• Korean Journal of Cognitive Science
• /
• v.35 no.1
• /
• pp.1-21
• /
• 2024

This study investigates the characteristics of visual working memory (VWM) representations by examining two theoretical models: the integrated-object and the parallel-independent feature storage models. Experiment I involved a change detection task where participants memorized arrays of either orientation bars, colored squares, or both. In the one-feature condition, the memory array consisted of one feature (either orientations or colors), whereas the two-feature condition included both. We found no differences in change detection performance between the conditions, favoring the integrated object model over the parallel-independent feature storage model. Experiment II employed a recall task with memory arrays of isosceles triangles' orientations, colored squares, or both, and one-feature and two-feature conditions were compared for their recall performance. We found again no clear difference in recall accuracy between the conditions, but the results of analyses for memory precision and guessing responses indicated the weak object model over the strong object model. For ongoing debates surrounding VWM's representational characteristics, these findings highlight the dominance of the integrated object model over the parallel independent feature storage model.

• Journal of Intelligence and Information Systems
• /
• v.18 no.4
• /
• pp.129-143
• /
• 2012

Recently, the rapid progress of a number of standardized web technologies and the proliferation of web users in the world bring an explosive increase of producing and consuming information documents on the web. In addition, most companies have produced, shared, and managed a huge number of information documents that are needed to perform their businesses. They also have discretionally raked, stored and managed a number of web documents published on the web for their business. Along with this increase of information documents that should be managed in the companies, the need of a solution to locate information documents more accurately among a huge number of information sources have increased. In order to satisfy the need of accurate search, the market size of search engine solution market is becoming increasingly expended. The most important functionality among much functionality provided by search engine is to locate accurate information documents from a huge information sources. The major metric to evaluate the accuracy of search engine is relevance that consists of two measures, precision and recall. Precision is thought of as a measure of exactness, that is, what percentage of information considered as true answer are actually such, whereas recall is a measure of completeness, that is, what percentage of true answer are retrieved as such. These two measures can be used differently according to the applied domain. If we need to exhaustively search information such as patent documents and research papers, it is better to increase the recall. On the other hand, when the amount of information is small scale, it is better to increase precision. Most of existing web search engines typically uses a keyword search method that returns web documents including keywords which correspond to search words entered by a user. This method has a virtue of locating all web documents quickly, even though many search words are inputted. However, this method has a fundamental imitation of not considering search intention of a user, thereby retrieving irrelevant results as well as relevant ones. Thus, it takes additional time and effort to set relevant ones out from all results returned by a search engine. That is, keyword search method can increase recall, while it is difficult to locate web documents which a user actually want to find because it does not provide a means of understanding the intention of a user and reflecting it to a progress of searching information. Thus, this research suggests a new method of combining ontology-based search solution with core search functionalities provided by existing search engine solutions. The method enables a search engine to provide optimal search results by inferenceing the search intention of a user. To that end, we build an ontology which contains concepts and relationships among them in a specific domain. The ontology is used to inference synonyms of a set of search keywords inputted by a user, thereby making the search intention of the user reflected into the progress of searching information more actively compared to existing search engines. Based on the proposed method we implement a prototype search system and test the system in the patent domain where we experiment on searching relevant documents associated with a patent. The experiment shows that our system increases the both recall and precision in accuracy and augments the search productivity by using improved user interface that enables a user to interact with our search system effectively. In the future research, we will study a means of validating the better performance of our prototype system by comparing other search engine solution and will extend the applied domain into other domains for searching information such as portal.

• Journal of the Korea Society for Simulation
• /
• v.15 no.3
• /
• pp.23-30
• /
• 2006

A recommender system for E-commerce site receives information from customers about which products they are interested in, and recommends products that are likely to fit their needs. In this paper, we investigate several methods for large-scale product purchase data for the purpose of producing useful recommendations to customers. We apply the traditional data mining techniques of cluster analysis and collaborative filtering(CF), and CF with reduction of product-dimensionality by use of latent semantic indexing(LSI). If reduced product-dimensionality obtained from LSI shows a similar latent trend of customers for buying products to that based on original customer-product purchase data, we expect less computational effort for obtaining the nearest-neighbor for target customer may improve the efficiency of recommendation performance. From simulation experiments on synthetic customer-product purchase data, CF-based method with reduction of product-dimensionality presents a better performance than the traditional CF methods with respect to the recall, precision and F1 measure. In general, the recommendation quality increases as the size of the neighborhood increases. However, our simulation results shows that, after a certain point, the improvement gain diminish. Also we find, as a number of products of recommendation increases, the precision becomes worse, but the improvement gain of recall is relatively small after a certain point. We consider these informations may be useful in applying recommender system.

• Journal of the Korean Society for information Management
• /
• v.19 no.4
• /
• pp.5-34
• /
• 2002

The purpose of this study is to investigate the effects of learning methods on students' information retrieval and information synthesis capability in web. This is an experimental study comparing the two different learning methods as task-based learning and technic-based learning. The findings of this study were as follows: 1. The task-based learning was more effective than the technic-based learning in information achievements as information retrieval capability (t= 3.59, p〈.05). 2. In the 1st retrieval (recall ratio t=1.81 precision ratio t=.61) of Naver Korean Web Retrieval, there was no significant difference (p〉.05). In the 2nd retrieval (recall ratio t=2.93 precision ratio t=2.45) and 3rd retrieval (recall ratio t=3.48 precision ratio t= 2.50), the task-based group was more effective than the technic-based group (p〈.05). 3. There was no significant difference in students' information synthesis capability between the task-based learning and technic-based learning (t= 1.95, p〉.05). The findings of this study suggest that the task-based learning approach is more effective to improve students' information literacy, and that professionals should consider better instructional principles for the improvement of instructional quality.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.50 no.3
• /
• pp.263-276
• /
• 2023

The purpose of this study was to evaluate the performance of a model using You Only Look Once (YOLO) for object detection of proximal caries in periapical radiographs of children. A total of 2016 periapical radiographs in primary dentition were selected from the M6 database as a learning material group, of which 1143 were labeled as proximal caries by an experienced dentist using an annotation tool. After converting the annotations into a training dataset, YOLO was trained on the dataset using a single convolutional neural network (CNN) model. Accuracy, recall, specificity, precision, negative predictive value (NPV), F1-score, Precision-Recall curve, and AP (area under curve) were calculated for evaluation of the object detection model's performance in the 187 test datasets. The results showed that the CNN-based object detection model performed well in detecting proximal caries, with a diagnostic accuracy of 0.95, a recall of 0.94, a specificity of 0.97, a precision of 0.82, a NPV of 0.96, and an F1-score of 0.81. The AP was 0.83. This model could be a valuable tool for dentists in detecting carious lesions in periapical radiographs.

• The Journal of Information Technology and Database
• /
• v.3 no.2
• /
• pp.75-96
• /
• 1996

This study is intended to compare the effectiveness of the neural network inductive learning model with a vector space model in information retrieval. As a result, searches responding to incomplete queries in the neural network inductive learning model produced a higher precision and recall as compared with searches responding to complete queries in the vector space model. The results show that the hybrid methodology of integrating an inductive learning technique with the neural network model can help solve information retrieval problems that are the results of inconsistent indexing and incomplete queries--problems that have plagued information retrieval effectiveness.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.324-331
• /
• 2005

In this paper, we propose a new customer profile model based on customer behavior in Internet shopping mall. The proposed technique defines customer profile model based on customer behavior information such as click data, buy data, and interest categories. We also implement CBCPM(Customer Behavior-based Customer Profile Model) and perform extensive experiments. The experimental results show that CBCPM has higher precision, recall, and F1 than the existing customer profile model.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10c
• /
• pp.218-221
• /
• 2006

본 논문은 인터넷의 대표적인 문제점중의 하나인 Adult Image 분류 연구에 대해 기술한다. 특히 우리는 이러한 Adult Image를 분류하기 위한 Data Set을 5가지 타입으로 구성한다. 이러한 각 Image에 대해 Color, Gradient, Edge Direction 특성의 Feature들을 추출하고 이를 Histogram으로 구성한다. 이렇게 구성된 Histogram을 Support Vector Machine에 적용하여 Adult Image를 분류한다. 그 결과, 우리는 8250개의 Test Set에 대하여 Recall(96.53%), Precision(97.33%), False Positive(2.96%), F-Measure(96.93%)의 성능 결과를 보여준다.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.22 no.4
• /
• pp.72-77
• /
• 2004

정보검색 시스템의 성능을 평가하는 요소는 재현율(recall)과 정확률(precision)이고, 재현율과 정확률을 결정하는데 가장 큰 영향을 미치는 것은 문서에 대한 색인어와 색인어 가중치이다[1]. '질의어'에 적합한 문서를 검색할 수 있는지를 결정하는 것은 "적합 문서에 대해 색인이 되어 있는가\ulcorner"하는 문제이며, 이는 재현율에 직접적인 영향을 미치게 된다. 즉, 적합 문서를 색인할 때 '질의어'에 대한 색인이 되어 있지 않은 문서는 검색이 되지 않으며, 또한 부적합 문서에 색인이 되어 있으면 부적합 문서들이 다수 검색되기 때문에 정확률이 낮아지게 된다.이 낮아지게 된다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.408-412
• /
• 2001

대용량 동영상 데이터의 효율적인 관리와 검색을 위해서는 장면 단위의 정확한 분할이 선행되어야 한다. 본 논문에서는 동영상의 시각적인 내용에 기반한 장면 전환 검출 방법을 연구하였다. 본 논문에서는 프레임 단위의 특징과 프레임 내의 부분영역 단위의 특징을 결합한 다중 특징을 사용한 장면 전환 검출 방법을 제안한다. 실험을 통한 성능 평가에서는 기존의 방법들에 비해 Recall과 Precision에서 각각 7.7%, 10%의 향상을 보였다.