• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.29-39
• /
• 2021

As damages to individuals, private sectors, and businesses increase due to newly occurring cyber attacks, the underlying network security problem has emerged as a major problem in computer systems. Therefore, NIDS using machine learning and deep learning is being studied to improve the limitations that occur in the existing Network Intrusion Detection System. In this study, a deep learning-based NIDS model study is conducted using the Convolution Neural Network (CNN) algorithm. For the image classification-based CNN algorithm learning, a discrete algorithm for continuity variables was added in the preprocessing stage used previously, and the predicted variables were expressed in a linear relationship and converted into easy-to-interpret data. Finally, the network packet processed through the above process is mapped to a square matrix structure and converted into a pixel image. For the performance evaluation of the proposed model, NSL-KDD, a representative network packet data, was used, and accuracy, precision, recall, and f1-score were used as performance indicators. As a result of the experiment, the proposed model showed the highest performance with an accuracy of 85%, and the harmonic mean (F1-Score) of the R2L class with a small number of training samples was 71%, showing very good performance compared to other models.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.3
• /
• pp.9-15
• /
• 2019

Large global online shopping malls, such as Amazon, offer services in English or in the language of a country when their products are sold. Since many customers purchase products based on the product reviews, the shopping malls actively utilize the sentimental analysis technique in judging preference of each product using the large amount of review data that the customer has written. And the result of such analysis can be used for the marketing to look the potential shoppers. However, it is difficult to apply this English-based semantic analysis system to different languages used around the world. In this study, more than 500,000 data from Amazon fine food reviews was used for training a deep learning based system. First, sentiment analysis evaluation experiments were carried out with three models of English test data. Secondly, the same data was translated into seven languages (Korean, Japanese, Chinese, Vietnamese, French, German and English) and then the similar experiments were done. The result suggests that although the accuracy of the sentimental analysis was 2.77% lower than the average of the seven countries (91.59%) compared to the English (94.35%), it is believed that the results of the experiment can be used for practical applications.

• Physical Therapy Korea
• /
• v.26 no.3
• /
• pp.1-10
• /
• 2019

Background: Winged scapular (WS) causes muscle imbalance with abnormal patterns when moving the arm. In particular, the over-activation of the upper trapezius (UT) and decrease in activity of the lower trapezius (LT) and serratus anterior (SA) produce abnormal scapulohumeral rhythm. Therefore, the SA requires special attention in all shoulder rehabilitation programs. In fact, many previous studies have been devoted to the SA muscle strength training needed for WS correction. Objects: The purpose of this study was to investigate the effect of shoulder girdle muscle and ratio according to the angle of shoulder abduction and external weight in supine position. Methods: Twenty three WS patients participated in this experiment. They performed scapular protraction exercise in supine position with the weights of 0 kg, 1 kg, 1.5 kg, and 2 kg at shoulder abduction angles of $0^{\circ}$, $30^{\circ}$, $60^{\circ}$, and $90^{\circ}$. The angle and weight applications were randomized. Surface electromyography (EMG) was used to collect the EMG data of the SA, pectoralis major (PM), and UT during the exercise. The ratio of PM/SA and UT/SA was confirmed. Two-way repeated analyses of variance were used to determine the statistical significance of SA, PM, and UT and the ratios of PM/SA and UT/SA. Results: There was a significant difference in SA according to angle (p<.05). Significant differences were also identified depending on the angle and weight (p<.05). The angle of abduction at $0^{\circ}$, $30^{\circ}$ and weight of 2 kg showed the highest SA activity. However, there was no significant difference between PM and UT (p>.05). There was a significant difference between PM/SA and UT/SA in ratio of muscle activity according to angle (p<.05). Significant differences were found at PM/SA angles of $30^{\circ}$, $60^{\circ}$ and $90^{\circ}$ (p<.05). For UT/SA, significant difference was only observed at $90^{\circ}$ (p<.05). Conclusion: Based on the results of this study, in order to strengthen the SA, it was found to be most effective to use 1 and 1.5 kg weights with abduction angles of $0^{\circ}$ and $30^{\circ}$ at shoulder protraction in supine position.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.55 no.1
• /
• pp.7-19
• /
• 2019

This study was conducted in order to improve opening efficiency of the miniaturized small-scale net for anchovy boat seine gear to reduce the fleet size. Field experiment was performed to observe geometry of nets by catcher boats. When the distance between the two ships was 150, 300 and 450 m and the speed of towing nets was 0.6, 0.9, and 1.2 kt, the vertical opening and actual opening of each part of the miniaturized small-scale net was as follows: the front part of the wing net, 6.8-9.5 m, 45-63%; the middle part of the wing net, 16.1-30.7 m, 34-65%; the entrance of the inside wing net, 21.6-41.2 m, 44-84%; the square and bosom, 17.4-34.0 m, 38-75%; the entrance of the body net, 16.5-29.4 m, 36-64%; the entrance of the bag net, 14.5-21.9 m, 70-106%; the flapper, 6.7-7.7 m, 81-83%, and the end of the bag net, 8.6-10.9 m, 64-81%. The tension of towing nets was measured to be 2,734-6,812 kg approximately, which indicates that the fleet can tow nets with 350 hp, the standard engine horse power. The fishing operation time was shortened comparing to existent net with the large-scale buoy attachment operation. It was also possible to operate the ship without fish detecting boat.

• Journal of Digital Convergence
• /
• v.17 no.1
• /
• pp.239-247
• /
• 2019

An accurate prediction of emotion is a very important issue for the sake of patient-centered medical device development and emotion-related psychology fields. Although there have been many studies on emotion prediction, no studies have applied the heart rate variability and neuro-fuzzy approach to emotion prediction. We propose ANFEP(Adaptive Neuro Fuzzy System for Emotion Prediction) HRV. The ANFEP bases its core functions on an ANFIS(Adaptive Neuro-Fuzzy Inference System) which integrates neural networks with fuzzy systems as a vehicle for training predictive models. To prove the proposed model, 50 participants were invited to join the experiment and Heart rate variability was obtained and used to input the ANFEP model. The ANFEP model with STDRR and RMSSD as inputs and two membership functions per input variable showed the best results. The result out of applying the ANFEP to the HRV metrics proved to be significantly robust when compared with benchmarking methods like linear regression, support vector regression, neural network, and random forest. The results show that reliable prediction of emotion is possible with less input and it is necessary to develop a more accurate and reliable emotion recognition system.

• Physical Therapy Rehabilitation Science
• /
• v.8 no.1
• /
• pp.45-51
• /
• 2019

Objective: The purpose of this study was to investigate the muscle activity ratio of the lower limb according to changes in straight leg raise (SLR) test angles on hamstring muscle shortening during squat exercises. Design: Randomized controlled trial. Methods: The subjects were 14 healthy adults who were informed of and agreed to the method and purpose of the study. The participants were classified into SLR groups according to two angles (over $80^{\circ}$ or under $80^{\circ}$) assessed using the SLR tests. After training and practicing the wall squat posture to be applied to the experiment, electromyography (EMG) was used to measure changes in muscle activity during the performance of a wall squat. After stretching, a sequence of pre-stretch tests were performed again, and the active and passive SLR tests were also reconducted; thereafter, a wall squat was performed again by attaching EMG electrodes. The EMG results before and after stretching were compared. Results: The muscle activity of the vastus lateralis oblique muscle increased in both groups. The muscle activity of the vastus medialis oblique muscle decreased in over both group. Rectus femorus activity increased in the under 80-degree groups but decreased in the over 80-degree group. The muscle activity of the biceps femoris muscle decreased after stretching in the over 80-degree group and increased in the under 80-degree group, and the semitendinosus muscle activity after stretching was decreased. The quadriceps-to-hamstring muscle (Q:H) ratio before and after stretching between groups showed that the hamstring muscle ratio decreased after stretching in both groups. Conclusions: The results of this study showed that the Q:H ratio before and after stretching between groups was not significantly different.

• Database Research
• /
• v.34 no.3
• /
• pp.137-147
• /
• 2018

A key to a well-performing human activity recognition (HAR) system through machine learning technique is the availability of a substantial amount of labeled data. Collecting sufficient labeled data is an expensive and time-consuming task. To build a HAR system in a new environment (i.e., the target domain) with very limited labeled data, it is unfavorable to naively exploit the data or trained classifier model from the existing environment (i.e., the source domain) as it is due to the domain difference. While traditional machine learning approaches are unable to address such distribution mismatch, transfer learning approach leverages the utilization of knowledge from existing well-established source domains that help to build an accurate classifier in the target domain. In this work, we propose a transfer learning approach to create an accurate HAR classifier with very limited data through the multitask neural network. The classifier loss function minimization for source and target domain are treated as two different tasks. The knowledge transfer is performed by simultaneously minimizing the loss function of both tasks using a single neural network model. Furthermore, we utilize the unlabeled data in an unsupervised manner to help the model training. The experiment result shows that the proposed work consistently outperforms existing approaches.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1131-1139
• /
• 2020

The static analysis of the source code is to find the remaining security weaknesses for a wide range of source codes. The static analysis tool is used to check the result, and the static analysis expert performs spying and false detection analysis on the result. In this process, the amount of analysis is large and the rate of false positives is high, so a lot of time and effort is required, and a method of efficient analysis is required. In addition, it is rare for experts to analyze only the source code of the line where the defect occurred when performing positive/false detection analysis. Depending on the type of defect, the surrounding source code is analyzed together and the final analysis result is delivered. In order to solve the difficulty of experts discriminating positive and false positives using these static analysis tools, this paper proposes a method of determining whether or not the security weakness found by the static analysis tools is a spy detection through artificial intelligence rather than an expert. In addition, the optimal size was confirmed through an experiment to see how the size of the training data (source code around the defects) used for such machine learning affects the performance. This result is expected to help the static analysis expert's job of classifying positive and false positives after static analysis.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.199-213
• /
• 2022

The unsupervised domain adaptation can solve the impractical issue of repeatedly collecting high-quality training data every year for annual crop classification. This study evaluates the applicability of deep learning-based unsupervised domain adaptation models for crop classification. Three unsupervised domain adaptation models including a deep adaptation network (DAN), a deep reconstruction-classification network, and a domain adversarial neural network (DANN) are quantitatively compared via a crop classification experiment using unmanned aerial vehicle images in Hapcheon-gun and Changnyeong-gun, the major garlic and onion cultivation areas in Korea. As source baseline and target baseline models, convolutional neural networks (CNNs) are additionally applied to evaluate the classification performance of the unsupervised domain adaptation models. The three unsupervised domain adaptation models outperformed the source baseline CNN, but the different classification performances were observed depending on the degree of inconsistency between data distributions in source and target images. The classification accuracy of DAN was higher than that of the other two models when the inconsistency between source and target images was low, whereas DANN has the best classification performance when the inconsistency between source and target images was high. Therefore, the extent to which data distributions of the source and target images match should be considered to select the best unsupervised domain adaptation model to generate reliable classification results.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_1
• /
• pp.597-608
• /
• 2022

Remotely sensed data have been used in various fields, such as disasters, agriculture, urban planning, and the military. Recently, the demand for the multitemporal dataset with the high-spatial-resolution has increased. This manuscript proposed an automatic image matching algorithm using a deep learning technique to utilize a multitemporal remotely sensed dataset. The proposed deep learning model was based on High Resolution Net (HRNet), widely used in image segmentation. In this manuscript, denseblock was added to calculate the correlation map between images effectively and to increase learning efficiency. The training of the proposed model was performed using the multitemporal orthophotos of the National Geographic Information Institute (NGII). In order to evaluate the performance of image matching using a deep learning model, a comparative evaluation was performed. As a result of the experiment, the average horizontal error of the proposed algorithm based on 80% of the image matching rate was 3 pixels. At the same time, that of the Zero Normalized Cross-Correlation (ZNCC) was 25 pixels. In particular, it was confirmed that the proposed method is effective even in mountainous and farmland areas where the image changes according to vegetation growth. Therefore, it is expected that the proposed deep learning algorithm can perform relative image registration and image matching of a multitemporal remote sensed dataset.