• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.573-580
• /
• 2005

In this paper, we propose an emotion recognition using static and dynamic facial images to effectively design human interface. The proposed method is constructed by HMM(Hidden Markov Model), PCA(Principal Component) and wavelet transform. Facial database consists of six basic human emotions including happiness, sadness, anger, surprise, fear and dislike which have been known as common emotions regardless of nation and culture. Emotion recognition in the static images is performed by using the discrete wavelet. Here, the feature vectors are extracted by using PCA. Emotion recognition in the dynamic images is performed by using the wavelet transform and PCA. And then, those are modeled by the HMM. Finally, we obtained better performance result from merging the recognition results for the static images and dynamic images.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.421-426
• /
• 2019

In this paper, we propose a method to visualize the geometric features of the contact region between proteins in a protein complex. When proteins or ligands are represented as curved surfaces with irregularities, the property that the two surfaces contact each other without intersections is called shape compatibility. Protein-Protein or Protein-Ligand docking researches have shown that shape complementarity, chemical properties, and entropy play an important role in finding contact regions. Usually, after finding a region with high shape complementarity, we can predict the contact region by using residual polarity and hydrophobicity of amino acids belonging to this region. In the research for predicting the contact region, it is necessary to investigate the geometrical features of the contact region in known protein complexes. For this purpose, it is essential to visualize the geometric features of the molecular surface. In this paper, we propose a method to find the contact region, and visualize the geometric features of it as normal vectors and mean curvatures of the protein complex.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.2
• /
• pp.58-65
• /
• 2021

Meta-heuristic algorithms have been developed to efficiently solve difficult problems and obtain a global optimal solution. A common feature mimics phenomenon occurring in nature and reliably improves the solution through repetition. And at the same time, the probability is used to deviate from the regional optimal solution and approach the global optimal solution. This study compares the algorithm created based on the above common points with existed SA and HS to show advantages in time and accuracy of results. Existing algorithms have problems of low accuracy, high memory, long runtime, and ignorance. In a two-variable polynomial, the existing algorithms show that the memory increases and the accuracy decrease. In order to improve the accuracy, the new algorithm increases the number of initial inputs and increases the efficiency of the search by introducing a direction using vectors. And, in order to solve the optimization problem, the results of the last experiment were learned to show the learning effect in the next experiment. The new algorithm found a solution in a short time under the experimental conditions of long iteration counts using a two-variable polynomial and showed high accuracy. And, it shows that the learning effect is effective in repeated experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.11
• /
• pp.1505-1511
• /
• 2021

Pretrained models with high performance in various tasks within natural language processing have the advantage of learning the linguistic patterns of sentences using large corpus during the training, allowing each token in the input sentence to be represented with appropriate feature vectors. One of the methods of constructing a corpus required for a pre-trained model training is a collection method using web crawler. However, sentences that exist on web may contain unnecessary words in some or all of the sentences because they have various patterns. In this paper, we propose a dataset construction method for filtering sentences containing unnecessary words using neural network models for corpus collected from the web. As a result, we construct a dataset containing a total of 2,330 sentences. We also evaluated the performance of neural network models on the constructed dataset, and the BERT model showed the highest performance with an accuracy of 93.75%.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.742-745
• /
• 2022

In this paper, we propose a hybrid image processing and deep learning-based method for detecting the presence of power lines in infrared images. Deep learning-based methods can learn feature vectors from a large number of data without much effort, resulting in outstanding performances in various fields. However, it is difficult to apply human intuition to the deep learning-based methods while image processing techniques can be used to apply human intuition. Based on these, we propose a method that exploits both advantages to detect the existence of power lines in infrared images. To this end, five methods have been applied and compared to find the most effective image processing technique for detecting the presence of power lines. As a result, the proposed method achieves 99.48% of accuracy which is higher than those of methods based on either image processing or deep learning.

• KNOM Review
• /
• v.24 no.2
• /
• pp.24-34
• /
• 2021

Service providers using edge computing provide a high level of service. As a result, devices store important information in inner storage and have become a target of the latest cyberattacks, which are more difficult to detect. Although experts use a security system such as intrusion detection systems, the existing intrusion systems have low detection accuracy. Therefore, in this paper, we proposed a machine learning model for more accurate intrusion detections of devices in edge computing. The proposed model is a hybrid model that combines a stacked sparse autoencoder (SSAE) and a convolutional neural network (CNN) to extract important feature vectors from the input data using sparsity constraints. To find the optimal model, we compared and analyzed the performance as adjusting the sparsity coefficient of SSAE. As a result, the model showed the highest accuracy as a 96.9% using the sparsity constraints. Therefore, the model showed the highest performance when model trains only important features.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.817-826
• /
• 2022

AI technology is being successfully introduced in many fields, and models deployed as a service are deployed with black box environment that does not expose the model's information to protect intellectual property rights and data. In a black box environment, attackers try to steal data or parameters used during training by using model output. This paper proposes a method of inferring the type of model to directly find out the composition of layer of the target model, based on the fact that there is no attack to infer the information about the type of model from the deep learning model. With ResNet, VGGNet, AlexNet, and simple convolutional neural network models trained with MNIST datasets, we show that the types of models can be inferred using the output values in the gray box and black box environments of the each model. In addition, we inferred the type of model with approximately 83% accuracy in the black box environment if we train the big and small relationship feature that proposed in this paper together, the results show that the model type can be infrerred even in situations where only partial information is given to attackers, not raw probability vectors.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.219-232
• /
• 2023

Mobility services need to change according to the regional characteristics of the target service area. Accordingly, analysis of mobility patterns and characteristics based on Origin-Destination (OD) data that reflect travel behaviors in the target service area is required. However, since conventional methods construct the OD data obtained from the administrative district-based zone system, it is hard to ensure spatial homogeneity. Hence, there are limitations in analyzing the inherent travel patterns of each mobility service, particularly for new mobility service like Demand Responsive Transit (DRT). Unlike the conventional approach, this study applies a data-driven clustering technique to conduct spatial analyses on OD travel patterns of regional mobility services based on reconstructed OD data derived from re-aggregation for original OD distributions. Based on the reconstructed OD data that contains information on the inherent feature vectors of the original OD data, the proposed method enables analysis of the spatial characteristics of regional mobility services, including public transit bus, taxi and DRT.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2
• /
• pp.88-95
• /
• 2006

In this Paper. a method for improving the performance of automatic speech recognition (ASR) system for conversational speech is proposed. which mainly focuses on increasing the robustness against the rapidly speaking utterances. The proposed method doesn't require an additional speech recognition task to represent speaking rate quantitatively. Energy distribution for special bands is employed to detect the vowel regions, the number of vowels Per unit second is then computed as speaking rate. To improve the Performance for fast speech. in the pervious methods. a sequence of the feature vectors is expanded by a given scaling factor, which is computed by a ratio between the standard phoneme duration and the measured one. However, in the method proposed herein. utterances are classified by their speaking rates. and the scaling factor is determined individually for each class. In this procedure, a maximum likelihood criterion is employed. By the results from the ASR experiments devised for the 10-digits mobile phone number. it is confirmed that the overall error rate was reduced by $17.8\%$ when the proposed method is employed

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.8
• /
• pp.390-396
• /
• 2007

In this letter, we propose a novel approach to improve the performance of speech/music classification for the selectable mode vocoder(SMV) of 3GPP2 using the Gaussian mixture model(GMM) which is based on the expectation-maximization(EM) algorithm. We first present an effective analysis of the features and the classification method adopted in the conventional SMV. And then feature vectors which are applied to the GMM are selected from relevant Parameters of the SMV for the efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme of the SMV.