• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권9호
• /
• pp.375-384
• /
• 2021

딥러닝 기법은 영상 처리 분야에서 높은 성능을 입증 받아 다양한 분야에서 적용되고 있다. 이러한 딥러닝 모델의 검증에 가장 널리 사용되는 방법으로는 홀드아웃 검증 방법, k-겹 교차 검증 방법, 부트스트랩 방법 등이 있다. 이러한 기존의 기법들은 데이터 셋을 분할하는 과정에서 클래스 간의 비율에 대한 균형을 고려하지만, 같은 클래스 내에서도 존재하는 다양한 특징들의 비율은 고려하지 않고 있다. 이러한 특징들을 고려하지 않을 경우, 일부 특징에 편향된 검증 결과를 얻게 될 수 있다. 따라서 본 논문에서는 기존 검증 방법들을 개선하여 영상 분류를 위한 데이터 특징 커버리지 기반의 딥러닝 모델 검증 기법을 제안한다. 제안하는 기법은 딥러닝 모델의 학습과 검증을 위한 훈련 데이터 셋과 평가 데이터 셋이 전체 데이터 셋의 특징을 얼마나 반영하고 있는지 수치로 측정할 수 있는 데이터 특징 커버리지를 제안한다. 이러한 방식은 전체 데이터 셋의 특징을 모두 포함하도록 커버리지를 보장하여 데이터 셋을 분할할 수 있고, 모델의 평가 결과를 생성한 특징 군집 단위로 분석할 수 있다. 검증결과, 훈련 데이터 셋의 데이터 특징 커버리지가 낮아질 경우, 모델이 특정 특징에 편향되게 학습하여 모델의 성능이 낮아지며, Fashion-MNIST의 경우 정확도가 8.9%까지 차이나는 것을 확인하였다.

• 정보보호학회논문지
• /
• 제30권3호
• /
• pp.357-367
• /
• 2020

2018년 시만텍 보고서에 따르면, 모바일 환경에서 변종 악성 앱은 전년도 대비 54% 증가하였고, 매일 24,000개의 악성 앱이 차단되고 있다. 최근 연구에서는 기존 악성 앱 분석 기술의 사용 한계를 파악하고, 신·변종 악성 앱을 탐지하기 위하여 기계학습을 통한 악성 앱 탐지 기법이 연구되고 있다. 하지만, 기계학습을 적용하는 경우에도 악성 앱의 특성을 적절하게 선택하여 학습하지 못하면 올바른 결과를 보일 수 없다. 본 연구에서는 신·변종 악성 앱의 특성을 찾아낼 수 있도록 개선된 특성 선택 방법을 적용하여 학습 모델의 정확도를 최고 98%까지 확인할 수 있었다. 향후 연구를 통하여 정밀도, 재현율 등 특정 지표의 향상을 목표로 할 수 있다.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.212-222
• /
• 2021

Multiple waves of COVID-19 highlighted one crucial aspect of this pandemic worldwide that factors affecting the spread of COVID-19 infection are evolving based on various regional and local practices and events. The introduction of vaccines since early 2021 is expected to significantly control and reduce the cases. However, virus mutations and its new variant has challenged these expectations. Several countries, which contained the COVID-19 pandemic successfully in the first wave, failed to repeat the same in the second and third waves. This work focuses on COVID-19 pandemic control and management in Saudi Arabia. This work aims to predict new cases using deep learning using various important factors. The proposed method is called Deep Learning and Dynamic Weighing-based (DLDW) COVID-19 cases prediction method. Special consideration has been given to the evolving factors that are responsible for recent surges in the pandemic. For this purpose, two weights are assigned to data instance which are based on feature importance and dynamic weight-based time. Older data is given fewer weights and vice-versa. Feature selection identifies the factors affecting the rate of new cases evolved over the period. The DLDW method produced 80.39% prediction accuracy, 6.54%, 9.15%, and 7.19% higher than the three other classifiers, Deep learning (DL), Random Forest (RF), and Gradient Boosting Machine (GBM). Further in Saudi Arabia, our study implicitly concluded that lockdowns, vaccination, and self-aware restricted mobility of residents are effective tools in controlling and managing the COVID-19 pandemic.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2188-2203
• /
• 2021

With the rapid development of mobile Internet, smart phones have been widely popularized, among which Android platform dominates. Due to it is open source, malware on the Android platform is rampant. In order to improve the efficiency of malware detection, this paper proposes deep learning Android malicious detection system based on behavior features. First of all, the detection system adopts the static analysis method to extract different types of behavior features from Android applications, and extract sensitive behavior features through Term frequency-inverse Document Frequency algorithm for each extracted behavior feature to construct detection features through unified abstract expression. Secondly, Long Short-Term Memory neural network model is established to select and learn from the extracted attributes and the learned attributes are used to detect Android malicious applications, Analysis and further optimization of the application behavior parameters, so as to build a deep learning Android malicious detection method based on feature analysis. We use different types of features to evaluate our method and compare it with various machine learning-based methods. Study shows that it outperforms most existing machine learning based approaches and detects 95.31% of the malware.

• 인터넷정보학회논문지
• /
• 제22권3호
• /
• pp.9-16
• /
• 2021

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.

• 한국전자통신학회논문지
• /
• 제19권1호
• /
• pp.249-256
• /
• 2024

기계학습 기반의 침입탐지 방법론들은 분류하고자 하는 각 클래스에 대해 균등한 많은 학습 데이터가 필요하며, 탐지 또는 분류하려는 공격유형의 추가 시 시스템을 모두 재학습해야 하는 문제점을 가지고 있다. 본 논문에서는 특징학습과 계층분류 방법을 이용하여, 비교적 적은 학습 데이터를 이용한 분류 문제 및 데이터 불균형 문제를 해결하고, 새로운 공격유형의 추가가 쉬운 침입탐지 방법론을 제안하고자 한다. 제안된 시스템은 KDD 침입탐지 데이터를 이용한 실험으로 가능성을 검증하였다.

• 한국물환경학회지
• /
• 제38권6호
• /
• pp.292-305
• /
• 2022

The Yeongsan River, one of the four largest rivers in South Korea, has been facing difficulties with water quality management with respect to algal bloom. The algal bloom menace has become bigger, especially after the construction of two weirs in the mainstream of the Yeongsan River. Therefore, the prediction and factor analysis of Chlorophyll-a (Chl-a) concentration is needed for effective water quality management. In this study, Chl-a prediction model was developed, and the performance evaluated using machine and deep learning methods, such as Deep Neural Network (DNN), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost). Moreover, the correlation analysis and the feature importance results were compared to identify the major factors affecting the concentration of Chl-a. All models showed high prediction performance with an R² value of 0.9 or higher. In particular, XGBoost showed the highest prediction accuracy of 0.95 in the test data.The results of feature importance suggested that Ammonia (NH₃-N) and Phosphate (PO₄-P) were common major factors for the three models to manage Chl-a concentration. From the results, it was confirmed that three machine learning methods, DNN, RF, and XGBoost are powerful methods for predicting water quality parameters. Also, the comparison between feature importance and correlation analysis would present a more accurate assessment of the important major factors.

• International Journal of Internet, Broadcasting and Communication
• /
• 제10권4호
• /
• pp.50-64
• /
• 2018

This paper describes a visual object detection approach utilizing ensemble based machine learning. Object detection methods employing 1D features have the benefit of fast calculation speed. However, for real image with complex background, detection accuracy and performance are degraded. In this paper, we propose an ensemble learning algorithm that combines a 1D feature classifier and 2D DNF (Disjunctive Normal Form) classifier to improve the object detection performance in a single input image. Also, to improve the computing efficiency and accuracy, we propose a feature selecting method to reduce the computing time and ensemble algorithm by combining the 1D features and 2D DNF features. In the verification experiments, we selected the Haar-like feature as the 1D image descriptor, and demonstrated the performance of the algorithm on a few datasets such as face and vehicle.

• 스마트미디어저널
• /
• 제9권3호
• /
• pp.9-17
• /
• 2020

Hippocampus is a complex brain structure embedded deep into the temporal lobe. Studies have shown that this structure gets affected by neurological and psychiatric disorders and it is a significant landmark for diagnosing neurodegenerative diseases. Hippocampus features play very significant roles in region-of-interest based analysis for disease diagnosis and prognosis. In this study, we have attempted to learn the embeddings of this important biomarker. As conventional metric learning methods for feature embedding is known to lacking in capturing semantic similarity among the data under study, we have trained deep Siamese convolutional neural network for learning metric of the hippocampus. We have exploited Gwangju Alzheimer's and Related Dementia cohort data set in our study. The input to the network was pairs of three-view patches (TVPs) of size 32 × 32 × 3. The positive samples were taken from the vicinity of a specified landmark for the hippocampus and negative samples were taken from random locations of the brain excluding hippocampi regions. We have achieved 98.72% accuracy in verifying hippocampus TVPs.

• 한국산업정보학회:학술대회논문집
• /
• 한국산업정보학회 2003년도 추계공동학술대회
• /
• pp.721-727
• /
• 2003

This study designed and implemented a system to extract of vowel from a word. The system is comprised of a voice feature extraction module and a neutral network module. The voice feature extraction module use a LPC(Linear Prediction Coefficient) model to extract a voice feature from a word. The neutral network module is comprised of a learning module and voice recognition module. The learning module sets up a learning pattern and builds up a neutral network to learn. Using the information of a learned neutral network, a voice recognition module extracts a vowel from a word. A neutral network was made to learn selected vowels(a, eo, o, e, i) to test the performance of a implemented vowel extraction recognition machine. Through this experiment, could confirm that speech recognition module extract of vowel from 4 words.