• Journal of Periodontal and Implant Science
• /
• 제26권1호
• /
• pp.161-175
• /
• 1996

There were many reports that elevations in the levels of active and latent collagenase in gingival crevicular fluid(GCF) have been correlated positively with periodontal disease activity. To provide a simple diagnostic approach for testing GCF collagenolytic activity, the detection limit of enzyme activity was compared using radiofibril assay(Sodek et.al.1981) and spectrophotometric collagenolytic assay(Nethery et al. 1986). The detection limits of both assay for standard bacterial enzyme were similar and the radiofibril assay showed a little (1/2) lower detection limit for tad pole collagenase. To evaluate the relationship between periodontal tissue destruction and the collagenolytic activity, GCF was collected, and latent and active enzyme activities were measured by a spectrophotometric collagenolytic assay. Twelve subjects showing progressive lesions were selected according to the presence of immediate tissue destruction, frequent abscess formation, and increasing need for tooth extraction, and the absence of underlying systemic disease and previous antibiotic medication history within 6 months. Comparisons were made between sites with either: 1) inflammation with a previous history of progressive loss of periodontal tissue and bone support(2l progressive sites): 2) previous history of bone loss and periodontal destruction but now clinically stable(12 comparably stable sites); or 3) no loss of periodontal tissue and bone support(11 control sites including 5 gingivitis sites and 6 healthy sites). Active collagenase activity was the highest in the progressive sites and decreased in the order of the gingivitis sites, the stable sites, and the healthy sites. The total enzyme activity was $2{\sim}3$ fold higher in the progressive sites and the gingivitis sites, compared to the stable and the healthy sites. The ratio of active to total collagenolytic activity was twice in the progressive sites. Analysis of active collagenase level(5mU) and the ratio of active to total collagenolytic activity(0.8) as a diagnositic test indicates that these measurements have the sensitivity of 0.81 and 0.86, the specificity of 0.70 and 0.65, and the overall agreement of 0.75 and 0.73, respectively. Thus, this method has significant merits as a diagnostic tool to determine wherher the site is in a state of remission or progression.

• 대한원격탐사학회지
• /
• 제37권5_1호
• /
• pp.1083-1094
• /
• 2021

접근불능지역에 대한 핵활동 모니터링을 위해서는 고해상도 위성영상을 이용하여 핵활동 관련 객체의 변화양상을 분석하는 방법론의 수립이 필요하다. 그러나, 위성영상을 이용한 전통적인 객체탐지 및 변화탐지 기법들은 영상 취득 시 계절, 날씨 등의 영향에 의하여 탐지 결과물들을 다양한 활용분야에 적용하기에 어려움이 있다. 따라서, 본 연구에서는 딥러닝 모델을 이용하여 위성영상에서 관심객체를 탐지하고, 이를 활용하여 다시기 위성영상 내의 객체 변화를 분석하고자 하였다. 이를 위하여, 객체탐지를 위한 공개데이터셋을 이용하여 딥러닝 모델의 선행학습을 수행하고, 관심지역에 대한 학습자료를 직접 제작하여 전이학습에 적용하였다. 다시기·다종 위성영상 내의 객체를 개별적으로 탐지한 후, 이를 활용하여 영상 내 객체의 변화양상을 탐지하였다. 이를 통해 접근불능지역에 대한 핵 활동 관련 모니터링을 위하여 다양한 위성영상에 대한 객체탐지 결과를 직접적으로 변화탐지에 활용할 수 있는 가능성을 확인하였다.

• 대한산업공학회지
• /
• 제40권5호
• /
• pp.492-500
• /
• 2014

Activity monitoring has been widely recognized as important and critical tools in system monitoring for detection of abnormal behavior. In this research, we propose a data-driven activity monitoring method to measure relative sales performance which is not sensitive to special event which frequently occur in marketing area. Moreover, the proposed method can automatically updates the monitoring threshold that accommodates a drastically changing business environment. The results from simulation and practical case study from sales of electronic devices demonstrate the usefulness and applicability of the proposed activity monitoring method.

• 전기학회논문지
• /
• 제57권2호
• /
• pp.286-293
• /
• 2008

The design and implementation of a personal navigation system including activity monitoring function is given in this paper. The system consists of a 3 dimensional MEMS accelerometer, digital compasses and ZigBee communication. An accelerometer and digital compasses are used to compute the position and activity. The obtained position and activity information is transmitted to a fixed beacon via ZigBee. At the same time, activity information is stored in the personal navigation system to a batch analysis program. The step detection algorithm which is robust to attaching location is proposed. Also two digital compass error compensation algorithms are proposed to find more precise headings. The experiments with a real system show that the activities of users and continuous locations less than 1.5m errors are obtained after 80m walking.

• 한국컴퓨터정보학회논문지
• /
• 제24권8호
• /
• pp.95-103
• /
• 2019

According to the Statistics Korea in 2017, the 10 leading causes of death contain a cardiac disorder disease, self-injury. In terms of these diseases, urgent assistance is highly required when people do not move for certain period of time. We propose an unusual event detection algorithm to identify abnormal user behaviors using dust, vision and activity sensors in their houses. Vision sensors can detect personalized activity behaviors within the CCTV range in the house in their lives. The pattern algorithm using the dust sensors classifies user movements or dust-generated daily behaviors in indoor areas. The accelerometer sensor in the smartphone is suitable to identify activity behaviors of the mobile users. We evaluated the proposed pattern algorithms and the fusion method in the scenarios.

• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.109-118
• /
• 2020

최근 다양한 질병 때문에 사람들은 집 안에서 많은 시간을 보내고 있다. 집 안에서 다치거나 질병에 감염되어 타인의 도움이 필요한 1인 가구의 경우 타인에게 도움을 요청하기 어렵다. 본 연구에서는 1인 가구가 집 안에서 부상이나 질병 감염 등 타인의 도움이 필요로 하는 상황인 이상 징후를 탐지하기 위한 알고리즘을 제안한다. 홈 CCTV를 이용한 영상 패턴 탐지 알고리즘과 인공지능 스피커 등을 이용한 음성 패턴 탐지 알고리즘, 스마트폰의 가속도 센서를 이용한 활동 패턴 탐지 알고리즘, 공기청정기 등을 이용한 먼지 패턴 탐지 알고리즘을 제안한다. 하지만, 홈 CCTV의 보안 문제로 사용하기 어려울 경우 음성, 활동, 먼지 패턴 센서를 결합한 융합 방식을 제안한다. 각 알고리즘은 유튜브와 실험을 통해 데이터를 수집하여 정확도를 측정했다.

• 디지털융복합연구
• /
• 제14권11호
• /
• pp.249-255
• /
• 2016

노인 음성은 연령에 따른 호흡, 발성, 공명 등의 생리적 변화에 의하여 다량의 잡음이 발생된다. 따라서 노인 음성으로 음성인식 및 합성, 분석 소프트웨어등과 같은 융복합 헬스케어 기기를 동작시키고자 할 때, 성능을 저하시키는 결과를 야기한다. 그러므로 노인 음성을 분석하여 그들의 목소리로 다양한 헬스케어 기기를 잘 운영할 수 있는 위한 연구 개발이 필요하다. 따라서 본 연구는 노인 음성 잡음을 고려하여 기존의 대칭 구조 고차 미분 에너지 함수를 이용하여 노인 음성에서의 음성 구간 검출 알고리즘을 연구하였으며, 자기상관함수와 AMDF 방법과 비교하여 노인 음성에서의 음성 구간 검출에 보다 우수한 성능을 가지는 것을 확인하였다. 본 논문에서 제시하는 음성 구간 검출 알고리즘은 노인을 위한 음성 인터페이스에 적용함으로써 노인들의 스마트 기기에의 접근성을 높이고, 더 나아가 노인들을 위한 융복합 웨어러블 디바이스 성능 개선 및 다양한 개발이 가능할 것으로 전망한다.

• ETRI Journal
• /
• 제33권1호
• /
• pp.99-109
• /
• 2011

This paper concerns a robust real-time voice activity detection (VAD) approach which is easy to understand and implement. The proposed approach employs several short-term speech/nonspeech discriminating features in a voting paradigm to achieve a reliable performance in different environments. This paper mainly focuses on the performance improvement of a recently proposed approach which uses spectral peak valley difference (SPVD) as a feature for silence detection. The main issue of this paper is to apply a set of features with SPVD to improve the VAD robustness. The proposed approach uses a weighted voting scheme in order to take the discriminative power of the employed feature set into account. The experiments show that the proposed approach is more robust than the baseline approach from different points of view, including channel distortion and threshold selection. The proposed approach is also compared with some other VAD techniques for better confirmation of its achievements. Using the proposed weighted voting approach, the average VAD performance is increased to 89.29% for 5 different noise types and 8 SNR levels. The resulting performance is 13.79% higher than the approach based only on SPVD and even 2.25% higher than the not-weighted voting scheme.

• 정보보호학회지
• /
• 제5권2호
• /
• pp.32-48
• /
• 1995

Our paper describes an Intrusion Detection Parallel System(IDPS) which detects an anomaly activity corresponding to the actions that interaction between near detection events. IDES uses parallel inductive approaches regarding the problem of real-time anomaly behavior detection on rule-based system. This approach uses sequential rule that describes user's behavior and characteristics dependent on time. and that audits user's activities by using rule base as data base to store user's behavior pattern. When user's activity deviates significantly from expected behavior described in rule base. anomaly behaviors are recorded. Observed behavior is flagged as a potential intrusion if it deviates significantly from the expected behavior or if it triggers a rule in the parallel inductive system.

• 한국컴퓨터정보학회논문지
• /
• 제24권3호
• /
• pp.87-93
• /
• 2019

In this paper, we propose a real-time drone-based violent protest detection system. Our proposed system uses drones to detect scenes of violent protest in real-time. The important problem is that the victims and violent actions have to be manually searched in videos when the evidence has been collected. Firstly, we focused to solve the limitations of existing collecting evidence devices by using drone to collect evidence live and upload in AWS(Amazon Web Service)[1]. Secondly, we built a Deep Learning based violence detection model from the videos using Yolov3 Feature Pyramid Network for human activity recognition, in order to detect three types of violent action. The built model classifies people with possession of gun, swinging pipe, and violent activity with the accuracy of 92, 91 and 80.5% respectively. This system is expected to significantly save time and human resource of the existing collecting evidence.