• 한국컴퓨터정보학회논문지
• /
• 제25권7호
• /
• pp.113-123
• /
• 2020

수면 장애 중 폐쇄성수면무호흡증은 비교적 흔한 질병 중 하나이다. 환자들은 수면다원검사를 통해 해당 질환의 여부를 알아볼 수 있다. 그러나 수면다원검사를 이용한 폐쇄성수면무호흡증 진단에 관한 한, 늘어나는 환자 수, 비싼 검사 비용, 검사 중 불편함, 수용 인원 제한 등 현실적인 문제점들이 지적됐다. 이에 따라, 수면다원검사를 대체할 목적으로 연구자들은 생체 신호를 활용한 기계학습 기반 폐쇄성수면무호흡증 진단 연구들을 활발히 진행해 왔다. 이 시점에서, 우리는 생체 신호 데이터를 기반으로 기계학습 기법을 적용하는 폐쇄성수면무호흡증 진단 연구를 복기한다. 그 결과, 본 논문은 복기 된 연구들에 대한 최신 분류 체계를 제시하고 그 연구들의 종합적인 비교 분석 결과를 제공한다. 또한, 본 논문은 생체 신호를 활용한 연구들의 다양한 한계점을 밝히고 사용된 기계학습 기법의 활용성에 대한 여러 개선점을 제안한다. 끝으로, 본 논문은 생체 신호를 활용한 기계학습 기법 적용과 관련한 향후 연구 주제를 제시한다.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.374-388
• /
• 2022

Cloud computing has been one of the most critical technology in the last few decades. It has been invented for several purposes as an example meeting the user requirements and is to satisfy the needs of the user in simple ways. Since cloud computing has been invented, it had followed the traditional approaches in elasticity, which is the key characteristic of cloud computing. Elasticity is that feature in cloud computing which is seeking to meet the needs of the user's with no interruption at run time. There are traditional approaches to do elasticity which have been conducted for several years and have been done with different modelling of mathematical. Even though mathematical modellings have done a forward step in meeting the user's needs, there is still a lack in the optimisation of elasticity. To optimise the elasticity in the cloud, it could be better to benefit of Machine Learning algorithms to predict upcoming workloads and assign them to the scheduling algorithm which would achieve an excellent provision of the cloud services and would improve the Quality of Service (QoS) and save power consumption. Therefore, this paper aims to investigate the use of machine learning techniques in order to predict the workload of Physical Hosts (PH) on the cloud and their energy consumption. The environment of the cloud will be the school of computing cloud testbed (SoC) which will host the experiments. The experiments will take on real applications with different behaviours, by changing workloads over time. The results of the experiments demonstrate that our machine learning techniques used in scheduling algorithm is able to predict the workload of physical hosts (CPU utilisation) and that would contribute to reducing power consumption by scheduling the upcoming virtual machines to the lowest CPU utilisation in the environment of physical hosts. Additionally, there are a number of tools, which are used and explored in this paper, such as the WEKA tool to train the real data to explore Machine learning algorithms and the Zabbix tool to monitor the power consumption before and after scheduling the virtual machines to physical hosts. Moreover, the methodology of the paper is the agile approach that helps us in achieving our solution and managing our paper effectively.

• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.49-56
• /
• 2023

Machine learning methods diversely applied to the Internet of Things (IoT) field have been successful due to the enhancement of computer processing power. They offer an effective way of detecting malicious intrusions in IoT because of their high-level feature extraction capabilities. In this paper, we proposed a novel feature selection method for malicious intrusion detection in IoT by using an evolutionary technique - Genetic Algorithm (GA) and Machine Learning (ML) algorithms. The proposed model is performing the classification of BoT-IoT dataset to evaluate its quality through the training and testing with classifiers. The data is reduced and several preprocessing steps are applied such as: unnecessary information removal, null value checking, label encoding, standard scaling and data balancing. GA has applied over the preprocessed data, to select the most relevant features and maintain model optimization. The selected features from GA are given to ML classifiers such as Logistic Regression (LR) and Support Vector Machine (SVM) and the results are evaluated using performance evaluation measures including recall, precision and f1-score. Two sets of experiments are conducted, and it is concluded that hyperparameter tuning has a significant consequence on the performance of both ML classifiers. Overall, SVM still remained the best model in both cases and overall results increased.

• Geomechanics and Engineering
• /
• 제30권1호
• /
• pp.75-91
• /
• 2022

This paper aims to show how to use several Machine Learning (ML) methods to estimate the TBM penetration rate systematically (TBM-PR). To this end, 1125 datasets including uniaxial compressive strength (UCS), Brazilian tensile strength (BTS), punch slope index (PSI), distance between the planes of weakness (DPW), orientation of discontinuities (alpha angle-α), rock fracture class (RFC), and actual/measured TBM-PRs were established. To evaluate the ML methods' ability to perform, the 5-fold cross-validation was taken into consideration. Eventually, comparing the ML outcomes and the TBM monitoring data indicated that the ML methods have a very good potential ability in the prediction of TBM-PR. However, the long short-term memory model with a correlation coefficient of 0.9932 and a route mean square error of 2.68E-6 outperformed the remaining six ML algorithms. The backward selection method showed that PSI and RFC were more and less significant parameters on the TBM-PR compared to the others.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권11호
• /
• pp.541-546
• /
• 2021

최근 전 세계적으로 인공지능과 머신러닝을 기반으로 임상정보를 활용한 다양한 고혈압 식별 및 예측 모델이 개발되고 있다. 그러나 고혈압 관련 모델에 대한 대부분의 선행연구는 침습적 및 고가의 분석비용을 통한 변수들이 대부분 사용되었고, 인종과 국가의 특징에 대한 고려가 충분히 제시되지 않았다. 따라서 이 연구의 목적은 일반적인 사회인구 통계학적 변수만을 사용하여 쉽게 이해할 수 있는 한국인 성인 고혈압 예측 모델을 제시하는 것이다. 이 연구에서 사용된 데이터는 질병관리청 국민건강영양조사 (2018년)를 이용하였다. 남성에서, wrapper-based feature subset selection 메소드와 naive Bayes를 이용한 모델이 가장 높은 예측 성능 (ROC = 0.790, kappa = 0.396)을 보였다. 여성의 경우, correlation-based feature subset selection 메소드와 naive Bayes를 사용한 모델이 가장 높은 예측 성능(ROC = 0.850, kappa = 0.495)을 나타내었다. 또한 모든 모델들에서 사회인구 통계학적 변수들만을 이용한 고혈압의 예측 성능이 남성보다 여성에게서 더 높게 나타나는 것을 발견하였다. 본 연구의 결과인 machine learning 기반 고혈압 예측 모델은 한국인에 대한 단순한 사회인구학적 특성만을 사용하였기 때문에 향후 공중 보건 및 역학 분야에서 쉽게 사용될 수 있을 것으로 예상된다.

• 제어로봇시스템학회논문지
• /
• 제21권12호
• /
• pp.1109-1114
• /
• 2015

This paper presents an improved learning-based visual inspection method for auto parts inspection in severe lighting changes. Automobile sunroof frames are produced automatically by robots in most production lines. In the sunroof frame manufacturing process, there is a quality problem with some parts such as volts are missed. Instead of manual sampling inspection using some mechanical jig instruments, a learning-based machine vision system was proposed in the previous research[1]. But, in applying the actual sunroof frame production process, the inspection accuracy of the proposed vision system is much lowered because of severe illumination changes. In order to overcome this capricious environment, some selective feature vectors and cascade classifiers are used for each auto parts. And we are able to improve the inspection accuracy through the re-learning concept for the misclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.

• 정보보호학회논문지
• /
• 제29권2호
• /
• pp.321-330
• /
• 2019

기업에서 내부자에 의한 기업 기밀 유출 방지는 기업의 생존을 위한 필수 과제이다. 내부자에 의한 정보유출 사고를 막기 위해 기업에서는 보안 솔류션을 도입하여 적용하고 있으나 접근 권한이 있는 내부자의 이상행위를 효과적으로 탐지하는 데에는 한계가 있다. 이번 연구에서는 기업의 제품 제조 이력, 품질 정보 등을 담고 있는 제조정보시스템의 작업자 작업화면 접근 로그 데이타를 기계학습 기법의 비지도학습 알고리즘을 활용하여 정상적인 접근 로그와 비정상적인 접근 로그를 효과적으로 군집화하는 방법을 연구하여 이상징후 탐지를 위한 최적화된 속성 선택 모델을 제시하고자 한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권9호
• /
• pp.3258-3273
• /
• 2021

Malware is a severe threat to the computing system and there's a long history of the battle between malware detection and anti-detection. Most traditional detection methods are based on static analysis with signature matching and dynamic analysis methods that are focused on sensitive behaviors. However, the usual detections have only limited effect when meeting the development of malware, so that the manual update for feature sets is essential. Besides, most of these methods match target samples with the usual feature database, which ignored the characteristics of the sample itself. In this paper, we propose a new malware detection method that could combine the features of a single sample and the general features of malware. Firstly, a structure of Directed Cyclic Graph (DCG) is adopted to extract features from samples. Then the sensitivity of each API call is computed with Markov Chain. Afterward, the graph is merged with the chain to get the final features. Finally, the detectors based on machine learning or deep learning are devised for identification. To evaluate the effect and robustness of our approach, several experiments were adopted. The results showed that the proposed method had a good performance in most tests, and the approach also had stability with the development and growth of malware.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권2호
• /
• pp.116-120
• /
• 2008

Clustering is a method for unsupervised learning. General clustering tools have been depended on statistical methods and machine learning algorithms. One of the popular clustering algorithms based on machine learning is the self organizing map(SOM). SOM is a neural networks model for clustering. SOM and extended SOM have been used in diverse classification and clustering fields such as data mining. But, SOM has had a problem determining optimal number of clusters. In this paper, we propose an improvement of SOM using gap statistic and probability distribution. The gap statistic was introduced to estimate the number of clusters in a dataset. We use gap statistic for settling the problem of SOM. Also, in our research, weights of feature nodes are updated by probability distribution. After complete updating according to prior and posterior distributions, the weights of SOM have probability distributions for optima clustering. To verify improved performance of our work, we make experiments compared with other learning algorithms using simulation data sets.

• Journal of Information Processing Systems
• /
• 제15권1호
• /
• pp.91-99
• /
• 2019

An innovative tone modeling framework based on deep neural networks in tone recognition was proposed in this paper. In the framework, both the prosodic features and the articulatory features were firstly extracted as the raw input data. Then, a 5-layer-deep deep belief network was presented to obtain high-level tone features. Finally, support vector machine was trained to recognize tones. The 863-data corpus had been applied in experiments, and the results show that the proposed method helped improve the recognition accuracy significantly for all tone patterns. Meanwhile, the average tone recognition rate reached 83.03%, which is 8.61% higher than that of the original method.