https://pubs.kist.re.kr/handle/123456789/75399 Mon, 13 Apr 2026 05:42:31 GMT 2026-04-13T05:42:31Z https://pubs.kist.re.kr/handle/201004/153999 Title: 이벤트 기반 센서의 신호 처리 연구 동향 Authors: Jongwan, Kim; Seijoon, Kim; Seongsik, Park; Sungroh, Yoon Sat, 01 Aug 2020 00:00:00 GMT https://pubs.kist.re.kr/handle/201004/153999 2020-08-01T00:00:00Z https://pubs.kist.re.kr/handle/201004/113859 Title: IMU-based Spectrogram Approach with Deep Convolutional Neural Networks for Gait Classification Authors: Mau Dung Nguyen; Mun, Kyung-Ryoul; Jung, Dawoon; Kim, Jinwook; Park, Mina; Kim, Jeuk; Han, Jooin Abstract: We propose a wearable sensor-based gait classification system. Our approach assumes that multiple IMU sensors attached to various body parts can capture the gait characteristics that are used to predict whether the subject has foot abnormalities or athletic performance. We first transform raw sensor signals into spectrogram images and feed this visual representation to deep CNN models. The IMU data were acquired from 7 sensors attached to the pelvis, thighs, shanks, and feet while 69 people in three groups walked on a 20-m straight path. We investigated classification accuracy according to the number and location of attached sensors to optimize performance. Our experimental results show that only a single IMU sensor data can successfully predict the subject groups even without requiring hand-craft extraction and selection of features. As a result, practical applications could be easily deployed with less energy consumption. We plan to generalize our approach to predicting various health status information of people living in the ambient intelligent environment. Wed, 01 Jan 2020 00:00:00 GMT https://pubs.kist.re.kr/handle/201004/113859 2020-01-01T00:00:00Z https://pubs.kist.re.kr/handle/201004/113858 Title: Trainable Multi-Contrast Windowing for Liver CT Segmentation Authors: Kwon, Jangho; Choi, Kihwan Abstract: This study proposes a trainable multi-contrast windowing method in order to optimally choose contrast windows for deep learning-based CT segmentation. Existing contrast windowing methods use parameters predefined by radiologists or manufacturers. These predefined contrast windows, however, have not been proven to be optimal set for machine learning based approaches. We therefore propose a trainable multi-contrast windowing module which can be easily integrated into deep convolutional neural networks. For performance evaluation, we investigate the effects of the trainable multi-contrast windows by applying the proposed windowing modules to a deep learning based segmentation network measuring liver tumors. The results show significant performance improvement when the windowing parameters are trainable. The proposed method enhances the performance for medical image analyses compared to rule-based windowing methods. Wed, 01 Jan 2020 00:00:00 GMT https://pubs.kist.re.kr/handle/201004/113858 2020-01-01T00:00:00Z https://pubs.kist.re.kr/handle/201004/113857 Title: Accurate estimation of the position and shape of the rolling joint in hyper-redundant manipulators Authors: Kim, J.; Moon, Y.; Kwon, S.-I.; Kim, K. Abstract: Hyper-redundant manipulators driven by cables are used in minimally invasive surgery because of their flexibility and small diameters. In particular, manipulators composed of many rigid links and joints have the advantages of high stiffness and payload. However, these manipulators have difficulty in estimating their positions and shapes using calculations based only on the kinematics model that assumes all joint angles are equal. In this paper, we present a method for estimating the position and shape of the rolling joint in hyper-redundant manipulators by minimizing the joint moments. This allows the determination the equilibrium position of all segments of the rolling joint, and therefore an estimation of its shape. We experimentally determine the position and shape of a prototype of the rolling joint and compare them to a simulation of our method. The maximum error between the simulation and the experimental results is 4.13 mm, which is a 77.22% improvement over the kinematic model that calculates the same joint angle. This verifies that our method accurately estimates the position and shape of the rolling joint. ？ 2020 IEEE. Thu, 01 Oct 2020 00:00:00 GMT https://pubs.kist.re.kr/handle/201004/113857 2020-10-01T00:00:00Z