• 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.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.109-125
• /
• 2019

As interest on intelligent search engines increases, various studies have been conducted to extract and utilize the features related to products intelligencely. In particular, when users search for goods in e-commerce search engines, the 'color' of a product is an important feature that describes the product. Therefore, it is necessary to deal with the synonyms of color terms in order to produce accurate results to user's color-related queries. Previous studies have suggested dictionary-based approach to process synonyms for color features. However, the dictionary-based approach has a limitation that it cannot handle unregistered color-related terms in user queries. In order to overcome the limitation of the conventional methods, this research proposes a model which extracts RGB values from an internet search engine in real time, and outputs similar color names based on designated color information. At first, a color term dictionary was constructed which includes color names and R, G, B values of each color from Korean color standard digital palette program and the Wikipedia color list for the basic color search. The dictionary has been made more robust by adding 138 color names converted from English color names to foreign words in Korean, and with corresponding RGB values. Therefore, the fininal color dictionary includes a total of 671 color names and corresponding RGB values. The method proposed in this research starts by searching for a specific color which a user searched for. Then, the presence of the searched color in the built-in color dictionary is checked. If there exists the color in the dictionary, the RGB values of the color in the dictioanry are used as reference values of the retrieved color. If the searched color does not exist in the dictionary, the top-5 Google image search results of the searched color are crawled and average RGB values are extracted in certain middle area of each image. To extract the RGB values in images, a variety of different ways was attempted since there are limits to simply obtain the average of the RGB values of the center area of images. As a result, clustering RGB values in image's certain area and making average value of the cluster with the highest density as the reference values showed the best performance. Based on the reference RGB values of the searched color, the RGB values of all the colors in the color dictionary constructed aforetime are compared. Then a color list is created with colors within the range of ${\pm}50$ for each R value, G value, and B value. Finally, using the Euclidean distance between the above results and the reference RGB values of the searched color, the color with the highest similarity from up to five colors becomes the final outcome. In order to evaluate the usefulness of the proposed method, we performed an experiment. In the experiment, 300 color names and corresponding color RGB values by the questionnaires were obtained. They are used to compare the RGB values obtained from four different methods including the proposed method. The average euclidean distance of CIE-Lab using our method was about 13.85, which showed a relatively low distance compared to 3088 for the case using synonym dictionary only and 30.38 for the case using the dictionary with Korean synonym website WordNet. The case which didn't use clustering method of the proposed method showed 13.88 of average euclidean distance, which implies the DBSCAN clustering of the proposed method can reduce the Euclidean distance. This research suggests a new color synonym processing method based on RGB values that combines the dictionary method with the real time synonym processing method for new color names. This method enables to get rid of the limit of the dictionary-based approach which is a conventional synonym processing method. This research can contribute to improve the intelligence of e-commerce search systems especially on the color searching feature.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.48 no.5
• /
• pp.25-33
• /
• 2011

This work proposes a skinny-type 10b 50MS/s 0.13um CMOS three-step pipeline ADC for CIS applications. Analog circuits for CIS applications commonly employ a high supply voltage to acquire a sufficiently acceptable dynamic range, while digital circuits use a low supply voltage to minimize power consumption. The proposed ADC converts analog signals in a wide-swing range to low voltage-based digital data using both of the two supply voltages. An op-amp sharing technique employed in residue amplifiers properly controls currents depending on the amplification mode of each pipeline stage, optimizes the performance of op-amps, and improves the power efficiency. In three FLASH ADCs, the number of input stages are reduced in half by the interpolation technique while each comparator consists of only a latch with low kick-back noise based on pull-down switches to separate the input nodes and output nodes. Reference circuits achieve a required settling time only with on-chip low-power drivers and digital correction logic has two kinds of level shifter depending on signal-voltage levels to be processed. The prototype ADC in a 0.13um CMOS to support 0.35um thick-gate-oxide transistors demonstrates the measured DNL and INL within 0.42LSB and 1.19LSB, respectively. The ADC shows a maximum SNDR of 55.4dB and a maximum SFDR of 68.7dB at 50MS/s, respectively. The ADC with an active die area of 0.53$mm^2$ consumes 15.6mW at 50MS/s with an analog voltage of 2.0V and two digital voltages of 2.8V ($=D_H$) and 1.2V ($=D_L$).

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.661-676
• /
• 2017

This study suggests a new method not only to produce the 1 km-resolution seasonal prediction but also to improve the seasonal prediction skill of temperature over South Korea. This method consists of four stages of experiments. The first stage, EXP1, is a low-resolution seasonal prediction of temperature obtained from Pusan National University Coupled General Circulation Model, and EXP2 is to produce 1 km-resolution seasonal prediction of temperature over South Korea by applying statistical downscaling to the results of EXP1. EXP3 is a seasonal prediction which considers the effect of temperature changes according to the altitude on the result of EXP2. Here, we use altitude information from ASTER GDEM, satellite observation. EXP4 is a bias corrected seasonal prediction using genetic algorithm in EXP3. EXP1 and EXP2 show poorer prediction skill than other experiments because the topographical characteristic of South Korea is not considered at all. Especially, the prediction skills of two experiments are lower at the high altitude observation site. On the other hand, EXP3 and EXP4 applying the high resolution elevation data based on remote sensing have higher prediction skill than other experiments by effectively reflecting the topographical characteristics such as temperature decrease as altitude increases. In addition, EXP4 reduced the systematic bias of seasonal prediction using genetic algorithm shows the superior performance for temporal variability such as temporal correlation, normalized standard deviation, hit rate and false alarm rate. It means that the method proposed in this study can produces high-resolution and high-quality seasonal prediction effectively.

• Journal of KIISE:Software and Applications
• /
• v.30 no.9
• /
• pp.829-842
• /
• 2003

In this Paper, we propose the new face detection and tracking method based on template matching for real-time applications such as, teleconference, telecommunication, front stage of surveillance system using face recognition, and video-phone applications. Since the main purpose of paper is to track a face regardless of various environments, we use template-based face tracking method. To generate robust face templates, we apply wavelet transform to the average face image and extract three types of wavelet template from transformed low-resolution average face. However template matching is generally sensitive to the change of illumination conditions, we apply Min-max normalization with histogram equalization according to the variation of intensity. Tracking method is also applied to reduce the computation time and predict precise face candidate region. Finally, facial components are also detected and from the relative distance of two eyes, we estimate the size of facial ellipse.

• Korean Security Journal
• /
• no.36
• /
• pp.177-200
• /
• 2013

As we enter a high industrial society that widens the gap between the rich and poor, demand for the security services has grown explosively. With the growth in quantitative expansion of security services, people have also placed increased requirements on more sophisticated and diversified security services. Consequently, market outlook for private security services industry is positive. However, Korea's private security services companies are experiencing difficulties in finding a direction to capture this new market opportunity due to their small sizes and lack of management-strategic thinking skills. Therefore, we intend to offer a direction of development for our private security services industry using a management-strategy theory and the Analytic Hierarchy Process(AHP), a structured decision-making method. A resource-based theory is one of the important management strategy theories. It explains that a company's overall performance is primarily determined by its competitive resources. Using this theory, we could analyze a company's unique resources and core competencies and set a strategic direction for the company accordingly. The usefulness and validity of this theory has been demonstrated as it has often been subject to empirical verification since 1990s. Based on this theory, we outlined a set of basic procedures to establish a management strategy for the private security services companies. We also used the AHP method to identify competitive resources, core competencies, and strategies from private security services companies in contrast with public companies. The AHP method is a technique that can be used in the decision making process by quantifying experts' knowledge and unstructured problems. This is a verified method that has been used in the management decision making in the corporate environment as well as for the various academic studies. In order to perform this method, we gathered data from 11 experts from academic, industrial, and research sectors and drew distinctive resources, competencies, and strategic direction for private security services companies vis-a-vis public organizations. Through this process, we came to the conclusion that private security services companies generally have intangible resources as their distinctive resources compared with public organization. Among those intangible resources, relational resources, customer information, and technologies were analyzed as important. In contrast, tangible resources such as equipment, funds, distribution channels are found to be relatively scarce. We also found the competencies in sales and marketing and new product development as core competencies. We chose a concentration strategy focusing on a particular market segment as a strategic direction considering these resources and competencies of private security services companies. A concentration strategy is the right fit for smaller companies as a strategy to allow them to focus all of their efforts on target customers in a single segment. Thus, private security services companies would face the important tasks such as developing a new market and appropriate products for such market segment and continuing marketing activities to manage their customers. Additionally, continuous recruitment is required to facilitate the effective use of human resources in order to strengthen their marketing competency in a long term.

• Geophysics and Geophysical Exploration
• /
• v.14 no.1
• /
• pp.80-87
• /
• 2011

Autonomous underwater vehicles (AUVs) present the important advantage of being able to approach the seafloor more closely than surface vessel surveys can. To collect bathymetric data, bottom material information, and sub-surface images, multibeam echosounder, sidescan sonar (SSS) and subbottom profiler (SBP) equipment mounted on an AUV are powerful tools. The 3000m class AUV URASHIMA was developed by the Japan Agency for Marine-Earth Science and Technology (JAMSTEC). After finishing the engineering development and examination phase of a fuel-cell system used for the vehicle's power supply system, a renovated lithium-ion battery power system was installed in URASHIMA. The AUV was redeployed from its prior engineering tasks to scientific use. Various scientific instruments were loaded on the vehicle, and experimental dives for science-oriented missions conducted from 2006. During the experimental cruise of 2007, high-resolution acoustic images were obtained by SSS and SBP on the URASHIMA around the northern Kumano Basin off Japan's Kii Peninsula. The map of backscatter intensity data revealed many debris objects, and SBP images revealed the subsurface structure around the north-eastern end of our study area. These features suggest a structure related to the formation of the latest submarine fan. However, a strong reflection layer exists below ~20 ms below the seafloor in the south-western area, which we interpret as a denudation feature, now covered with younger surface sediments. We continue to improve the vehicle's performance, and expect that many fruitful results will be obtained using URASHIMA.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.12 s.159
• /
• pp.1747-1758
• /
• 2006

Rapid development of the information technology has influenced on the changes in every sector of human environments. One prominent change in retail market is an increase of electronic stores, which has prompted practical and research interest in the product and store attributes that include consumer to purchase products from the electronic shopping. Therefore many marketers are paying much attention to the criteria of evaluating clothing and web service on internet shopping malls. The purpose of this study is to examine differences of clothing and web service criteria of consumer groups (High-Involvement & High-Ability, Low-Involvement & High-Ability, High-Involvement & Low-Ability, and Low-Involvement & Low-Ability) who are classified into consumer involvement and internet use ability. The subjects of this study were 305 people aged between 19 and 39s, living in Seoul and Gyeonggi-do area, and having experiences in buying products on the internet shopping. Statistical analyses used for this study were the frequency, percentage, factor analysis, ANOVA and Duncan test. The results of this study were as follows: Regarded on the criteria of evaluating clothing, the low different groups had significant differences in the esthetic, the quality performance and the extrinsic criterion. Both HIHA group and HILA group showed the similar results. They considered every criterion of evaluating clothing more important, compared with other groups. Regarded on the criteria of evaluating web service related to the low different groups, there were significant differences in the factors related to the shopping mall reliance, the product, the satisfaction after purchase, and the promotion and policy criterion. Both HIHA group and HILA group showed the similar results as well. They considered every criterion of evaluating web service more important, compared with other groups. In conclusion, HI groups perceive relatively more dangerous factors which can be occurred during internet shopping. Therefore, internet shopping malls need to provide clothing that can satisfy the HI groups as well as make efforts to remove the dangerous factors on the internet.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.293-299
• /
• 2007

Intelligent pipeline inspection gauges (PIGs) are inspection vehicles that move along within a (gas or oil) pipeline and acquire signals (also called sensor data) from their surrounding rings of sensors. By analyzing the signals captured in intelligent PIGs, we can detect pipeline defects, such as holes and curvatures and other potential causes of gas explosions. There are two major data access patterns apparent when an analyzer accesses the pipeline signal data. The first is a sequential pattern where an analyst reads the sensor data one time only in a sequential fashion. The second is the repetitive pattern where an analyzer repeatedly reads the signal data within a fixed range; this is the dominant pattern in analyzing the signal data. The existing PIG software reads signal data directly from the server at every user#s request, requiring network transfer and disk access cost. It works well only for the sequential pattern, but not for the more dominant repetitive pattern. This problem becomes very serious in a client/server environment where several analysts analyze the signal data concurrently. To tackle this problem, we devise a fast in-memory cache manager, called T-Cache, by considering pipeline sensor data as multiple time-series data and by efficiently caching the time-series data at T-Cache. To the best of the authors# knowledge, this is the first research on caching pipeline signals on the client-side. We propose a new concept of the signal cache line as a caching unit, which is a set of time-series signal data for a fixed distance. We also provide the various data structures including smart cursors and algorithms used in T-Cache. Experimental results show that T-Cache performs much better for the repetitive pattern in terms of disk I/Os and the elapsed time. Even with the sequential pattern, T-Cache shows almost the same performance as a system that does not use any caching, indicating the caching overhead in T-Cache is negligible.