• Journal of Software Assessment and Valuation
• /
• v.17 no.1
• /
• pp.51-58
• /
• 2021

Microservices are not only developed independently, but can also be run and deployed independently, ensuring more flexible scaling and efficient collaboration in a cloud computing environment. This impact has led to a surge in migrating to microservices-oriented application environments in recent years. In order to introduce microservices, the problem of identifying microservice units in a single application built with a single architecture must first be solved. In this paper, we propose an algorithm-based approach to identify microservices from legacy systems. A graph is generated using the meta-information of the legacy code, and a microservice candidate is extracted by applying a clustering algorithm. Modularization quality is evaluated using metrics for the extracted microservice candidates. In addition, in order to validate the proposed method, candidate services are derived using codes of open software that are widely used for benchmarking, and the level of modularity is evaluated using metrics. It can be identified as a smaller unit of microservice, and as a result, the module quality has improved.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.641-649
• /
• 2021

Fuel oil consumption (FOC) must be minimized to determine the economic route of a ship; hence, the ship power must be predicted prior to route planning. For this purpose, a numerical method using test results of a model has been widely used. However, predicting ship power using this method is challenging owing to the uncertainty of the model test. An onboard test should be conducted to solve this problem; however, it requires considerable resources and time. Therefore, in this study, a deep feed-forward neural network (DFN) is used to predict ship power using deep learning methods that involve data pattern recognition. To use data in the DFN, the input data and a label (output of prediction) should be configured. In this study, the input data are configured using ocean environmental data (wave height, wave period, wave direction, wind speed, wind direction, and sea surface temperature) and the ship's operational data (draft, speed, and heading). The ship power is selected as the label. In addition, various treatments have been used to improve the prediction accuracy. First, ocean environmental data related to wind and waves are preprocessed using values relative to the ship's velocity. Second, the structure of the DFN is changed based on the characteristics of the input data. Third, the prediction accuracy is analyzed using a combination comprising five hyperparameters (number of hidden layers, number of hidden nodes, learning rate, dropout, and gradient optimizer). Finally, k-means clustering is performed to analyze the effect of the sea state and ship operational status by categorizing it into several models. The performances of various prediction models are compared and analyzed using the DFN in this study.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.39-48
• /
• 2023

This study was conducted to provide a solution to the problem of sizing errors occurring in online purchases due to discrepancies and non-standardization in clothing sizes. This paper discusses an implementation approach for a machine learning-based recommender system capable of providing personalized sizes to online consumers. We trained multiple validated collaborative filtering algorithms including Non-Negative Matrix Factorization (NMF), Singular Value Decomposition (SVD), k-Nearest Neighbors (KNN), and Co-Clustering using purchasing data derived from online commerce and compared their performance. As a result of the study, we were able to confirm that the NMF algorithm showed superior performance compared to other algorithms. Despite the characteristic of purchase data that includes multiple buyers using the same account, the proposed model demonstrated sufficient accuracy. The findings of this study are expected to contribute to reducing the return rate due to sizing errors and improving the customer experience on e-commerce platforms.

• Journal of Internet Computing and Services
• /
• v.24 no.2
• /
• pp.67-74
• /
• 2023

Stock price prediction research in the financial sector aims to ensure trading stability and achieve profit realization. Conventional statistical prediction techniques are not reliable for actual trading decisions due to low prediction accuracy compared to randomly predicted results. Artificial intelligence models improve accuracy by learning data characteristics and fluctuation patterns to make predictions. However, predicting stock prices using long-term time series data remains a challenging problem. This paper proposes a stable and reliable stock price prediction method using K-means clustering-based data augmentation and normalization techniques and LSTM models specialized in time series learning. This enables obtaining more accurate and reliable prediction results and pursuing high profits, as well as contributing to market stability.

• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1138-1148
• /
• 2017

Topic extraction is a technology that automatically extracts a set of topics from a set of documents, and this has been a major research topic in the area of natural language processing. Representative topic extraction methods include Latent Dirichlet Allocation (LDA) and word clustering-based methods. However, there are problems with these methods, such as repeated topics and mixed topics. The problem of repeated topics is one in which a specific topic is extracted as several topics, while the problem of mixed topic is one in which several topics are mixed in a single extracted topic. To solve these problems, this study proposes a method to extract topics using an LDA that is robust against the problem of repeated topic, going through the steps of separating and merging the topics using the similarity between words to correct the extracted topics. As a result of the experiment, the proposed method showed better performance than the conventional LDA method.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.171-176
• /
• 2020

This paper proposes polynomial-time algorithm for maximum weighted independent set(MWIS) problem that is well known as NP-hard. The known algorithms for MWIS problem are polynomial-time to specialized in particular graph type, distributed, or clustering method. But there is no unified algorithm is suitable to all kinds of graph types. Therefore, this paper suggests unique polynomial-time algorithm that is suitable to all kinds of graph types. The proposed algorithm merges the maximum weighted vertex v_i and maximum weighted vertex v_j that is not adjacent to v_i. As a result of apply to undirected graphs and trees, this algorithm can be get the optimal solution. This algorithm improves previously known solution to new optimal solution.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.2
• /
• pp.105-111
• /
• 2020

In this paper, we propose a scheme that minimizes the energy imbalance problem of solar-powered wireless sensor network (SP-WSN) using both a mobile sink capable of wireless power transfer and an efficient clustering scheme (including cluster head election). The proposed scheme charges the cluster head using wireless power transfer from a mobile sink and mitigates the energy hotspot of the nodes nearby the head. SP-WSNs can continuously harvest energy, alleviating the energy constraints of battery-based WSN. However, if a fixed sink is used, the energy imbalance problem, which is energy consumption rate of nodes located near the sink is relatively increased, cannot be solved. Thus, recent research approaches the energy imbalance problem by using a mobile sink in SP-WSN. Meanwhile, with the development of wireless power transmission technology, a mobile sink may play a role of energy charging through wireless power transmission as well as data gathering in a WSN. Simulation results demonstrate that increase the amount of collected data by the sink using the proposed scheme.

• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.901-911
• /
• 2005

With the development of e-commerce and the proliferation of easily accessible information, information filtering has become a popular technique to prune large information spaces so that users are directed toward those items that best meet their needs and preferences. While many collaborative filtering systems have succeeded in capturing the similarities among users or items based on ratings to provide good recommendations, there are still some challenges for them to be more efficient, especially the user bias problem, non-transitive association problem and cold start problem. Those three problems impede us to capture more accurate similarities among users or items. In this paper, we provide probabilistic model approaches for UCHM and ICHM which are suggested to solve the addressed problems in hopes of achieving better performance. In this probabilistic model, objects (users or items) are classified into groups and predictions are made for users considering the Gaussian distribution of user ratings. Experiments on a real-word data set illustrate that our proposed approach is comparable with others.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.4
• /
• pp.109-117
• /
• 2019

In modern society, due to various accidents and crime threats committed to an unspecified number of people, individual security awareness is increasing throughout society and various surveillance techniques are being actively studied. Still, there is a decline in robustness due to many problems, requiring higher reliability monitoring techniques. Thus, this paper suggests a real-time change detection technique to complement the low robustness problem in various environments and dynamic/static change detection and to solve the cost efficiency problem. We used the Self-Organizing Map (SOM) applied as a data clustering technique to implement change detection, and we were able to confirm the superiority of noise robustness and abnormal detection judgment compared to the detection technique applied to the existing image surveillance system through simulation in the indoor office environment.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.167-172
• /
• 2023

The P-3C maritime patrol aircraft operated by the Republic of Korea Navy is equipped with various sensor devices (LRUs, line replace units) for tactical data collection. Depending on the characteristics of the sensor device, it operates with various communication protocols such as IEEE 802.3, MIL-STD-1553A/B, and ARINC-429. In addition, the collected tactical data is processed in the tactical station for mission operators, and this tactical station constitutes a clustering network on Gigabit Ethernet and operates in a distributed processing method. For communication with the sensor device, a specific tactical station mounts a peripheral device (eg. ARINC-429 interface card). The problem is that the performance of the entire distributed processing according to the peripheral device control and communication relay of this specific device is degraded, and even the operation stop of the tactical station has a problem of disconnecting the communication with the related sensor device. In this paper, we propose a method to mount a separate gateway to solve this problem, and the validity of the proposed application is demonstrated through the operation result of this gateway.