○International Award

Mr.Seong-Ho Kwon
He is a Ph.D. candidate at Gwangju Institute of Science and Technology (GIST), Gwangju, Korea. He received the B.S. degree in automotive engineering from Kookmin University, Seoul, Korea in 2015 and the M.S. degree in mechanical engineering from GIST in 2017. His research interests include distributed control of multi-agent systems, rigidity theories and autonomous navigation.

受賞論文「 Topological Controllability of Undirected Networks of Diffusively-Coupled Agents」
This study presents conditions for establishing topological controllability in undirected networks of diffusively-coupled agents. Specifically, controllability is considered based on the signs of the edges (negative, positive or zero). Our approach differs from well-known structural controllability conditions for linear systems or consensus networks, where controllability conditions are based on edge connectivity (i.e., zero or nonzero edges). Our results first provide a process for merging controllable graphs into a larger controllable graph. Then, based on this process, we provide a graph decomposition process for evaluating the topological controllability of a given network.

He received the B.E. degree in engineering from Hokkaido University, Sapporo, Japan, in 2019. He has been in the Master’s course at Graduate School of Information Science and Technology, Hokkaido University. His research interests include measurement and skill evaluation system for surgery, and Computer Assisted Surgery (CAS).

受賞論文「A Measurement System for Skill Evaluation of Laparoscopic Surgical Procedures」
This paper describes a measurement system for skill evaluation of laparoscopic surgical procedures. Individual marker sets are attached to a grasping forceps, a scissors forceps, a clip applier, and needle holders respectively, and hence the developed system can detect exchanges of surgical instruments. Two marker sets are attached to a forceps, one to the sheath of the forceps and the other to the handle. The opening ratio of the gripper of the forceps is estimated by the relative distance of the two marker sets. A strain gauge is attached to the gripper of a grasping forceps to measure the grasping force during a surgical operation. Lymphadenectomy and renal parenchyma suturing using organs of cadaver pigs were performed in the measurement experiment, and the movements of surgeons were captured by the developed system. A questionnaire survey was also carried out on the operation feeling of forceps for 45 subjects after the measurement experiments and the results are briefly presented in this paper.

○Yong Author's Award

Mr.Akihisa MITO
He received the B. E. and M. E. degrees in electrical engineering from Hiroshima University, Hiroshima, Japan, in 2015 and 2017, respectively. He is currently a Ph.D. candidate at the Hiroshima University. His research interests include biological signal sensors and signal processing.

受賞論文「Unconstrained Monitoring of Pulse Pressure Waves from the Surface of the Subject’s Back」
This paper proposed a novel technique to estimate continuous pulse pressure waves based on aortic pulse wave (APW) that were measured in an unconstrained manner at the back of a user via an APW sensor. The APW signal was denoised and amplified by the physical characteristics of the sensor, and then converted into a pulse pressure wave by signal processing with a nonlinear model that was constructed beforehand using the preprocessed APWs and continuous arterial pressure waves measured from other human subjects. In the paper, the converted pulse pressure waves were compared with continuous arterial pressure waves measured using a commercial sphygmomanometer to evaluate the accuracy of the proposed technique.

○Poster Presentation Award

Mr.Minh Tri NGUYEN
He received B. S. degree in Information Technology from the University of Science, Ho Chi Minh City, Vietnam, in 2016 and M. Sc. Degree in Information Science from the Japan Advanced Institute of Science and Technology, Ishikawa, Japan, in 2019. His research interests include the applications of deep learning in various computer vision problems.

受賞論文「Saliency Map Extraction in Human Crowd RGB Data」
Saliency map in human crowded scene is a prediction of regions which attracts human visual attention. Humans have an ability to analyze the context of visual scene and focus their attention to salient regions in the crowd scene. In this work, we propose a novel convolutional neural network based method for saliency prediction. Unlike classical works on crowd scene using hand-crafted face features, our model extracts deep features using convolutional layers from image classification model and learns the global context using large receptive convolutional layers. Self-attention mechanism is applied to detect the dependency between elements of feature maps. This model overperformed state-of-the-art methods on the saliency in human crowd Eyecrowd dataset.