• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.585-587
• /
• 2023

Long-tailed datasets have an imbalanced distribution because they consist of a different number of data samples for each class. However, there are problems of the performance degradation in tail-classes and class-accuracy imbalance for all classes. To address these problems, this paper suggests a learning method for training of long-tailed dataset. The proposed method uses and combines two methods; one is a resampling method to generate a uniform mini-batch to prevent the performance degradation in tail-classes, and the other is a reweighting method to address the accuracy imbalance problem. The purpose of our proposed method is to train the learning models to have uniform accuracy for each class in a long-tailed dataset.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 춘계학술발표대회
• /
• pp.689-691
• /
• 2023

불균형 데이터의 분류의 성능을 향상시키기 위한 앙상블 구성 방법에 관하여 연구한다. 앙상블의 성능은 앙상블을 구성한 기계학습 모델 간의 상호 다양성에 큰 영향을 받는다. 기존 방법에서는 앙상블에 속할 모델 간의 상호 다양성을 높이기 위해 Feature Engineering 을 사용하여 다양한 모델을 만들어 사용하였다. 그럼에도 생성된 모델 가운데 유사한 모델들이 존재하며 이는 상호 다양성을 낮추고 앙상블 성능을 저하시키는 문제를 가지고 있다. 불균형 데이터의 경우에는 유사 모델 판별을 위한 기존 다양성 지표가 다수 클래스에 편향된 수치를 산출하기 때문에 적합하지 않다. 본 논문에서는 기존 다양성 지표를 개선하고 가지치기 방안을 결합하여 유사 모델을 판별하고 상호 다양성이 높은 후보 모델들을 앙상블에 포함시키는 방법을 제안한다. 실험 결과로써 제안한 방법으로 구성된 앙상블이 불균형이 심한 데이터의 분류 성능을 향상시킴을 확인하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.605-607
• /
• 2023

Recent research has highlighted the effectiveness of Deep Learning (DL) techniques in automating the detection of lung sound anomalies. However, the available lung sound datasets often suffer from limitations in both size and balance, prompting DL methods to employ data preprocessing such as augmentation and transfer learning techniques. These strategies, while valuable, contribute to the increased complexity of DL models and necessitate substantial training memory. In this study, we proposed a streamlined and lightweight DL method but effectively detects lung sound anomalies from small and imbalanced dataset. The utilization of 1D dilated convolutional neural networks enhances sensitivity to lung sound anomalies by efficiently capturing deep temporal features and small variations. We conducted a comprehensive evaluation of the ICBHI dataset and achieved a notable improvement over state-of-the-art results, increasing the average score of sensitivity and specificity metrics by 2.7%.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.652-655
• /
• 2024

COPD(Chronic Obstructive Pulmonary Disease)는 장기간에 걸쳐 기도가 좁아지는 폐질환으로, 규칙적 운동은 호흡을 용이하게 하고 증상을 개선할 수 있는 주요 자가관리 중재법 중 하나이다. 건강정보 데이터와 인공지능을 사용하여 규직적 운동 이행군과 불이행군을 선별하여 자가관리 취약 집단을 파악하는 것은 질병관리 측면에서 비용효과적인 전략이다. 하지만 많은 양의 데이터를 확보하기 어렵고, 규칙적 운동군과 그렇지 않은 환자의 비율이 상이하기 때문에 인공지능 모델의 전체적인 선별 능력을 향상시키기 어렵다는 한계가 있다. 이러한 한계를 극복하기 위해 본 연구에서는 국민건강영양조사 데이터를 사용하여 머신러닝 모델인 XGBoost와 딥러닝 모델인 MLP에 오버샘플링, 언더샘플링, 가중치 부여 등 불균형 데이터 처리 기법을 적용 후 성능을 비교하여 가장 효과적인 불균형 데이터 처리 기법을 제시한다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.294-297
• /
• 2024

Malware detection has become increasingly critical with the proliferation of end devices. To improve detection rates and efficiency, the research focus in malware detection has shifted towards leveraging machine learning and deep learning approaches. This shift is particularly relevant in the context of the widespread adoption of end devices, including smartphones, Internet of Things devices, and personal computers. Machine learning techniques are employed to train models on extensive datasets and evaluate various features, while deep learning algorithms have been extensively utilized to achieve these objectives. In this research, we introduce TabNet, a novel architecture designed for deep learning with tabular data, specifically tailored for enhancing malware detection techniques. Furthermore, the Synthetic Minority Over-Sampling Technique is utilized in this work to counteract the challenges posed by imbalanced datasets in machine learning. SMOTE efficiently balances class distributions, thereby improving model performance and classification accuracy. Our study demonstrates that SMOTE can effectively neutralize class imbalance bias, resulting in more dependable and precise machine learning models.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.1-12
• /
• 2023

Ensuring the security of Supervisory Control and Data Acquisition (SCADA) and Industrial Control Systems (ICS) is paramount to safeguarding the reliability and safety of critical infrastructure. This paper addresses the significant threat posed by reconnaissance attacks on SCADA/ICS networks and presents an innovative methodology for enhancing their protection. The proposed approach strategically employs imbalance dataset handling techniques, ensemble methods, and feature engineering to enhance the resilience of SCADA/ICS systems. Experimentation and analysis demonstrate the compelling efficacy of our strategy, as evidenced by excellent model performance characterized by good precision, recall, and a commendably low false negative (FN). The practical utility of our approach is underscored through the evaluation of real-world SCADA/ICS datasets, showcasing superior performance compared to existing methods in a comparative analysis. Moreover, the integration of feature augmentation is revealed to significantly enhance detection capabilities. This research contributes to advancing the security posture of SCADA/ICS environments, addressing a critical imperative in the face of evolving cyber threats.

• 센서학회지
• /
• 제33권3호
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• ETRI Journal
• /
• 제46권1호
• /
• pp.118-126
• /
• 2024

In human conversations, listeners often utilize brief backchannels such as "uh-huh" or "yeah." Timely backchannels are crucial to understanding and increasing trust among conversational partners. In human-machine conversation systems, users can engage in natural conversations when a conversational agent generates backchannels like a human listener. We propose a method that simultaneously predicts backchannels and recognizes speech in real time. We use a streaming transformer and adopt multitask learning for concurrent backchannel prediction and speech recognition. The experimental results demonstrate the superior performance of our method compared with previous works while maintaining a similar single-task speech recognition performance. Owing to the extremely imbalanced training data distribution, the single-task backchannel prediction model fails to predict any of the backchannel categories, and the proposed multitask approach substantially enhances the backchannel prediction performance. Notably, in the streaming prediction scenario, the performance of backchannel prediction improves by up to 18.7% compared with existing methods.

• 한국융합학회논문지
• /
• 제12권1호
• /
• pp.49-55
• /
• 2021

최근에는 데이터베이스의 발달로 금융, 보안, 네트워크 등에서 생성된 많은 데이터가 저장 가능하며, 기계학습 기반 분류기를 통해 분석이 이루어지고 있다. 이 때 주로 야기되는 문제는 데이터 불균형으로, 학습 시 다수 범주의 데이터들로 과적합이 되어 분류 정확도가 떨어지는 경우가 발생한다. 이를 해결하기 위해 소수 범주의 데이터 수를 증가시키는 오버샘플링 전략이 주로 사용되며, 데이터 분포에 적합한 기법과 인자들을 다양하게 조절하는 과정이 필요하다. 이러한 과정의 개선을 위해 본 연구에서는 스모트와 생성적 적대 신경망 등 다양한 기법 기반의 오버샘플링 조합과 비율을 유전알고리즘을 통해 탐색하고 최적화 하는 전략을 제안한다. 제안된 전략과 단일 오버샘플링 기법으로 신용카드 사기 탐지 데이터를 샘플링 한 뒤, 각각의 데이터들로 학습한 분류기의 성능을 비교한다. 그 결과 유전알고리즘으로 기법별 비율을 탐색하여 최적화 한 전략의 성능이 기존 전략들 보다 우수했다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권12호
• /
• pp.3218-3241
• /
• 2023

Financial fraud undermines the sustainable development of financial markets. Financial statements can be regarded as the key source of information to obtain the operating conditions of listed companies. Current research focuses more on mining financial digital data instead of looking into text data. However, text data can reveal emotional information, which is an important basis for detecting financial fraud. The audit opinion of the financial statement is especially the fair opinion of a certified public accountant on the quality of enterprise financial reports. Therefore, this research was carried out by using the data features of 4,153 listed companies' financial annual reports and audits of text opinions in the past six years, and the paper puts forward a financial fraud detection model integrating audit opinions. First, the financial data index database and audit opinion text database were built. Second, digitized audit opinions with deep learning Bert model was employed. Finally, both the extracted audit numerical characteristics and the financial numerical indicators were used as the training data of the LightGBM model. What is worth paying attention to is that the imbalanced distribution of sample labels is also one of the focuses of financial fraud research. To solve this problem, data enhancement and Focal Loss feature learning functions were used in data processing and model training respectively. The experimental results show that compared with the conventional financial fraud detection model, the performance of the proposed model is improved greatly, with Area Under the Curve (AUC) and Accuracy reaching 81.42% and 78.15%, respectively.