Digital Library[ Search Result ]
Saliency-based SVG Image Placeholder Generation
http://doi.org/10.5626/JOK.2019.46.1.39
Image placeholders are small file-size images used instead of original images for fast and efficient loading of large file-size images, or large-scale of images on the web. While various image placeholder generation techniques based on Scalar Vector Graphics (SVG) have been proposed, file size of the image placeholder increases inevitably for detailed description. Our method generates an SVG-based image placeholder by optimal placement of geometric primitives based on visual saliency. This method generates a smaller file-size placeholder while showing similar visual effects. From experimental results, we could observe that the saliency-based method produces high level-of-detail without increasing file size. Saliency-based SVG image placeholder generation will be useful for web-based services.
Visual Scene Understanding with Contexts
http://doi.org/10.5626/JOK.2018.45.12.1279
In this paper, as a visual scene understanding problem, we address the problem of generating corresponding scene graphs and image captions from input images. While a scene graph is a formal knowledge representation expressing in-image objects and their relationships, an image caption is a natural language sentence describing the scene captured in the given image. To address the problem effectively, we propose a novel deep neural network model, CSUN(Context-based Scene Understanding Network), to generate two different representations in a complementary way, by exchanging useful contexts with each other. The proposed model consists of three different layers, such as object detection, relationship detection, and caption generation, each of which makes use of proper context to accomplish its own task. To evaluate performance of the proposed model, we conduct various experiments on a large-scale benchmark dataset, Visual Genome. Through these experiments, we demonstrate that our model using useful contexts, achieves significant improvements in accuracy over state-of-the-art models.
Inferring User Traits from Applications Installed on a Smart Phone
Hongdo Ki, Jaehong Lee, Heewoong Park, Moon-jung Chae, Sangwoo Choi, Jonghun Park
http://doi.org/10.5626/JOK.2018.45.12.1240
Needs for customized services are increasing as a smart phone personalized device, has been used generally. Demographic information is beneficial for customized services, so inferring user traits based various data using statistical learning has been actively studied. This study conducted experiments of inferring user traits with a list of installed applications differed by users’ interest and lifestyle, and may can be accessed easily as a snapshot without explicit permission. Four feature vectors are used for inferring user traits, including vectors using application category or description that can be collected from the application market. Especially, one of the feature vectors is generated by applying Doc2Vec, a text embedding method based on a neural network, to application description. The application selection method we proposed is also used to achieve better performances than could be achieved by using all applications on the list. Last, we collected 100 lists of installed applications for experiments of inferring gender, age, relationship status, residential type, living together or not, income, outcome, height, weight, religion, semester and college, and confirmed effectiveness of proposed feature vectors and the application selection method.
Partial Embedding Approach for Knowledge Completion
Wan-Gon Lee, Batselem Jagvaral, Ji-Hun Hong, Hyun-Young Choi, Young-Tack Park
http://doi.org/10.5626/JOK.2018.45.11.1168
Knowledge graphs are large networks that describe real world entities and their relationships with triples. Most of the knowledge graphs are far from being complete, and many previous studies have addressed this problem using low dimensional graph embeddings. Such methods assume that knowledge graphs are fixed and do not change. However, real-world knowledge graphs evolve at a rapid pace with the addition of new triples.Repeated retraining of embedding models for the entire graph is computationally expensive and impractical. In this paper, we propose a partial embedding method for partial completion of evolving knowledge graphs. Our method employs ontological axioms and contextual information to extract relations of interest and builds entity and relation embedding models based on instances of such relations. Our experiments demonstrated that the proposed partial embedding method can produce comparable results on knowledge graph completion with state-of-the-art methods while significantly reducing the computation time of entity and relation embeddings by 49%–90% for the Freebase and WiseKB datasets.
Automatic Segmentation of Renal Parenchyma using Shape and Intensity Information based on Multi-atlas in Abdominal CT Images
Hyeonjin Kim, Helen Hong, Kidon Chang, Koon Ho Rha
http://doi.org/10.5626/JOK.2018.45.9.937
Renal parenchyma segmentation is necessary to predict contralateral hypertrophy after renal partial nephrectomy. In this paper, we propose an automatic segmentation method of renal parenchyma using shape and intensity information based on the multi-atlas in abdominal CT images. First, similar atlases are selected using volume-based similarity registration and intensity-similarity measure. Second, renal parenchyma is segmented using two-stage registration and constrained intensity-based locally-weighted voting. Finally, renal parenchyma is refined using a Gaussian mixture model-based multi-thresholds and shape-prediction map in under- and over-segmented data. The average dice similarity coefficient of renal parenchyma was 91.34%, which was 18.19%, 1.35% higher than the segmentation method using majority voting and locally-weighted voting in dice similarity coefficient, respectively.
Graph Construction Based on Fast Low-Rank Representation in Graph-Based Semi-Supervised Learning
http://doi.org/10.5626/JOK.2018.45.1.15
Low-Rank Representation (LRR) based methods are widely used in many practical applications, such as face clustering and object detection, because they can guarantee high prediction accuracy when used to constructing graphs in graph – based semi-supervised learning. However, in order to solve the LRR problem, it is necessary to perform singular value decomposition on the square matrix of the number of data points for each iteration of the algorithm; hence the calculation is inefficient. To solve this problem, we propose an improved and faster LRR method based on the recently published Fast LRR (FaLRR) and suggests ways to introduce and optimize additional constraints on the underlying optimization goals in order to address the fact that the FaLRR is fast but actually poor in classification problems. Our experiments confirm that the proposed method finds a better solution than LRR does. We also propose Fast MLRR (FaMLRR), which shows better results when the goal of minimizing is added.
Controlling a Traversal Strategy of Abstract Reachability Graph-based Software Model Checking
http://doi.org/10.5626/JOK.2017.44.10.1034
Although traversal strategies are important for the performance of model checking, many studies have ignored the impact of traversal strategies in model checking with a block-encoded abstract reachability graph. Studies have considered traversal strategies only for an abstract reachability graph without block-encoding. Block encoding plays a crucial role in the model checking performance. This paper therefore describes Dual-traversal strategy, a simple and novel technique to control traversal strategies in a block-encoded abstract reachability graph. This method uses two traversal strategies for a model checking, one for effective block-encoding, and the other for traversal in an encoded abstract reachability graph. Dual-traversal strategy is very simple and can be implemented without overhead compared to the existing single-traversal strategy. We implemented the Dual-traversal strategy in an open source model checking tool and compare the performances of different traversal strategies. The results show that the model checking performance varies from the traversal strategies for the encoded abstract reachability graph.
Efficient Shortest Path Techniques on a Summarized Graph based on the Relationships
Hyunwook Kim, HoJin Seo, Young-Koo Lee
http://doi.org/10.5626/JOK.2017.44.7.710
As graphs are becoming increasingly large, the costs for storing and managing data are increasing continuously. Shortest path discovery over a large graph requires long running time due to frequent disk I/Os and high complexity of the graph data. Recently, graph summarization techniques have been studied, which reduce the size of graph data and disk I/Os by representing highly dense subgraphs as a single super-node. Decompressing should be minimized for efficient shortest path discovery over the summarized graph. In this paper, we analyze the decompression performance of a summarized graph and propose an approximate technique that discovers the shortest path quickly with a minimum error ratio. We also propose an exact technique that efficiently discovered the shortest path by exploiting an index built on paths containing super-nodes. In our experiments, we showed that the proposed technique based on the summarized graph can reduce the running time by up to 70% compared with the existing techniques performed on the original graph.
Graph-based Wi-Fi Radio Map Construction and Update Method
http://doi.org/10.5626/JOK.2017.44.6.643
Among Wi-Fi based indoor positioning systems, fingerprinting localization is the most common technique with high precision. However, construction of the initial radio map and the update process require considerable labor and time effort. To address this problem, we propose an efficient method that constructs the initial radio map at each vertex based on a graph. In addition, we introduce a method to update the radio map automatically by mapping signal data acquired from users to the reference point created on each edge. Since the proposed method collects signal data manually only at the vertex of the graph to build the initial radio map and updates it automatically, our proposed method can dramatically reduce labor and time effort, which are the disadvantages of the conventional fingerprinting method. In our experimental study, we show validity of our radio map update method by comparing with the actual reference point data. We also show that our proposed method is able to construct the radio map with an accuracy of about 3.5m by automatically updating the radio map.
Automatic Keyword Extraction using Hierarchical Graph Model Based on Word Co-occurrences
Keyword extraction can be utilized in text mining of massive documents for efficient extraction of subject or related words from the document. In this study, we proposed a hierarchical graph model based on the co-occurrence relationship, the intrinsic dependency relationship between words, and common sub-word in a single document. In addition, the enhanced TextRank algorithm that can reflect the influences of outgoing edges as well as those of incoming edges is proposed. Subsequently a novel keyword extraction scheme using the proposed hierarchical graph model and the enhanced TextRank algorithm is proposed to extract representative keywords from a single document. In the experiments, various evaluation methods were applied to the various subject documents in order to verify the accuracy and adaptability of the proposed scheme. As the results, the proposed scheme showed better performance than the previous schemes.
Search
Journal of KIISE
- ISSN : 2383-630X(Print)
- ISSN : 2383-6296(Electronic)
- KCI Accredited Journal
Editorial Office
- Tel. +82-2-588-9240
- Fax. +82-2-521-1352
- E-mail. chwoo@kiise.or.kr