• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.2111-2112
• /
• 2006

얼굴 영상에서 사람의 눈을 검출하는 것은 얼굴 인식의 전체적인 성능을 좌우하는 매우 중요한 사항이다. 눈 검출은 얼굴 영상의 특징이 변하기 때문에 항상 신뢰할 수 있는 결과를 얻는 것은 어려우며, 또한 실시간 얼굴 인식에 응용되기 위해서는 빠른 연산 시간도 고려되어야 한다. 본 논문에서는 빠르고 정확한 새로운 눈 검출 방법을 제안하다. 첫째, Ada-Boosting 알고리즘을 사용하여 얼굴 영역을 검출한다. 둘째, Intensity valley와 edge 정보를 사용하여 얼굴 영상의 회전(Rotation in plane)을 보상한다. 셋째, Intensity edge정보를 사용하여 두 눈의 수직, 수평라인을 검출한다. 넷째, 일반적인 (generic) 사람 눈의 패턴을 이용하여 고안된 Filter로 두 눈의 위치를 검출한다. 본 논문을 통하여 새로 제안된 알고리즘에 대한 논의와 실험 결과를 통해 새로운 알고리즘이 눈 검출에 적합함을 제시한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.3144-3164
• /
• 2019

Face recognition systems have several potential applications, such as security and biometric access control. Ongoing research is focused to develop a robust face recognition algorithm that can mimic the human vision system. Face pose, non-uniform illuminations, and low-resolution are main factors that influence the performance of face recognition algorithms. This paper proposes a novel method to handle the aforementioned aspects. Proposed face recognition algorithm initially uses 68 points to locate a face in the input image and later partially uses the PCA to extract mean image. Meanwhile, the AdaBoost and the LDA are used to extract face features. In final stage, classic nearest centre classifier is used for face classification. Proposed method outperforms recent state-of-the-art face recognition algorithms by producing high recognition rate and yields much lower error rate for a very challenging situation, such as when only frontal ($0^{\circ}$) face sample is available in gallery and seven poses ($0^{\circ}$, ${\pm}30^{\circ}$, ${\pm}35^{\circ}$, and ${\pm}45^{\circ}$) as a probe on the LFW and the CMU Multi-PIE databases.

• 소성∙가공
• /
• 제32권6호
• /
• pp.329-334
• /
• 2023

The process of heat treatment in cold forging is an essential role in enhancing mechanical properties. However, it relies heavily on the experience and skill of individuals. The aim of this study is to predict hardness using machine learning to optimize production efficiency in cold forging manufacturing. Random Forest (RF), Gradient Boosting Regressor (GBR), Extra Trees (ET), and ADAboosting (ADA) models were utilized. In the result, the RF, GBR, and ET models show the excellent performance. However, it was observed that GBR and ET models leaned significantly towards the influence of temperature, unlike the RF model. We suggest that RF model demonstrates greater reliability in predicting hardness due to its ability to consider various variables that occur during the cold forging process.

• 한국통신학회논문지
• /
• 제37권2A호
• /
• pp.95-104
• /
• 2012

혼합분류기를 이용한 패턴인식은 약한 분류기를 결합하여 강한 분류기를 구성하는 형태이다. 본 논문에서는 고정된 카메라를 통해 입력된 영상을 이용하여 특징을 추출하고 이것들을 이용한 약한 분류기의 결합으로 강한 분류기를 만들어 낸다. 제안하는 시스템 구성은 차영상 기법을 이용해서 이진화된 전경 영상을 얻고 모폴로지 침식연산 수행으로 얻어진 혼잡도 가중치 영상을 이용해 특징을 추출하게 된다. 추출된 특징을 조합하고 혼잡도를 판단하기 위한 모델의 훈련 및 인식을 위한 혼합분류기 알고리즘으로 부스팅 방법을 사용하였다. 혼합 분류기는 약한 분류기의 조합으로 하나의 강한 분류기를 만들어 내는 분류기로서 그림자나 반사 등이 일어나는 환경에서도 잠재적인 특징들을 잘 활용할 수 있다. 제안하는 시스템의 성능실험은 "AVSS 2007"의 도로환경의 차량 영상과 철도환경내의 승강장 영상을 사용하였다. 조명변화가 심한 야외환경과 승강장과 같은 복잡한 환경에서도 시스템의 우수한 성능을 보여주었다.

• 대한건축학회논문집:구조계
• /
• 제35권11호
• /
• pp.155-162
• /
• 2019

The construction industry is the highest safety accident causing industry as 28.55% portion of all industries' accidents in Korea. In particular, falling is the highest accidents type composed of 60.16% among the construction field accidents. Therefore, we analyzed the factors of major disaster affecting the fall accident and then derived feature importances by considering various variables. We used data collected from Korea Occupational Safety & Health Agency (KOSHA) for learning and predicting in the proposed model. We have an effort to predict the degree of occupational fall accidents by using the machine learning model, i.e., Adaboost, short for Adaptive Boosting. Adaboost is a machine learning meta-algorithm which can be used in conjunction with many other types of learning algorithms to improve performance. Decision trees were combined with AdaBoost in this model to predict and classify the degree of occupational fall accidents. HyOperpt was also used to optimize hyperparameters and to combine k-fold cross validation by hierarchy. We extracted and analyzed feature importances and affecting fall disaster by permutation technique. In this study, we verified the degree of fall accidents with predictive accuracy. The machine learning model was also confirmed to be applicable to the safety accident analysis in construction site. In the future, if the safety accident data is accumulated automatically in the network system using IoT(Internet of things) technology in real time in the construction site, it will be possible to analyze the factors and types of accidents according to the site conditions from the real time data.

• 아태비즈니스연구
• /
• 제13권3호
• /
• pp.293-309
• /
• 2022

Purpose - The purpose of this study is to explore the possibility of predicting the degree of smartphone overdependence based on mobile phone usage patterns. Design/methodology/approach - In this study, a survey conducted by Korea Internet and Security Agency(KISA) called "problematic smartphone use survey" was analyzed. The survey consists of 180 questions, and data were collected from 29,712 participants. Based on the data on the smartphone usage pattern obtained through the questionnaire, the smartphone addiction level was predicted using machine learning techniques. k-NN, gradient boosting, XGBoost, CatBoost, AdaBoost and random forest algorithms were employed. Findings - First, while various factors together influence the smartphone overdependence level, the results show that all machine learning techniques perform well to predict the smartphone overdependence level. Especially, we focus on the features which can be obtained from the smartphone log data (without psychological factors). It means that our results can be a basis for diagnostic programs to detect problematic smartphone use. Second, the results show that information on users' age, marriage and smartphone usage patterns can be used as predictors to determine whether users are addicted to smartphones. Other demographic characteristics such as sex or region did not appear to significantly affect smartphone overdependence levels. Research implications or Originality - While there are some studies that predict smartphone overdependence level using machine learning techniques, but the studies only present algorithm performance based on survey data. In this study, based on the information gain measure, questions that have more influence on the smartphone overdependence level are presented, and the performance of algorithms according to the questions is compared. Through the results of this study, it is shown that smartphone overdependence level can be predicted with less information if questions about smartphone use are given appropriately.

• 대한안전경영과학회지
• /
• 제26권2호
• /
• pp.23-31
• /
• 2024

In the military, ammunition and explosives stored and managed can cause serious damage if mishandled, thus securing safety through the utilization of ammunition reliability data is necessary. In this study, exploratory data analysis of ammunition inspection records data is conducted to extract reliability information of stored ammunition and to predict the ammunition condition code, which represents the lifespan information of the ammunition. This study consists of three stages: ammunition inspection record data collection and preprocessing, exploratory data analysis, and classification of ammunition condition codes. For the classification of ammunition condition codes, five models based on boosting algorithms are employed (AdaBoost, GBM, XGBoost, LightGBM, CatBoost). The most superior model is selected based on the performance metrics of the model, including Accuracy, Precision, Recall, and F1-score. The ammunition in this study was primarily produced from the 1980s to the 1990s, with a trend of increased inspection volume in the early stages of production and around 30 years after production. Pre-issue inspections (PII) were predominantly conducted, and there was a tendency for the grade of ammunition condition codes to decrease as the storage period increased. The classification of ammunition condition codes showed that the CatBoost model exhibited the most superior performance, with an Accuracy of 93% and an F1-score of 93%. This study emphasizes the safety and reliability of ammunition and proposes a model for classifying ammunition condition codes by analyzing ammunition inspection record data. This model can serve as a tool to assist ammunition inspectors and is expected to enhance not only the safety of ammunition but also the efficiency of ammunition storage management.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.101-106
• /
• 2023

Chronic illnesses are among the most common serious problems affecting human health. Early diagnosis of chronic diseases can assist to avoid or mitigate their consequences, potentially decreasing mortality rates. Using machine learning algorithms to identify risk factors is an exciting strategy. The issue with existing feature selection approaches is that each method provides a distinct set of properties that affect model correctness, and present methods cannot perform well on huge multidimensional datasets. We would like to introduce a novel model that contains a feature selection approach that selects optimal characteristics from big multidimensional data sets to provide reliable predictions of chronic illnesses without sacrificing data uniqueness.[1] To ensure the success of our proposed model, we employed balanced classes by employing hybrid balanced class sampling methods on the original dataset, as well as methods for data pre-processing and data transformation, to provide credible data for the training model. We ran and assessed our model on datasets with binary and multivalued classifications. We have used multiple datasets (Parkinson, arrythmia, breast cancer, kidney, diabetes). Suitable features are selected by using the Hybrid feature model consists of Lassocv, decision tree, random forest, gradient boosting,Adaboost, stochastic gradient descent and done voting of attributes which are common output from these methods.Accuracy of original dataset before applying framework is recorded and evaluated against reduced data set of attributes accuracy. The results are shown separately to provide comparisons. Based on the result analysis, we can conclude that our proposed model produced the highest accuracy on multi valued class datasets than on binary class attributes.[1]

• 품질경영학회지
• /
• 제52권2호
• /
• pp.185-199
• /
• 2024

Purpose: The improvement of yield and quality in product manufacturing is crucial from the perspective of process management. Controlling key variables within the process is essential for enhancing the quality of the produced items. In this study, we aim to identify key variables influencing product defects and facilitate quality enhancement in CNC machining process using SHAP(SHapley Additive exPlanations) Methods: Firstly, we conduct model training using boosting algorithm-based models such as AdaBoost, GBM, XGBoost, LightGBM, and CatBoost. The CNC machining process data is divided into training data and test data at a ratio 9:1 for model training and test experiments. Subsequently, we select a model with excellent Accuracy and F1-score performance and apply SHAP to extract variables influencing defects in the CNC machining process. Results: By comparing the performances of different models, the selected CatBoost model demonstrated an Accuracy of 97% and an F1-score of 95%. Using Shapley Value, we extract key variables that positively of negatively impact the dependent variable(good/defective product). We identify variables with relatively low importance, suggesting variables that should be prioritized for management. Conclusion: The extraction of key variables using SHAP provides explanatory power distinct from traditional machine learning techniques. This study holds significance in identifying key variables that should be prioritized for management in CNC machining process. It is expected to contribute to enhancing the production quality of the CNC machining process.

• 전자공학회논문지CI
• /
• 제47권3호
• /
• pp.11-21
• /
• 2010

최근 웹페이지의 생성 및 웹이 가진 정보량이 기하급수적으로 늘면서 사용자의 검색 목적을 파악하여 효율을 높이기 위한 다양한 방법이 연구되고 있으며, 태깅 시스템이 하나의 대안으로 떠오르고 있다. 태깅 시스템은 인터넷 사용자로 하여금 태그라고 불리는 메타데이터를 글, 사진, 동영상 등에 부여하도록 함으로써 콘텐츠의 검색 및 브라우징을 편리하게 하는 시스템이다. 이처럼 태그는 해당 페이지의 대표 키워드를 의미하므로 콘텐츠 분류의 기준을 마련할 수 있으나, 사용자에 의해 직접 입력되어야 하는 수고가 필요하고, 또한 무분별한 태깅으로 인해 오히려 분류에 방해가 되는 등의 문제점들이 있다. 본 논문에서는 이러한 태깅의 문제를 해결하기 위한 방법으로 얼굴인식 알고리즘을 활용한 영상콘텐츠 내에서의 다중 얼굴 태깅 자동화 방법을 제시한다. 이를 위해 먼저 여러 얼굴검출 방법 중 Haar-like features와 AdaBoost 알고리즘을 이용하여 빠른 속도와 높은 정확도로 영상콘텐츠 내에서 얼굴 영역을 검출한다. 이후 PCA와 고유얼굴을 이용하여, 검출해 낸 얼굴을 데이터베이스에 미리 저장해 놓은 프로필 사진과 비교, 인식해냄으로써 해당 인물에 대한 정보를 불러와서 자동으로 태깅하는 시스템을 구현하였다. 이러한 새로운 방식의 태깅 기술은 현존하는 사진공유, 쇼핑, 검색 등의 수많은 웹서비스에 적용이 가능하며, 특히 소셜네트워크서비스에서의 사진 관리나 인물검색 등에서 활용할 때 큰 효과를 보일 것으로 기대된다.