• Journal of the Korea Society of Computer and Information
• /
• v.23 no.9
• /
• pp.81-86
• /
• 2018

Software defect severity is very important in projects with limited historical data or new projects. But general software defect prediction is very difficult to collect the label information of the training set and cross-project defect prediction must have a lot of data. In this paper, an unclassified data set with defect severity is clustered according to the distribution ratio. And defect severity-based prediction model is proposed by way of labeling. Proposed model is applied CLAMI in JM1, PC4 with the least ambiguity of defect severity-based NASA dataset. And it is evaluated the value of ACC compared to original data. In this study experiment result, proposed model is improved JM1 0.15 (15%), PC4 0.12(12%) than existing defect severity-based prediction models.

• Journal of the Korea Institute of Building Construction
• /
• v.10 no.2
• /
• pp.115-123
• /
• 2010

Defects in apartments, which are one of the major residential types in Korea,produce unexpected inconvenience for their owners. If construction companiespaid more careful attention to the management of defect information, manydefects could be prevented. In this context, this study attempted to derive an improved defect information management system. First, research into cases of defects that were caused by weaknesses in the defect information management system were advanced to confirm the necessity of improving the defect information management system, and as the next step, a survey was conducted to identify problems with the current defect information management system, and the requirements of animproved system. In conclusion, an improved defect information management system will contribute to preventing defects in apartments in Korea.

• International conference on construction engineering and project management
• /
• 2013.01a
• /
• pp.7-13
• /
• 2013

Recently, defect management have been considered as one of the major issues for more large-sized and complicated in domestic construction industry. However, the defect management have not been performed systematically because of special manpower, excessive amount of documents, 2D based inspection work, unclear traditional checklists, complicated work process and difficulty in communicating construction information. Therefore, the construction field manager could not performed the quality inspection and defect management work on time as well as the reliability of recorded quality and defect factors was decreased. The primary objective of this study is develop a Construction Defect Management Application CDMA) using a mobile (smartphone). The application can be sharing a huge information and communication technology based on RFID (Radio-Frequency Identification), BIM (Building Information Modeling) which enables field mangers to efficiently gather the information of defection in construction on-site.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.9 no.3
• /
• pp.1-11
• /
• 2010

In the construction industry, IT based information system has been diversely applied to increase productivity. Although IT device such as PDA, RFID, Barcode, wireless network and web camera has been introduced to gather information in construction site, the effect of the IT device is limited, because of bringing about additional works of engineer. In this paper, we proposed a defect management system which is based on handwritten document digitalization framework for introducing applicability of new IT device, digital pen. By the proposed system, we can effectively gather and input defect information to defect management system by using digital pen and paper like conventional way. Applying the data gathering device, digital pen to defect management, it is able to increase productivity by improving work process, building up and utilizing defect information database of good quality.

• Journal of the Society of Disaster Information
• /
• v.9 no.3
• /
• pp.300-314
• /
• 2013

Defects on apartment which is one of the major residential types in Korea have produced unexpected inconveniences to owners of apartments. If construction companies paid more careful attention to defect information management, a lot of flaws could be prevented. In this situation, this study attempted to seek improved defect information DB management system. First, research on defect information DB management system of large construction firms was conducted to confirm necessities of improved system. Following survey showed problems of current defect information DB management system and the need of improvement. The study came up with remedies expected to contribute to preventing faults.

• The KIPS Transactions:PartA
• /
• v.17A no.2
• /
• pp.81-92
• /
• 2010

There has been some research in the equipment defect detection based on vibration information. Most research of them is based on vibration monitoring to determine the equipment defect or not. In this paper, we introduce more accurate system for engine defect detection based on vibration information and we focus on detection of engine defect for boat and system control. First, it uses the duplicated-checking method for vibration information to determine the engine defect or not. If there is a defect happened, we use the method using error part of vibration information basis with error range to determine which kind of error is happened. On the other hand, we use the engine trend analysis and standard of safety engine to implement the vibration information database. Our simulation results show that the probability of engine defect determination is 100% and the probability of engine defect classification and detection is 96%.

• Korean Journal of Construction Engineering and Management
• /
• v.20 no.4
• /
• pp.13-21
• /
• 2019

The purpose of this study is to suggest an Improvement Model of defect information management system. The improvement model adapts methods for the residents to input defect information correctly and share to defect information with construction company. The adapted research method is review for existing defect information management system and suggested for data flow diagram of improvement model. The results of this study are as follows: The basic design of the information input window of the defect information management system for connecting with big data was made. And 5 point scale was applied to evaluate the convenience, simplicity, accuracy, necessity, and usability of the improvement model. It is evaluated that the economic effect caused by using the improvement model is saved by about 151 million KRW compared to the existing method. The Improvement model is used utilize big data in correct defect management and decision making.

• IE interfaces
• /
• v.21 no.2
• /
• pp.151-160
• /
• 2008

Defect size distribution is a probability density function for the defects that occur on wafers or glasses during semiconductor/LCD fabrication. It is one of the most important information to estimate manufacturing yield using well-known statistical estimation methods. The defects are detected by automatic optical inspection (AOI) facilities. However, the data that is provided from AOI is not accurate due to resolution of AOI and its defect detection mechanism. It causes distortion of defect size distribution and results in wrong estimation of the manufacturing yield. In this paper, I suggest a size conversion method and a maximum likelihood estimator to overcome the vague defect size information of AOI. The methods are verified by the Monte Carlo simulation that is constructed as similar as real situation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.20 no.2
• /
• pp.73-83
• /
• 2015

This paper proposes a TFT-LCD defect blob detection algorithm using the sequential defect detection method. First, for every pixel, a defect possibility is determined by the intensity difference and the defect candidates are detected according to the sequential defect detection method. For detected candidate pixels, the defect probability that indicates a potential included in the defect according to the each step. By applying the morphological operation, blobs are comprised of the detected candidates and the defect blobs are detected using the defect possibility of blobs. The validity of the proposed method was demonstrated a simulated image and also then it was tested a real TFT-LCD image. By the experimental results, the proposed method is very effective in TFT-LCD detect detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.245-265
• /
• 2022

In response to problems such as insufficient extraction information, low detection accuracy, and frequent misdetection in the field of Thangka image defects, this paper proposes a YOLOv5 prediction algorithm fused with the attention mechanism. Firstly, the Backbone network is used for feature extraction, and the attention mechanism is fused to represent different features, so that the network can fully extract the texture and semantic features of the defect area. The extracted features are then weighted and fused, so as to reduce the loss of information. Next, the weighted fused features are transferred to the Neck network, the semantic features and texture features of different layers are fused by FPN, and the defect target is located more accurately by PAN. In the detection network, the CIOU loss function is used to replace the GIOU loss function to locate the image defect area quickly and accurately, generate the bounding box, and predict the defect category. The results show that compared with the original network, YOLOv5-SE and YOLOv5-CBAM achieve an improvement of 8.95% and 12.87% in detection accuracy respectively. The improved networks can identify the location and category of defects more accurately, and greatly improve the accuracy of defect detection of Thangka images.