• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.141-141
• /
• 2017

본 연구에서는 대하천의 8개의 수질인자(수온, 용존산소, 수소이온농도, 전기전도도, 총질소, 총인, 탁도, 클로로필-a)를 예측할 수 있는 인공신경망모델을 개발하였다. 인공신경망모델(ANN)은 수질데이터가 가지는 불확실성 및 비정상성, 복잡한 상호관련성에 효과적으로 대응할 수 있는 데이터기반 모델이다. 데이터기반 모델의 특성상 예측정확도를 높이기 위해서 양질의 입력데이터를 구성하는 것이 가장 중요하다. 때문에 각각의 수질인자뿐만 아니라 기상학적 인자 또한 예측을 위한 입력자료로 사용하였으며, 요인분석 및 층화표층추출법을 적용하여 입력데이터를 구성하였고 앙상블기법을 이용하여 추가적으로 예측의 정확도를 향상시켰다. 개발된 모델을 이용하여 지천유입이 있는 북한강의 수질자료를 예측한 결과 탁도를 제외한 7개의 수질인자 모두 0.85 이상의 설명력을 보였으며, 실측값과 예보값을 비교해본 결과 평균적으로 10% 미만의 에러값을 나타냈다. 요인분석을 통하여 연관성있는 인자를 입력인자로 추가한 경우 향상된 결과값을 보였주었으며, 앙상블기법을 적용한 결과 정확도 면에서 큰 향상을 보여주었다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.497-497
• /
• 2018

복잡한 기상조건 하에서 강우의 예측은 수문 기상 분야에서 필수적인 과정이라 할 수 있다. 특히 월 단위의 강우 예측은 장기적인 수자원 관리 및 계획 수립 시 매우 중요한 기준이 되기 때문에 보다 정확하고 신뢰도 있는 예측을 필요로 하고 있다. 이를 위해 전 지구적 기후 변동의 양상을 수치화 하여 나타낼 수 있는 기상인자의 활용이 활발해지고 있으며 다양한 모형을 기반으로 한 강우 예측이 수행되고 있다. 최근에는 인공지능 기법을 활용한 인공신경망 모형의 적용이 활발해짐에 따라 높은 예측력을 바탕으로 강우 예측에 대한 연구가 이루어지고 있지만 초기 가중치의 무작위성 또는 과적합으로 인한 문제도 함께 나타나고 있다. 본 연구에서는 인공신경망 모형의 활용성을 높이고 신뢰성을 확보하기 위한 강우 예측을 수행하고자 하였다. 이를 위해 다양한 기상인자를 활용하여 인공신경망 모형을 위한 정보를 구축하고 인공신경망 모형을 통해 생성되는 결과로부터 단일 예측이 아닌 앙상블 예측을 활용함으로써 강우 앙상블을 생성하고 조합하였다. 그 결과 인공신경망 모형을 통한 단일 예측보다 앙상블을 통한 예측으로 안정적이고 정확한 예측 결과를 산정할 수 있었으며 기존에 인공신경망 모형을 통한 예측의 문제점을 보완할 수 있었다.

• Journal of Integrative Natural Science
• /
• v.11 no.4
• /
• pp.167-183
• /
• 2018

Electroencephalogram (EEG) recording provides a new way to support human-machine communication. It gives us an opportunity to analyze the neuro-dynamics of human cognition. Machine learning is a powerful for the EEG classification. In addition, machine learning can compensate for high variability of EEG when analyzing data in real time. However, the optimal EEG electrode location must be prioritized in order to extract the most relevant features from brain wave data. In this paper, we propose an intelligent system model for the extraction of EEG data by training the optimal electrode location of EEG in a specific problem. The proposed system is basically a fuzzy system and uses a neural network structurally. The fuzzy clustering method is used to determine the optimal number of fuzzy rules using the features extracted from the EEG data. The parameters and weight values found in the process of determining the number of rules determined here must be tuned for optimization in the learning process. Genetic algorithms are used to obtain optimized parameters. We present useful results by using optimal rule numbers and non - symmetric membership function using EEG data for four movements with the right arm through various experiments.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.213-216
• /
• 2018

본 논문에서는 사람의 인지 시각 특성 중 하나인 JND(Just Noticeable Difference)를 이용한 인지 비디오 부호화 기법을 제안한다. JND 기반 인지 부호화 방법은 사람의 인지 시각 특성을 이용해 시각적으로 인지가 잘 되지 않는 인지 신호를 제거함으로 부호화 효율을 높이는 방법이다. 제안된 방법은 기존 수학적 모델 기반의 JND 기법이 아닌 최근 각광 받고 있는 데이터 중심(data-driven) 모델링 방법인 심층 신경망 기반 JND 모델 생성 기법을 제안한다. 제안된 심층 신경망 기반 JND 모델은 비디오 부호화 과정에서 입력 영상에 대한 전처리를 통해 입력 영상의 인지 중복(perceptual redundancy)를 제거하는 역할을 수행한다. 부호화 실험에서 제안된 방법은 동일하거나 유사한 인지화질을 유지한 상태에서 평균 16.86 %의 부호화 비트를 감소 시켰다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.5
• /
• pp.289-295
• /
• 2021

Recently, owing to the development of autonomous vehicles, research on precisely determining the position of a moving object has been actively conducted. Previous research mainly used the fusion of GNSS/IMU (Global Positioning System / Inertial Navigation System) and sensors attached to the vehicle through a Kalman filter. However, in recent years, new technologies have been used to determine the location of a moving object owing to the improvement in computing power and the advent of deep learning. Various techniques using RNN (Recurrent Neural Network), LSTM (Long Short-Term Memory), and NARX (Nonlinear Auto-Regressive eXogenous model) exist for such learning-based positioning methods. The purpose of this study is to compare the precision of existing filter-based sensor fusion technology and the NARX-based method in case of GNSS signal blockages using simulation data. When the filter-based sensor integration technology was used, an average horizontal position error of 112.8 m occurred during 60 seconds of GNSS signal outages. The same experiment was performed 100 times using the NARX. Among them, an improvement in precision was confirmed in approximately 20% of the experimental results. The horizontal position accuracy was 22.65 m, which was confirmed to be better than that of the filter-based fusion technique.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2188-2203
• /
• 2021

With the rapid development of mobile Internet, smart phones have been widely popularized, among which Android platform dominates. Due to it is open source, malware on the Android platform is rampant. In order to improve the efficiency of malware detection, this paper proposes deep learning Android malicious detection system based on behavior features. First of all, the detection system adopts the static analysis method to extract different types of behavior features from Android applications, and extract sensitive behavior features through Term frequency-inverse Document Frequency algorithm for each extracted behavior feature to construct detection features through unified abstract expression. Secondly, Long Short-Term Memory neural network model is established to select and learn from the extracted attributes and the learned attributes are used to detect Android malicious applications, Analysis and further optimization of the application behavior parameters, so as to build a deep learning Android malicious detection method based on feature analysis. We use different types of features to evaluate our method and compare it with various machine learning-based methods. Study shows that it outperforms most existing machine learning based approaches and detects 95.31% of the malware.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.426-437
• /
• 2022

To understand the multilateral characteristics of human behavior and physiological markers related to physical, emotional, and environmental states, extensive lifelog data collection in a real-world environment is essential. Here, we propose a data collection method using multimodal mobile sensing and present a long-term dataset from 22 subjects and 616 days of experimental sessions. The dataset contains over 10 000 hours of data, including physiological, data such as photoplethysmography, electrodermal activity, and skin temperature in addition to the multivariate behavioral data. Furthermore, it consists of 10 372 user labels with emotional states and 590 days of sleep quality data. To demonstrate feasibility, human activity recognition was applied on the sensor data using a convolutional neural network-based deep learning model with 92.78% recognition accuracy. From the activity recognition result, we extracted the daily behavior pattern and discovered five representative models by applying spectral clustering. This demonstrates that the dataset contributed toward understanding human behavior using multimodal data accumulated throughout daily lives under natural conditions.

• Journal of Information Processing Systems
• /
• v.18 no.2
• /
• pp.245-257
• /
• 2022

In the Internet of Things (IoT) era, the types of devices used by one user are becoming more diverse and the number of devices is also increasing. However, a forensic investigator is restricted to exploit or collect all the user's devices; there are legal issues (e.g., privacy, jurisdiction) and technical issues (e.g., computing resources, the increase in storage capacity). Therefore, in the digital forensics field, it has been a challenge to acquire information that remains on the devices that could not be collected, by analyzing the seized devices. In this study, we focus on the fact that multiple devices share data through account synchronization of the online platform. We propose a novel way of identifying the user's interest through analyzing the remnants of targeted advertising which is provided based on the visited websites or search terms of logged-in users. We introduce a detailed methodology to pick out the targeted advertising from cache data and infer the user's interest using deep learning. In this process, an improved learning model considering the unique characteristics of advertisement is implemented. The experimental result demonstrates that the proposed method can effectively identify the user interest even though only one device is examined.

• Structural Engineering and Mechanics
• /
• v.83 no.1
• /
• pp.79-92
• /
• 2022

In this paper, the impact of a vernacular pozzolanic kaolinite mine on concrete alkali-silica reaction and strength has been evaluated. For making the samples, kaolinite powder with various levels has been used in the quality specification test of aggregates based on the ASTM C1260 standard in order to investigate the effect of kaolinite particles on reducing the reaction of the mortar bars. The compressive strength, X-Ray Diffraction (XRD) and Scanning Electron Microscope (SEM) experiments have been performed on concrete specimens. The obtained results show that addition of kaolinite powder to concrete will cause a pozzolanic reaction and decrease the permeability of concrete samples comparing to the reference concrete specimen. Further, various machine learning methods have been used to predict ASR-induced expansion per different amounts of kaolinite. In the process of modeling methods, optimal method is considered to have the lowest mean square error (MSE) simultaneous to having the highest correlation coefficient (R). Therefore, to evaluate the efficiency of the proposed model, the results of the support vector machine (SVM) method were compared with the decision tree method, regression analysis and neural network algorithm. The results of comparison of forecasting tools showed that support vector machines have outperformed the results of other methods. Therefore, the support vector machine method can be mentioned as an effective approach to predict ASR-induced expansion.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.18-25
• /
• 2022

Neuromorphic computing generally shows significantly better power, area, and speed performance than neural network computation using CPU and GPU. These characteristics are suitable for resource-constrained IoT environments where energy consumption is important. However, there is a problem in that it is necessary to modify the source code for environment setting and application operation according to heterogeneous IoT devices that support neuromorphic computing. To solve these problems, NAAL was proposed and implemented in this paper. NAAL provides functions necessary for IoT device control and neuromorphic architecture abstraction and inference model operation in various heterogeneous IoT device environments based on common APIs of NAAL. NAAL has the advantage of enabling additional support for new heterogeneous IoT devices and neuromorphic architectures and computing devices in the future.