• Smart Structures and Systems
• /
• 제31권5호
• /
• pp.485-500
• /
• 2023

Machine learning-based structural health monitoring (ML-based SHM) methods are researched extensively in the recent decade due to the availability of advanced information and sensing technology. ML methods are well-known for their pattern recognition capability for complex problems. However, the main obstacle of ML-based SHM is that it often requires pre-collected historical data for model training. In most actual scenarios, damage presence can be detected using the unsupervised learning method through anomaly detection, but to further identify the damage types would require prior knowledge or historical events as references. This creates the cold-start problem, especially for new and unobserved structures. Modal-based methods identify damages based on the changes in the structural global properties but often require dense measurements for accurate results. Therefore, a two-stage hybrid modal-machine learning damage detection scheme is proposed. The first stage detects damage presence using Principal Component Analysis-Frequency Response Function (PCA-FRF) in an unsupervised manner, whereas the second stage further identifies the damage. To solve the cold-start problem, mode shape assessment using the first mode is initiated when no trained model is available yet in the second stage. The damage identified by the modal-based method would be stored for future training. This work highlights the performance of the scheme in alleviating the cold-start issue as it transitions through different phases, starting from zero damage sample available. Results showed that single and multiple damages can be identified at an acceptable accuracy level even when training samples are limited.

• 한국ITS학회 논문지
• /
• 제18권3호
• /
• pp.95-105
• /
• 2019

최근 들어 도로 노면 파손의 위치 정보를 수집하기 위한 영상 처리 기술에 대한 연구가 활발히 진행되고 있다. 대표적으로 차량에 탑재가 가능한 스마트폰이나 블랙박스를 통해 영상을 얻고 이를 영상처리 알고리즘을 사용하여 인식하는 기술이 주로 사용된다. GPS 모듈과 연계하여 실제 파손 위치를 파악할 때 가장 중요한 기술은 영상 처리 알고리즘인데, 근래에는 대부분 인공지능을 통한 알고리즘이 연구 주제로 주목받고 있다. 이와 같은 맥락에서 본 연구에서도 영역 기반의 합성곱 방식 계열의 객체인식 (Object Detection) 방법을 사용한 인공지능 영상 처리 알고리즘에 대하여 논의하고자 한다. 도로 노면 파손 객체 인식 성능을 향상시키기 위하여 도로 노면 파손 영상 600여 장과 일반적인 도로 주행 영상 1500여 장으로 학습 데이터베이스를 구성하였다. 또한 배경 객체 인식 방법을 적용한 지도 학습을 수행하여 도로 노면 파손의 오탐을 감소시켰다. 그 결과 동일한 테스트용 데이터베이스를 통해 알고리즘의 인식 성능을 mAP 평균값 기준 9.44%만큼 향상시킨 새로운 방법을 소개하고자 한다.

• 지능정보연구
• /
• 제10권1호
• /
• pp.65-75
• /
• 2004

네트워크로 연결된 환경에서 PIN 번호를 이용해 사용자의 신분을 증명하고 인증하는 방식이 일반적으로 활용되고 있다. 그러나, 아이디나 비밀번호가 해킹을 통해 유출되면 금전적인 피해뿐만 아니라 개인의 사생활까지도 침해받게 된다. 본 논문에서는 아이디나 비밀번호가 유출될 염려가 없는 안전한 인증방식으로 얼굴인식을 채택하였다. 또한, 2-Tier 간의 인증방식이 아닌 점점 분산화 되어 가는 네트워크 시스템을 고려해 3-Tier이상의 분산된 환경에서 원격으로 신분을 증명하고 인증할 수 있는 시스템을 제안하였다. 본 인증시스템의 얼굴인식 알고리즘으로는 최근 분류(Classification)와 특징추출(Feature Extraction)에서 빠른 속도와 정확성을 보이는 SVM(Support Vector Machine)과 PCA를 이용해 얼굴 특징을 분석하고, 분산된 환경에서 인공지능 기법을 활용해 인식속도 및 정확성을 높일 수 있는 분산형 인공지능 얼굴인증 모듈을 구현하였다.

• 한국통신학회논문지
• /
• 제36권11B호
• /
• pp.1339-1345
• /
• 2011

적조란 유해조류 대 번식으로 바다물의 색깔이 변하는 자연현상이다. 적조의 피해가 증가함에 따라서 적조에 대한 많은 연구가 이루어지고 있다. 그러나 자동으로 적조류를 분류하는 연구는 미흡한 실정이다. 적조류는 영상 객체를 일치 할 수 있는 기준 중심 특정이 없기 때문에 인식이 어렵다. 이 때문에 기존이 연구들은 단순히 몇 종류의 적조류 만을 분류에 이용하고 있다. 본 논문은 주성분분석과 영상 객체의 원형율을 이용한 새로운 적조류 인식 방법을 제안한다.

• 대한전자공학회논문지SP
• /
• 제48권5호
• /
• pp.23-29
• /
• 2011

적조에 의한 양식업 및 수산업의 피해가 증가함에 따라서 적조에 대한 많은 연구가 이루어지고 있다. 그러나 자동으로 적조 이미지를 인식하는 국내의 연구는 미흡한 실정이다. 적조 생물은 이미지 객체를 일치 할 수 있는 기준 중심 특징이 없기 때문에 인식이 어렵다. 이 때문에 기존이 연구들은 단순히 몇 종류의 적조 생물만을 이미지 분류에 이용하고 있다. 본 논문은 비음수 행렬 분해의 의미 특징과 이미지 객체의 원형율을 이용한 새로운 적조 이미지 인식 방법을 제안한다.

• Journal of Trauma and Injury
• /
• 제21권1호
• /
• pp.8-14
• /
• 2008

Iatrogenic ureteral injury is a complication that can occur during a variety of pelvic or abdominal surgeries. The most frequent causes are gynecological ones, followed by colon and vascular surgeries. Management of ureteric injury depends on the time of diagnosis and the severity of organ damage. Injuries diagnosed intraoperatively should be treated immediately. Occasionally, intraoperative ureteral injury is overlooked, and symptoms of the late diagnosis of ureteral injury are usually nonspecific; therefore, the diagnosis is delayed for days or weeks postoperatively. Management of injuries diagnosed postoperatively is more complex. There are differing opinions on whether an initial conservative or immediate operative intervention is the best line of action. Delayed repair is suggested on the grounds that it will reduce inflammation and tissue edema. However, many authors are in favor of early repair, perhaps because tissue planes are easier to find before fibrosis becomes too dense. Ureteral injuries occurring at the level of the pelvic brim should be best managed with an end-to-end anastomosis, preferably around a ureteric stent. More distal injuries also should be ideally managed with an end-to-end anastomosis, after excision of the crushed or compromised segments. However, if the remaining distal segment is short, ureteral reimplantation is the procedure of choice. The Boari flap technique for ureteral reimplantation is invaluable in cases with a short proximal segment. Delayed recognition of iatrogenic ureteral injury may be associated with serious complications, so prompt recognition of ureteral injuries is important. Recognition of the injury before closure is the key to easy, successful, and complications-free repair. Increased awareness of the risk for ureteral damage during certain operative maneuvers is vital to prevent injury, and to decrease the incidence of iatrogenic injury. A sound knowledge of abdominal and pelvic anatomy is the best prevention.

• Smart Structures and Systems
• /
• 제21권4호
• /
• pp.421-433
• /
• 2018

Carbon fiber reinforced polymer (CFRP) cable has good mechanical properties and corrosion resistance. However, the anchorage of CFRP cable is a big issue due to the anisotropic property of CFRP material. In this article, a high-efficient bonding anchorage with novel configuration is developed for CFRP cables. The acoustic emission (AE) technique is employed to evaluate the performance of anchorage in the fatigue test and post-fatigue ultimate bearing capacity test. The obtained AE signals are analyzed by using a combination of unsupervised K-means clustering and supervised K-nearest neighbor classification (K-NN) for quantifying the performance of the anchorage and damage evolutions. An AE feature vector (including both frequency and energy characteristics of AE signal) for clustering analysis is proposed and the under-sampling approaches are employed to regress the influence of the imbalanced classes distribution in AE dataset for improving clustering quality. The results indicate that four classes exist in AE dataset, which correspond to the shear deformation of potting compound, matrix cracking, fiber-matrix debonding and fiber fracture in CFRP bars. The AE intensity released by the deformation of potting compound is very slight during the whole loading process and no obvious premature damage observed in CFRP bars aroused by anchorage effect at relative low stress level, indicating the anchorage configuration in this study is reliable.

• Structural Monitoring and Maintenance
• /
• 제1권1호
• /
• pp.111-130
• /
• 2014

The increased use of carbon fiber reinforced polymer (CFRP) in retrofitting reinforced concrete (RC) members has led to the need to develop non-destructive techniques that can monitor and characterize the unique damage mechanisms exhibited by such structural systems. This paper presented the damage characterization results of six CFRP retrofitted RC beam specimens tested in the laboratory and monitored using acoustic emission (AE). The focus of this study was to continuously monitor the change in AE parameters and analyze them both qualitatively and quantitatively, when brittle failure modes such as debonding occur in these beams. Although deterioration of structural integrity was traceable and can be quantified by monitoring the AE data, individual failure mode characteristics could not be identified due to the complexity of the system failure modes. In all, AE was an effective non-destructive monitoring tool that can trace the failure progression in RC beams retrofitted with CFRP. It would be advantageous to isolate signals originating from the CFRP and concrete, leading to a more clear understanding of the progression of the brittle damage mechanism involved in such a structural system. For practical applications, future studies should focus on spectral analysis of AE data from broadband sensors and automated pattern recognition tools to classify and better correlate AE parameters to failure modes observed.

• Smart Structures and Systems
• /
• 제17권2호
• /
• pp.167-194
• /
• 2016

This paper investigates the Synergetics based Damage Detection Method (SDDM) for frame structures by using surface-bonded PZT (Lead Zirconate Titanate) patches. After analyzing the mechanism of pattern recognition from Synergetics, the operating framework with cooperation-competition-update process of SDDM was proposed. First, the dynamic identification equation of structural conditions was established and the adjoint vector (AV) set of original vector (OV) set was obtained by Generalized Inverse Matrix (GIM).Then, the order parameter equation and its evolution process were deduced through the strict mathematics ratiocination. Moreover, in order to complete online structural condition update feature, the iterative update algorithm was presented. Subsequently, the pathway in which SDDM was realized through the modified Synergetic Neural Network (SNN) was introduced and its assessment indices were confirmed. Finally, the experimental platform with a two-story frame structure was set up. The performances of the proposed methodology were tested for damage identifications by loosening various screw nuts group scenarios. The experiments were conducted in different damage degrees, the disturbance environment and the noisy environment, respectively. The results show the feasibility of SDDM using piezoceramic sensors and actuators, and demonstrate a strong ability of anti-disturbance and anti-noise in frame structure applications. This proposed approach can be extended to the similar structures for damage identification.

• 한국조리학회지
• /
• 제6권2호
• /
• pp.315-330
• /
• 2000

The development of foodservice franchise is inevitable in the developmental process of domestic foodservice industry and it has been led by some big enterprises and foreign brands, but foodservice franchise of a new and differential form will be rapidly developed. The success of franchise can be resulted under the recognition that franchiser and franchise are in the common fate as the partner. Franchisee must make its best efforts to enhance the unity and value of brand jointly with franchiser. Therefore. franchisee has to make efforts to maintain the quality of commodity and service, not to damage the value of title and follow the guidance and effort of franchiser it chose. Franchiser must have the recognition that the success of franchisee is the key of that of franchiser and give franchisee a reliability in order that it follows the order of franchiser. It must have the consciousness that it can achieve the success through the increase of sales by franchisee and support franchisee with trust not to have the easygoing way of thinking to derive its income of commission from increasing the number of franchisees.