• 품질경영학회지
• /
• 제50권3호
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3584-3602
• /
• 2022

NFV realizes flexible and rapid software deployment and management of network functions in the cloud network, and provides network services in the form of chained virtual network functions (VNFs). However, using VNFs to provide quality guaranteed services is still a challenge because of the inherent difficulty in intelligently scaling VNFs to handle traffic fluctuations. Most existing works scale VNFs with fixed-capacity instances, that is they take instances of the same size and determine a suitable deployment location without considering the cloud network resource distribution. This paper proposes a traffic forecasted assisted proactive VNF scaling approach, and it adopts the instance capacity adaptive to the node resource. We first model the VNF scaling as integer quadratic programming and then propose a proactive adaptive VNF scaling (PAVS) approach. The approach employs an efficient traffic forecasting method based on LSTM to predict the upcoming traffic demands. With the obtained traffic demands, we design a resource-aware new VNF instance deployment algorithm to scale out under-provisioning VNFs and a redundant VNF instance management mechanism to scale in over-provisioning VNFs. Trace-driven simulation demonstrates that our proposed approach can respond to traffic fluctuation in advance and reduce the total cost significantly.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.334-342
• /
• 2022

Nowadays, as we can notice on social media, most users choose to use more than one language in their online postings. Thus, social media analytics needs reviewing as code-switching analytics instead of traditional analytics. This paper aims to present evidence comparable to the accuracy of code-switching analytics techniques in analysing the mood state of social media users. We conducted a systematic literature review (SLR) to study the social media analytics that examined the effectiveness of code-switching analytics techniques. One primary question and three sub-questions have been raised for this purpose. The study investigates the computational models used to detect and measures emotional well-being. The study primarily focuses on online postings text, including the extended text analysis, analysing and predicting using past experiences, and classifying the mood upon analysis. We used thirty-two (32) papers for our evidence synthesis and identified four main task classifications that can be used potentially in code-switching analytics. The tasks include determining analytics algorithms, classification techniques, mood classes, and analytics flow. Results showed that CNN-BiLSTM was the machine learning algorithm that affected code-switching analytics accuracy the most with 83.21%. In addition, the analytics accuracy when using the code-mixing emotion corpus could enhance by about 20% compared to when performing with one language. Our meta-analyses showed that code-mixing emotion corpus was effective in improving the mood analytics accuracy level. This SLR result has pointed to two apparent gaps in the research field: i) lack of studies that focus on Malay-English code-mixing analytics and ii) lack of studies investigating various mood classes via the code-mixing approach.

• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.186-197
• /
• 2023

In this study, we focus on the improvement of data quality transmitted from a weather buoy that guides a route of ships. The buoy has an Internet-of-Thing (IoT) including sensors to collect meteorological data and the buoy's status, and it also has a wireless communication device to send them to the central database in a ground control center and ships nearby. The time interval of data collected by the sensor is irregular, and fault data is often detected. Therefore, this study provides a framework to improve data quality using machine learning models. The normal data pattern is trained by machine learning models, and the trained models detect the fault data from the collected data set of the sensor and adjust them. For determining fault data, interquartile range (IQR) removes the value outside the outlier, and an NGBoost algorithm removes the data above the upper bound and below the lower bound. The removed data is interpolated using NGBoost or long-short term memory (LSTM) algorithm. The performance of the suggested process is evaluated by actual weather buoy data from Korea to improve the quality of 'AIR_TEMPERATURE' data by using other data from the same buoy. The performance of our proposed framework has been validated through computational experiments based on real-world data, confirming its suitability for practical applications in real-world scenarios.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• 제4권4호
• /
• pp.159-176
• /
• 2023

The conservation of the raccoon dog (Nyctereutes procyonoides) in South Korea requires the protection and preservation of natural habitats while additionally ensuring coexistence with human activities. Applying habitat map modeling techniques provides information regarding the distributional patterns of raccoon dogs and assists in the development of future conservation strategies. The purpose of this study is to generate potential habitat distribution maps for the raccoon dog in South Korea using geospatial technology-based models. These models include the frequency ratio (FR) as a bivariate statistical approach, the group method of data handling (GMDH) as a machine learning algorithm, and convolutional neural network (CNN) and long short-term memory (LSTM) as deep learning algorithms. Moreover, the imperialist competitive algorithm (ICA) is used to fine-tune the hyperparameters of the machine learning and deep learning models. Moreover, there are 14 habitat characteristics used for developing the models: elevation, slope, valley depth, topographic wetness index, terrain roughness index, slope height, surface area, slope length and steepness factor (LS factor), normalized difference vegetation index, normalized difference water index, distance to drainage, distance to roads, drainage density, and morphometric features. The accuracy of prediction is evaluated using the area under the receiver operating characteristic curve. The results indicate comparable performances of all models. However, the CNN demonstrates superior capacity for prediction, achieving accuracies of 76.3% and 75.7% for the training and validation processes, respectively. The maps of potential habitat distribution are generated for five different levels of potentiality: very low, low, moderate, high, and very high.

• 한국컴퓨터정보학회논문지
• /
• 제25권5호
• /
• pp.47-56
• /
• 2020

주가지수는 한 국가의 경제 지표뿐만 아니라 투자판단의 지표로도 활용되므로 이를 예측하는 연구가 지속해서 진행되고 있다. 주가지수 예측을 하는 작업은 기술적, 경제적 및 심리적 요인 등이 반영된 것으로 예측의 정확도를 위해서는 복합적 요인을 고려해야 한다. 따라서 지수의 변동에 영향을 미치는 요인들을 선별하여 반영한 주가지수 예측모델연구가 필요하다. 이와 관련한 기존 연구에서는 시장의 변동을 만들어 내는 뉴스 정보 또는 거시 경제 지표를 각각 이용하거나, 몇 가지의 지표 조합만을 반영한 예측 연구가 대부분이었다. 따라서 본 연구에서는 미국 다우존스지수 예측을 위해 뉴스 정보의 감성 분석과 다양한 거시경제지표를 고려하여 효과적인 지표 조합을 제시하고자 한다. 뉴스 정보의 감성 분석은 최신 자연어처리 기법인 BERT와 NLTK VADER를 사용하고, 예측모델은 주가예측모델로 적합하다고 알려진 딥러닝 예측모델 LSTM을 적용하여 가장 효과적인 지표 조합을 제시했다.

• Journal of Platform Technology
• /
• 제10권4호
• /
• pp.47-55
• /
• 2022

사물인터넷 환경에서는 다양한 무선 통신 기술을 사용하는 기기들이 점점 증가하고 있다. 특히, 다양한 무선 신호 변조 유형을 정확하게 식별하기 위해 효율적인 특성 추출 기법을 설계하고 무선 신호의 종류를 분류하는 것이 필수적이다. 하지만, 실제 환경에서 레이블이 지정된 무선 신호 데이터를 수집하는 것은 쉬운 문제가 아니다. 최근 무선 신호 분류를 위해 딥러닝 기반의 다양한 학습 기법들이 제안되어졌다. 딥러닝의 경우 훈련 데이터셋이 적을 경우 과대적합에 빠질 가능성이 높으며, 이는 딥러닝 모델을 활용한 무선 신호 분류 기법의 성능 저하를 유발한다. 본 연구에서는 다양한 무선 신호들이 존재할 때 분류 성능을 높이기 위해 생성적 적대 신경망 기반 데이터 증대 기법을 제안한다. 분류해야 하는 무선 신호의 종류가 다양할 때 특정 무선 신호를 나타내는 데이터의 양이 적거나 균형이 맞지 않는 경우 제안한 기법을 활용하여 필요한 무선 신호와 관련된 데이터의 양을 증가시킨다. 제안한 데이터 증강 알고리즘의 유효성을 검증하기 위해 무선 신호의 데이터양을 증가시키고 균형을 맞춘 결과를 바탕으로 CNN 및 LSTM 기반 무선 신호 분류기를 구현하여 실험해본 결과 데이터 균형을 맞추지 않았을 때보다 분류 정확도가 높아지는 것을 확인하였다.

• 지능정보연구
• /
• 제25권1호
• /
• pp.163-177
• /
• 2019

스마트폰이 널리 보급되고 현대인들의 생활 속에 깊이 자리 잡으면서, 스마트폰에서 수집된 다종 데이터를 바탕으로 사용자 개인의 행동을 인식하고자 하는 연구가 활발히 진행되고 있다. 그러나 타인과의 상호작용 행동 인식에 대한 연구는 아직까지 상대적으로 미진하였다. 기존 상호작용 행동 인식 연구에서는 오디오, 블루투스, 와이파이 등의 데이터를 사용하였으나, 이들은 사용자 사생활 침해 가능성이 높으며 단시간 내에 충분한 양의 데이터를 수집하기 어렵다는 한계가 있다. 반면 가속도, 자기장, 자이로스코프 등의 물리 센서의 경우 사생활 침해 가능성이 낮으며 단시간 내에 충분한 양의 데이터를 수집할 수 있다. 본 연구에서는 이러한 점에 주목하여, 스마트폰 상의 다종 물리 센서 데이터만을 활용, 딥러닝 모델에 기반을 둔 사용자의 동행 상태 인식 방법론을 제안한다. 사용자의 동행 여부 및 대화 여부를 분류하는 동행 상태 분류 모델은 컨볼루션 신경망과 장단기 기억 순환 신경망이 혼합된 구조를 지닌다. 먼저 스마트폰의 다종 물리 센서에서 수집한 데이터에 존재하는 타임 스태프의 차이를 상쇄하고, 정규화를 수행하여 시간에 따른 시퀀스 데이터 형태로 변환함으로써 동행 상태분류 모델의 입력 데이터를 생성한다. 이는 컨볼루션 신경망에 입력되며, 데이터의 시간적 국부 의존성이 반영된 요인 지도를 출력한다. 장단기 기억 순환 신경망은 요인 지도를 입력받아 시간에 따른 순차적 연관 관계를 학습하며, 동행 상태 분류를 위한 요인을 추출하고 소프트맥스 분류기에서 이에 기반한 최종적인 분류를 수행한다. 자체 제작한 스마트폰 애플리케이션을 배포하여 실험 데이터를 수집하였으며, 이를 활용하여 제안한 방법론을 평가하였다. 최적의 파라미터를 설정하여 동행 상태 분류 모델을 학습하고 평가한 결과, 동행 여부와 대화 여부를 각각 98.74%, 98.83%의 높은 정확도로 분류하였다.

• 한국공간구조학회논문집
• /
• 제20권2호
• /
• pp.51-58
• /
• 2020

Recently, deep learning that is the most popular and effective class of machine learning algorithms is widely applied to various industrial areas. A number of research on various topics about structural engineering was performed by using artificial neural networks, such as structural design optimization, vibration control and system identification etc. When nonlinear semi-active structural control devices are applied to building structure, a lot of computational effort is required to predict dynamic structural responses of finite element method (FEM) model for development of control algorithm. To solve this problem, an artificial neural network model was developed in this study. Among various deep learning algorithms, a recurrent neural network (RNN) was used to make the time history response prediction model. An RNN can retain state from one iteration to the next by using its own output as input for the next step. An eleven-story building structure with semi-active tuned mass damper (TMD) was used as an example structure. The semi-active TMD was composed of magnetorheological damper. Five historical earthquakes and five artificial ground motions were used as ground excitations for training of an RNN model. Another artificial ground motion that was not used for training was used for verification of the developed RNN model. Parametric studies on various hyper-parameters including number of hidden layers, sequence length, number of LSTM cells, etc. After appropriate training iteration of the RNN model with proper hyper-parameters, the RNN model for prediction of seismic responses of the building structure with semi-active TMD was developed. The developed RNN model can effectively provide very accurate seismic responses compared to the FEM model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권8호
• /
• pp.4123-4141
• /
• 2019

Autonomous driving technology is divided into 0~5 levels. Of these, Level 5 is a fully autonomous vehicle that does not require a person to drive at all. The automobile industry has been trying to develop Level 5 to satisfy safety, but commercialization has not yet been achieved. In order to commercialize autonomous unmanned vehicles, there are several problems to be solved for driving safety. To solve one of these, this paper proposes 'A Deep Learning Part-diagnosis Platform(DLPP) based on an In-vehicle On-board gateway for an Autonomous Vehicle' that diagnoses not only the parts of a vehicle and the sensors belonging to the parts, but also the influence upon other parts when a certain fault happens. The DLPP consists of an In-vehicle On-board gateway(IOG) and a Part Self-diagnosis Module(PSM). Though an existing vehicle gateway was used for the translation of messages happening in a vehicle, the IOG not only has the translation function of an existing gateway but also judges whether a fault happened in a sensor or parts by using a Loopback. The payloads which are used to judge a sensor as normal in the IOG is transferred to the PSM for self-diagnosis. The Part Self-diagnosis Module(PSM) diagnoses parts itself by using the payloads transferred from the IOG. Because the PSM is designed based on an LSTM algorithm, it diagnoses a vehicle's fault by considering the correlation between previous diagnosis result and current measured parts data.