• Journal of Korea Multimedia Society
• /
• v.23 no.5
• /
• pp.641-649
• /
• 2020

As the usage of mobile devices extremely increases, malicious mobile apps(applications) that target mobile users are also increasing. It is challenging to detect these malicious apps using traditional malware detection techniques due to intelligence of today's attack mechanisms. Deep learning (DL) is an alternative technique of traditional signature and rule-based anomaly detection techniques and thus have actively been used in numerous recent studies on malware detection. In order to develop DL-based defense mechanisms against intelligent malicious apps, feeding recent datasets into DL models is important. In this paper, we develop a DL-based model for detecting intelligent malicious apps using KU-CISC 2018-Android, the most up-to-date dataset consisting of benign and malicious Android apps. This dataset has hardly been addressed in other studies so far. We extract OPcode sequences from the Android apps and preprocess the OPcode sequences using an N-gram model. We then feed the preprocessed data into LSTM and apply the concept of Information Gain to improve performance of detecting malicious apps. Furthermore, we evaluate our model with numerous scenarios in order to verify the model's design and performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.2
• /
• pp.45-52
• /
• 2020

Since the opening of the national petition site, it has attracted much attention. In this paper, we perform topic analysis of the national petition site and propose a prediction model for answerable petitions based on deep learning. First, 1,500 petitions are collected, topics are extracted based on the petitions' contents. Main subjects are defined using K-means clustering algorithm, and detailed subjects are defined using topic modeling of petitions belonging to the main subjects. Also, long short-term memory (LSTM) is used for prediction of answerable petitions. Not only title and contents but also categories, length of text, and ratio of part of speech such as noun, adjective, adverb, verb are also used for the proposed model. Our experimental results show that the type 2 model using other features such as ratio of part of speech, length of text, and categories outperforms the type 1 model without other features.

• Phonetics and Speech Sciences
• /
• v.11 no.2
• /
• pp.57-64
• /
• 2019

In this paper, we construct a Korean text-to-speech system using the Merlin toolkit which is an open source system for speech synthesis. In the text-to-speech system, the HMM-based statistical parametric speech synthesis method is widely used, but it is known that the quality of synthesized speech is degraded due to limitations of the acoustic modeling scheme that includes context factors. In this paper, we propose an acoustic modeling architecture that uses deep neural network technique, which shows excellent performance in various fields. Fully connected deep feedforward neural network (DNN), recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional LSTM (BLSTM) are included in the architecture. Experimental results have shown that the performance is improved by including sequence modeling in the architecture, and the architecture with LSTM or BLSTM shows the best performance. It has been also found that inclusion of delta and delta-delta components in the acoustic feature parameters is advantageous for performance improvement.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.319-328
• /
• 2021

Parallel administration of numerous drugs increases Drug-Drug Interaction (DDI) because one drug might affect the activity of other drugs. DDI causes negative or positive impacts on therapeutic output. So there is a need to discover DDI to enhance the safety of consuming drugs. Though there are several DDI system exist to predict an interaction but nowadays it becomes impossible to maintain with a large number of biomedical texts which is getting increased rapidly. Mostly the existing DDI system address classification issues, and especially rely on handcrafted features, and some features which are based on particular domain tools. The objective of this paper to predict DDI in a way to avoid adverse effects caused by the consumed drugs, to predict similarities among the drug, Drug pair similarity calculation is performed. The best optimal weight is obtained with the support of KHA. LSTM function with weight obtained from KHA and makes bets prediction of DDI. Our methodology depends on (LSTM-KHA) for the detection of DDI. Similarities among the drugs are measured with the help of drug pair similarity calculation. KHA is used to find the best optimal weight which is used by LSTM to predict DDI. The experimental result was conducted on three kinds of dataset DS1 (CYP), DS2 (NCYP), and DS3 taken from the DrugBank database. To evaluate the performance of proposed work in terms of performance metrics like accuracy, recall, precision, F-measures, AUPR, AUC, and AUROC. Experimental results express that the proposed method outperforms other existing methods for predicting DDI. LSTMKHA produces reasonable performance metrics when compared to the existing DDI prediction model.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.2
• /
• pp.115-123
• /
• 2021

A lot of sensor and control signals is generated by an industrial controller and related internet-of-things in discrete manufacturing system. The acquired signals are such records indicating whether several process operations have been correctly conducted or not in the system, therefore they are usually composed of binary numbers. For example, once a certain sensor turns on, the corresponding value is changed from 0 to 1, and it means the process is finished the previous operation and ready to conduct next operation. If an actuator starts to move, the corresponding value is changed from 0 to 1 and it indicates the corresponding operation is been conducting. Because traditional fault detection approaches are generally conducted with analog sensor signals and the signals show stationary during normal operation states, it is not simple to identify whether the manufacturing process works properly via conventional fault detection methods. However, digital control signals collected from a programmable logic controller continuously vary during normal process operation in order to show inherent sequence information which indicates the conducting operation tasks. Therefore, in this research, it is proposed to a recurrent neural network-based fault detection approach for considering sequential patterns in normal states of the manufacturing process. Using the constructed long short-term memory based fault detection, it is possible to predict the next control signals and detect faulty states by compared the predicted and real control signals in real-time. We validated and verified the proposed fault detection methods using digital control signals which are collected from a laser marking process, and the method provide good detection performance only using binary values.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.2
• /
• pp.94-107
• /
• 2022

Accidents prevention and mitigation is the highest priority of nuclear power plant (NPP) operation, particularly in the aftermath of the Fukushima Daiichi accident, which has reignited public anxieties and skepticism regarding nuclear energy usage. To deal with accident scenarios more effectively, operators must have ample and precise information about key safety parameters as well as their future trajectories. This work investigates the potential of machine learning in forecasting NPP response in real-time to provide an additional validation method and help reduce human error, especially in accident situations where operators are under a lot of stress. First, a base-case SGTR simulation is carried out by the best-estimate code RELAP5/MOD3.4 to confirm the validity of the model against results reported in the APR1400 Design Control Document (DCD). Then, uncertainty quantification is performed by coupling RELAP5/MOD3.4 and the statistical tool DAKOTA to generate a large enough dataset for the construction and training of neural-based machine learning (ML) models, namely LSTM, GRU, and hybrid CNN-LSTM. Finally, the accuracy and reliability of these models in forecasting system response are tested by their performance on fresh data. To facilitate and oversee the process of developing the ML models, a Systems Engineering (SE) methodology is used to ensure that the work is consistently in line with the originating mission statement and that the findings obtained at each subsequent phase are valid.

• Geomechanics and Engineering
• /
• v.31 no.6
• /
• pp.545-556
• /
• 2022

Evaluation and optimization of tunnel wall convergence (TWC) plays a vital role in preventing potential problems during tunnel construction and utilization stage. When convergence occurs at a high rate, it can lead to significant problems such as reducing the advance rate and safety, which in turn increases operating costs. In order to design an effective solution, it is important to accurately predict the degree of TWC; this can reduce the level of concern and have a positive effect on the design. With the development of soft computing methods, the use of deep learning algorithms and neural networks in tunnel construction has expanded in recent years. The current study aims to employ the long-short-term memory (LSTM) deep neural network predictor model to predict the TWC, based on 550 data points of observed parameters developed by collecting required data from different tunnelling projects. Among the data collected during the pre-construction and construction phases of the project, 80% is randomly used to train the model and the rest is used to test the model. Several loss functions including root mean square error (RMSE) and coefficient of determination (R²) were used to assess the performance and precision of the applied method. The results of the proposed models indicate an acceptable and reliable accuracy. In fact, the results show that the predicted values are in good agreement with the observed actual data. The proposed model can be considered for use in similar ground and tunneling conditions. It is important to note that this work has the potential to reduce the tunneling uncertainties significantly and make deep learning a valuable tool for planning tunnels.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.333-333
• /
• 2021

최근 전 지구적인 기후변화 및 온난화의 영향으로 태풍 및 집중호우가 빈번하게 일어나고 있으며, 이로 인한 한천범람 등 홍수재해로 인명 및 재산 피해가 크게 증가하고 있다. 우리나라에서도 태풍 및 집중호우로 인한 호수피해는 매년 발생하고 있으며, 피해 빈도와 강도가 증가하고 있는 실정이다. 이러한 현실을 고려하였을 때에 하천 인근 주민의 생명과 재산을 보호하기 위하여 실시간으로 홍수위 예측을 수행하는 것은 매우 중요하다 할 수 있다. 국내에서 수위예측을 위하여 대표적으로 저류함수모형(Storage Function Model, SFM)을 채택하고 있지만, 유역면적이 작아 홍수 도달시간이 짧은 중소하천에서는 충분한 선행시간과 정확도를 확보하기 어려운 문제점이 있다. 이는 유역면적이 작은 중소하천에서는 유역 및 기상 특성과 관련된 여러 인자 사이의 비선형성이 대하천 유역에 비해 커지는 문제점이 있기 때문이다. 본 연구에서는 위와같은 문제를 해결할 수 있도록, 수문자료와 딥러닝 기법을 적용하여 실시간으로 홍수위를 예측할 수 있는 방법론을 제시하였다. 지난 태풍 및 집중호우로 인하여 급격한 수위상승이 있던 낙동강 지류하천에 대하여 LSTM(Long-Short Term Memory) 모형 기반 실시간 수위예측 모형을 개발하였으며, 선행시간 30~180분 별로 홍수위를 예측하고 관측 수위와 비교함으로써 모형의 적용성을 검증하였다. 선행시간 180분 기준으로 영강 유역 수위예측 결과와 실제 관측치의 평균제곱근 오차는 0.29m, 상관계수는 0.92로 나타났으며, 밀양강 유역의 경우 각각 0.30m, 0.94로 나타났다. 본 연구에서 제시된 딥러닝 기반모형에 10분 단위 실시간 수문자료가 입력된다면, 다음 관측자료가 입력되기 전 홍수예측 결과가 산출되므로 실질적인 홍수예경보체계에 유용하게 사용될 수 있을 것이라 보인다. 모형에 적용할 수 있는 더욱 다양한 수문자료와 매개변수 조정을 통하여 예측결과에 대한 신뢰성을 더욱 높일 수 있다면, 기존의 저류함수모형과 연계하여 홍수대응 능력을 향상시키는데 도움이 될 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.43-52
• /
• 2023

Rubber produced by rubber companies is subjected to quality suitability inspection through rheometer test, followed by secondary processing for automobile parts. However, rheometer test is being conducted by humans and has the disadvantage of being very dependent on experts. In order to solve this problem, this paper proposes a deep learning-based rheometer quality inspection system. The proposed system combines LSTM(Long Short-Term Memory) and CNN(Convolutional Neural Network) to take advantage of temporal and spatial characteristics from the rheometer. Next, combination materials of each rubber was used as an auxiliary input to enable quality conformity inspection of various rubber products in one model. The proposed method examined its performance with 30,000 validation datasets. As a result, an F1-score of 0.9940 was achieved on average, and its excellence was proved.

• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.375-390
• /
• 2024

Edge computing architecture has effectively alleviated the computing pressure on cloud platforms, reduced network bandwidth consumption, and improved the quality of service for user experience; however, it has also introduced new security issues. Existing anomaly detection methods in big data scenarios with cloud-edge computing collaboration face several challenges, such as sample imbalance, difficulty in dealing with complex network traffic attacks, and difficulty in effectively training large-scale data or overly complex deep-learning network models. A lightweight deep-learning model was proposed to address these challenges. First, normalization on the user side was used to preprocess the traffic data. On the edge side, a trained Wasserstein generative adversarial network (WGAN) was used to supplement the data samples, which effectively alleviates the imbalance issue of a few types of samples while occupying a small amount of edge-computing resources. Finally, a trained lightweight deep learning network model is deployed on the edge side, and the preprocessed and expanded local data are used to fine-tune the trained model. This ensures that the data of each edge node are more consistent with the local characteristics, effectively improving the system's detection ability. In the designed lightweight deep learning network model, two sets of convolutional pooling layers of convolutional neural networks (CNN) were used to extract spatial features. The bidirectional long short-term memory network (BiLSTM) was used to collect time sequence features, and the weight of traffic features was adjusted through the attention mechanism, improving the model's ability to identify abnormal traffic features. The proposed model was experimentally demonstrated using the NSL-KDD, UNSW-NB15, and CIC-ISD2018 datasets. The accuracies of the proposed model on the three datasets were as high as 0.974, 0.925, and 0.953, respectively, showing superior accuracy to other comparative models. The proposed lightweight deep learning network model has good application prospects for anomaly traffic detection in cloud-edge collaborative computing architectures.