• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.43-56
• /
• 2020

Recommender systems help users make the best choice among various options. Especially, recommender systems play important roles in internet sites as digital information is generated innumerable every second. Many studies on recommender systems have focused on an accurate recommendation. However, there are some problems to overcome in order for the recommendation system to be commercially successful. First, there is a lack of transparency in the recommender system. That is, users cannot know why products are recommended. Second, the recommender system cannot immediately reflect changes in user preferences. That is, although the preference of the user's product changes over time, the recommender system must rebuild the model to reflect the user's preference. Therefore, in this study, we proposed a recommendation methodology using topic modeling and sequential association rule mining to solve these problems from review data. Product reviews provide useful information for recommendations because product reviews include not only rating of the product but also various contents such as user experiences and emotional state. So, reviews imply user preference for the product. So, topic modeling is useful for explaining why items are recommended to users. In addition, sequential association rule mining is useful for identifying changes in user preferences. The proposed methodology is largely divided into two phases. The first phase is to create user profile based on topic modeling. After extracting topics from user reviews on products, user profile on topics is created. The second phase is to recommend products using sequential rules that appear in buying behaviors of users as time passes. The buying behaviors are derived from a change in the topic of each user. A collaborative filtering-based recommendation system was developed as a benchmark system, and we compared the performance of the proposed methodology with that of the collaborative filtering-based recommendation system using Amazon's review dataset. As evaluation metrics, accuracy, recall, precision, and F1 were used. For topic modeling, collapsed Gibbs sampling was conducted. And we extracted 15 topics. Looking at the main topics, topic 1, top 3, topic 4, topic 7, topic 9, topic 13, topic 14 are related to "comedy shows", "high-teen drama series", "crime investigation drama", "horror theme", "British drama", "medical drama", "science fiction drama", respectively. As a result of comparative analysis, the proposed methodology outperformed the collaborative filtering-based recommendation system. From the results, we found that the time just prior to the recommendation was very important for inferring changes in user preference. Therefore, the proposed methodology not only can secure the transparency of the recommender system but also can reflect the user's preferences that change over time. However, the proposed methodology has some limitations. The proposed methodology cannot recommend product elaborately if the number of products included in the topic is large. In addition, the number of sequential patterns is small because the number of topics is too small. Therefore, future research needs to consider these limitations.

• Fire Science and Engineering
• /
• v.26 no.3
• /
• pp.35-39
• /
• 2012

This paper analyzes the combustion diffusion pattern when a water purifier is artificially ignited outside and inside in order to provide data to examine the cause of fire of a water purifier damaged by fire. The analysis result of the combustion diffusion pattern of a water purifier shows that the combustion diffused at a higher speed when it was ignited inside the purifier than when ignited outside. It took approximately 360 seconds for the water purifier to be half-burned when ignited on the outside, and approximately 180 seconds when ignited from inside. That is, it is thought that the internal combustion speed is higher because the internal ignition causes the generated heat to be accumulated and radiated instantly. It was observed that the water purifier damaged by fire caused by external ignition showed a uniform carbonization pattern and the carbide burned down at the bottom were gradually deposited. The water purifier damaged by internal ignition showed a relatively clear boundary of carbonized surface, which formed a V-pattern. The difference in the combustion patterns presents an objective base from which to determine where the fire started. By the time the purifier was half-burned by fire, the built-in fuse had not melted and the power supply protection device did not operate. In addition, as was found in the case of the fuse damaged by a general fire, carbonization occurred at the metal holder, and it is thought that this fact may be used as a basis from which to determine the cause of a fire.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.85-107
• /
• 2019

Online consumers browse products belonging to a particular product line or brand for purchase, or simply leave a wide range of navigation without making purchase. The research on the behavior and purchase of online consumers has been steadily progressed, and related services and applications based on behavior data of consumers have been developed in practice. In recent years, customization strategies and recommendation systems of consumers have been utilized due to the development of big data technology, and attempts are being made to optimize users' shopping experience. However, even in such an attempt, it is very unlikely that online consumers will actually be able to visit the website and switch to the purchase stage. This is because online consumers do not just visit the website to purchase products but use and browse the websites differently according to their shopping motives and purposes. Therefore, it is important to analyze various types of visits as well as visits to purchase, which is important for understanding the behaviors of online consumers. In this study, we explored the clustering analysis of session based on click stream data of e-commerce company in order to explain diversity and complexity of search behavior of online consumers and typified search behavior. For the analysis, we converted data points of more than 8 million pages units into visit units' sessions, resulting in a total of over 500,000 website visit sessions. For each visit session, 12 characteristics such as page view, duration, search diversity, and page type concentration were extracted for clustering analysis. Considering the size of the data set, we performed the analysis using the Mini-Batch K-means algorithm, which has advantages in terms of learning speed and efficiency while maintaining the clustering performance similar to that of the clustering algorithm K-means. The most optimized number of clusters was derived from four, and the differences in session unit characteristics and purchasing rates were identified for each cluster. The online consumer visits the website several times and learns about the product and decides the purchase. In order to analyze the purchasing process over several visits of the online consumer, we constructed the visiting sequence data of the consumer based on the navigation patterns in the web site derived clustering analysis. The visit sequence data includes a series of visiting sequences until one purchase is made, and the items constituting one sequence become cluster labels derived from the foregoing. We have separately established a sequence data for consumers who have made purchases and data on visits for consumers who have only explored products without making purchases during the same period of time. And then sequential pattern mining was applied to extract frequent patterns from each sequence data. The minimum support is set to 10%, and frequent patterns consist of a sequence of cluster labels. While there are common derived patterns in both sequence data, there are also frequent patterns derived only from one side of sequence data. We found that the consumers who made purchases through the comparative analysis of the extracted frequent patterns showed the visiting pattern to decide to purchase the product repeatedly while searching for the specific product. The implication of this study is that we analyze the search type of online consumers by using large - scale click stream data and analyze the patterns of them to explain the behavior of purchasing process with data-driven point. Most studies that typology of online consumers have focused on the characteristics of the type and what factors are key in distinguishing that type. In this study, we carried out an analysis to type the behavior of online consumers, and further analyzed what order the types could be organized into one another and become a series of search patterns. In addition, online retailers will be able to try to improve their purchasing conversion through marketing strategies and recommendations for various types of visit and will be able to evaluate the effect of the strategy through changes in consumers' visit patterns.

• Korean Journal of Applied Biomechanics
• /
• v.19 no.1
• /
• pp.27-36
• /
• 2009

The purpose of this study was to identify effects of restricted trunk motion on the performances of the maximum vertical jump. Ten healthy males performed normal countermovement jump(NJ) and control type of countermovement jump(CJ), in which subjects were required to restrict trunk motion as much as possible. The results showed 10% decreases of jumping height in CJ compared with NJ, which is primarily due to vertical velocity at take off. NJ with trunk motion produced significantly higher GRF than RJ, especially at the early part of propulsive phase, which resulted from increased moments on hip joint. And these were considered the main factors of performance enhancement in NJ. There were no significant differences in the mechanical outputs on knee and ankle joint between NJ and RJ. With trunk motion restricted, knee joint alternatively played a main role for propulsion, which is contrary on the normal jump that hip joint was highest contributor. And restricted trunk motion resulted in the changes of coordination pattern, knee-hip extension timing compared with normal proximal-distal sequence. In conclusion these results suggest that trunk motion is effective strategy for increasing performance of vertical jumping.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.253-259
• /
• 2021

In line with the modern society where artificial intelligence has spread throughout society, the Ministry of Education decided to provide AI education in kindergartens, elementary, middle and high school classes in 2025, and develop related learning materials and textbooks from 2021. Korea currently does not have state-led AI education for kindergarten and elementary school, so there is no systematic teaching material. Therefore, this study designed and presented textbooks for pattern analysis-based computational thinking development based on the GPS curriculum, a kindergarten SW curriculum studied by Y. S. Jeong and S. E. Lim (2020). Class procedures for using the textbooks were classified as introduction activities, development activities, and organization activities. Supplementary explanations were presented by presenting textbooks and teaching aids along with explanations of each activity. In order for this study to help AI education conducted in 2025, research must be conducted to demonstrate its effectiveness through actual application in the future.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.2
• /
• pp.193-200
• /
• 2022

Unknown cryptographic communication protocols may have advantage of guaranteeing personal and data privacy, but when used for malicious purposes, it is almost impossible to identify and respond to using existing network security equipment. In particular, there is a limit to manually analyzing a huge amount of traffic in real time. Therefore, in this paper, we attempt to identify packets of unknown cryptographic communication protocols and separate fields comprising a packet by using machine learning techniques. Using sequential patterns analysis, hierarchical clustering, and Pearson's correlation coefficient, we found that the structure of packets can be automatically analyzed even for an unknown cryptographic communication protocol.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.1
• /
• pp.133-146
• /
• 2015

Ever sophisticated e-finance fraud techniques have led to an increasing number of reported phishing incidents. Financial authorities, in response, have recommended that we enhance existing Fraud Detection Systems (FDS) of banks and other financial institutions. FDSs are systems designed to prevent e-finance accidents through real-time access and validity checks on client transactions. The effectiveness of an FDS depends largely on how fast it can analyze and detect abnormalities in large amounts of customer transaction data. In this study we detect fraudulent transaction patterns and establish detection rules through e-finance accident data analyses. Abnormalities are flagged by comparing individual client transaction patterns with client profiles, using the ruleset. We propose an effective flagging method that uses decision trees to normalize detection rules. In demonstration, we extracted customer usage patterns, customer profile informations and detection rules from the e-finance accident data of an actual domestic(Korean) bank. We then compared the results of our decision tree-normalized detection rules with the results of a sequential detection and confirmed the efficiency of our methods.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.834-839
• /
• 2015

Recently, wellness has become an issue related to improvements in personal health and quality of life. Data that are accumulated daily, such as meals and momentum records, in addition to body measurement information such as body weight, BMI and blood pressure have been used to analyze the personal health data of an individual. Therefore, it has become possible to prevent potential disease and to analyze dietary or exercise patterns. In terms of food and nutrition, analyses are performed to evaluate the health status of an individual using dietary data. However, it is very difficult to process the large amount of dietary data. An analysis of dietary data includes four steps, and each step contains a series of iterative tasks that are executed over a long time. This paper proposes a problem solving environment that automates dietary data analysis, and the proposed framework increases the speed with which an experiment can be conducted.

• Journal of Internet Computing and Services
• /
• v.6 no.5
• /
• pp.45-56
• /
• 2005

The weak foundation of the computing environment caused information leakage and hacking to be uncontrollable, Therefore, dynamic control of security threats and real-time reaction to identical or similar types of accidents after intrusion are considered to be important, h one of the solutions to solve the problem, studies on intrusion detection systems are actively being conducted. To improve the anomaly IDS using system calls, this study focuses on neural networks learning using the soundex algorithm which is designed to change feature selection and variable length data into a fixed length learning pattern, That Is, by changing variable length sequential system call data into a fixed iength behavior pattern using the soundex algorithm, this study conducted neural networks learning by using a backpropagation algorithm. The backpropagation neural networks technique is applied for anomaly detection of system calls using Sendmail Data of UNM to demonstrate its performance.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.1
• /
• pp.351-356
• /
• 2011

In this paper, we design a pet location tracking and remote monitoring system that uses ultrasonic, temperature, humidity and illumination sensors to study behavioral patterns and habits. Using ultrasonic waves to calculate distances, a WSN(Wireless Sensor Network) was constructed to transmit data at pet's location, such as temperature, humidity and illumination, to a sink mote. Data received by the system are stored in the database in real time to trace pet's location. Interference among transmitting motes was eliminated by sequentially transmitting RF beacons using sink mote's beacon as the reference signal. Experiments were performed with the laboratory prototype of a pet animal monitoring system implemented for this study. The system analyzes locations of a pet and displays movement patterns, areas of movement, temperature, humidity and illumination using a GUI (graphical user interface).