Faculty Profiles - HANAZAWA Akitoshi

Papers - HANAZAWA Akitoshi

Division display1 - 20 of about 65／ All the affair displays >>

Flexible Natural Language-Based Image Data Downlink Prioritization for Nanosatellites Reviewed International journal

Fielding E., Hanazawa A.

Aerospace 11 ( 11 ) 2024.11

Flood susceptibility mapping leveraging open-source remote-sensing data and machine learning approaches in Nam Ngum River Basin (NNRB), Lao PDR Reviewed International journal

Mangkhaseum S., Bhattarai Y., Duwal S., Hanazawa A.

Geomatics, Natural Hazards and Risk 15 ( 1 ) 2024.01

Clothing Recognition System Using MLLM and Its Utility Reviewed

Suzuki K., Hanazawa A.

Proceedings of SPIE - The International Society for Optical Engineering 13510 2025.01

Identification of original markers by object recognition algorithms using machine learning Reviewed

So A., Hanazawa A.

Proceedings of SPIE - The International Society for Optical Engineering 13164 2024.01

Harnessing Multi-satellite Remote Sensing Data and Machine Learning for Flood Risk Assessment in Nam Ngum River Basin, Lao PDR Reviewed International journal

Mangkhaseum S., Duwal S., Bhattarai Y., Hanazawa A.

Proceedings of SPIE - The International Society for Optical Engineering 13083 2024.01

Attitude determination of small satellites using Earth images matching Reviewed International journal

Honda M., Hanazawa A.

Proceedings of SPIE - The International Society for Optical Engineering 13164 2024.01

Flood Susceptibility Mapping Using Publicly Available Big Data with Google Earth Engine and Deep Learning Algorithms Reviewed International journal

Mangkhaseum S., Bhattarai Y., Duwal S., Hanazawa A.

2024 5th International Conference on Big Data Analytics and Practices, IBDAP 2024 38 - 43 2024.01

VERTECS: A COTS-based payload interface board to enable next generation astronomical imaging payloads Reviewed International journal

Fielding E., Schulz V.H., Chatar K.A.A., Sano K., Hanazawa A.

Proceedings of SPIE - The International Society for Optical Engineering 13101 2024.01

Leveraging Deep Learning Algorithms and Open-Source Spatial Datasets for Analysis of Flood and its relationship with land cover change, population growth in the Nam Ngum River Basin (NNRB), Lao PDR Reviewed

Mangkhaseum S., Hanazawa A.

Proceedings of the International Astronautical Congress, IAC 438 - 450 2024.01

Image compression method using convolutional autoencoder with low computational resources

MORIKAWA Yasuhito, HANAZAWA Akitoshi

Proceedings of the Annual Conference of JSAI ( The Japanese Society for Artificial Intelligence ) JSAI2023 ( 0 ) 3T5GS702 - 3T5GS702 2023.01

Authorship：Last author,　Corresponding author Language：Japanese Publishing type：Research paper (bulletin of university, research institution)

In recent years, nano-satellites such as CubeSat have been developed by various organizations. Since nano-satellites have limited communication capacity and computational resources, image compression must be performed with reduced computational resources for transmission and reception of captured satellite images. In this study, the designs of computationally resource-efficient convolutional autoencoder that can be installed in a nano-satellite is a compared in terms of recovery accuracy by using different downsampling methods. Three models were evaluated by SSIM and PSNR for images after compression: a model with pooling layers, a model using convolutional layers with wide stride widths instead of pooling layers, and a model using only convolutional layers with wide stride widths. The results showed that using convolutional layers with wide stride widths instead of pooling layers improved the restoration accuracy and better preserved the edges of the image.

DOI： 10.11517/pjsai.jsai2023.0_3t5gs702

CiNii Research

Other Link： https://kyutech.repo.nii.ac.jp/records/2001562

Performance Evaluation of Machine Learning Methods for Anomaly Detection in CubeSat Solar Panels Reviewed International journal

Cespedes A.J.J., Pangestu B.H.B., Hanazawa A., Cho M.

Applied Sciences (Switzerland) 12 ( 17 ) 2022.09

Validation of Random Forest Algorithm to Monitor Land Cover Classification and Change Detection using Remote Sensing Data in Google Earth Engine Reviewed International journal

Mangkhaseum S., Hanazawa A.

Proceedings of SPIE - The International Society for Optical Engineering 12177 2022.01

Comparison of Machine Learning Classifiers for Land Cover Changes using Google Earth Engine Reviewed International journal

Mangkhaseum S., Hanazawa A.

Proceedings of the 2021 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2021 2021.01

Human detection using color contrast-based histograms of oriented gradients Reviewed International journal

Matsumura Ryo, Hanazawa Akitoshi

International Journal of Innovative Computing, Information and Control ( ICIC International ) 15 ( 4 ) 1211 - 1222 2019.08

A proposal of a hand-bath method for post-stroke hemiplegic hand improvement Reviewed

Nagai Akemi, Nagahiro Chie, Yamamoto Mayumi, Hanazawa Akitoshi, Natsume Kiyohisa

Structure and Function ( Co-medical Research Society of Structure and Function ) 17 ( 2 ) 86 - 93 2019.01

Language：English Publishing type：Research paper (scientific journal)

Post-stroke hemiplegic hand recovery is extremely difficult. After a stroke, a three-month period of spontaneous recovery was regarded as the time window for hand recovery (hereinafter the phenomenon is called plateau), and training of the affected hand was discontinued after the plateau.In such circumstances, the WHO acknowledged the effectiveness of acupuncture for post-stroke hemiplegia, and the WHO Standard (“Standard Acupuncture Point Locations”) was released.In nursing, hand-baths have been provided as a method of hygiene care throughout the ages.The aim of this study was to develop a new hand-bath method for post-stroke hemiplegic hand improvement, using the “WHO Standard”. We incorporated acupressure washing, using twelve acupoints from elbow to fingertips, along with stretching reported to be effective for contracture improvement.The participants were three chronic stroke patients with hemiplegic hand, and the hand-bath was conducted for 6 consecutive days for each patient. As a result, the grip motion of two patients improved, and their systolic and diastolic blood pressures after the hand-bath significantly decreased. The third patient did not show any improvement after the hand-baths.Results suggest our hand-bath is effective in improving post-stroke hemiplegic hand function beyond the plateau. Hand-baths are low-cost and easily integrated with other effective therapies. However, our study was small in scale and further trials are required to confirm these results.

DOI： 10.11172/keitaikinou.17.86

CiNii Article

CiNii Research

Other Link： https://ci.nii.ac.jp/naid/130007661091

Strategy of The Visual Processing of The Soccer Players in The Wide Area Field of Vision Range Reviewed

IMAMURA Ritsuko, INUI Masahiro, TOKUSHIMA Satoru, HANAZAWA Toshiaki, SAKAMOTO Mizuki, YAMAMOTO Katsuaki, ISOGAI Hirohisa

Journal of Biomedical Fuzzy Systems Association ( Biomedical Fuzzy Systems Association ) 16 ( 1 ) 105 - 116 2014.01

Language：Japanese Publishing type：Research paper (scientific journal)

The purpose of this study was to examine the distance of fixation point to investigate acquired visual information strategy by soccer players. In addition, the visual stimuli were presented with an effective field of viewing angle of 110° and a physiological field of viewing angle of 180°. The stimulus presentation monitors were set up three meters from the subject in a semicircle. The subject conducted two tasks (manual reaction time and whole body reaction time) in the three visual stimulus conditions (the front side, effective field of viewing angle, and the physiological field of viewing angle). The result of this study indicated there was no significant difference in the distance of fixation point by stimuli conditions. However, in the result of the relationship between the reaction time and the distance of fixation point, a longer fixation point distance indicated a faster reaction time in whole body reaction. In addition, there was a significant correlation between the performance evaluation from coaches and the distance of fixation points under all of the conditions in whole body reaction. Therefore, this study might suggest that a soccer player who has a longer distance of fixation point will be evaluated as a "player who is good at assessing their situation in a game" by coaches.

DOI： 10.24466/jbfsa.16.1_105

Kyutacar

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/110009818168

Smile Measurement for Estimation of Emotional Recovery in Dementia Elders

Hanazawa Akitoshi, Nakamura Katsuki

Proceedings of the Fuzzy System Symposium ( Japan Society for Fuzzy Theory and Intelligent Informatics ) 29 ( 0 ) 79 - 79 2013.01

Authorship：Lead author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

Learning therapy is a kind of non-drug therapy for dementia elders. It ameliorates, stops or slows the progress of dementia symptoms. Its effectiveness is observed not only in the functional recovery of intelligence but also in that of emotion. The recovery of intelligence is quantified by indices measured by tests similar to intelligence tests. On the other hand, the recovery of emotion has been a matter of subjective impression shared by staffs in nursing homes. We, thus, attempted to quantify the recovery of emotion by measuring smile intensity. We recorded movies of elders undergoing the learning therapy across a year, and developed an image analysis program that can measure the smile intensity of elder people.

DOI： 10.14864/fss.29.0_79

Kyutacar

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/130005480482

Occipital gamma-oscillations modulated during eye movement tasks: Simultaneous eye tracking and electrocorticography recording in epileptic patients Reviewed

58 ( 4 ) 1101 - 1109 2011.10

Human detection by boosting-based co-occurrence of HOG and color feature. Reviewed

Matsumura R,Hanazawa A

International Workshop on Advanced Image Technology 2011 2011.01

GPGPU accelerated real-time joint implementation of spatiotemporal energy model and disparity energy model. Reviewed

Akitoshi Hanazawa

International Workshop on Advanced Image Technology 2011 2011.01

　PREV- NEXT 　

<HANAZAWA Akitoshi>

Papers - HANAZAWA Akitoshi