• Title/Summary/Keyword: Classification Model

Search Result 4,201, Processing Time 0.031 seconds

Binary classification of bolts with anti-loosening coating using transfer learning-based CNN (전이학습 기반 CNN을 통한 풀림 방지 코팅 볼트 이진 분류에 관한 연구)

  • Noh, Eunsol;Yi, Sarang;Hong, Seokmoo
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.22 no.2
    • /
    • pp.651-658
    • /
    • 2021
  • Because bolts with anti-loosening coatings are used mainly for joining safety-related components in automobiles, accurate automatic screening of these coatings is essential to detect defects efficiently. The performance of the convolutional neural network (CNN) used in a previous study [Identification of bolt coating defects using CNN and Grad-CAM] increased with increasing number of data for the analysis of image patterns and characteristics. On the other hand, obtaining the necessary amount of data for coated bolts is difficult, making training time-consuming. In this paper, resorting to the same VGG16 model as in a previous study, transfer learning was applied to decrease the training time and achieve the same or better accuracy with fewer data. The classifier was trained, considering the number of training data for this study and its similarity with ImageNet data. In conjunction with the fully connected layer, the highest accuracy was achieved (95%). To enhance the performance further, the last convolution layer and the classifier were fine-tuned, which resulted in a 2% increase in accuracy (97%). This shows that the learning time can be reduced by transfer learning and fine-tuning while maintaining a high screening accuracy.

A Development of Road Crack Detection System Using Deep Learning-based Segmentation and Object Detection (딥러닝 기반의 분할과 객체탐지를 활용한 도로균열 탐지시스템 개발)

  • Ha, Jongwoo;Park, Kyongwon;Kim, Minsoo
    • The Journal of Society for e-Business Studies
    • /
    • v.26 no.1
    • /
    • pp.93-106
    • /
    • 2021
  • Many recent studies on deep learning-based road crack detection have shown significantly more improved performances than previous works using algorithm-based conventional approaches. However, many deep learning-based studies are still focused on classifying the types of cracks. The classification of crack types is highly anticipated in that it can improve the crack detection process, which is currently relying on manual intervention. However, it is essential to calculate the severity of the cracks as well as identifying the type of cracks in actual pavement maintenance planning, but studies related to road crack detection have not progressed enough to automated calculation of the severity of cracks. In order to calculate the severity of the crack, the type of crack and the area of the crack in the image must be identified together. This study deals with a method of using Mobilenet-SSD that is deep learning-based object detection techniques to effectively automate the simultaneous detection of crack types and crack areas. To improve the accuracy of object-detection for road cracks, several experiments were conducted to combine the U-Net for automatic segmentation of input image and object-detection model, and the results were summarized. As a result, image masking with U-Net is able to maximize object-detection performance with 0.9315 mAP value. While referring the results of this study, it is expected that the automation of the crack detection functionality on pave management system can be further enhanced.

Development of Permit Vehicle Classification System for Bridge Evaluation in Korea (허가차량 통행에 대한 교량의 안전성 평가를 위한 허가차량 분류 체계 개발)

  • Yu, Sang Seon;Kim, Kyunghyun;Paik, Inyeol;Kim, Ji Hyeon
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.21 no.12
    • /
    • pp.845-856
    • /
    • 2020
  • This study proposes a bridge evaluation system for indivisible permit vehicles such as hydraulic cranes. The permit loads for the bridge evaluation are divided into three categories: routine permit loads, special permit 1 loads, and special permit 2 loads. Routine permit and special permit 1 vehicles are allowed to cross a bridge with normal traffic. For these two permits, the standard lane model in the Korean Highway Bridge Design Code was adopted to consider normal traffic in the same lane. Special permit 2 vehicles are assumed to cross a bridge without other traffic. Structural analyses of two prestressed-beam bridges and two steel box girder bridges were conducted for the proposed permit loads. The rating factors of the four bridges for all permit loads were calculated as sufficiently large values for the moment and shear force so that crossing the bridges can be permitted. A reliability assessment of the bridges was performed to identify the reliability levels for the permit vehicles. It was confirmed that the reliability level of the minimum required strength obtained by the load-resistance factors yields the target reliability index of the design code for the permit vehicles.

LMU Design Optimization for the Float-Over Installation of Floating Offshore Platforms (부유식 해양구조물의 플로트오버 설치용 LMU 최적설계)

  • Kim, Hyun-Seok;Park, Byoungjae;Sung, Hong Gun;Lee, Kangsu
    • Journal of the Computational Structural Engineering Institute of Korea
    • /
    • v.34 no.1
    • /
    • pp.43-50
    • /
    • 2021
  • A Leg Mating Unit (LMU) is a device utilized during the float-over installation of offshore structures that include hyperelastic pads and mating part. The hyperelastic pads absorb the loads, whereas the mating part works as guidance between topside and supporting structures during the mating sequence of float-over installation. In this study, the design optimization of an LMU for the float-over installation of floating-type offshore structures is conducted to enhance the performance and to satisfy the requirements defined by classification society regulations. The initial dimensions of the LMU are referred to the dimensions of those used in fixed-type float-over installation because only the location and the number of LMUs are known. The two-parameter Mooney-Rivlin model is adopted to describe the hyperelastic pads under given material parameters. Geometric variables, such as the thickness, height, and width of members, as well as configuration variables, such as the angle and number of members, are defined as design variables and are parameterized. A sampling-based design sensitivity analysis based on latin hypercube sampling method is performed to filter the important design variables. The design optimization problem is formulated to minimize the total mass of the LMU under maximum von Mises stress and reaction force constraints.

Comparative Analysis by Batch Size when Diagnosing Pneumonia on Chest X-Ray Image using Xception Modeling (Xception 모델링을 이용한 흉부 X선 영상 폐렴(pneumonia) 진단 시 배치 사이즈별 비교 분석)

  • Kim, Ji-Yul;Ye, Soo-Young
    • Journal of the Korean Society of Radiology
    • /
    • v.15 no.4
    • /
    • pp.547-554
    • /
    • 2021
  • In order to quickly and accurately diagnose pneumonia on a chest X-ray image, different batch sizes of 4, 8, 16, and 32 were applied to the same Xception deep learning model, and modeling was performed 3 times, respectively. As a result of the performance evaluation of deep learning modeling, in the case of modeling to which batch size 32 was applied, the results of accuracy, loss function value, mean square error, and learning time per epoch showed the best results. And in the accuracy evaluation of the Test Metric, the modeling applied with batch size 8 showed the best results, and the precision evaluation showed excellent results in all batch sizes. In the recall evaluation, modeling applied with batch size 16 showed the best results, and for F1-score, modeling applied with batch size 16 showed the best results. And the AUC score evaluation was the same for all batch sizes. Based on these results, deep learning modeling with batch size 32 showed high accuracy, stable artificial neural network learning, and excellent speed. It is thought that accurate and rapid lesion detection will be possible if a batch size of 32 is applied in an automatic diagnosis study for feature extraction and classification of pneumonia in chest X-ray images using deep learning in the future.

The Consumption Value of Goods Effect on Purchase Intention of Corporate Brand Products: Study According to The Type of Goods (굿즈의 소비가치가 기업브랜드 제품 구매의도에 미치는 영향: 굿즈의 종류에 따른 연구)

  • Kim, Eun-Young;Lee, Sang-Yun;Chae, Myeong-Sin
    • The Journal of the Convergence on Culture Technology
    • /
    • v.7 no.3
    • /
    • pp.321-334
    • /
    • 2021
  • In this study, in order to analyze the effect of the consumption value of goods on the purchase intention of corporate brand products, the model was tested using SPSS 21.0 and Smart PLS 3.0 by receiving questionnaires from 457 men and women who have purchased goods. After examining the consumption values of goods, such as limited, functional, aesthetic, hedonistic, innovative, and social ego values, and product satisfaction, the effect on purchase intention of corporate brand products was analyzed. All were found to be significant except for innovative value, and product satisfaction had a significant effect on brand attachment and purchase intention of corporate brand products. We have recently redefine goods according to the trend of the times, and put an academic significance on the first classification of goods into four categories: human brand goods, brand goods, tourism goods, and character goods. It was confirmed that there was a partial difference in consumption value and satisfaction according to the type of goods. Through research, it is intended to broaden the understanding of goods and suggest the possibility of effective and useful marketing by suggesting planning and development directions according to the target.

Performance Analysis of Automatic Target Recognition Using Simulated SAR Image (표적 SAR 시뮬레이션 영상을 이용한 식별 성능 분석)

  • Lee, Sumi;Lee, Yun-Kyung;Kim, Sang-Wan
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.3
    • /
    • pp.283-298
    • /
    • 2022
  • As Synthetic Aperture Radar (SAR) image can be acquired regardless of the weather and day or night, it is highly recommended to be used for Automatic Target Recognition (ATR) in the fields of surveillance, reconnaissance, and national security. However, there are some limitations in terms of cost and operation to build various and vast amounts of target images for the SAR-ATR system. Recently, interest in the development of an ATR system based on simulated SAR images using a target model is increasing. Attributed Scattering Center (ASC) matching and template matching mainly used in SAR-ATR are applied to target classification. The method based on ASC matching was developed by World View Vector (WVV) feature reconstruction and Weighted Bipartite Graph Matching (WBGM). The template matching was carried out by calculating the correlation coefficient between two simulated images reconstructed with adjacent points to each other. For the performance analysis of the two proposed methods, the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset was used, which has been recently published by the U.S. Defense Advanced Research Projects Agency (DARPA). We conducted experiments under standard operating conditions, partial target occlusion, and random occlusion. The performance of the ASC matching is generally superior to that of the template matching. Under the standard operating condition, the average recognition rate of the ASC matching is 85.1%, and the rate of the template matching is 74.4%. Also, the ASC matching has less performance variation across 10 targets. The ASC matching performed about 10% higher than the template matching according to the amount of target partial occlusion, and even with 60% random occlusion, the recognition rate was 73.4%.

Development of online drone control management information platform (온라인 드론방제 관리 정보 플랫폼 개발)

  • Lim, Jin-Taek;Lee, Sang-Beom
    • Journal of the Institute of Convergence Signal Processing
    • /
    • v.22 no.4
    • /
    • pp.193-198
    • /
    • 2021
  • Recently, interests in the 4th industry have increased the level of demand for pest control by farmers in the field of rice farming, and the interests and use of agricultural pest control drones. Therefore, the diversification of agricultural control drones that spray high-concentration pesticides and the increase of agricultural exterminators due to the acquisition of national drone certifications are rapidly developing the agricultural sector in the drone industry. In addition, as detailed projects, an effective platform is required to construct large-scale big data due to pesticide management, exterminator management, precise spraying, pest control work volume classification, settlement, soil management, prediction and monitoring of damages by pests, etc. and to process the data. However, studies in South Korea and other countries on development of models and programs to integrate and process the big data such as data analysis algorithms, image analysis algorithms, growth management algorithms, AI algorithms, etc. are insufficient. This paper proposed an online drone pest control management information platform to meet the needs of managers and farmers in the agricultural field and to realize precise AI pest control based on the agricultural drone pest control processor using drones and presented foundation for development of a comprehensive management system through empirical experiments.

Development of A Quantitative Risk Assessment Model by BIM-based Risk Factor Extraction - Focusing on Falling Accidents - (BIM 기반 위험요소 도출을 통한 정량적 위험성 평가 모델 개발 - 떨어짐 사고를 중심으로 -)

  • Go, Huijea;Hyun, Jihun;Lee, Juhee;Ahn, Joseph
    • Korean Journal of Construction Engineering and Management
    • /
    • v.23 no.4
    • /
    • pp.15-25
    • /
    • 2022
  • As the incidence and mortality of serious disasters in the construction industry are the highest, various efforts are being made in Korea to reduce them. Among them, risk assessment is used as data for disaster reduction measures and evaluation of risk factors at the construction stage. However, the existing risk assessment involves the subjectivity of the performer and is vulnerable to the domestic construction site. This study established a DB classification system for risk assessment with the aim of early identification and pre-removal of risks by quantitatively deriving risk factors using BIM in the risk assessment field and presents a methodology for risk assessment using BIM. Through this, prior removal of risks increases the safety of construction workers and reduces additional costs in the field of safety management. In addition, since it can be applied to new construction methods, it improves the understanding of project participants and becomes a tool for communication. This study proposes a framework for deriving quantitative risks based on BIM, and will be used as a base technology in the field of risk assessment using BIM in the future.

Analysis of the Cultural Resources of the Gyeokryeolbi Yeoldo at the End of the West Sea in South Korea (서해 끝 무인도 '격렬비열도'의 문화자원 분석)

  • Kim, Jeong-Seob
    • Journal of Korea Entertainment Industry Association
    • /
    • v.15 no.1
    • /
    • pp.143-152
    • /
    • 2021
  • The extremely isolated uninhabited island at the end of the West Sea in South Korea called "The Gyeokryeolbi Yeoldo" has recently begun to be managed by the government under the influence of public opinion demanding the island to be strictly protected. The island was created 70 million years ago by volcanic activities. So it is older than the birth history of Jeju Island, which is estimated to have been born about a million years ago. This study has focused on providing the basis for imagetelling and storytelling of the Gyeokryeolbi Yeoldo, known for its important value by exploring the cultural resources of the island. For the research, the ethnography including in-depth local interview and on-site investigation have been applied for 3 years from February 2018 to December 2020 in Taean, Chungnam Province, where the island is located. To analyze the cultural resources of this island, the resource classification model has been designed and used, which is modified from Valentine (2001) and Chi-ho Nam (2007). As a result, the "tangible cultural resources (TCR)" including various remains found on the island were mainly symbols of cultural bridge in the history of Korea-China exchange, and the spiritual land of life-saving. Also "intangible cultural resources (ICR)" extracted from the island were focused on the images of life protection, safety, bravery, and romance. Based on this study, the core concept of identity to be applied when refurbishing the island with a prominent cultural placeness( "sense of place") can be proposed as "a cultural ecological island centered on the Circular Yellow Sea that ruminates memories of love."