Fumitake Fujii

Prof. Dr. Fumitake Fujii

orcid

Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 October 2019 in Physics in Medicine & Biology
Verified
Journal Article
Closed access
PDF file
KJKai Jiang
Kai Jiang
FFFumitake Fujii
Fumitake Fujii
TSTakehiro Shiinoki
Takehiro Shiinoki
The present note addresses the development of a lung tumor position predictor to be used in dynamic tumor tracking radiotherapy, abbreviated as DTT-RT. As there exists 50–500 ms positioning lag in the control of the multi-leaf collimator (MLC) of commercial medical linear accelerators, prediction of future lung tumor position with sufficiently long prediction horizon is inevitable for the successful implementation of DTT-RT. The present article proposes a lung tumor position predictor, which is classified as a nonlinear autoregressive model with exogenous input (NARX). The proposed predictor was trained using seven lung tumor motion trajectories of patients who underwent respiratory gated radiotherapy at Yamaguchi University Hospital. We considered three different prediction horizons, 600 ms, 800 ms and 1 s, which were sufficiently long to compensate for the possible positioning control lag of the MLC. A patient-specific model corresponding to an intended prediction horizon was obtained by training it using the selected tumor motion trajectory with the specified horizon. Accordingly, we obtained three NARX predictors for a single patient. We calculated two performance metrics: the RMS prediction errors and the rate of coverage of the entire tumor trajectory defined by the number of samples of the measured tumor position which was inside the 4 mm cube centered at the corresponding predicted tumor position. The latter quantifies the feasibility of the predictors to generate future gating cubes in the implementation of DTT-RT. The (mean standard deviation) values of the rates of 600 ms, 800 ms and 1 s prediction horizon calculated using the proposed NARX predictors were %, % and %, respectively.

6 July 2018 in Actuators
Verified
Journal Article
Open access
PDF file
FFFumitake Fujii
Fumitake Fujii
KTKen’ichi Tatebatake
Ken’ichi Tatebatake
KMKohei Morita
Kohei Morita
TSTakehiro Shiinoki
Takehiro Shiinoki
This paper proposes an enhancement of the Bouc–Wen hysteresis model to capture the frequency-dependent hysteretic behavior of a thin bimorph-type piezoelectric actuator which also exhibits odd harmonic oscillation (OHO) at specific input frequencies. The odd harmonic repetitive controller has recently been proposed to compensate for the hysteresis, and attenuates the OHO of the piezoelectric actuator for which the hysteresis nonlinearity is regarded as a disturbance. This paper proposes an alternate treatment of the hysteresis compensation with the attenuation of the OHO observed at some input frequencies. It will be shown that the proposed compensator fully utilizes the mathematical structure of the enhanced Bouc–Wen model proposed in this paper to compensate the hysteresis and to attenuate the OHO. The results of the hysteresis compensation experiment illustrate the excellent performance of the proposed control system, especially at the frequencies where OHO is conspicuous.

8 March 2021 in Processes
Verified
Journal Article
Open access
PDF file
FFFumitake Fujii
Fumitake Fujii
AKAkinori Kaneishi
Akinori Kaneishi
TNTakafumi Nii
Takafumi Nii
RMRyu’ichiro Maenishi
Ryu’ichiro Maenishi
STSoma Tanaka
Soma Tanaka
Proportional–integral–derivative (PID) control remains the primary choice for industrial process control problems. However, owing to the increased complexity and precision requirement of current industrial processes, a conventional PID controller may provide only unsatisfactory performance, or the determination of PID gains may become quite difficult. To address these issues, studies have suggested the use of reinforcement learning in combination with PID control laws. The present study aims to extend this idea to the control of a multiple-input multiple-output (MIMO) process that suffers from both physical coupling between inputs and a long input/output lag. We specifically target a thin film production process as an example of such a MIMO process and propose a self-tuning two-degree-of-freedom PI controller for the film thickness control problem. Theoretically, the self-tuning functionality of the proposed control system is based on the actor-critic reinforcement learning algorithm. We also propose a method to compensate for the input coupling. Numerical simulations are conducted under several likely scenarios to demonstrate the enhanced control performance relative to that of a conventional static gain PI controller.

1 January 2005 in Advanced Robotics
Verified
Journal Article
Closed access
FFFumitake Fujii
Fumitake Fujii
KWKenzo Wada
Kenzo Wada
The electrically powered wheelchair (EPW) is now recognized to be an indispensable tool for people with motor disabilities. However, using EPW in daily life might be a cause of danger because of the poor maneuverability of some commercially available EPW products. In order to ease the manipulating sensitivity and produce a pleasant and secure EPW, a model representing the operator's control ability while using the EPW is necessary when designing an embedded controller. This paper proposes a model which describes the control characteristics of the human operator while she/he is using an EPW. The proposed model is constructed based on, and coincides with, the pilot model which represents the control capability of the human operator while doing her/his accustomed tasks. The model should be called the error model of the EPW, control because it contains two errors to be stabilized for pleasant and secure operation of the EPW. In addition, the proposed model is an enhanced version of the pilot model in the sense that the effects of the environmental changes acting on the pilot are taken into account. Experimental results show the validity of the error model and indicate that an inappropriately designed EPW controller strictly deteriorates the manual control performance. The results obtained will serve as a good basis for the design of the EPW controller.

1 January 2000 in TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C
Verified
Journal Article
Closed access
FFFumitake Fujii
Fumitake Fujii
KWKenzo Wada
Kenzo Wada

18 March 2024 in IEEE Access
Verified
Journal Article
Open access
YYYongxuan Yan
Yongxuan Yan
FFFumitake Fujii
Fumitake Fujii
TSTakehiro Shiinoki
Takehiro Shiinoki
SLShengping Liu
Shengping Liu
Accurately determining tumor regions from stereo fluoroscopic images during radiotherapy is a challenging task. As a result, high-density fiducial markers are implanted around tumors in clinical practice as internal surrogates of the tumor, which leads to associated surgical risks. This study was conducted to achieve lung tumor localization without the use of fiducial markers. We propose training a cascade U-net system to perform color to grayscale conversion, enhancement, bone suppression, and tumor detection to determine the precise tumor region. We generated Digitally Reconstructed Radiographs (DRRs) and tumor labels from 4D planning CT images as training data. An improved maximum projection algorithm and a novel color-to-gray conversion algorithm were proposed to improve the quality of the generated training data. Training a bone suppression model using bone-enhanced and bone-suppressed DRRs enables the bone suppression model to achieve better bone suppression performance. The mean peak signal-to-noise ratios in the test sets of the trained translation and bone suppression models are 39.284 ± 0.034 dB and 37.713 ± 0.724 dB, respectively. The results indicate that our proposed markerless tumor localization method is applicable in seven out of ten cases; in applicable cases, the centroid position error of the tumor detection model is less than 1.13 mm; and the calculated tumor center motion trajectories using the proposed network highly coincide with the motion trajectories of implanted fiducial markers in over 60% of captured groups, providing a promising direction for markerless tumor localization tracking methods.