• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.45-51
• /
• 2011

In this paper, we propose an unsupervised learning method for modeling motion trajectory patterns effectively. In our approach, observations of an object on a trajectory are treated as words in a document for latent dirichlet allocation algorithm which is used for clustering words on the topic in natural language process. This allows clustering topics (e.g. go straight, turn left, turn right) effectively in complex scenes, such as crossroads. After this procedure, we learn patterns of word sequences in each cluster using Baum-Welch algorithm used to find the unknown parameters in a hidden markov model. Evaluation of abnormality can be done using forward algorithm by comparing learned sequence and input sequence. Results of experiments show that modeling of semantic region is robust against noise in various scene.

• Smart Structures and Systems
• /
• v.26 no.4
• /
• pp.495-506
• /
• 2020

Monitoring of complex processes faces several challenges mainly due to the lack of relevant sensory information or insufficient elaborated decision-making strategies. These challenges motivate researchers to adopt complex data processing and analysis in order to improve the process representation. This paper presents the development and implementation of quality monitoring framework based on a model-driven approach using embedded artificial intelligence strategies. In this work, the strategies are applied to the supervision of a microfabrication process aiming at showing the great performance of the framework in a very complex system in the manufacturing sector. The procedure involves two methods for modelling a representative quality variable, such as surface roughness. Firstly, the hybrid incremental modelling strategy is applied. Secondly, a generalized fuzzy clustering c-means method is developed. Finally, a comparative study of the behavior of the two models for predicting a quality indicator, represented by surface roughness of manufactured components, is presented for specific manufacturing process. The manufactured part used in this study is a critical structural aerospace component. In addition, the validation and testing are performed at laboratory and industrial levels, demonstrating proper real-time operation for non-linear processes with relatively fast dynamics. The results of this study are very promising in terms of computational efficiency and transfer of knowledge to manufacturing industry.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.85-91
• /
• 2018

Most banks use only demographic information such as gender, age, occupation and address to segment customers, but they do not reflect financial behavior patterns of customers. In this study, we aim to solve the problems by using various big data in a bank and to develop customer segmentation method which can be widely used in many banks in the future. In this paper, we propose an approach of segmenting clustering blocks with bottom-up method. This method has an advantage that it can accurately reflect various financial needs of customers based on various transaction patterns, channel contact patterns, and existing demographic information. Based on this, we will develop various marketing models such as product recommendation, financial need rating calculation, and customer churn-out prediction based on this, and we will adapt this models for the marketing strategy of NH Bank.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.3
• /
• pp.549-555
• /
• 2019

According to a recent report by anti-virus vendors, the number of new and modified malware increased exponentially. Therefore, malware analysis research using machine learning has been actively researched in order to replace passive analysis method which has low analysis speed. However, when using supervised learning based machine learning, many studies use low-reliability malware family name provided by the antivirus vendor as the label. In order to solve the problem of low-reliability of malware label, this paper introduces a new labeling technique, "Unified Labeling", and further verifies the malicious behavior similarity through the feature analysis of the fine-grained method. To verify this study, various clustering algorithms were used and compared with existing labeling techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.1957-1980
• /
• 2021

The significant aim of this research has always been to evaluate the mechanism for efficient and inherently aware usage of vitality in-home devices, thus improving the information of smart metering systems with regard to the usage of selected homes and the time of use. Advances in information processing are commonly used to quantify gigantic building activity data steps to boost the activity efficiency of the building energy systems. Here, some smart data mining models are offered to measure, and predict the time series for energy in order to expose different ephemeral principles for using energy. Such considerations illustrate the use of machines in relation to time, such as day hour, time of day, week, month and year relationships within a family unit, which are key components in gathering and separating the effect of consumers behaviors in the use of energy and their pattern of energy prediction. It is necessary to determine the multiple relations through the usage of different appliances from simultaneous information flows. In comparison, specific relations among interval-based instances where multiple appliances use continue for certain duration are difficult to determine. In order to resolve these difficulties, an unsupervised energy time-series data clustering and a frequent pattern mining study as well as a deep learning technique for estimating energy use were presented. A broad test using true data sets that are rich in smart meter data were conducted. The exact results of the appliance designs that were recognized by the proposed model were filled out by Deep Convolutional Neural Networks (CNN) and Recurrent Neural Networks (LSTM and GRU) at each stage, with consolidated accuracy of 94.79%, 97.99%, 99.61%, for 25%, 50%, and 75%, respectively.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.10 no.4
• /
• pp.59-71
• /
• 2000

Due to the advance of computer and communication technology, intrusions or crimes using a computer have been increased rapidly while various information has been provided to users conveniently. As a results, many studies are necessary to detect the activities of intruders effectively. In this paper, a new association algorithm for the anomaly detection model is proposed in the process of generating user\`s normal patterns. It is that more recently observed behavior get more affection on the process of data mining. In addition, by clustering generated normal patterns for each use or a group of similar users, it is possible to identify the usual frequency of programs or command usage for each user or a group of uses. The performance of the proposed anomaly detection system has been tested on various system Parameters in order to identify their practical ranges for maximizing its detection rate.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.10
• /
• pp.5097-5104
• /
• 2013

To derive implication for marketing strategy for Korean cosmetic products in China, an analysis was conducted on the difference in quality perception and purchase behavior between two groups of Chinese women classified by their awareness of Korean Wave. Analytical methods including k-means clustering method, independent samples t-test, factor analysis were applied on the survey results of Chinese women residing in Guangzhou city. The positive impact of Korean Wave on quality perception and brand image is much stronger for higher awareness group, compared against for lower awareness group, that leads to higher product satisfaction and willingness to recommend purchases. Thus, marketing strategies need to be adjusted based on the difference in customers awareness of Korean Wave. However, the low price is the primary inducement for purchases for both groups, increased efforts to enhance brand image and product quality as premium products is strongly required, together with the utilization of Koran Wave.

• Korean Journal of Materials Research
• /
• v.22 no.7
• /
• pp.329-334
• /
• 2012

Two types of nanoclusters, termed Cluster (1) and Cluster (2) here, both play an important role in the age-hardening behavior in Al-Mg-Si alloys. Small amounts of additions of Cu and Ag affect the formation of nanoclusters. Two exothermic peaks were clearly detected in differential scanning calorimetry(DSC) curves by means of peak separation by the Gaussian method in the base, Cu-added, Ag-added and Cu-Ag-added Al-Mg-Si alloys. The formation of nanoclusters in the initial stage of natural aging was suppressed in the Ag-added and Cu-Ag-added alloys, while the formation of nanoclusters was enhanced at an aging time longer than 259.2 ks(3 days) of natural aging with the addition Cu and Ag. The formation of nanoclusters while aging at $100^{\circ}C$ was accelerated in the Cu-added, Ag-added and Cu-Ag-added alloys due to the attractive interaction between the Cu and Ag atoms and the Mg atoms. The influence of additions of Cu and Ag on the clustering behavior during low-temperature aging was well characterized based on the interaction energies among solute atoms and on vacancies derived from the first-principle calculation of the full-potential Korrinaga-Kohn-Rostoker(FPKKR)-Green function method. The effects of low Cu and Ag additions on the formation of nanoclusters were also discussed based on the age-hardening phenomena.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.131-156
• /
• 2023

The traditional retail industry significantly changed over the past decade due to the mobile and online technologies. This change has been accompanied by a shift in consumer behavior regarding purchasing patterns. Despite the rise of online shopping, there are still specific categories of products, such as "Processed food" in Mongolia, for which traditional shopping remains the preferred purchase method. To prepare for the inevitable future of retail businesses, firms need to closely analyze the performance of their offline stores to plan their further actions in a new multi-channel environment. Retailers must integrate diverse channels into their operations to stay relevant and adjust to the shifting market. In this research, we have analyzed the performance data such as sales, profit, and amount of sales of offline stores by using clustering approach. From the clustering, we have found the several distinct insights by comparing the circumstances and performance of retail stores. For the certain retail stores, we have proposed three different strategies: a fulfillment hub store between online and offline channels, an experience store to elongate customers' time on the premises, and a merge between two non-related channels that could complement each other to increase traffic based on the store characteristics. With the proposed strategies, it may enhance the user experience and profit at the same time.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.775-782
• /
• 2002

As electronic commerce systems have been widely used, the necessity of adaptive e-commerce agent systems has been increased. These kinds of agents can monitor customer's purchasing behaviors, clutter them in similar categories, and induce customer's preference from each category. In order to implement our adaptive e-commerce agent system, we focus on following 3 components-the monitor agent which can monitor customer's browsing/purchasing data and abstract them, the conceptual cluster agent which cluster customer's abstract data, and the customer profile agent which generate profile from cluster, In order to infer more accurate customer's preference, we propose a 2 layered structure consisting of conceptual cluster and inductive profile generator. Many systems have been suffered from errors in deriving user profiles by using a single structure. However, our proposed 2 layered structure enables us to improve the qualify of user profile by clustering user purchasing behavior in advance. This approach enables us to build more user adaptive e-commerce system according to user purchasing behavior.