• Journal of the Semiconductor & Display Technology
• /
• v.10 no.3
• /
• pp.75-81
• /
• 2011

This paper presents a novel method for image classification based on a hybrid genetic algorithm (GA) and support vector machine (SVM) approach which can significantly improve the classification performance for content-based image retrieval (CBIR). Though SVM has been widely applied to CBIR, it has some problems such as the kernel parameters setting and feature subset selection of SVM which impact the classification accuracy in the learning process. This study aims at simultaneously optimizing the parameters of SVM and feature subset without degrading the classification accuracy of SVM using GA for CBIR. Using the hybrid GA and SVM model, we can classify more images in the database effectively. Experiments were carried out on a large-size database of images and experiment results show that the classification accuracy of conventional SVM may be improved significantly by using the proposed model. We also found that the proposed model outperformed all the other models such as neural network and typical SVM models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2895-2912
• /
• 2014

Content-based image retrieval has been the most important technique for managing huge amount of images. The fundamental yet highly challenging problem in this field is how to measure the content-level similarity based on the low-level image features. The primary difficulties lie in the great variance within images, e.g. background, illumination, viewpoint and pose. Intuitively, an ideal similarity measure should be able to adapt the data distribution, discover and highlight the content-level information, and be robust to those variances. Motivated by these observations, we in this paper propose a probabilistic similarity learning approach. We first model the distribution of low-level image features and derive the free energy kernel (FEK), i.e., similarity measure, based on the distribution. Then, we propose a learning approach for the derived kernel, under the criterion that the kernel outputs high similarity for those images sharing the same class labels and output low similarity for those without the same label. The advantages of the proposed approach, in comparison with previous approaches, are threefold. (1) With the ability inherited from probabilistic models, the similarity measure can well adapt to data distribution. (2) Benefitting from the content-level hidden variables within the probabilistic models, the similarity measure is able to capture content-level cues. (3) It fully exploits class label in the supervised learning procedure. The proposed approach is extensively evaluated on two well-known databases. It achieves highly competitive performance on most experiments, which validates its advantages.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.145-155
• /
• 2002

In content-based image retrieval (CBIR), most conventional approaches assume a linear relationship between different features and require users themselves to assign the appropriate weights to each feature. However, the linear relationship assumed between the features is too restricted to accurately represent high-level concepts and the intricacies of human perception. In this paper, a neural network-based image retrieval (NNIR) model is proposed. It has been developed based on a human-computer interaction approach to CBIR using a radial basis function network (RBFN). By using the RBFN, this approach determines the nonlinear relationship between features and it allows the user to select an initial query image and search incrementally the target images via relevance feedback so that more accurate similarity comparison between images can be supported. The experiment was performed to calculate the level of recall and precision based on a database that contains 1,015 images and consists of 145 classes. The experimental results showed that the recall and level of the proposed approach were 93.45% and 80.61% respectively, which is superior than precision the existing approaches such as the linearly combining approach, the rank-based method, and the backpropagation algorithm-based method.

• Journal of the Semiconductor & Display Technology
• /
• v.13 no.2
• /
• pp.45-52
• /
• 2014

This paper proposes an efficient photo retrieval system that automatically indexes for searching of relevant images, using a combination of geo-coded information, direction/location of image capture device and content-based visual features. A photo image is labeled with its GPS (Global Positioning System) coordinates and direction of the camera view at the moment of capture, and the label leads to generate a geo-spatial index with three core elements of latitude, longitude and viewing direction. Then, content-based visual features are extracted and combined with the geo-spatial information, for indexing and retrieving the photo images. For user's querying process, the proposed method adopts two steps as a progressive approach, filtering the relevant subset prior to use a content-based ranking function. To evaluate the performance of the proposed scheme, we assess the simulation performance in terms of average precision and F-score, using a natural photo collection. Comparing the proposed approach to retrieve using only visual features, an improvement of 20.8% was observed. The experimental results show that the proposed method exhibited a significant enhancement of around 7.2% in retrieval effectiveness, compared to previous work. These results reveal that a combination of context and content analysis is markedly more efficient and meaningful that using only visual feature for image search.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.479-484
• /
• 1998

As technology in a computer hardware and software advances, efficient information retrieval from multimedia database gets highly demanded. Recently, it has been actively exploited to retrieve information based on the stored contents. However, most of the methods emphasize on the points which are far from human intuition or emotion. In order to overcome this shortcoming , this paper attempts to apply interactive genetic algorithm to content-based image retrieval. A preliminary result with subjective test shows the usefulness of this approach.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.11
• /
• pp.5673-5691
• /
• 2019

Information centric mobile network can significantly improve the data retrieving efficiency by caching contents at mobile edge. However, the cache pollution attack can affect the data obtaining process severely by requiring unpopular contents deliberately. To tackle the problem, we design an algorithm of mitigating cache pollution attacks in information centric mobile network. Particularly, the content popularity distribution statistic is proposed to detect abnormal behavior. Then a probabilistic caching strategy based on abnormal behavior is applied to dynamically maintain the steady-state distribution for content visiting probability and achieve the purpose of defense. The experimental results show that the proposed scheme can achieve higher request hit ratio and smaller latency for false locality content pollution attack than the CacheShield approach and the baseline approach where no mitigation approach is applied.

• Journal of The Korean Association For Science Education
• /
• v.32 no.8
• /
• pp.1356-1366
• /
• 2012

As the recent demand for human resources in science, technology, engineering, and mathematics (STEM), the development of professional STEM teacher is called worldwide. It is becoming a critical need in teacher education in order to educate student teachers, and prepare pre-service and beginning teachers for high quality of teaching competency. To promote the competency for $21^{st}$ century STEM teachers, the epistemology of technological pedagogical content knowledge (TPACK) is currently considered as the essential qualities of knowledge for highly qualified teachers. The aim of this study is explore the effect of case-based learning approach on TPACK competency of pre-service STEM teachers. In order to develop the pre-service teachers' competency regarding effective integration of technologies into teaching specific content areas, a series of innovative case study teaching in science and mathematics was presented to 43 participants of pre-service physics, chemistry, biology, mathematics, and computer teachers during a course of information and communication technology (ICT) in Education at Khon Kaen University, Thailand. After finishing a case presentation, the pre-service teachers were encouraged into a forum of critical open discussion by considering the potential impact of the case and the TPACK framework. They were investigated instructional design competency of using ICT tools into student learning process and their personal beliefs about ICT in educational process both before and after. The participant's reactions and learning was evaluated by using a self-reported questionnaire and an implementation log of content-specific learning process design, respectively. Results showed a change of their beliefs and the transformation of their TPACK competency in STEM teaching. In an effort to better serve the needs of high quality STEM teachers, the results of this study illustrated that the competency of TPACK could be particularly considered as a core attributes for future STEM teachers. By the way, case-based learning approach can play an effective part in preparing and professing the TPACK competency for STEM teachers.

• Asia pacific journal of information systems
• /
• v.33 no.3
• /
• pp.541-572
• /
• 2023

Amazon Go is a cashierless convenience store concept, which is seen as a disruption in the grocery retail segment. Although Amazon Go has the ability to disrupt the retail segment, there are speculations on how Amazon Go will be perceived by users. Existing studies have not utilized user-generated content to understand the factors that affect customer behaviour in case of Amazon Go. Additionally, in case of phygital retail, studies have not attempted at understanding the effect of emotions and gratifications on user behaviour. To address the gap of exploring user perspectives based on their experience, we have examined the impact of gratifications and emotions on the acceptance of phygital retail using user-generated-content. A mixed-method approach has been utilized using only user-generated content. Utilizing topic-modelling based content analysis and emotion analysis on 30 articles related to Amazon Go, we found themes like, convenience, technology, experience, personalization, enjoyment and emotions like, bad, good, annoyance, success. In the empirical analysis, we have utilized 522 reviews about Amazon Go from the cognition and emotion theory stance, and found that hedonic gratifications have a positive impact on challenge emotions. We also found a significant impact of emotions on customer's favourite behaviour.

• The KIPS Transactions:PartD
• /
• v.18D no.5
• /
• pp.323-328
• /
• 2011

For content-based image retrieval, the earth mover's distance and the optimal color composition distance are proposed to measure the dissimilarity. Although providing good retrieval results, both methods are too time-consuming to be used in a large image database. To solve the problem, we propose a new distance function that calculates an approximate earth mover's distance in linear time. To calculate the dissimilarity in linear time, the proposed approach employs the space-filling curve. We have performed extensive experiments to show the effectiveness and efficiency of the proposed approach. The results reveal that our approach achieves almost the same results with the EMD in linear time.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.5
• /
• pp.1097-1104
• /
• 2011

In this paper, we propose a semantic web approach for personalized book recommendation. Our approach takes advantage of the content-based recommendation and improves its disadvantage that users should input their interesting fields into all book search systems they use. Our approach provides the sharing of users' profile with their interesting fields by enabling user's interesting fields to be described over each book classification ontology of various book information providers. We also provide a middleware that manages users' profiles written in RDF and analizes similarity between user's interesting field and each concept over the book classification ontology. Our approach provide better performance than traditional keyword-based search by sharing the user's profile among book recommendation systems.