• Journal of Korea Society of Industrial Information Systems
• /
• v.23 no.5
• /
• pp.61-76
• /
• 2018

Everything is coming into the world of network where modern people are living. The Internet of Things that attach sensors to objects allows real-time data transfer to and from the network. Mobile devices, essential for modern humans, play an important role in keeping all traces of everyday life in real time. Through the social network services, information acquisition activities and communication activities are left in a huge network in real time. From the business point of view, customer needs analysis begins with SNS data. In this research, we want to build an automatic collection system of SNS contents of web environment in real time using Python. We want to help customers' needs analysis through the typical data collection system of Instagram, Twitter, and YouTube, which has a large number of users worldwide. It is stored in database through the exploitation process and NLP process by using the virtual web browser in the Python web server environment. According to the results of this study, we want to conduct service through the site, the desired data is automatically collected by the search function and the netizen's response can be confirmed in real time. Through time series data analysis. Also, since the search was performed within 5 seconds of the execution result, the advantage of the proposed algorithm is confirmed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.6
• /
• pp.13-23
• /
• 2022

In this paper, we propose a detailed component image classification algorithm by fashion item for unstructured data retrieval in the fashion field. Due to the COVID-19 environment, AI-based online shopping malls are increasing recently. However, there is a limit to accurate unstructured data search with existing keyword search and personalized style recommendations based on user surfing behavior. In this study, pre-processing using Mask R-CNN was conducted using images crawled from online shopping sites and then classified components for each fashion item through CNN. We obtain the accuaracy for collar of the shirt's as 93.28%, the pattern of the shirt as 98.10%, the 3 classese fit of the jeans as 91.73%, And, we further obtained one for the 4 classes fit of jeans as 81.59% and the color of the jeans as 93.91%. At the results for the decorated items, we also obtained the accuract of the washing of the jeans as 91.20% and the demage of jeans accuaracy as 92.96%.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.10
• /
• pp.43-53
• /
• 2009

Knowledge retrieval service that uses collective intelligence which has special quality of open structure and can share the accumulative data is gaining popularity. However, acquiring the right needs for users from massive public knowledge is getting harder. Recently, search results from Google which is known for it's exquisite algorism, shows results for collective intelligence such as Wikipedia, Yahoo Q/A at the highest rank. Objective of this paper is to show that most answers come from human and to find the most influential people in on-line knowledge retrieval service. Hereupon, this paper suggest the influence value calculation algorism by analyzing user relation as centrality which social network is based on user activeness and reliance in Naver 지식iN. The influence value calculated by the suggested algorism will be an important index in distinguishing reliable and the right user for the question by ranking users with troubleshooting solutions in the knowledge retrieval service. This will contribute in search satisfaction by acquiring the right information and knowledge for the users which is the most important objective for knowledge retrieval service.

• The Journal of Korean Association of Computer Education
• /
• v.12 no.4
• /
• pp.57-64
• /
• 2009

Protein structure comparison is a task that requires a lot of computing resources because many atoms in proteins need to be processed. To address the issue, Grid computing environment has been employed for processing time-consuming jobs in a distributed manner. However, controling the Grid computing environment may not be easy for non-experts. In this paper, we present a JXTA-based system for protein structure comparison that can be easily controled by non-experts. To search proteins similar to a query protein, the geometric hashing algorithm that consists of preprocessing and recognition was employed. Experimental results indicate that the system can find the correct protein structure for a given query protein structure and the proposed system can be easily extended to solve the protein docking problem. It is expected that the proposed system can be useful for non-experts, especially users who do not have sophisticated knowledge of distributed systems in general such as college students who major in biology or chemistry.

• The KIPS Transactions:PartD
• /
• v.10D no.3
• /
• pp.427-438
• /
• 2003

In a data warehouse, users typically search for trends, patterns, or unusual data behaviors by issuing queries interactively. The OLAP range-sum query is widely used in finding trends and in discovering relationships among attributes in the data warehouse. In a recent environment of enterprises, data elements in a data cube are frequently changed. The problem is that the cost of updating a prefix sum cube is very high. In this paper, we propose a novel algorithm which reduces the update cost significantly by an index structure called the Δ-tree. Also, we propose a hybrid method to provide either approximate or precise results to reduce the overall cost of queries. It is highly beneficial for various applications that need quick approximate answers rather than time consuming accurate ones, such as decision support systems. An extensive experiment shows that our method performs very efficiently on diverse dimensionalities, compared to other methods.

• Journal of Communications and Networks
• /
• v.14 no.3
• /
• pp.286-295
• /
• 2012

To meet the increased demand of video-on-demand (VoD) services, peer-to-peer (P2P) mesh-based multiple video approaches have been recently proposed, where each peer is able to find a video segment interested without resort to the video server. However, they have not considered the constraint of the server's upload bandwidth and the fairness between upload and download amounts at each peer. In this paper, we propose a novel P2P VoD streaming system, named peer cache adaptation (PECAN) where each peer adjusts its cache capacity adaptively to meet the server's upload bandwidth constraint and achieve the fairness. For doing so, we first propose a new cache replacement algorithm that designs the number of caches for a segment to be proportional to its popularity. Second, we mathematically prove that if the cache capacity of a peer is proportional to its segment request rate, the fairness between upload and download amounts at each peer can be achieved. Third, we propose a method that determines each peer's cache capacity adaptively according to the constraint of the server's upload bandwidth. Against the proposed design objective, some selfish peers may not follow our protocol to increase their payoff. To detect such peers, we design a simple distributed reputation and monitoring system. Through simulations, we show that PECAN meets the server upload bandwidth constraint, and achieves the fairness well at each peer. We finally verify that the control overhead in PECAN caused by the search, reputation, and monitoring systems is very small, which is an important factor for real deployment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.650-669
• /
• 2017

Coordinated multiple points transmission and reception (CoMP) technology is used to mitigate the inter-cell interference, and increase cell average user normalized throughput and cell edge user normalized throughput. There are two kinds of radio resource schedule strategies in LTE-A/5G CoMP system, and they are called centralized scheduling strategy and distributed scheduling strategy. The regional centralized scheduling cannot solve interference of inter-region, and the distributed scheduling leads to worse efficiency in the utilize of resources. In this paper, a novel distributed scheduling scheme named 9-Cell alternate authorization (9-CAA) is proposed. In our scheme, time-domain resources are divided orthogonally by coloring theory for inter-region cooperation in 9-Cell scenario [6]. Then, we provide a formula based on 0-1 integer programming to get chromatic number in 9-CAA. Moreover, a feasible optimal chromatic number search algorithm named CNS-9CAA is proposed. In addition, this scheme is expanded to 3-Cell scenario, and name it 3-Cell alternate authorization (3-CAA). At last, simulation results indicate that 9/3-CAA scheme exceed All CU CoMP, 9/3C CU CoMP and DLC resource scheduling scheme in cell average user normalized throughput. Especially, compared with the non-CoMP scheme as a benchmark, the 9-CAA and 3-CAA have improved the edge user normalized throughput by 17.2% and 13.0% respectively.

• Journal of Digital Convergence
• /
• v.10 no.7
• /
• pp.141-152
• /
• 2012

The typical evacuation guidance system based on fire detectors, which is being widely used in theaters and large buildings, is often operated in an analog manner. In case of fire, it often causes the system to lose a wired line or wireless fire detection sensor, resulting in the difficulty of transmitting signals from a wired or wireless fire detection sensor to the main fire monitoring device. Accordingly, this paper has proposed the broadcasting system for disaster management, having an efficient evacuation guidance plan when a disaster occurs. The system reacts to an emergency situation along with fire alarm sirens in real time. We have implemented the above system by means of a simulation program that prints the evacuation guidance information (e.g., location and time of fire, and evacuation path) on an LCD located in a building through the fire sensor network in case of an emergency (e.g., actual fire). We have developed the simulation system by using mathematical algorithms, such as the optimal path search and the fire smoke diffusion algorithm. This simulation program considers the structure of a building and the location where the fire has initially occurred, applying it to the simulator.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.109-117
• /
• 2022

Most of real-world decision-making processes are used to optimize problems with many objectives of conflicting. Since the betterment of some objectives requires the sacrifice of other objectives, different objectives may not be optimized simultaneously. Consequently, Pareto solution can be considered as candidates of a solution with respect to a multi-objective optimization (MOP). Such problem involves two main procedures: finding Pareto solutions and choosing one solution among them. So-called multi-objective genetic algorithms have been proved to be effective for finding many Pareto solutions. In this study, we suggest a fitness evaluation method based on the achievement level up to the target value to improve the solution search performance by the multi-objective genetic algorithm. Using numerical examples and benchmark problems, we compare the proposed method, which considers the achievement level, with conventional Pareto ranking methods. Based on the comparison, it is verified that the proposed method can generate a highly convergent and diverse solution set. Most of the existing multi-objective genetic algorithms mainly focus on finding solutions, however the ultimate aim of MOP is not to find the entire set of Pareto solutions, but to choose one solution among many obtained solutions. We further propose an interactive decision-making process based on a visualized trade-off analysis that incorporates the satisfaction of the decision maker. The findings of the study will serve as a reference to build a multi-objective decision-making support system.

• Journal of Intelligence and Information Systems
• /
• v.20 no.2
• /
• pp.137-148
• /
• 2014

Recommender system has become one of the most important technologies in e-commerce in these days. The ultimate reason to shop online, for many consumers, is to reduce the efforts for information search and purchase. Recommender system is a key technology to serve these needs. Many of the past studies about recommender systems have been devoted to developing and improving recommendation algorithms and collaborative filtering (CF) is known to be the most successful one. Despite its success, however, CF has several shortcomings such as cold-start, sparsity, gray sheep problems. In order to be able to generate recommendations, ordinary CF algorithms require evaluations or preference information directly from users. For new users who do not have any evaluations or preference information, therefore, CF cannot come up with recommendations (Cold-star problem). As the numbers of products and customers increase, the scale of the data increases exponentially and most of the data cells are empty. This sparse dataset makes computation for recommendation extremely hard (Sparsity problem). Since CF is based on the assumption that there are groups of users sharing common preferences or tastes, CF becomes inaccurate if there are many users with rare and unique tastes (Gray sheep problem). This study proposes a new algorithm that utilizes Social Network Analysis (SNA) techniques to resolve the gray sheep problem. We utilize 'degree centrality' in SNA to identify users with unique preferences (gray sheep). Degree centrality in SNA refers to the number of direct links to and from a node. In a network of users who are connected through common preferences or tastes, those with unique tastes have fewer links to other users (nodes) and they are isolated from other users. Therefore, gray sheep can be identified by calculating degree centrality of each node. We divide the dataset into two, gray sheep and others, based on the degree centrality of the users. Then, different similarity measures and recommendation methods are applied to these two datasets. More detail algorithm is as follows: Step 1: Convert the initial data which is a two-mode network (user to item) into an one-mode network (user to user). Step 2: Calculate degree centrality of each node and separate those nodes having degree centrality values lower than the pre-set threshold. The threshold value is determined by simulations such that the accuracy of CF for the remaining dataset is maximized. Step 3: Ordinary CF algorithm is applied to the remaining dataset. Step 4: Since the separated dataset consist of users with unique tastes, an ordinary CF algorithm cannot generate recommendations for them. A 'popular item' method is used to generate recommendations for these users. The F measures of the two datasets are weighted by the numbers of nodes and summed to be used as the final performance metric. In order to test performance improvement by this new algorithm, an empirical study was conducted using a publically available dataset - the MovieLens data by GroupLens research team. We used 100,000 evaluations by 943 users on 1,682 movies. The proposed algorithm was compared with an ordinary CF algorithm utilizing 'Best-N-neighbors' and 'Cosine' similarity method. The empirical results show that F measure was improved about 11% on average when the proposed algorithm was used