• International journal of advanced smart convergence
• /
• v.13 no.2
• /
• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.1
• /
• 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
• /
• v.11 no.2
• /
• 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
• /
• v.16 no.18
• /
• 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
• /
• v.20 no.11
• /
• 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.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• 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.

• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.315-328
• /
• 2024

Purpose: The purpose of this paper is to present a service construction plan using multiple complex sensor information to detect abnormal situations in urban life safety that are difficult to identify on CCTV. Method: This study selected service scenarios based on actual testbed data and analyzed service importance for local government control center operators, which are main users. Result: Service scenarios were selected as detection of day and night dynamic object, Detection of sudden temperature changes, and Detection of time-series temperature changes. As a result of AHP analysis, walking and mobility collision risk situation services and fire foreshadowing detection services leading to immediate major disasters were highly evaluated. Conclusion: This study is significant in proposing a plan to build an anomaly detection service that can be used in local governments based on real data. This study is significant in proposing a plan to build an anomaly detection service that can be used by local governments based on testbed data.

• Journal of information and communication convergence engineering
• /
• v.6 no.4
• /
• 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.

• Journal of Convergence for Information Technology
• /
• v.11 no.5
• /
• pp.1-8
• /
• 2021

In this paper, we propose the construction of an IOT that monitors foresters' physical abnormalities in real time, performs emergency measures, and provides alarms for natural disasters or heatstroke such as a nearby forest fire or landslide. Nodes provided to foresters include 6-axis sensors, temperature sensors, GPS, and LoRa, and transmit the measured data to the network server through the gateway using LoRa communication. The network server uses 6-axis sensor data to determine whether or not a forester has any signs of abnormal body, and performs emergency measures by tracking GPS location. After analyzing the temperature data, it provides an alarm when there is a possibility of heat stroke or when a forest fire or landslide occurs in the vicinity. In this paper, it was confirmed that the real-time detection of physical abnormalities of foresters and the establishment of disaster early warning IOT is possible by analyzing the data obtained by constructing a node and a gateway and constructing a network server.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• 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.