• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.309-316
• /
• 2018

Objectives: Both the valence and arousal components of affect are important considerations when managing mental healthcare because they are associated with affective and physiological responses. Research on arousal and valence analysis, which uses images, texts, and physiological signals that employ deep learning, is actively underway; research investigating how to improve the recognition rate is needed. The goal of this research was to design a deep learning framework and model to classify arousal and valence, indicating positive and negative degrees of emotion as high or low. Methods: The proposed arousal and valence classification model to analyze the affective state was tested using data from 40 channels provided by a dataset for emotion analysis using electrocardiography (EEG), physiological, and video signals (the DEAP dataset). Experiments were based on 10 selected featured central and peripheral nervous system data points, using long short-term memory (LSTM) as a deep learning method. Results: The arousal and valence were classified and visualized on a two-dimensional coordinate plane. Profiles were designed depending on the number of hidden layers, nodes, and hyperparameters according to the error rate. The experimental results show an arousal and valence classification model accuracy of 74.65 and 78%, respectively. The proposed model performed better than previous other models. Conclusions: The proposed model appears to be effective in analyzing arousal and valence; specifically, it is expected that affective analysis using physiological signals based on LSTM will be possible without manual feature extraction. In a future study, the classification model will be adopted in mental healthcare management systems.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.10
• /
• pp.437-446
• /
• 2022

Text classification task from Natural Language Processing (NLP) combined with state-of-the-art (SOTA) Machine Learning (ML) and Deep Learning (DL) algorithms as the core engine is widely used to detect and classify voice phishing call transcripts. While numerous studies on the classification of voice phishing call transcripts are being conducted and demonstrated good performances, with the increase of non-face-to-face financial transactions, there is still the need for improvement using the latest NLP technologies. This paper conducts a benchmarking of Korean voice phishing detection performances of the pre-trained Korean language model KoBERT, against multiple other SOTA algorithms based on the classification of related transcripts from the labeled Korean voice phishing dataset called KorCCVi. The results of the experiments reveal that the classification accuracy on a test set of the KoBERT model outperforms the performances of all other models with an accuracy score of 99.60%.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.39-47
• /
• 2023

The development of autonomous driving and Advanced Driver Assistance System (ADAS) technology has grown rapidly in recent years. As most traffic accidents occur due to human error, self-driving vehicles can drastically reduce the number of accidents and crashes that occur on the roads today. Obviously, technical advancements in autonomous driving can lead to improved public driving safety. However, due to the current limitations in technology and lack of public trust in self-driving cars (and drones), the actual use of Autonomous Vehicles (AVs) is still significantly low. According to prior studies, people's acceptance of an AV is mainly determined by trust. It is proven that people still feel much more comfortable in personalized ADAS, designed with the way people drive. Based on such needs, a new attempt for a customized ADAS considering each driver's driving style is proposed in this paper. Each driver's behavior is divided into two categories: assertive and defensive. In this paper, a novel customized ADAS algorithm with high classification accuracy is designed, which divides each driver based on their driving style. Each driver's driving data is collected and simulated using CARLA, which is an open-source autonomous driving simulator. In addition, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) machine learning algorithms are used to optimize the ADAS parameters. The proposed scheme results in a high classification accuracy of time series driving data. Furthermore, among the vast amount of CARLA-based feature data extracted from the drivers, distinguishable driving features are collected selectively using Support Vector Machine (SVM) technology by comparing the amount of influence on the classification of the two categories. Therefore, by extracting distinguishable features and eliminating outliers using SVM, the classification accuracy is significantly improved. Based on this classification, the ADAS sensors can be made more sensitive for the case of assertive drivers, enabling more advanced driving safety support. The proposed technology of this paper is especially important because currently, the state-of-the-art level of autonomous driving is at level 3 (based on the SAE International driving automation standards), which requires advanced functions that can assist drivers using ADAS technology.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.19 no.2
• /
• pp.101-110
• /
• 2013

In order to classify the trophic state and environmental quality of marine coastal system, an approach using the characteristics and biochemical composition in the sediments can be available. This research, including 25 coastal bay, belong to 131 stations, was carried out along the south coasts of Korea in February 2007. Type of sediment, total ogranic carbon, total nitrogen, phytopigments and biochemical composition(proteins, lipids, carbohydrates) were analyzed. Result from Multi-dimensional Scaling(MDS) ordination indicates that four group can be identified. The result of ANOVA with tukey test shows that the concentrations of proteins, carbohydrates and biopolymeric carbon were significantly different to four groups. We propose the trophic state classification for these groups using the biochemical composition of sediment organic matter. I group(Masan, Jinhae, Haengam) has been defined as hypertrophic state, II group(Tongyeong, Goseong；Jaran, Geoje et al.), as eutrophic; III group(Gamak, Deungnyang, Yeoja et al.), as mesotrophic and IV group(Sinan, Jindo, Muan), as oligotrophic. On the basis of results reported in this study, the biochemical composition of sediment organic matter could be considered an useful and sensitive tool for the classification of the trophic state of marine coastal systems.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.6 no.3
• /
• pp.213-225
• /
• 2004

The number of tunnels are in fact increasing as a part of linear improvement project of general national highway and road enlargement and pavement project. Recently, collapses of portal slope are also occurring considerably, due to local raining from severe rain storm and abnormal weather. Accordingly, it was risen a necessity to efficiently respond to tunnel portal slope damage and maintenance in Korea and oversea nations. This paper is a basic proposal to execute a survey on the current status and state of the tunnel portal slopes that were already installed and are now being operated along general national highways, and also to execute state evaluation for the purpose of managing those effectively. As a research method, domestic tunnels were analyzed in accordance with geometrical shape such as access type, portal form, and tunnel type, etc. via field survey to analyze the types of tunnel portal slopes along national highways. State evaluation classification sheet is presented to divide classes for the danger state of the surveyed portal slopes, and then the related grades are divided. It is mainly aimed at classifying the tunnel portal slope along national highways with using this state evaluation, to use it as basic data so that continuous maintenance can be executed in the future in accordance with danger classes.

• Korean Journal of Remote Sensing
• /
• v.34 no.5
• /
• pp.811-827
• /
• 2018

The purpose of this study is to compare machine learning algorithm and deep learning algorithm in crop classification using multi-temporal remote sensing data. For this, impacts of machine learning and deep learning algorithms on (a) hyper-parameter and (2) training sample size were compared and analyzed for Haenam-gun, Korea and Illinois State, USA. In the comparison experiment, support vector machine (SVM) was applied as machine learning algorithm and convolutional neural network (CNN) was applied as deep learning algorithm. In particular, 2D-CNN considering 2-dimensional spatial information and 3D-CNN with extended time dimension from 2D-CNN were applied as CNN. As a result of the experiment, it was found that the hyper-parameter values of CNN, considering various hyper-parameter, defined in the two study areas were similar compared with SVM. Based on this result, although it takes much time to optimize the model in CNN, it is considered that it is possible to apply transfer learning that can extend optimized CNN model to other regions. Then, in the experiment results with various training sample size, the impact of that on CNN was larger than SVM. In particular, this impact was exaggerated in Illinois State with heterogeneous spatial patterns. In addition, the lowest classification performance of 3D-CNN was presented in Illinois State, which is considered to be due to over-fitting as complexity of the model. That is, the classification performance was relatively degraded due to heterogeneous patterns and noise effect of input data, although the training accuracy of 3D-CNN model was high. This result simply that a proper classification algorithms should be selected considering spatial characteristics of study areas. Also, a large amount of training samples is necessary to guarantee higher classification performance in CNN, particularly in 3D-CNN.

• 한국신재생에너지학회:학술대회논문집
• /
• 2009.06a
• /
• pp.554-556
• /
• 2009

Wind classification for exact estimation of wind energy resources was carried out using numerically simulated wind data for three years. The MM5(a fifth-generation Mesoscale Model), developed at Penn State University and the National Center for Atmospheric Research (NCAR), was used to estimate the wind fields in this study. We also use a variant of the K-mean clustering to classify the wind district and define the relation between districts. Wind estimated at surface and 100 m high at Busan area is classified into the 10 and 7 classes, respectively. These discrepancies of wind districts pattern at surface and upper air meteorological data indicates the quantity of wind resources can be changed according to the level of wind data used in estimation. Therefore, the estimation of wind district classification by reasonable wind data is utilized to build the effective policy for wind energy dissemination.

• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2580-2582
• /
• 2004

In this paper, a Neural Network(NN) based approach for classification of two dimensions images. The proposed algorithm is able to apply in the actual industry. The described diagnostic algorithm is presented to defect surface failures on tiles. A way to get data for a digital image process is several kinds of it. The tiles are scanned and the digital images are preprocessed and classified using neural networks. It is important to reduce the amount of input data with problem specific preprocessing. The auto-associative neural network is used for feature generation and selection while the probabilistic neural network is used for classification. The proposed algorithm is evaluated experimentally using one hundred of the real tile images. Sample image data to preprocess have histogram. The histogram is used as input value of probabilistic neural network. Auto-associative neural network compress input data and compressed data is classified using probabilistic neural network. Classified sample images are determined by human state. So it is intervened human subjectivity. But digital image processing and neural network are better than human classification ability. Therefore it is very useful of quality control improvement.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1125-1129
• /
• 2017

LSTM(Long Short-term Memory) is a kind of RNN(Recurrent Neural Network) in which a next-state is updated by remembering the previous states. The information of calling a sequence in a malware can be defined as system call function that is called at each time. In this paper, we use calling sequences of system calls in malware codes as input for malware classification to utilize the feature remembering previous states via LSTM. We run an experiment to show that our method can classify malware and measure accuracy by changing the length of system call sequences.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.14 no.1
• /
• pp.63-78
• /
• 2016

To meet nuclear regulatory requirements, more than 95% individual radionuclides in the low- and intermediate-level radioactive waste inventory have to be identified. In this study, the radionuclide inventory has been estimated by taking the long-term radioactive waste generation, the development plan of disposal facility, and the new radioactive waste classification into account. The state of radioactive waste cumulated from 2014 was analyzed for various radioactive sources and future prospects for predicting the long-term radioactive waste generation. The predicted radionuclide inventory results are expected to contribute to secure the development of waste disposal facility and to deploy the safety case for its long-term safety assessment.