• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.35-38
• /
• 2009

The paper presents an effective method to detect fire in video surveillance and monitoring system. The main contribution of this work is that we successfully use the Hidden Markov Models in the process of detecting the fire with a few preprocessing steps. First, the moving pixels detected from image difference, the color values obtained from the fire flames, and their pixels clustering are applied to obtain the image regions labeled as fire candidates; secondly, utilizing massive training data, including fire videos and non-fire videos, creates the Hidden Markov Models of fire and non-fire, which are used to make the final decision that whether the frame of the real-time video has fire or not in both temporal and spatial analysis. Experimental results demonstrate that it is not only robust but also has a very low false alarm rate, furthermore, on the ground that the HMM training which takes up the most time of our whole procedure is off-line calculated, the real-time detection and alarm can be well implemented when compared with the other existing methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.477-480
• /
• 2022

반도체 성능 향상으로 신호를 전달하는 회로의 단위가 마이크로 미터에서 나노미터로 미세화되어 선폭(linewidth)이 점점 좁아지고 있다. 이러한 변화는 검출해야 할 불량의 크기가 작아지고, 정상 공정상태와 비정상 공정상태의 차이도 상대적으로 감소되어, 공정오차 및 공정조건의 허용범위가 축소되었음을 의미한다. 따라서 검출해야 할 이상징후 탐지가 더욱 어렵게 되어, 높은 정밀도와 해상도를 갖는 검사공정이 요구되고 있다. 이러한 이유로, 미세 공정변화를 파악할 수 있는 신규 검사 및 계측 공정이 추가되어 TAT(Turn-around Time)가 증가하게 되었고, 웨이퍼가 가공되어 완제품까지 도달하는데 필요한 공정시간이 증가하여 제조원가 상승의 원인으로 작용한다. 본 논문에서는 웨이퍼의 검계측 데이터가 아닌, 제조공정 과정에서 발생하는 다양한 센서 및 장비 데이터를 기반으로 웨이퍼 제조 결과가 양품인지 그렇지 않으면 불량인지 구별할 수 있는 가상계측 모델을 제안한다. 기계학습의 여러 알고리즘 중에서 다양한 장점을 갖는 XGBoost 알고리즘을 이용하여 예측모델을 구축하였고, 데이터 전처리(data-preprocessing), 주요변수 추출(feature selection), 모델 구축(model design), 모델 평가(model evaluation)의 순서로 연구를 수행하였다. 결과적으로 약 94% 이상의 정확성을 갖는 모형을 구축하는데 성공하였으나 더욱 높은 정확성을 확보하기 위해서는 반도체 공정과 관련된 Domain Knowledge 를 반영한 모델구축과 같은 추가적인 연구가 필요하다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.484-487
• /
• 2022

This study suggests an XAI-based machine learning method to predict the productivity of tight oil reservoirs according to the production period. The XAI algorithm refers to interpretable artificial intelligence and provides the basis for the predicted result and the validity of the derivation process. In this study, we proposed a supervised learning model that predicts productivity in the early and late stages of production after performing data preprocessing based on field data. and then based on the model results, the factors affecting the productivity prediction model were analyzed using XAI.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.437-440
• /
• 2022

In modern society, the use of the image processing field is increasing rapidly due to the 4th industrial revolution and the development of IoT technology. In particular, edge detection is widely used in various fields as an essential preprocessing process in image processing applications such as image classification and object detection. Conventional methods for detecting an edge include a Sobel edge detection filter, a Roberts edge detection filter, a Prewitt edge detection filter, Laplacian of Gaussian (LoG), and the like. However, existing methods have the disadvantage of showing somewhat insufficient performance of edge detection characteristics in a low-light level environment with low contrast. Therefore, this paper proposes an edge detection algorithm based on contrast analysis to increase edge detection characteristics even in low-light level environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1466-1488
• /
• 2022

Recently, the importance and necessity of artificial intelligence (AI), especially machine learning, has been emphasized. In fact, studies are actively underway to solve complex and challenging problems through the use of AI systems, such as intelligent CCTVs, intelligent AI security systems, and AI surgical robots. Information security that involves analysis and response to security vulnerabilities of software is no exception to this and is recognized as one of the fields wherein significant results are expected when AI is applied. This is because the frequency of malware incidents is gradually increasing, and the available security technologies are limited with regard to the use of software security experts or source code analysis tools. We conducted a study on MalDC, a technique that converts malware into images using machine learning, MalDC showed good performance and was able to analyze and classify different types of malware. MalDC applies a preprocessing step to minimize the noise generated in the image conversion process and employs an image augmentation technique to reinforce the insufficient dataset, thus improving the accuracy of the malware classification. To verify the feasibility of our method, we tested the malware classification technique used by MalDC on a dataset provided by Microsoft and malware data collected by the Korea Internet & Security Agency (KISA). Consequently, an accuracy of 97% was achieved.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.623-625
• /
• 2021

Rubber o-rings are produced by conventional injection molding methods. In this case, products that are not normally molded are determined to be defective. However, if images acquired during image-based reading are read as original, there is a problem of poor accuracy. We have thus learned from convolutional neural networks using adaptive binarization and Convex Hull algorithms by extracting only rubber oring parts from the original images through pre-processing. During the test process, it was confirmed that the defect detection performance of the learning method applied pre-processing was better than the standard suggested.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.121-123
• /
• 2021

Image processing is being used in various forms in important fields of the 4th industrial revolution, such as artificial intelligence, smart factories, and the IoT industry. In particular, in systems that require data processing such as object tracking, medical images, and object recognition, noise removal is used as a preprocessing step, but the existing algorithm has a drawback in that blurring occurs in the filtering process. Therefore, in this paper, we propose a filter algorithm using switching fuzzy weights. The proposed algorithm switches the fuzzy function by dividing the low-frequency region and the high-frequency region by the standard deviation of the filtering mask, and obtains the final output according to the fuzzy weight. The proposed algorithm showed improved results compared to the existing method, and showed excellent characteristics in the region where the high-frequency component is strong.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.4
• /
• pp.23-30
• /
• 2022

In this paper, we propose an algorithm that can accurately segment a fire even when it is surrounded by smoke of a similar color. Existing fire area segmentation algorithms have a problem in that they cannot separate fire and smoke from fire images. In this paper, the fire was successfully separated from the smoke by applying the color compensation method and the fog removal method as a preprocessing process before applying the fire area segmentation algorithm. In fact, it was confirmed that it segments fire more effectively than the existing methods in the image of the fire scene covered with smoke. In addition, we propose a method that can use the proposed fire segmentation algorithm for efficient fire detection in factories and homes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2788-2808
• /
• 2023

Brain tumors are one of the most threatening malignancies for humans. Misdiagnosis of brain tumors can result in false medical intervention, which ultimately reduces a patient's chance of survival. Manual identification and segmentation of brain tumors from Magnetic Resonance Imaging (MRI) scans can be difficult and error-prone because of the great range of tumor tissues that exist in various individuals and the similarity of normal tissues. To overcome this limitation, the Amended Convolutional Neural Network (ACNN) model has been introduced, a unique combination of three techniques that have not been previously explored for brain tumor detection. The three techniques integrated into the ACNN model are image tissue preprocessing using the Kalman Bucy Smoothing Filter to remove noisy pixels from the input, image tissue segmentation using the Isotonic Regressive Image Tissue Segmentation Process, and feature extraction using the Marr Wavelet Transformation. The extracted features are compared with the testing features using a sigmoid activation function in the output layer. The experimental findings show that the suggested model outperforms existing techniques concerning accuracy, precision, sensitivity, dice score, Jaccard index, specificity, Positive Predictive Value, Hausdorff distance, recall, and F1 score. The proposed ACNN model achieved a maximum accuracy of 98.8%, which is higher than other existing models, according to the experimental results.

• Journal of Information Processing Systems
• /
• v.20 no.4
• /
• pp.442-457
• /
• 2024

The issues were studied of an open-source scaling drone imagery platform, called WebODM. It is known that processing drone images has a high demand for resources because of many preprocessing and post-processing steps involved in image loading, orthophoto, georeferencing, texturing, meshing, and other procedures. By default, WebODM allocates one node for processing. We explored methods to expand the platform's capability to handle many processing requests, which should be beneficial to platform designers. Our primary objective was to enhance WebODM's performance to support concurrent users through the use of container technology. We modified the original process to scale the task vertically and horizontally utilizing the Kubernetes cluster. The effectiveness of the scaling approaches enabled handling more concurrent users. The response time per active thread and the number of responses per second were measured. Compared to the original WebODM, our modified version sometimes had a longer response time by 1.9%. Nonetheless, the processing throughput was improved by up to 101% over the original WebODM's with some differences in the drone image processing results. Finally, we discussed the integration with the infrastructure as code to automate the scaling is discussed.