• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.195-204
• /
• 2024

In this paper, we investigate the comparative performance of two leading object detection architectures, YOLOv7 and Detection Transformer (DETR), across varying levels of data augmentation using CycleGAN. Our experiments focus on chest scan images within the context of biomedical informatics, specifically targeting the detection of abnormalities. The study reveals that YOLOv7 consistently outperforms DETR across all levels of augmented data, maintaining better performance even with 75% augmented data. Additionally, YOLOv7 demonstrates significantly faster convergence, requiring approximately 30 epochs compared to DETR's 300 epochs. These findings underscore the superiority of YOLOv7 for object detection tasks, especially in scenarios with limited data and when rapid convergence is essential. Our results provide valuable insights for researchers and practitioners in the field of computer vision, highlighting the effectiveness of YOLOv7 and the importance of data augmentation in improving model performance and efficiency.

• 산업경영시스템학회지
• /
• 제47권1호
• /
• pp.9-19
• /
• 2024

Deep learning-based computer vision anomaly detection algorithms are widely utilized in various fields. Especially in the manufacturing industry, the difficulty in collecting abnormal data compared to normal data, and the challenge of defining all potential abnormalities in advance, have led to an increasing demand for unsupervised learning methods that rely on normal data. In this study, we conducted a comparative analysis of deep learning-based unsupervised learning algorithms that define and detect abnormalities that can occur when transparent contact lenses are immersed in liquid solution. We validated and applied the unsupervised learning algorithms used in this study to the existing anomaly detection benchmark dataset, MvTecAD. The existing anomaly detection benchmark dataset primarily consists of solid objects, whereas in our study, we compared unsupervised learning-based algorithms in experiments judging the shape and presence of lenses submerged in liquid. Among the algorithms analyzed, EfficientAD showed an AUROC and F1-score of 0.97 in image-level tests. However, the F1-score decreased to 0.18 in pixel-level tests, making it challenging to determine the locations where abnormalities occurred. Despite this, EfficientAD demonstrated excellent performance in image-level tests classifying normal and abnormal instances, suggesting that with the collection and training of large-scale data in real industrial settings, it is expected to exhibit even better performance.

• Journal of Genetic Medicine
• /
• 제11권2호
• /
• pp.49-55
• /
• 2014

Genetic ultrasonography refers to the evaluation of risk of chromosomal abnormalities via various soft sonographic markers. Although the maternal serum test is the primary screening method for chromosomal abnormalities, genetic ultrasonography is also widely used and can help increase detection rates. To date, many soft markers, including choroid plexus cysts, echogenic intracardiac foci, mild ventriculomegaly, nuchal fold thickening, echogenic bowel, mild pyelectasis, short femur and humerus length, and absent or hypoplastic nasal bone, have been reported. An aberrant right subclavian artery was the most novel soft marker introduced. Because these soft markers involve diverse relative risks of chromosomal abnormalities, it is difficult to apply them to clinical practice. To optimize the efficacy of genetic ultrasonography, it is important to understand the precise relative risks of chromosomal abnormalities innumerous soft markers and integrate these risks with each other and the results of maternal serum screening.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권18호
• /
• pp.8491-8494
• /
• 2016

Purpose: To compare unsatisfactory rates and detection of abnormal cervical cytology between conventional cytology or Papanicolaou smear (CC) and liquid-based cytology (LBC). Materials and Methods: A total of 23,030 cases of cervical cytology performed at King Chulalongkorn Memorial Hospital during 2012-2013 were reviewed. The percentage unsatisfactory and detection rates of abnormal cytology were compared between CC and LBC methods. Results: There was no difference in unsatisfactory rates between CC and LBC methods (0.1% vs. 0.1%, p = 0.84). The detection rate for squamous cell abnormalities was significantly higher with the LBC method (7.7% vs. 11.5%, p < 0.001), but those for overall abnormal glandular epithelium were similar (0.4% vs. 0.6%, p = 0.13). Low grade squamous lesion (ASC-US and LSIL) were more frequently detected by the LBC method (6.1% vs. 9.5%, p < 0.001). However, there was no difference in high gradd squamous lesions (1.1% vs. 1.1%, p = 0.95). When comparing between types of glandular abnormality, there was no significant difference the groups. Conclusions: There was no difference in unsatisfactory rates between the conventional smear and LBC. However, LBC could detect low grade squamous cell abnormalities more than CC, while there were similar rates of detection of high grade squamous cell lesions and glandular cell abnormalities.

• Journal of Mechanical Science and Technology
• /
• 제20권11호
• /
• pp.1873-1880
• /
• 2006

The results of this study suggest the use of a Back Propagation Network (BPN) algorithm for the detection of esophageal erosions or abnormalities - which are the important signs of esophagitis - in the analysis of the color and textural aspects of clinical images obtained by endoscopy. The authors have investigated the optimization of the learning condition by the number of neurons in the hidden layer within the structure of the neural network. By optimizing learning parameters, we learned and have validated esophageal erosion images and/or ulcers functioning as the critical diagnostic criteria for esophagitis and associated abnormalities. Validation was established by using twenty clinical images. The success rates for detection of esophagitis during calibration and during validation were 97.91% and 96.83%, respectively.

• 산업경영시스템학회지
• /
• 제43권1호
• /
• pp.123-131
• /
• 2020

There have been a lot of studies in the past for the method of predicting the failure of a machine, and recently, a lot of researches and applications have been generated to diagnose the physical condition of the machine and the parts and to calculate the remaining life through various methods. Survival models are also used to predict plant failures based on past anomaly cycles. In particular, special machine that reflect the fluid flow and process characteristics of chemical plants are connected to hundreds or thousands of sensors, so there are not many factors that need to be considered, such as process and material data as well as application of derivative variables. In this paper, the data were preprocessed through time series anomaly detection based on unsupervised learning to predict the abnormalities of these special machine. Next, clustering results reflecting clustering-based data characteristics were applied to produce additional variables, and a learning data set was created based on the history of past facility abnormalities. Finally, the prediction methodology based on the supervised learning algorithm was applied, and the model update was confirmed to improve the accuracy of the prediction of facility failure. Through this, it is expected to improve the efficiency of facility operation by flexibly replacing the maintenance time and parts supply and demand by predicting abnormalities of machine and extracting key factors.

• 한국재난정보학회 논문집
• /
• 제20권2호
• /
• pp.315-328
• /
• 2024

연구목적: 본 논문은 CCTV에서 확인하기 어려운 도심 생활안전 이상상황을 감지하기 위해 다종 복합 센서 정보를 활용한 서비스 구축방안을 제시하는데 목적이 있다. 연구방법:본 연구는 실제 테스트베드 데이터를 기반으로 서비스 시나리오를 선정하고, 주요 수요처인 지자체 스마트도시통합운영센터 운영자를 대상으로 서비스 중요도 분석을 수행하였다. 연구결과:서비스 시나리오는 크게 주야간 동적 객체 감지, 급격한 객체의 온도변화 감지, 시계열적 객체의 상대 온도변화 감지 유형으로 도출되었다. AHP 분석 결과, 사람, 차량 등 동적객체로 인한 보행, 모빌리티 충돌 위험상황 서비스와 즉각적인 대형 재난으로 이어지는 화재 전조현상 감지 서비스의 중요도가 높게 나타났다. 결론:본 연구는 테스트베드 실데이터 기반으로 지자체에서 활용 가능한 이상감지 서비스 구축방안을 제시한 의의가 있다. 이를 통해 지자체의 서비스 도입 의사결정을 지원하는 기초자료로 활용될 것으로 판단된다.

• Journal of information and communication convergence engineering
• /
• 제6권4호
• /
• pp.425-429
• /
• 2008

We investigated algorithm to detect and characterize interstitial lung abnormalities seen at chest radiographs. This method includes a process of 4 directional Laplaction-Gaussian filtering, and a process of linear opacity judgment. Two regions of interest (ROIs) were selected in each right lung of patients, and these ROIs were processed by our computer-analyzing system. For quantitative analysis of interstitial opacities, the radiographic index, which is the percentage of opacity areas in a ROI, was obtained and evaluated in the images. From or result, abnormal lungs were well differentiated from normal lungs. In our algorithm, the processing results were not only given as the numeric data named "radiographic index" but also confirmed with radiologists observation on CRT. The approach, by which the interstitial abnormalities themselves are extracted, is good enough because the results can be confirmed by the observations of radiologists. In conclusion, our system is useful for the detection and characterization of interstitial lung abnormalities.

• 융합정보논문지
• /
• 제11권5호
• /
• pp.1-8
• /
• 2021

본 논문에서는 임업인의 신체 이상 징후를 실시간 모니터링하여 응급 조치를 수행함과 동시에 인근의 산불이나 산사태와 같은 자연재해 또는 열사병에 대한 알람을 제공하는 IOT 구축을 제안한다. 임업인에게 제공되는 노드에 6축 센서, 온도 센서, GPS, LoRa를 포함하도록 하고, LoRa 통신을 이용하여 측정된 데이터를 게이트웨이를 통해 네트워크 서버에 송신한다. 네트워크 서버는 6축 센서 데이터로 임업인의 신체 이상 징후 여부를 판단한 후 GPS 위치를 추적하여 응급 조치를 수행한다. 온도 데이터를 분석한 후 열사병 가능성이 있는 경우 또는 인근에서 산불 및 산사태가 발생했을 경우에 알람을 제공한다. 본 논문에서는 노드 및 게이트웨이를 제작하고, 네트워크 서버를 구축하여 얻은 데이터를 분석하여 임업인의 신체 이상 징후 실시간 감지 및 재해조기경보 IOT 구축이 가능함을 확인하였다.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.915-926
• /
• 2020

Outlier detection methods help one to identify unusual instances in data that may correspond to erroneous, exceptional, or surprising events or behaviors. This work studies conditional outlier detection, a special instance of the outlier detection problem, in the context of incorrect data label identification. Unlike conventional (unconditional) outlier detection methods that seek abnormalities across all data attributes, conditional outlier detection assumes data are given in pairs of input (condition) and output (response or label). Accordingly, the goal of conditional outlier detection is to identify incorrect or unusual output assignments considering their input as condition. As a solution to conditional outlier detection, this paper proposes the ratio-based outlier scoring (ROS) approach and its variant. The propose solutions work by adopting conventional outlier scores and are able to apply them to identify conditional outliers in data. Experiments on synthetic and real-world image datasets are conducted to demonstrate the benefits and advantages of the proposed approaches.