• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.505-518
• /
• 2023

3D point cloud semantic segmentation is a computer vision task that involves dividing the point cloud into different objects and regions by predicting the class label of each point. Existing 3D semantic segmentation models have some limitations in performing sufficient fusion of multi-modal features while ensuring both characteristics of 2D visual features extracted from RGB images and 3D geometric features extracted from point cloud. Therefore, in this paper, we propose MMCA-Net, a novel 3D semantic segmentation model using 2D-3D multi-modal features. The proposed model effectively fuses two heterogeneous 2D visual features and 3D geometric features by using an intermediate fusion strategy and a multi-modal cross attention-based fusion operation. Also, the proposed model extracts context-rich 3D geometric features from input point cloud consisting of irregularly distributed points by adopting PTv2 as 3D geometric encoder. In this paper, we conducted both quantitative and qualitative experiments with the benchmark dataset, ScanNetv2 in order to analyze the performance of the proposed model. In terms of the metric mIoU, the proposed model showed a 9.2% performance improvement over the PTv2 model using only 3D geometric features, and a 12.12% performance improvement over the MVPNet model using 2D-3D multi-modal features. As a result, we proved the effectiveness and usefulness of the proposed model.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.18 no.1
• /
• pp.47-65
• /
• 2023

As stakeholder demands and sustainable finance grow, ESG management and ESG evaluation are becoming important. SMEs should also prepare for the trends of ESG rating practices that affects supply chain management and financial transactions. However, SMEs have no choice but to focus on survival first, so there are restrictions on putting into ESG management. In addition, there is a lack of research on the legitimacy of ESG management by SMEs, and volatility in ESG evaluation systems and rating grades is also increasing. Accordingly, it is necessary to review ESG evaluation trends and practical guidelines along with the review of previous studies. As a result of the exploratory study, SMEs need to implement ESG management and make efforts to specialize in ESG related new businesses under conditions in which their survival base is guaranteed in terms of implementation strategies. In addition, it is necessary to focus on the strategic use of various evaluation results along with accumulating information favorable for ESG evaluation through organizational learning and software management. The implications of this study are that various studies such as the classification criteria for SMEs and the relationship between ESG evaluation grades and long-term survival rates are needed in ESG evaluation of SMEs. At the government policy level, it is time to consider the ESG evaluation system exclusively for SMEs so that ESG management can be implemented and ESG evaluation at different levels by industry and size.

• Information Systems Review
• /
• v.23 no.1
• /
• pp.1-22
• /
• 2021

This study aims to analyze online game user's game items transacting behaviors for the two game genres such as MMORPG and sports game. For the sake of conducting the analysis, we adopted a fuzzy logic agent-based modeling. In the online game fields, game items transactions are crucial to game company's profitability. However, there are lack of previous studies investigating the online game user's game items transacting activities. Since many factors need to be addressed in a complicated way, ABM (agent-based modeling) simulation mechanism is adopted. Besides, a fuzzy logic is also considered due to the fact that a number of uncertainties and ambiguities exist with respect to online game user's complex behaviors in transacting game items. Simulation results from applying the fuzzy logic ABM method revealed that MMORPG game users are motivated to pay expensive price for high-performance game items, while sports game users tend to transact game items within a reasonable price range. We could conclude that the proposed fuzzy logic ABM simulation mechanism proved to be very useful in organizing an effective strategy for online game items management and customers retention.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.284-290
• /
• 2024

Speech emotion recognition (SER) is a technique that is used to analyze the speaker's voice patterns, including vibration, intensity, and tone, to determine their emotional state. There has been an increase in interest in artificial intelligence (AI) techniques, which are now widely used in medicine, education, industry, and the military. Nevertheless, existing researchers have attained impressive results by utilizing acted-out speech from skilled actors in a controlled environment for various scenarios. In particular, there is a mismatch between acted and spontaneous speech since acted speech includes more explicit emotional expressions than spontaneous speech. For this reason, spontaneous speech-emotion recognition remains a challenging task. This paper aims to conduct emotion recognition and improve performance using spontaneous speech data. To this end, we implement deep learning-based speech emotion recognition using the VGG (Visual Geometry Group) after converting 1-dimensional audio signals into a 2-dimensional spectrogram image. The experimental evaluations are performed on the Korean spontaneous emotional speech database from AI-Hub, consisting of 7 emotions, i.e., joy, love, anger, fear, sadness, surprise, and neutral. As a result, we achieved an average accuracy of 83.5% and 73.0% for adults and young people using a time-frequency 2-dimension spectrogram, respectively. In conclusion, our findings demonstrated that the suggested framework outperformed current state-of-the-art techniques for spontaneous speech and showed a promising performance despite the difficulty in quantifying spontaneous speech emotional expression.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.243-250
• /
• 2024

Biomimetic robots, which emulate characteristics of biological entities such as birds or insects, have the potential to offer a tactical advantage in surveillance and reconnaissance in future battlefields. To effectively utilize these robots, it is essential to develop technologies that emulate the wing flapping of birds or the movements of cockroaches. However, this effort is complicated by the challenges associated with securing the necessary hardware and the complexities involved in software development and validation processes. In this paper, we presents the design and implementation of a multi-HILS based biomimic robot software validation testbed using modeling and simulation (M&S). By employing this testbed, developers can overcome the absence of hardware, simulate future battlefield scenarios, and conduct software development and testing. However, the multi-HILS based testbed may experience inter-device communication delays as the number of test robots increases, significantly affecting the reliability of simulation results. To address this issue, we propose the data distribution service priority (DDSP), a priority-based middleware. DDSP demonstrates an average delay reduction of 1.95 ms compared to the existing DDS, ensuring the required data transmission quality for the testbed.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.260-268
• /
• 2024

Cervical cancer is the fourth most common cancer in women worldwide, and more than 604,000 new cases were reported in 2020 alone, resulting in approximately 341,831 deaths. The Cox regression model is a major model widely adopted in cancer research, but considering the existence of nonlinear associations, it faces limitations due to linear assumptions. To address this problem, this paper proposes ResSurvNet, a new model that improves the accuracy of cervical cancer mortality prediction using ResNet's residual learning framework. This model showed accuracy that outperforms the DNN, CPH, CoxLasso, Cox Gradient Boost, and RSF models compared in this study. As this model showed accuracy that outperformed the DNN, CPH, CoxLasso, Cox Gradient Boost, and RSF models compared in this study, this excellent predictive performance demonstrates great value in early diagnosis and treatment strategy establishment in the management of cervical cancer patients and represents significant progress in the field of survival analysis.

• Journal of Service Research and Studies
• /
• v.14 no.2
• /
• pp.69-81
• /
• 2024

The The purpose of this study is to have a positive impact on the evaluation of the traditional market revitalization project by discussing the business details and implementation process of the commercial district revitalization project in depth. The research method uses practical methods for traditional market revitalization projects. First, the activation method of the place was examined through the concepts of Oldenburg's 'Third Place' and Carr et al.'s 'Five Demands for Public Space' and the theories related to non-face-to-face transactions were examined. The first study case was the commercial district revitalization project of the Cheongju Global Market Development Project(Seongan-gil Street Shopping Mall and Yukgeori traditional Market), which discussed revitalization of open space, revitalization through reproduction, and revitalization through festivals. The revitalization project through representation is a project to install a symbolic sculpture at the estimated location of the 'Namseokgyo' buried in Yukgeori traditional Market. The revitalization through the festival is the Korea Sale Festa, which is a vibrant business due to increased sales at traditional markets and shopping malls and floating population in open spaces. The second study case was the Cultural Tourism Promotion Project(Hanmin traditional Market), which discussed revitalization through the development of local brands and SNS content. In the conclusion, the relationship between the six projects and commercial district revitalization methods was discussed, and policy recommendations were made, mentioning the importance of reflecting regional characteristics in design planning. We hope that this study will be used to positively evaluate the traditional market revitalization project, showing that stakeholders are working hard to produce positive results within institutional limitations.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.6
• /
• pp.269-277
• /
• 2024

With the advancement of modern IT technologies, the operation of autonomous vehicles is becoming a reality, and route planning is essential for this. Generally, route planning involves proposing the shortest path to minimize travel distance and the quickest path to minimize travel time. However, the quality of these routes depends on the topological characteristics of the road network graph. If the connectivity structure of the road network is not rational, there are limits to the performance improvement that routing algorithms can achieve. Real drivers consider psychological factors such as the number of turns, surrounding environment, traffic congestion, and road quality when choosing routes, and they particularly prefer routes with fewer turns. This paper introduces a simple path algorithm that seeks routes with the fewest turns, in addition to the traditional shortest distance and quickest time routes, to evaluate the characteristics of road networks. Using this simple path algorithm, we compare and evaluate the connectivity characteristics of road networks in 20 major cities worldwide. By analyzing these road network characteristics, we can identify the strengths and weaknesses of urban road networks and develop more efficient and safer route planning algorithms. This paper comprehensively examines the quality of road networks and the efficiency of route planning by analyzing and comparing the road network characteristics of each city using the proposed simple path algorithm.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.4
• /
• pp.199-207
• /
• 2024

Local reservoirs are crucial sources for agricultural water supply, necessitating stable water level management to prepare for extreme climate conditions such as droughts. Water level prediction is significantly influenced by local climate characteristics, such as localized rainfall, as well as seasonal factors including cropping times, making it essential to understand the correlation between input and output data as much as selecting an appropriate prediction model. In this study, extensive multivariate data from over 400 reservoirs in Jeollabuk-do from 1991 to 2022 was utilized to train and validate a water level prediction model that comprehensively reflects the complex hydrological and climatological environmental factors of each reservoir, and to analyze the impact of each input feature on the prediction performance of water levels. Instead of focusing on improvements in water level performance through neural network structures, the study adopts a basic Feedforward Neural Network composed of fully connected layers, batch normalization, dropout, and activation functions, focusing on the correlation between multivariate input data and prediction performance. Additionally, most existing studies only present short-term prediction performance on a daily basis, which is not suitable for practical environments that require medium to long-term predictions, such as 10 days or a month. Therefore, this study measured the water level prediction performance up to one month ahead through a recursive method that uses daily prediction values as the next input. The experiment identified performance changes according to the prediction period and analyzed the impact of each input feature on the overall performance based on an Ablation study.