• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.9
• /
• pp.849-854
• /
• 2001

GTM(Generative Topographic Mapping) model is a probabilistic version of the SOM(Self Organizing Maps) which was proposed by T. Kohonen. The GTM is modelled by latent or hidden variables of probability distribution of data. It is a unique characteristic not implemented in SOM model, and, therefore, it is possible with GTM to analyze data accurately, thereby overcoming the limits of SOM. In the present investigation we proposed a BGTM(Bayesian GTM) combined with Bayesian learning and GTM model that has a small mis-classification ratio. By combining fast calculation ability and probabilistic distribution of data of GTM with correct reasoning based on Bayesian model, the BGTM model provided improved results, compared with existing models.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.278-288
• /
• 2021

Recently, IoT systems are cloud-based, so that continuous and large amounts of data collected from sensor nodes are processed in the data server through the cloud. However, in the centralized configuration of large-scale cloud computing, computational processing must be performed at a physical location where data collection and processing take place, and the need for edge computers to reduce the network load of the cloud system is gradually expanding. In this paper, a cluster system consisting of 6 inexpensive Raspberry Pi boards was constructed to perform fast data processing. And we propose "Kubernetes cluster system(KCS)" for processing large data collection and analysis by model distribution and data pipeline method. To compare the performance of this study, an ensemble model of deep learning was built, and the accuracy, processing performance, and processing time through the proposed KCS system and model distribution were compared and analyzed. As a result, the ensemble model was excellent in accuracy, but the KCS implemented as a data pipeline proved to be superior in processing speed..

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.1
• /
• pp.49-59
• /
• 2019

Generative adversarial networks(GANs) have received great attention in the machine learning field for their capacity to model high-dimensional and complex data distribution implicitly and generate new data samples from the model distribution. This paper investigates the model training methodology, architecture, and various applications of generative adversarial networks. Experimental evaluation is also conducted for generating synthetic image dataset for defense using two types of GANs. The first one is for military image generation utilizing the deep convolutional generative adversarial networks(DCGAN). The other is for visible-to-infrared image translation utilizing the cycle-consistent generative adversarial networks(CycleGAN). Each model can yield a great diversity of high-fidelity synthetic images compared to training ones. This result opens up the possibility of using inexpensive synthetic images for training neural networks while avoiding the enormous expense of collecting large amounts of hand-annotated real dataset.

• The Journal of Industrial Distribution & Business
• /
• v.13 no.8
• /
• pp.19-27
• /
• 2022

Purpose: CEOs develop policies through their effective decision-making while employees implement the policies so that a business realizes the expected returns. This research focuses on the importance of the CEO's sustainable leadership to distribute environmental education culture to improve employees' environmental performance. Research design, data and methodology: The PRISMA that is selected by the present research is an evidence-based minimum group of entities for reporting in systematic reviews and meta-analyses. The core focus of the concept is to note studies that evaluate the impacts of intervention and can also be utilized as a basis for writing systematic reviews rather than intervention evaluations. Results: The current investigation indicates that there are four kinds of suggestions (a. Increased organizational learning, b. Open communication, c. Participative decision making, d. Psychological empowerment) how the management should develop sustainable leadership for distributing green culture and improving employee green performance. Conclusions: Based on four solutions, the present research concludes that sustainable leadership for CEOs is not only of advantage in terms of protecting the environment and the people, but it fosters increased organizational learning. Increased organizational learning leads to better employee sustainable performance, which includes financial performance and the social and environmental initiatives the organization implements.

• Asian Journal of Business Environment
• /
• v.12 no.3
• /
• pp.1-12
• /
• 2022

Purpose: This study aims to investigate whether AIS data can be used as a supporting indicator or as an initial signal to describe Indonesia's export-import conditions in real-time. Research design, data, and methodology: This study performs several stages of data selection to obtain indicators from AIS that truly reflect export-import activities in Indonesia. Also, investigate the potential of AIS indicators in producing forecasts of the value and volume of Indonesian export-import using conventional statistical methods and machine learning techniques. Results: The six preprocessing stages defined in this study filtered AIS data from 661.8 million messages to 73.5 million messages. Seven predictors were formed from the selected AIS data. The AIS indicator can be used to provide an initial signal about Indonesia's import-export activities. Each export or import activity has its own predictor. Conventional statistical methods and machine learning techniques have the same ability both in forecasting Indonesia's exports and imports. Conclusions: Big data AIS can be used as a supporting indicator as a signal of the condition of export-import values in Indonesia. The right method of building indicators can make the data valuable for the performance of the forecasting model.

• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.531-536
• /
• 2022

In order to efficeintly manage a battery, it is important to accurately estimate and manage the SOH(State of Health) and RUL(Remaining Useful Life) of the batteries. Even if the batteries are of the same type, the characteristics such as facility capacity and voltage are different, and when the battery for the training model and the battery for prediction through the model are different, there is a limit to measuring the accuracy. In this paper, We proposed the entropy index using voltage distribution and discharge time is generalized, and four batteries are defined as a training set and a test set alternately one by one to predict the health status of batteries through linear regression analysis of machine learning. The proposed method showed a high accuracy of more than 95% using the MAPE(Mean Absolute Percentage Error).

• Journal of information and communication convergence engineering
• /
• v.22 no.3
• /
• pp.221-230
• /
• 2024

The aim of this study is to investigate the automatic recognition and analysis of Jeju marine-life images using artificial intelligence (AI) technology. The dataset of marine-life images was prepared using tools such as Python, TensorFlow, and Google Colab (Google Colaboratory). We also developed models by training deep learning AI in image recognition to automatically recognize the species found in these images and extract their associated information, such as taxonomy, characteristics, and distribution. This study is innovative in that it uses deep learning technology combined with imagerecognition technology for marine biodiversity research. In addition, these results will lead to the development of the marine-life industry in Jeju by supporting marine environment monitoring and marine resource conservation. Furthermore, this study is anticipated to contribute to academic advancement, specifically in the study of marine species diversity.

• Korean Journal of Agricultural Science
• /
• v.49 no.4
• /
• pp.837-845
• /
• 2022

In this study, tomato maturity was estimated based on deep learning for a harvesting robot. Tomato images were obtained using a RGB camera installed on a monitoring robot, which was developed previously, and the samples were cropped to 128 × 128 size images to generate a dataset for training the classification model. The classification model was constructed based on convolutional neural networks, and the mean-variance loss was used to learn implicitly the distribution of the data features by class. In the test stage, the tomato maturity was estimated as a continuous index, which has a range of 0 to 1, by calculating the expected class value. The results show that the F1-score of the classification was approximately 0.94, and the performance was similar to that of a deep learning-based classification task in the agriculture field. In addition, it was possible to estimate the distribution in each maturity stage. From the results, it was found that our approach can not only classify the discrete maturation stages of the tomatoes but also can estimate the continuous maturity.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.4
• /
• pp.1103-1111
• /
• 2000

The hyper-geometric distribution software reliability growth model (HGDM) usually assumes that all the software faults detected are perfectly removed without introducing new faults. However, since new faults can be introduced during the test-and-debug phase, the perfect debugging assumption should be relaxed. In this context, Hou, Kuo and Chang [7] developed a modified HGDM for imperfect debugging environment, assuming tat the learning factor is constant. In this paper we extend the existing imperfect debugging HGDM for tow respects: introduction of random sensitivity factor and allowance of variable learning factor. Then the statistical characteristics of he suggested model are studied and its applications to two real data sets are demonstrated.

• Proceedings of the KIEE Conference
• /
• 1999.11b
• /
• pp.131-133
• /
• 1999

This paper proposed the technique of the fault-types classification using Adaptive Network Fuzzy Inference System in the distribution system. Fault and fault-like data in the linear RL load, arc furnace load and converter load were extracted by EMTP. These were characterized into 5 input variables and fuzzified automatically by learning. This technique was tested using another fault data unused learning.