• Journal of Biomedical Engineering Research
• /
• v.42 no.6
• /
• pp.287-294
• /
• 2021

Cardiotoxicity assessment of all drugs has been performed according to the ICH guidelines since 2005. Non-clinical evaluation S7B has focused on the hERG assay, which has a low specificity problem. The comprehensive in vitro proarrhythmia assay (CiPA) project was initiated to correct this problem, which presented a model for classifying the Torsade de pointes (TdP)-induced risk of drugs as biomarkers calculated through an in silico ventricular model. In this study, we propose a TdP-induced risk group classifier of artificial neural network (ANN)-based. The model was trained with 12 drugs and tested with 16 drugs. The ANN model was performed according to nine features, seven features, five features as an individual ANN model input, and the model with the highest performance was selected and compared with the classification performance of the qNet input logistic regression model. When the five features model was used, the results were AUC 0.93 in the high-risk group, AUC 0.73 in the intermediate-risk group, and 0.92 in the low-risk group. The model's performance using qNet was lower than the ANN model in the high-risk group by 17.6% and in the low-risk group by 29.5%. This study was able to express performance in the three risk groups, and it is a model that solved the problem of low specificity, which is the problem of hERG assay.

• Journal of Biomedical Engineering Research
• /
• v.42 no.6
• /
• pp.268-276
• /
• 2021

Functional near-infrared spectroscopy-based brain-computer interface (fNIRS-based BCI) has been receiving much attention. However, we are practically constrained to obtain a lot of fNIRS data by inherent hemodynamic delay. For this reason, when employing machine learning techniques, a problem due to the high-dimensional feature vector may be encountered, such as deteriorated classification accuracy. In this study, we employ an elastic net-based feature selection which is one of the embedded methods and demonstrate the utility of which by analyzing the results. Using the fNIRS dataset obtained from 18 participants for classifying brain activation induced by mental arithmetic and idle state, we calculated classification accuracies after performing feature selection while changing the parameter α (weight of lasso vs. ridge regularization). Grand averages of classification accuracy are 80.0 ± 9.4%, 79.3 ± 9.6%, 79.0 ± 9.2%, 79.7 ± 10.1%, 77.6 ± 10.3%, 79.2 ± 8.9%, and 80.0 ± 7.8% for the various values of α = 0.001, 0.005, 0.01, 0.05, 0.1, 0.2, and 0.5, respectively, and are not statistically different from the grand average of classification accuracy estimated with all features (80.1 ± 9.5%). As a result, no difference in classification accuracy is revealed for all considered parameter α values. Especially for α = 0.5, we are able to achieve the statistically same level of classification accuracy with even 16.4% features of the total features. Since elastic net-based feature selection can be easily applied to other cases without complicated initialization and parameter fine-tuning, we can be looking forward to seeing that the elastic-based feature selection can be actively applied to fNIRS data.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.705-710
• /
• 2021

Nowadays, cutting-edge information communication technology is the genuine core technology of the fourth Industrial Revolution and is still making great progress rapidly among various technology fields. The biggest issue in ICT fields is the machine learning based Artificial Intelligence applications using big data in cloud computing environment on the basis of wireless network, and also the technology fields of autonomous control applications such as Autonomous Car or Mobile Robot. Since value of the high-tech ICT technology depends on the surrounded environmental factors and is very flexible, the precise technology valuation method is urgently needed in order to get successful technology transfer, transaction and commercialization. In this research, we analyze the characteristics of the high-tech ICT technology and the main factors in technology transfer or commercialization process, and propose the precise technology valuation method that reflects the characteristics of the ICT technology through phased analysis of the existing technology valuationmodel.

• Journal of Environmental Science International
• /
• v.30 no.12
• /
• pp.1101-1111
• /
• 2021

In this study, among the W-S-R(Wiper-Signal-Rainfall) relationship methods used to produce sensor-based rain information in real time, we sought to produce actual rainfall information by applying machine learning techniques to account for the effects of wiper operation. To this end, we used the gradient descent and threshold map methods for pre-processing the cumulative value of the difference before and after wiper operation by utilizing four sensitive channels for optical sensors which collected rain sensor data produced by five rain conditions in indoor artificial rainfall experiments. These methods produced rainfall information by calculating the average value of the threshold according to the rainfall conditions and channels, creating a threshold map corresponding to the 4 (channel) × 5 (considering rainfall information) grid and applying Optima Rainfall Intensity among the big data processing techniques. To verify these proposed results, the application was evaluated by comparing rainfall observations.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.4
• /
• pp.127-132
• /
• 2022

An anonymous encrypted communication networks that make it difficult to identify the trace of a user's access by passing through several virtual computers and/or networks, such as Tor, provides user and data privacy in the process of Internet communications. However, when it comes to abuse for inappropriate purposes, such as sharing of illegal contents, arms trade, etc. through such anonymous encrypted communication networks, it is difficult to detect and take appropriate countermeasures. In this paper, by extending the website fingerprinting technique that can identify access to a specific site even in anonymous encrypted communication, a method for specifying and classifying service types of websites for not only well-known sites but also unknown sites is proposed. This approach can be used to identify hidden sites that can be used for malicious purposes.

• Smart Media Journal
• /
• v.11 no.5
• /
• pp.63-74
• /
• 2022

Initial public offering (IPO) has a legal framework for investor protection, and because there are various quantitative evaluation factors, objective analysis is possible, and various studies have been conducted. In addition, crowdfunding also has several devices to prevent indiscriminate funding as the legal system for investor protection. On the other hand, the blockchain-based cryptocurrency white paper (ICO), which has recently been in the spotlight, has ambiguous legal means and standards to protect investors and lacks quantitative evaluation methods to evaluate ICOs objectively. Therefore, this study collects online-published ICO white papers to detect fraud in ICOs, performs ICO fraud predictions based on BERT, a text embedding technique, and compares them with existing Random Forest machine learning techniques, and shows the possibility on fraud detection. Finally, this study is expected to contribute to the study of ICO fraud detection based on quantitative methods by presenting the possibility of using a quantitative approach using unstructured data to identify frauds in ICOs.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1462-1468
• /
• 2022

Among the data used for the diagnosis of calf disease, feces play an important role in disease diagnosis. In the image of calf feces, the health status can be known by the shape, color, and texture. For the fecal image that can identify the health status, data of 207 normal calves and 158 calves with diarrhea were pre-processed according to fecal status and used. In this paper, images of fecal variables are detected among the collected calf data and images are trained by applying GLCM-CNN, which combines the properties of CNN and GLCM, on a dataset containing disease symptoms using convolutional network technology. There was a significant difference between CNN's 89.9% accuracy and GLCM-CNN, which showed 91.7% accuracy, and GLCM-CNN showed a high accuracy of 1.8%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1453-1461
• /
• 2022

The accuracy of peripheral object recognition algorithms using 3D data sensors such as LiDAR in autonomous vehicles has been increasing through many studies, but this requires high performance hardware and complex structures. This object recognition algorithm acts as a large load on the main processor of an autonomous vehicle that requires performing and managing many processors while driving. To reduce this load and simultaneously exploit the advantages of 3D sensor data, we propose 2D data-based recognition using the ROI generated by extracting physical properties from 3D sensor data. In the environment where the brightness value was reduced by 50% in the basic image, it showed 5.3% higher accuracy and 28.57% lower performance time than the existing 2D-based model. Instead of having a 2.46 percent lower accuracy than the 3D-based model in the base image, it has a 6.25 percent reduction in performance time.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.494-499
• /
• 2022

It is reported that genome-wide RNA-seq profiles has potential as biomarkers of aging. A number of researches achieved promising prediction performance based on gene expression profiles. We develop an age prediction method based on the transcriptome of human dermal fibroblasts by selecting a proper age interval. The proposed method executes multiple rules in a sequential manner and a rule utilizes a classifier and a regression model to determine whether a given test sample belongs to the target age interval of the rule. If a given test sample satisfies the selection condition of a rule, age is predicted from the associated target age interval. Our method predicts age to a mean absolute error of 5.7 years. Our method outperforms prior best performance of mean absolute error of 7.7 years achieved by an ensemble based prediction method. We observe that it is possible to predict age based on genome-wide RNA-seq profiles but prediction performance is not stable but varying with age.

• Geomechanics and Engineering
• /
• v.30 no.2
• /
• pp.187-199
• /
• 2022

Kriging metamodel, as a flexible machine learning method for approximating deterministic analysis models of an engineering system, has been widely used for efficiently estimating slope reliability in recent years. However, the autocorrelation function (ACF), a key input to Kriging that affects the accuracy of reliability estimation, is usually selected based on empiricism. This paper proposes an adaption of the Kriging method, named as Genetic Algorithm optimized Whittle-Matérn Kriging (GAWMK), for addressing this issue. The non-classical two-parameter Whittle-Matérn (WM) function, which can represent different ACFs in the Matérn family by controlling a smoothness parameter, is adopted in GAWMK to avoid subjectively selecting ACFs. The genetic algorithm is used to optimize the WM model to adaptively select the optimal autocorrelation structure of the GAWMK model. Monte Carlo simulation is then performed based on GAWMK for a subsequent slope reliability analysis. Applications to one explicit analytical example and two slope examples are presented to illustrate and validate the proposed method. It is found that reliability results estimated by the Kriging models using randomly chosen ACFs might be biased. The proposed method performs reasonably well in slope reliability estimation.