• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.510-512
• /
• 2023

In order to enhance a model's capability for detecting facial expressions, this research suggests a pipeline that makes use of the GradCAM component. The patching module and the pseudo-labeling module make up the pipeline. The patching component takes the original face image and divides it into four equal parts. These parts are then each input into a 2Dconvolutional layer to produce a feature vector. Each picture segment is assigned a weight token using GradCAM in the pseudo-labeling module, and this token is then merged with the feature vector using principal component analysis. A convolutional neural network based on transfer learning technique is then utilized to extract the deep features. This technique applied on a public dataset MMI and achieved a validation accuracy of 96.06% which is showing the effectiveness of our method.

• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.173-178
• /
• 2018

Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

• Korean Journal of Radiology
• /
• v.24 no.1
• /
• pp.51-61
• /
• 2023

Objective: To develop and test a machine learning model for classifying human papillomavirus (HPV) status of patients with oropharyngeal squamous cell carcinoma (OPSCC) using ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET-derived parameters in derived parameters and an appropriate combination of machine learning methods in patients with OPSCC. Materials and Methods: This retrospective study enrolled 126 patients (118 male; mean age, 60 years) with newly diagnosed, pathologically confirmed OPSCC, that underwent ¹⁸F-FDG PET-computed tomography (CT) between January 2012 and February 2020. Patients were randomly assigned to training and internal validation sets in a 7:3 ratio. An external test set of 19 patients (16 male; mean age, 65.3 years) was recruited sequentially from two other tertiary hospitals. Model 1 used only PET parameters, Model 2 used only clinical features, and Model 3 used both PET and clinical parameters. Multiple feature transforms, feature selection, oversampling, and training models are all investigated. The external test set was used to test the three models that performed best in the internal validation set. The values for area under the receiver operating characteristic curve (AUC) were compared between models. Results: In the external test set, ExtraTrees-based Model 3, which uses two PET-derived parameters and three clinical features, with a combination of MinMaxScaler, mutual information selection, and adaptive synthetic sampling approach, showed the best performance (AUC = 0.78; 95% confidence interval, 0.46-1). Model 3 outperformed Model 1 using PET parameters alone (AUC = 0.48, p = 0.047) and Model 2 using clinical parameters alone (AUC = 0.52, p = 0.142) in predicting HPV status. Conclusion: Using oversampling and mutual information selection, an ExtraTree-based HPV status classifier was developed by combining metabolic parameters derived from ¹⁸F-FDG PET/CT and clinical parameters in OPSCC, which exhibited higher performance than the models using either PET or clinical parameters alone.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.3
• /
• pp.139-146
• /
• 2014

This paper proposes an efficient method for automatically distinguishing various facial expressions. To recognize the emotions from facial expressions, the facial images are obtained by digital cameras, and a number of feature points were extracted. The extracted feature points are then transformed to 49-dimensional feature vectors which are robust to scale and translational variations, and the facial emotions are recognized by statistical pattern classifiers such Naive Bayes, MLP (multi-layer perceptron), and SVM (support vector machine). Based on the experimental results with 5-fold cross validation, SVM was the best among the classifiers, whose performance was obtained by 50.8% for 6 emotion classification, and 78.0% for 3 emotions.

• Journal of Biomedical Engineering Research
• /
• v.44 no.1
• /
• pp.25-32
• /
• 2023

Recognizing the size and location of prostate cancer is critical for prostate cancer diagnosis, treatment, and predicting prognosis. This paper proposes a model to classify the tumor region and normal tissue with cross-sectional visual images of prostatectomy tissue. We used specimen images of 44 prostate cancer patients who received prostatectomy at Gachon University Gil Hospital. A total of 289 prostate slice images consist of 200 slices including tumor region and 89 slices not including tumor region. Images were divided based on the presence or absence of tumor, and a total of 93 features from each slice image were extracted using Radiomics: 18 first order, 24 GLCM, 16 GLRLM, 16 GLSZM, 5 NGTDM, and 14 GLDM. We compared feature selection techniques such as LASSO, ANOVA, SFS, Ridge and RF, LR, SVM classifiers for the model's high performances. We evaluated the model's performance with AUC of the ROC curve. The results showed that the combination of feature selection techniques LASSO, Ridge, and classifier RF could be best with an AUC of 0.99±0.005.

• Korean Journal of Radiology
• /
• v.21 no.12
• /
• pp.1345-1354
• /
• 2020

Objective: To evaluate radiomics analysis in studies on mild cognitive impairment (MCI) and Alzheimer's disease (AD) using a radiomics quality score (RQS) system to establish a roadmap for further improvement in clinical use. Materials and Methods: PubMed MEDLINE and EMBASE were searched using the terms 'cognitive impairment' or 'Alzheimer' or 'dementia' and 'radiomic' or 'texture' or 'radiogenomic' for articles published until March 2020. From 258 articles, 26 relevant original research articles were selected. Two neuroradiologists assessed the quality of the methodology according to the RQS. Adherence rates for the following six key domains were evaluated: image protocol and reproducibility, feature reduction and validation, biologic/clinical utility, performance index, high level of evidence, and open science. Results: The hippocampus was the most frequently analyzed (46.2%) anatomical structure. Of the 26 studies, 16 (61.5%) used an open source database (14 from Alzheimer's Disease Neuroimaging Initiative and 2 from Open Access Series of Imaging Studies). The mean RQS was 3.6 out of 36 (9.9%), and the basic adherence rate was 27.6%. Only one study (3.8%) performed external validation. The adherence rate was relatively high for reporting the imaging protocol (96.2%), multiple segmentation (76.9%), discrimination statistics (69.2%), and open science and data (65.4%) but low for conducting test-retest analysis (7.7%) and biologic correlation (3.8%). None of the studies stated potential clinical utility, conducted a phantom study, performed cut-off analysis or calibration statistics, was a prospective study, or conducted cost-effectiveness analysis, resulting in a low level of evidence. Conclusion: The quality of radiomics reporting in MCI and AD studies is suboptimal. Validation is necessary using external dataset, and improvements need to be made to feature reproducibility, feature selection, clinical utility, model performance index, and pursuits of a higher level of evidence.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.71-78
• /
• 2023

Employee turnover is one of the most important challenges facing modern organizations. It causes job experiences and skills such as distinguished faculty members in universities, rare-specialized doctors, innovative engineers, and senior administrators. HR analytics has enhanced the area of data analytics to an extent that institutions can figure out their employees' characteristics; where inaccuracy leads to incorrect decision making. This paper aims to develop a novel model that can help decision-makers to classify the problem of Employee Turnover. By using feature selection methods: Information Gain and Chi-Square, the most important four features have been extracted from the dataset. These features are over time, job level, salary, and years in the organization. As one of the important results of this research, these features should be planned carefully to keep organizations their employees as valuable assets. The proposed model based on machine learning algorithms. Classification algorithms were used to implement the model such as Decision Tree, SVM, Random Frost, Neuronal Network, and Naive Bayes. The model was trained and tested by using a dataset that consists of 1470 records and 25 features. To develop the research model, many experiments had been conducted to find the best one. Based on implementation results, the Neural Network algorithm is selected as the best one with an Accuracy of 84 percents and AUC (ROC) 74 percents. By validation mechanism, the model is acceptable and reliable to help origination decision-makers to manage their employees in a good manner.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.3
• /
• pp.268-273
• /
• 2005

We propose the specialized product-line development methodology for developing the embedded system of an MSDFS (Multi Sensor Data Fusion System : called MSDFS). The product-line methodology provides a simultaneous design between software and hardware, high level reusability. However this is insufficient in requirement analysis stage due to be focused on software architecture, detailed design and code. Thus we apply the business model based on IDEF0 technique to traditional methodology. In this paper, we describe the processes of developing Core-Asset, which are requirement analysis, feature modeling, validation. The proposed model gives the efficient result for eliciting features, and ensures the high level reusability of modules performing on embedded system.

• The Journal of Bigdata
• /
• v.1 no.1
• /
• pp.61-66
• /
• 2016

With big data analysis, companies use the customized marketing strategy based on customer's information. However, because of the concerns about privacy issue and identity theft, people start erasing their personal information or changing the privacy settings on social network site. Facebook, the most used social networking site, has the feature called 'Likes' which can be used as a tool to predict user's demographic profiles, such as sex and age range. To make accurate analysis model for the study, 'Likes' data has been processed by using Gaussian RBF and nFactors for dimensionality reduction. With random Forest and 5-fold cross-validation, the result shows that sex has 75% and age has 97.85% accuracy rate. From this study, we expect to provide an useful guideline for companies and marketers who are suffering to collect customers' data.

• Nuclear Engineering and Technology
• /
• v.55 no.1
• /
• pp.100-108
• /
• 2023

In this study, a neural network model inspired by a one-dimensional convolution U-net is developed to automatically accelerate edge localized mode (ELM) detection from big diagnostic data of fusion devices and increase the detection accuracy regardless of the hyperparameter setting. This model recognizes the input signal patterns and overcomes the problems of existing detection algorithms, such as the prominence algorithm and those of differential methods with high sensitivity for the threshold and signal intensity. To train the model, 10 sets of discharge radiation data from the KSTAR are used and sliced into 11091 inputs of length 12 ms, of which 20% are used for validation. According to the receiver operating characteristic curves, our model shows a positive prediction rate and a true prediction rate of approximately 90% each, which is comparable to the best detection performance afforded by other algorithms using their optimized hyperparameters. The accurate and automatic ELM-burst detection methodology used in our model can be beneficial for determining plasma properties, such as the ELM frequency from big data measured in multiple experiments using machines from the KSTAR device and ITER. Additionally, it is applicable to feature detection in the time-series data of other engineering fields.