robust estimation of NLOS condition for indoor localization and robustness of the localization itself.

  • Sensorless Contact Force Evaluation of Bone-conducted Sound Transducer by Electrical Impedance in Limited Frequency Range

    by Satoki Ogiso, Koichi Mizutani, Naoto Wakatsuki, Keiichi Zempo, Yuka Maeda

    A contact force estimation method of bone-conducted sound transducer was evaluated with data in limited frequency ranges. The estimation method uses three-layered neural network to estimate the contact force from electrical impedance. An experiment was performed with 12 subjects to evaluate contact force estimation accuracy. The electrical impedance was measured for 300 points in a frequency range of 10 Hz to 60 kHz. For evaluating the estimation accuracy with different frequency ranges, 464 combinations of start and stop frequencies were evaluated. The result showed that it is possible to reduce the frequency range without compromise on estimation error. With the limited frequency range, the measurement time can be reduced up to 5.4% of the 10 H-60 kHz range.


  • Robust Localization of Mobile Robot in Reverberant Rooms Using Acoustic Beacons with Iterative Bayesian Filtering

    by Satoki Ogiso, Koichi Mizutani, Naoto Wakatsuki, Tadashi Ebihara

    A method of estimating location by acoustical signal and microphone array without the detection of direction-of-arrival is proposed. The proposed method consists of the following steps. First, acoustic beacons in the environment emit signals and the localizing target receives the signals with a microphone array. Next, the localizing target calculates the probability distribution of the location by a particle filter. The cross-correlation functions of the microphone array elements correspond to the location and beacon arrangement. Herein, the cross-correlation functions are used as a likelihood function by projecting them to the localizing state space. The localization result is calculated as the weighted sum of the particles based on their likelihoods. The proposed method is tested and evaluated in an indoor environment with four beacons. The result shows that the proposed method can achieve better localization than the previous method.


  • Open Access

    Evaluation of Time-Difference-of-Arrival Error of Acoustic Beacons Caused by Velocity of Microphone Array

    by Satoki Ogiso, Koichi Mizutani, Naoto Wakatsuki, Tadashi Ebihara

    In this paper, we described a criterion of estimating the quality of time-difference-of-arrival (TDOA) estimation with a moving microphone array. The microphone array was supposed to receive a known signal from an acoustic beacon which transmitted a binary code with binary phase shift keying (BPSK). The movement of the microphone array may cause two kinds of error on the TDOA estimation; physical change of TDOA caused by the movement, and apparent change caused by the lower correlation values of Doppler-shifted signals. For evaluating the latter error, we employed the peak to average power ratio (PAPR) of the cross correlation function. The Doppler effect on TDOA error were evaluated with a computer simulation. The microphone array was moved at -2 to 2 m/s, covering the velocity range of indoor mobile robot. Besides the velocity, following three parameters of the sound were investigated. The types of the code for evaluation were chosen as M-, Gold and Kasami sequences, carrier frequencies were 0-40 kHz, and chip rates of the binary code were 0.5 - 20 kHz. As the results, it was confirmed that if PAPR is lower than a certain value, 40 in this simulation, the peak detection of the cross correlation is difficult and it results in high and unpredictable TDOA errors. Higher chip rates and lower carrier frequencies showed better resilience against the Doppler effect. The proposed criterion may infer the maximum velocities at which TDOA can be estimated without any measure against the Doppler effect for realistic parameters. This criterion would contribute to the on-line evaluation of the quality of TDOA, which may be beneficial for estimating sound direction of arrival.


  • Open Access

    Effect of Movement on Positioning Accuracy in a Transponder-based Acoustical Positioning

    by Hirokazu Iwaya, Satoki Ogiso, Koichi Mizutani, Tadashi Ebihara, Naoto Wakatsuki

    A transponder-based positioning method using audible sounds for a large-scale area positioning has been proposed by the authors. The proposed method has two characteristics; it employs audible sounds instead of ultrasounds to measure long distance by using audible sounds, and it achieves positioning without clock synchronization among devices which is required additional equipment such as radio wave. However, positioning of the moving object (terminal) is still challenging because the proposed method requires longer measurement time than other methods since it measures the round-trip time of flight (TOF) among the terminal and the anchors (transponders). In this paper, we evaluated the effect of the terminal movement on positioning in simulations and experiments. From simulations and experimental results, it was found that the effect of Doppler and the terminal movement cause random error and offset in TOF/distance, respectively. Consequently, it was found that our proposed method is sensitive to the terminal movement.