http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Automatic Detection of Sleep Stages based on Accelerometer Signals from a Wristband
Minsoo Yeo,Yong Seo Koo,Cheolsoo Park 대한전자공학회 2017 IEIE Transactions on Smart Processing & Computing Vol.6 No.1
In this paper, we suggest an automated sleep scoring method using machine learning algorithms on accelerometer data from a wristband device. For an experiment, 36 subjects slept for about eight hours while polysomnography (PSG) data and accelerometer data were simultaneously recorded. After the experiments, the recorded signals from the subjects were preprocessed, and significant features for sleep stages were extracted. The extracted features were classified into each sleep stage using five machine learning algorithms. For validation of our approach, the obtained results were compared with PSG scoring results evaluated by sleep clinicians. Both accuracy and specificity yielded over 90 percent, and sensitivity was between 50 and 80 percent. In order to investigate the relevance between features and PSG scoring results, information gains were calculated. As a result, the features that had the lowest and highest information gain were skewness and band energy, respectively. In conclusion, the sleep stages were classified using the top 10 significant features with high information gain.
Automatic Malware Detection with Machine Learning Algorithms in a Smart Office Environment
Minsoo Yeo,Ilsub Bang,Donghyun Kim,Abbas Ahmad,Hamza Baqa,Jaeseung Song,Cheolsoo Park 대한전자공학회 2018 IEIE Transactions on Smart Processing & Computing Vol.7 No.4
The threat of malware in the Internet of Things (IoT) environment is increasing due to a lack of detectors. This paper proposes a method to predict the intrusion of malware using state-of-the- art machine learning algorithms that can detect malware faster and more accurately, compared with the existing methods (that is, payload, port-based, and statistical methods). A smart office environment was implemented to capture the flow of packet datasets, where malware and normal packets were captured, and 11 features were extracted from them. Four machine learning algorithms (random forest, a support vector machine, AdaBoost, and a Gaussian mixture model-based naïve Bayes classifier) were investigated to implement the automatic malware monitoring system. Random forest and AdaBoost could separate the malware and normal flows perfectly, due to their ensemble structures, which could classify unbalanced and noisy datasets.
Minsoo Son,Hyunsoo Kim,Injoon Yeo,Yoseop Kim,Areum Sohn,Youngsoo Kim 한국생물공학회 2019 Biotechnology and Bioprocess Engineering Vol.24 No.2
Quantifying multiple protein biomarkers in a blood sample at one time has many advantages for diagnosing human diseases. In this study, 34 multiplex assays by multiple reaction monitoring-mass spectrometry (MRM-MS) for serum biomarkers were characterized according to Clinical Proteomic Tumor Analysis Consortium (CPTAC) guidelines. The assays revealed that the median lower limit of quantitation (LLOQ) was 0.37 fmol/μL (16.0 ng/mL) and that the median total coefficient of variation (CV) was 18.2%, 12.2%, and 10.6% in the low-, medium-, and high-quality control (QC) samples. With regard to selectivity, the median mean differences in slope and concentration were 2.1% and 4.3%, respectively. The median values for all CVs and %difference from the nominal concentration for stability were 9.5% and 2.7% in low-QC and 3.8% and 3.1% in medium-QC. The median total CV was 9.8% in the reproducibility. Finally, 17 protein-based biomarker assays were reliable and transferrable for preclinical purposes per CPTAC guidelines.
Multimodal Drowsiness Detection Methods using Machine Learning Algorithms
Youngchul Kim,Minsoo Yeo,Illsoo Sohn,Cheolsoo Park 대한전자공학회 2018 IEIE Transactions on Smart Processing & Computing Vol.7 No.5
Drowsiness is a main threat to drivers, and induces inefficiency in various fields, such as industry and education. In this paper, monitoring drowsiness is investigated in which five healthy volunteers participated in an experiment to elicit drowsiness. The subjects were asked to limit their sleep duration to only two to three hours and restrict caffeine intake during the 24 hours prior to the experiment. In the experiment, a one-channel electrocardiogram (ECG) and a single-channel electroencephalogram (EEG) were simultaneously recorded. The ECG and EEG features were extracted and fed into machine learning, random forest, multilayer perceptron, and support vector machine algorithms. Various feature combinations were utilized to train the algorithms, and random forest yielded the best performance at about 90% accuracy, precision, and recall, with 10-second epochs in the ECG and EEG.
Su Hyun AN,Seong Hee YEO,Minsoo KANG 한국인공지능학회 2021 인공지능연구 (KJAI) Vol.9 No.1
This paper predicted a model that indicates whether to buy a car based on primary health insurance customer data. Currently, automobiles are being used to land transportation and living, and the scope of use and equipment is expanding. This rapid increase in automobiles has caused automobile insurance to emerge as an essential business target for insurance companies. Therefore, if the car insurance sales are predicted and sold using the information of existing health insurance customers, it can generate continuous profits in the insurance company s operating performance. Therefore, this paper aims to analyze existing customer characteristics and implement a predictive model to activate advertisements for customers interested in such auto insurance. The goal of this study is to maximize the profits of insurance companies by devising communication strategies that can optimize business models and profits for customers. This study was conducted through the Microsoft Azure program, and an automobile insurance purchase prediction model was implemented using Health Insurance Cross-sell Prediction data. The program algorithm uses Two-Class Logistic Regression and Two-Class Boosted Decision Tree at the same time to compare two models and predict and compare the results. According to the results of this study, when the Threshold is 0.3, the AUC is 0.837, and the accuracy is 0.833, which has high accuracy. Therefore, the result was that customers with health insurance could induce a positive reaction to auto insurance purchases.