• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3836-3854
• /
• 2022

The student group division is benefit for universities to do the student management based on the group profile. With the widespread use of student smart cards on campus, especially where students living in campus residence halls, students' daily activities on campus are recorded with information such as smart card swiping time and location. Therefore, it is feasible to depict the students with the daily activity data and accordingly group students based on objective measuring from their campus behavior with some regular student attributions collected in the management system. However, it is challenge in feature representation due to diverse forms of the student data. To effectively and comprehensively represent students' behaviors for further student group division, we proposed to adopt activity data from student smart cards and student attributes as input data with taking account of activity and attribution relationship types from different perspective. Specially, we propose a novel student group division method based on a multi-view student attribute heterogeneous information network (MSA-HIN). The network nodes in our proposed MSA-HIN represent students with their multi-dimensional attribute information. Meanwhile, the edges are constructed to characterize student different relationships, such as co-major, co-occurrence, and co-borrowing books. Based on the MSA-HIN, embedded representations of students are learned and a deep graph cluster algorithm is applied to divide students into groups. Comparative experiments have been done on a real-life campus dataset collected from a university. The experimental results demonstrate that our method can effectively reveal the variability of student attributes and relationships and accordingly achieves the best clustering results for group division.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.8
• /
• pp.243-252
• /
• 2023

Satellite imageries are at a greatest importance for land cover examining. Numerous studies have been conducted with satellite images and uses semantic segmentation techniques to extract information which has higher altitude viewpoint. The device which is taking these images must employee wireless communication links to send them to receiving ground stations. Wireless communications from a satellite are inevitably affected due to transmission errors. Evidently images which are being transmitted are distorted because of the information loss. Current semantic segmentation techniques are not made for segmenting distorted images. Traditional image enhancement methods have their own limitations when they are used for satellite images enhancement. This paper proposes an auto-encoder based image pre-enhancing method for satellite images. As a distorted satellite images dataset, images received from a real radio transmitter were used. Training process of the proposed auto-encoder was done by letting it learn to produce a proper approximation of the source image which was sent by the image transmitter. Unlike traditional image enhancing methods, the proposed method was able to provide more applicable image to a segmentation model. Results showed that by using the proposed pre-enhancing technique, segmentation results have been greatly improved. Enhancements made to the aerial images are contributed the correct assessment of land resources.

• Dementia and Neurocognitive Disorders
• /
• v.23 no.1
• /
• pp.1-10
• /
• 2024

Background and Purpose: Voice, reflecting cerebral functions, holds potential for analyzing and understanding brain function, especially in the context of cognitive impairment (CI) and Alzheimer's disease (AD). This study used voice data to distinguish between normal cognition and CI or Alzheimer's disease dementia (ADD). Methods: This study enrolled 3 groups of subjects: 1) 52 subjects with subjective cognitive decline; 2) 110 subjects with mild CI; and 3) 59 subjects with ADD. Voice features were extracted using Mel-frequency cepstral coefficients and Chroma. Results: A deep neural network (DNN) model showed promising performance, with an accuracy of roughly 81% in 10 trials in predicting ADD, which increased to an average value of about 82.0%±1.6% when evaluated against unseen test dataset. Conclusions: Although results did not demonstrate the level of accuracy necessary for a definitive clinical tool, they provided a compelling proof-of-concept for the potential use of voice data in cognitive status assessment. DNN algorithms using voice offer a promising approach to early detection of AD. They could improve the accuracy and accessibility of diagnosis, ultimately leading to better outcomes for patients.

• Korean Journal of Remote Sensing
• /
• v.34 no.6_3
• /
• pp.1415-1425
• /
• 2018

Kompsat-5 is the first Earth Observation Satellite which is equipped with an SAR in Korea. SAR images are generated by receiving signals reflected from an object by microwaves emitted from a SAR antenna. Because the wavelengths of microwaves are longer than the size of particles in the atmosphere, it can penetrate clouds and fog, and high-resolution images can be obtained without distinction between day and night. However, there is no color information in SAR images. To overcome these limitations of SAR images, colorization of SAR images using Cycle GAN, a deep learning model developed for domain translation, was conducted. Training of Cycle GAN is unstable due to the unsupervised learning based on unpaired dataset. Therefore, we proposed MS Cycle GAN applying multi-scale discriminator to solve the training instability of Cycle GAN and to improve the performance of colorization in this paper. To compare colorization performance of MS Cycle GAN and Cycle GAN, generated images by both models were compared qualitatively and quantitatively. Training Cycle GAN with multi-scale discriminator shows the losses of generators and discriminators are significantly reduced compared to the conventional Cycle GAN, and we identified that generated images by MS Cycle GAN are well-matched with the characteristics of regions such as leaves, rivers, and land.

• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.23-30
• /
• 2021

This paper proposes a noise-tolerant image classification system using multiple autoencoders. The development of deep learning technology has dramatically improved the performance of image classifiers. However, if the images are contaminated by noise, the performance degrades rapidly. Noise added to the image is inevitably generated in the process of obtaining and transmitting the image. Therefore, in order to use the classifier in a real environment, we have to deal with the noise. On the other hand, the autoencoder is an artificial neural network model that is trained to have similar input and output values. If the input data is similar to the training data, the error between the input data and output data of the autoencoder will be small. However, if the input data is not similar to the training data, the error will be large. The proposed system uses the relationship between the input data and the output data of the autoencoder, and it has two phases to classify the images. In the first phase, the classes with the highest likelihood of classification are selected and subject to the procedure again in the second phase. For the performance analysis of the proposed system, classification accuracy was tested on a Gaussian noise-contaminated MNIST dataset. As a result of the experiment, it was confirmed that the proposed system in the noisy environment has higher accuracy than the CNN-based classification technique.

• International journal of advanced smart convergence
• /
• v.11 no.1
• /
• pp.19-27
• /
• 2022

Across the world, 'housing' comprises a significant portion of wealth and assets. For this reason, fluctuations in real estate prices are highly sensitive issues to individual households. In Korea, housing prices have steadily increased over the years, and thus many Koreans view the real estate market as an effective channel for their investments. However, if one purchases a real estate property for the purpose of investing, then there are several risks involved when prices begin to fluctuate. The purpose of this study is to design a real estate price 'return rate' prediction model to help mitigate the risks involved with real estate investments and promote reasonable real estate purchases. Various approaches are explored to develop a model capable of predicting real estate prices based on an understanding of the immovability of the real estate market. This study employs the LSTM method, which is based on artificial intelligence and deep learning, to predict real estate prices and validate the model. LSTM networks are based on recurrent neural networks (RNN) but add cell states (which act as a type of conveyer belt) to the hidden states. LSTM networks are able to obtain cell states and hidden states in a recursive manner. Data on the actual trading prices of apartments in autonomous districts between January 2006 and December 2019 are collected from the Actual Trading Price Disclosure System of the Ministry of Land, Infrastructure and Transport (MOLIT). Additionally, basic data on apartments and commercial buildings are collected from the Public Data Portal and Seoul Metropolitan Government's data portal. The collected actual trading price data are scaled to monthly average trading amounts, and each data entry is pre-processed according to address to produce 168 data entries. An LSTM model for return rate prediction is prepared based on a time series dataset where the training period is set as April 2015~August 2017 (29 months), the validation period is set as September 2017~September 2018 (13 months), and the test period is set as December 2018~December 2019 (13 months). The results of the return rate prediction study are as follows. First, the model achieved a prediction similarity level of almost 76%. After collecting time series data and preparing the final prediction model, it was confirmed that 76% of models could be achieved. All in all, the results demonstrate the reliability of the LSTM-based model for return rate prediction.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.52 no.2
• /
• pp.39-50
• /
• 2024

Color is an essential visual element that has a significant impact on the formation of a city's image and people's perceptions. Quantitative analysis of color in urban environments is a complex process that has been difficult to implement in the past. However, with recent rapid advances in Machine Learning, it has become possible to analyze city colors using photos shared by tourists. This study selected Dali City, a popular tourist destination in China, as a case study. Photos of Dali City shared by tourists were collected, and a method to measure large-scale city colors was explored by combining machine learning techniques. Specifically, the DeepLabv3+ model was first applied to perform a semantic segmentation of tourist sharing photos based on the ADE20k dataset, thereby separating artificial elements in the photos. Next, the K-means clustering algorithm was used to extract colors from the artificial elements in Dali City, and an adjacency matrix was constructed to analyze the correlations between the dominant colors. The research results indicate that the main color of the artificial elements in Dali City has the highest percentage of orange-grey. Furthermore, gray tones are often used in combination with other colors. The results indicated that local ethnic and Buddhist cultures influence the color characteristics of artificial elements in Dali City. This research provides a new method of color analysis, and the results not only help Dali City to shape an urban color image that meets the expectations of tourists but also provide reference materials for future urban color planning in Dali City.

• Journal of Distribution Science
• /
• v.18 no.1
• /
• pp.15-26
• /
• 2020

Purpose: This study is to analyze the image classification using Convolution Neural Network and Transfer Learning for Jeju Island and to suggest related implications. As the biggest tourist destination in Korea, Jeju Island encounters environmental issues frequently caused by marine debris along the seaside. The ever-increasing volume of plastic waste requires multidirectional management and protection. Research design, data and methodology: In this study, the deep learning CNN algorithm was used to train a number of images from Jeju clean and polluted beaches. In the process of validating and testing pre-processed images, we attempted to explore their applicability to coastal tourism applications through probabilities of classifying images and predicting clean shores. Results: We transformed and augmented 194 small image dataset into 3,880 image data. The results of the pre-trained test set were 85%, 70% and 86%, and then its accuracy has increased through the process. We finally obtained a rapid convergence of 97.73% and 100% (20/20) in the actual training and validation sets. Conclusions: The tested algorithms are expected to implement in applications for tourism service distribution aimed at reducing coastal waste or in CCTVs as a detector or indicator for residents and tourists to protect clean beaches on Jeju Island.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.1
• /
• pp.9-16
• /
• 2020

The k-anonymity scheme has been widely used to protect private information when Big Data are distributed to a third party for research purposes. When the scheme is applied, an optimal k value determination is one of difficult problems to be resolved because many factors should be considered. Currently, the determination has been done almost manually by human experts with their intuition. This leads to degrade performance of the anonymization, and it takes much time and cost for them to do a task. To overcome this problem, a simple idea has been proposed that is based on machine learning. This paper describes implementations and experiments to realize the proposed idea. In thi work, a deep neural network (DNN) is implemented using tensorflow libraries, and it is trained and tested using input dataset. The experiment results show that a trend of training errors follows a typical pattern in DNN, but for validation errors, our model represents a different pattern from one shown in typical training process. The advantage of the proposed approach is that it can reduce time and cost for experts to determine k value because it can be done semi-automatically.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.