• Korean Journal of Radiology
• /
• v.23 no.11
• /
• pp.1078-1088
• /
• 2022

Objective: To develop and validate a model using radiomics features from apparent diffusion coefficient (ADC) map to diagnose local tumor recurrence in head and neck squamous cell carcinoma (HNSCC). Materials and Methods: This retrospective study included 285 patients (mean age ± standard deviation, 62 ± 12 years; 220 male, 77.2%), including 215 for training (n = 161) and internal validation (n = 54) and 70 others for external validation, with newly developed contrast-enhancing lesions at the primary cancer site on the surveillance MRI following definitive treatment of HNSCC between January 2014 and October 2019. Of the 215 and 70 patients, 127 and 34, respectively, had local tumor recurrence. Radiomics models using radiomics scores were created separately for T2-weighted imaging (T2WI), contrast-enhanced T1-weighted imaging (CE-T1WI), and ADC maps using non-zero coefficients from the least absolute shrinkage and selection operator in the training set. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic performance of each radiomics score and known clinical parameter (age, sex, and clinical stage) in the internal and external validation sets. Results: Five radiomics features from T2WI, six from CE-T1WI, and nine from ADC maps were selected and used to develop the respective radiomics models. The area under ROC curve (AUROC) of ADC radiomics score was 0.76 (95% confidence interval [CI], 0.62-0.89) and 0.77 (95% CI, 0.65-0.88) in the internal and external validation sets, respectively. These were significantly higher than the AUROC values of T2WI (0.53 [95% CI, 0.40-0.67], p = 0.006), CE-T1WI (0.53 [95% CI, 0.40-0.67], p = 0.012), and clinical parameters (0.53 [95% CI, 0.39-0.67], p = 0.021) in the external validation set. Conclusion: The radiomics model using ADC maps exhibited higher diagnostic performance than those of the radiomics models using T2WI or CE-T1WI and clinical parameters in the diagnosis of local tumor recurrence in HNSCC following definitive treatment.

• Korean Journal of Applied Biomechanics
• /
• v.21 no.3
• /
• pp.383-390
• /
• 2011

In this study, 26 normal subjects were studied to compare the biomechanical Analysis of Lower Limbs on Speed of Nordic Walking. The biomechanical variables were determined by performing three-dimensional gait analysis, and the measurements items were spatial and temporal parameters; vertical ground reaction force; and moments of the hip, knee, and ankle joints. The purpose of this study based on the speed of Nordic Walking to the vertical ground reaction force and joint moments of each were analyzed. Nordic Walking with poles while being whether this weight is reduced to load, not the improvement of muscle activity by identify Nordic walking is to allow efficient. The results of the analysis were follows. The spatial parameters of step length, stride length significantly increased with increase in velocity(p<0.001). The temporal parameters of step time, stride time, the duration of double support use, and the duration of single support use also significantly decreased with increase in velocity(p<0.001), but cadence significantly increased(p<0.01). Analysis of the changes in ground reaction force revealed that vertical ground reaction force significantly increased at the initial contact and the terminal stance and decreased at the mid stance with increase in velocity(p<0.001). Moments of the hip and knee joints significantly in creased with increase in velocity whereas that of the ankle joint did not. Gait analysis revealed that weight-bearing decreased and moments of the hip and knee joints increased with increase in velocity(p<0.01). The results of this study may help people perform Nordic walking efficiently and Nordic walking can be used in the gait training of people with an abnormal gait.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.30 no.3
• /
• pp.161-171
• /
• 1994

Mesh selection analysis for the trawl net were carried out at the Southern Korean Sea and the East China Sea during the 1992-1994 years by the training ship Seabada of the National Fisheries University of Pusan, using A type (51.2mm), B type (70.2mm), C type (77.6mm), D type (88.0mm) square mesh cod-ends. The fishing trials were made using bottom trawl of the trouser type cod-end with cover net. Selection curves and selection parameters were calculated by a logistic model for Sphyraena pinguis, Pampus argenteus, Trachurus japonicus, Pagrus major, Callanthias japonicus, Trichiurus lepturus. The results obtained are summarized as follows: 1. Red barracuda : Selection range and fifty percent selection length in the A type was 115.8mm, 292.8mm, respectively. 2. Harvest fish : Each selection range and fifty percent selection length in the B. C. and D type was 37.7mm, 113.8mm : 40.1mm, 131.7mm and 64.8mm, 148.6mm, respectively. Selection parameters of master curve were : slope, 3.81 : intercept, -6.4. Optimum mesh size was 89.3mm. 3. Horse mackerel : Each selection range and fifty percent selection length in the A, B, C and D type was 43.0mm, 148.3mm : 60.7mm, 183.2mm, 214.5mm and 91.4mm, 254.9mm, respectively. Selection parameters of master curve were : slope 2.30 : intercept, -6.4. Optimum mesh size was 66.8mm. 4. Red seabrem : Selection range and fifty percent selection length in the D type was 42.7mm, 203.4mm, respectively. 5. Yellowsail red bass : Selection range and fifty percent selection length in the A type was 84.0mm, 110.6mm, respectively. 6. Hair tail : Each selection range and fifty percent selection length in the A, B and C type was 59.7mm, 176.0mm : 100.9mm, 250.7mm and 178.6mm, 307.0mm, respectively. Selection parameters of master curve were : slope, 1.54 : intercept, -5.4. Optimum mesh size was 57.5mm.

• Journal of Biomedical Engineering Research
• /
• v.41 no.2
• /
• pp.107-119
• /
• 2020

The deep neural networks (DNN) that can replicate the behavior of the human expert who recognizes the characteristics of ECG waveform have been developed and studied to analyze ECG. However, although the existing DNNs can not provide the explanations for their decisions, those trials have attempted to determine whether patients have certain diseases or not and those decisions could not be accepted because of the absence of relating theoretical basis. In addition, these DNNs required a lot of training data to obtain sufficient accuracy in spite of the difficulty in the acquisition of relating clinical data. In this study, a small-sized continuous data processing DNN (C-DNN) was suggested to determine the simple characteristics of ECG wave that were not required additional explanations about its decisions and the C-DNN can be easily trained with small training data. Although it can analyze small input data that was selected in narrow region on whole ECG, it can continuously scan all ECG data and find important points such as start and end points of P, QRS and T waves within a short time. The star and end points of ECG waves determined by the C-DNNs were compared with the results performed by human experts to estimate the accuracies of the C-DNNs. The C-DNN has 150 inputs, 51 outputs, two hidden layers and one output layer. To find the start and end points, two C-DNNs were trained through deep learning technology and applied to a parameter acquisition algorithms. 12 lead ECG data measured in four patients and obtained through PhysioNet was processed to make training data by human experts. The accuracy of the C-DNNs were evaluated with extra data that were not used at deep learning by comparing the results between C-DNNs and human experts. The averages of the time differences between the C-DNNs and experts were 0.1 msec and 13.5 msec respectively and those standard deviations were 17.6 msec and 15.7 msec. The final step combining the results of C-DNN through the waveforms of 12 leads was successfully determined all 33 waves without error that the time differences of human experts decision were over 20 msec. The reliable decision of the ECG wave's start and end points benefits the acquisition of accurate ECG parameters such as the wave lengths, amplitudes and intervals of P, QRS and T waves.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Korean Chemical Engineering Research
• /
• v.58 no.4
• /
• pp.588-595
• /
• 2020

Prediction and control of nitrogen oxides (NO_x) emission is of great interest in industry due to stricter environmental regulations. Herein, we propose an artificial intelligence (AI)-based framework for prediction of NO_x emission. The framework includes pre-processing of data for training of neural networks and evaluation of the AI-based models. In this work, Long-Short-Term Memory (LSTM), one of the recurrent neural networks, was adopted to reflect the time series characteristics of NO_x emissions. A decision tree was used to determine a time window of LSTM prior to training of the network. The neural network was trained with operational data from a heating furnace. The optimal model was obtained by optimizing hyper-parameters. The LSTM model provided a reliable prediction of NO_x emission for both training and test data, showing an accuracy of 93% or more. The application of the proposed AI-based framework will provide new opportunities for predicting the emission of various air pollutants with time series characteristics.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.6
• /
• pp.57-66
• /
• 2005

In this paper, a new rehabilitation training system was developed to improve equilibrium sense by combining virtual reality technology with a fixed exercise bicycle. The subjects consisted of two groups. A group of young people, was compared against a group of elderly. We measured three different running modes of virtual bicycle system with two successive sets. The parameters measured were running time, velocity, the weight movement, the degree of the deviation from the road, and the variables about the center of pressure. The repeated training, our results showed that the running capability of the elderly improve compared. In addition, it was found out that the ability of postural control and the equilibrium sense was improved with the presentation of the visual feedback information of the distribution of weight. From the results of this experiment, we showed that our newly developed system might be useful in the diagnosis of equilibrium sense or in the improvement of the sense of sight and, somatic, and vestibular sense of the elderly in the field of rehabilitation training.

• Journal of Korea Water Resources Association
• /
• v.36 no.2
• /
• pp.195-209
• /
• 2003

Spatial-Stochastic Neural Networks Model(SSNNM) is used to estimate long-term streamflow in the parallel reservoir groups. SSNNM employs two kinds of backpropagation algorithms, based on LMBP and BFGS-QNBP separately. SSNNM has three layers, input, hidden, and output layer, in the structure and network configuration consists of 8-8-2 nodes one by one. Nodes in input layer are composed of streamflow, precipitation, pan evaporation, and temperature with the monthly average values collected from Andong and Imha reservoir. But some temporal differences apparently exist in their time series. For the SSNNM training procedure, the training sets in input layer are generated by the PARMA(1,1) stochastic model and they covers insufficient time series. Generated data series are used to train SSNNM and the model parameters, optimal connection weights and biases, are estimated during training procedure. They are applied to evaluate model validation using observed data sets. In this study, the new approaches give outstanding results by the comparison of statistical analysis and hydrographs in the model validation. SSNNM will help to manage and control water distribution and give basic data to develop long-term coupled operation system in parallel reservoir groups of the Upper Nakdong River.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.1
• /
• pp.8-14
• /
• 2002

In this paper, we realized a real-time text-independent speaker recognition system using gaussian mixture model, and applied frame level likelihood normalization method which shows its effects in verification system. The system has three parts as front-end, training, recognition. In front-end part, cepstral mean normalization and silence removal method were applied to consider speaker's speaking variations. In training, gaussian mixture model was used for speaker's acoustic feature modeling, and maximum likelihood estimation was used for GMM parameter optimization. In recognition, likelihood score was calculated with speaker models and test data at frame level. As test sentences, we used text-independent sentences. ETRI 445 and KLE 452 database were used for training and test, and cepstrum coefficient and regressive coefficient were used as feature parameters. The experiment results show that the frame-level likelihood method's recognition result is higher than conventional method's, independently the number of registered speakers.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.1-9
• /
• 2021

In this paper, we propose a training algorithm of support vector machine (SVM) with a sensitive variable. Although machine learning models enable automatic decision making in the real world applications, regulations prohibit sensitive information from being used to protect privacy. In particular, the privacy protection of the legally protected attributes such as race, gender, and disability is compulsory. We present an efficient least square SVM (LSSVM) training algorithm using a fully homomorphic encryption (FHE) to protect a partial sensitive attribute. Our framework posits that data owner has both non-sensitive attributes and a sensitive attribute while machine learning service provider (MLSP) can get non-sensitive attributes and an encrypted sensitive attribute. As a result, data owner can obtain the encrypted model parameters without exposing their sensitive information to MLSP. In the inference phase, both non-sensitive attributes and a sensitive attribute are encrypted, and all computations should be conducted on encrypted domain. Through the experiments on real data, we identify that our proposed method enables to implement privacy-preserving sensitive LSSVM with FHE that has comparable performance with the original LSSVM algorithm. In addition, we demonstrate that the efficient sensitive LSSVM with FHE significantly improves the computational cost with a small degradation of performance.