Search

Patient similarity analytics has emerged as an essential tool to identify cohorts of patients who have similar clinical characteristics to some specific patient of interest. In this study, we propose a patient similarity measure called D3K that incorporates domain knowledge and data-driven insights. Using the electronic health records (EHRs) of 169,434 patients with either diabetes, hypertension or dyslipidaemia (DHL), we construct patient feature vectors containing demographics, vital signs, laboratory test results, and prescribed medications. We discretize the variables of interest into various bins based on domain knowledge and make the patient similarity computation to be aligned with clinical guidelines. Key findings from this study are: (1) D3K outperforms baseline approaches in all seven sub-cohorts, (2) our domain knowledge-based binning strategy outperformed the traditional percentile-based binning in all seven sub-cohorts, (3) there is substantial agreement between D3K and physicians (κ = 0.746), indicating that D3K can be applied to facilitate shared decision making. This is the first study to use patient similarity analytics on a cardiometabolic syndrome-related dataset sourced from medical institutions in Singapore. We consider patient similarity among patient cohorts with the same medical conditions to develop localized models for personalized decision support to improve the outcomes of a target patient.

Credit risk assessment is an important process for every financial institution. Most current studies in this area focus on the development of the classifiers. However, besides the classifiers, data analysis and mining also play an important role in improving the accuracy. In this paper, an integrated feature selection method is proposed combing the analysis of the data in one feature but belongs to different labels and the analysis of the relationship between a single feature and labels. Back propagation neural network is used as the classification model. Experiments are done on Australian credit approval dataset. The results show that the proposed integrated feature selection can improve the accuracy of assessment compared with other previous work.

This paper investigates the foot types and structural features of Chinese four-syllable abbreviations. Results show that: first, whether for the need of complexity and richness of ideogram or for avoiding ambiguity, these abbreviated forms are an essential and meaningful part of modern Chinese abbreviations; second, most of the existing forms tend to present 2 + 2 balanced prosodic structure, nominal attribute in part of speech. In addition, there also exists the possibility of abbreviation further to less than four syllables under some specific conditions.

Large-scale image datasets and deep convolutional neural networks (DCNNs) are the two primary driving forces for the rapid progress in generic object recognition tasks in recent years. While lots of network architectures have been continuously designed to pursue lower error rates, few efforts are devoted to enlarging existing datasets due to high labeling costs and unfair comparison issues. In this article, we aim to achieve lower error rates by augmenting existing datasets in an automatic manner. Our method leverages both the web and DCNN, where the web provides massive images with rich contextual information, and DCNN replaces humans to automatically label images under the guidance of web contextual information. Experiments show that our method can automatically scale up existing datasets significantly from billions of web pages with high accuracy. The performance on object recognition tasks and transfer learning tasks have been significantly improved by using the automatically augmented datasets, which demonstrates that more supervisory information has been automatically gathered from the web. Both the dataset and models trained on the dataset have been made publicly available.

We propose the Unified Visual-Semantic Embeddings (Unified VSE) for learning a joint space of visual representation and textual semantics. The model unifies the embeddings of concepts at different levels: objects, attributes, relations, and full scenes. We view the sentential semantics as a combination of different semantic components such as objects and relations; their embeddings are aligned with different image regions. A contrastive learning approach is proposed for the effective learning of this fine-grained alignment from only image-caption pairs. We also present a simple yet effective approach that enforces the coverage of caption embeddings on the semantic components that appear in the sentence. We demonstrate that the Unified VSE outperforms baselines on cross-modal retrieval tasks; the enforcement of the semantic coverage improves the model's robustness in defending text-domain adversarial attacks. Moreover, our model empowers the use of visual cues to accurately resolve word dependencies in novel sentences.

Background Helicobacter pylori infection increases the risk of gastric cancer. The study aimed to compare cost-effectiveness ratios of H. pylori test-and-treat programs to prevent gastric cancer in Taiwan, referring to the nationwide reimbursement database and expected years of life lost. Materials and Methods During 1998–2009, there were 12,857 females and 24,945 males with gastric adenocarcinoma in Taiwan National Cancer Registry. They were followed up to 2010 and linked to the reimbursement database of National Health Insurance and the national mortality registry to determine lifetime health expenditures and expected years of life lost. Cost-effectiveness ratios of H. pylori test-and-treat programs for prevention of gastric adenocarcinoma were compared between screenings with 13C-urea breath test and with anti-H. pylori IgG. Results The test-and-treat program with anti-H. pylori IgG to prevent gastric adenocarcinoma had lower incremental cost-effectiveness ratios than that with 13C-urea breath test in both sexes (females: 244 vs 1071 US dollars/life-year; males: 312 vs 1431 US dollars/life-year). Cost saving would be achieved in an endemic area where H. pylori prevalence was >73.5%, or by selecting subpopulations with high absolute risk reduction rates of cancer after eradication. Moreover, expected years of life lost of gastric adenocarcinoma were higher and the incremental cost-effectiveness ratios of test-and-treat programs were more cost-effective in young adults (30–69 y/o) than in elders (≥70 y/o). Conclusions The test-and-treat program with anti-H. pylori IgG shall be cost-effective to prevent gastric adenocarcinoma in a high endemic area, especially beginning at 30 years of age when H. pylori prevalence rates become stabilized.

Since 1997, internet-based e-government has been promoted by the Research and Development Review Board of Executive Yuan, R.O.C., and the application of electronic forms is one of the e-government processes. Electronic form system includes integrated document management and files management systems and is integrated with an electronic attendance system as well. In this way, other than merely achieving creating a paperless system, it also reduces the manpower required for paper-form transmission and shortens document delivery time.

In order to help individuals effectively manage and record these health check physiological measurement data, this research developed an “Integrated Health Check Report Analysis and Tracking Platform” together with H&B Health Centers. Using this platform, the public can query health check data and analysis charts from health check centers through a website. The information will include suggestions from doctors, nutritionists and representatives of various health check categories. The meanings behind various data can be explained to the general public using illustrations.

An incisive understanding of user personality is not only essential to many scientific disciplines, but also has a profound business impact on practical applications such as digital marketing, personalized recommendation, mental diagnosis, and human resources management. Previous studies have demonstrated that language usage in social media is effective in personality prediction. However, except for single language features, a less researched direction is how to leverage the heterogeneous information on social media to have a better understanding of user personality. In this paper, we propose a Heterogeneous Information Ensemble framework, called HIE, to predict users' personality traits by integrating heterogeneous information including self-language usage, avatar, emoticon, and responsive patterns. In our framework, to improve the performance of personality prediction, we have designed different strategies extracting semantic representations to fully leverage heterogeneous information on social media. We evaluate our methods with extensive experiments based on a real-world data covering both personality survey results and social media usage from thousands of volunteers. The results reveal that our approaches significantly outperform several widely adopted state-of-the-art baseline methods. To figure out the utility of HIE in a real-world interactive setting, we also present DiPsy, a personalized chatbot to predict user personality through heterogeneous information in digital traces and conversation logs.

The present study aimed to investigate the abilities of visual information processing in racket sport players, and to compare the differences with their peers. Fifty-four male college-aged athletes were recruited and divided into two racket sport groups, including table tennis (TT, n = 22) and badminton (BT, n = 32) groups. Additionally, 22 healthy college students without regular physical activities were randomly selected and served as control subjects. The covert orienting of visuo-spatial attention tasks was used to evaluate the abilities of visual information processing. The data including the reaction time (RT) and response error rate (RER) were recorded and analyzed. Results showed that the athletes in TT and BT groups performed significantly better than the control subjects in the reaction time. In addition, RT of upper limbs, lower limbs, dominant side and non-dominant side was significantly different between the groups, and RT of upper limbs was quicker than that of lower limbs in both groups. Except control group, the RT of dominant side was quicker than that of non-dominant side. In conclusion, elite racket sport players had quicker RT than their peers, but those players seemed not to perform better in RER. It is recommended to recruit more athletes participating in different sports to acquire further information on sport-specific characteristics of visual information processing. Furthermore, it is undisputable for the selection of efficient talent athletes to establish the database of visual information processing abilities in different kinds of sports.

It combines the augmented reality technology and mobile learning devices, and integrates the real scene and virtual augmented information in the mobile learning device. This paper discusses the principle of Augmented Reality and the mobile learning based on Augmented Reality based on the cloud computing. It will have some reference value for the future development.

Digital urban management system is an important part of digital city construction and urban components collecting system is base of digital urban management system. This paper proposes a scheme of urban collecting system mainly with collecting urban components information by car-borne road information system and supplementing with RTK survey.

There are various kinds of valuable semantic information about real-world entities embedded in webpages and databases. Extracting and integrating these entity information from the Web is of great significance. Comparing to traditional information extraction problems, web entity extraction needs to solve several new challenges to fully take advantage of the unique characteristic of the Web. In this paper, we introduce our recent work on statistical extraction of structured entities, named entities, entity facts and relations from Web. We also briefly introduce iKnoweb, an interactive knowledge mining framework for entity information integration. We will use two novel web applications, Microsoft Academic Search (aka Libra) and EntityCube, as working examples.

Recently a few systems for automatically solving math word problems have reported promising results. However, the datasets used for evaluation have limitations in both scale and diversity. In this paper, we build a large-scale dataset which is more than 9 times the size of previous ones, and contains many more problem types. Problems in the dataset are semi-automatically obtained from community question-answering (CQA) web pages. A ranking SVM model is trained to automatically extract problem answers from the answer text provided by CQA users, which significantly reduces human annotation cost. Experiments conducted on the new dataset lead to interesting and surprising results.

Labelled image datasets are the backbone for high-level image understanding tasks with wide application scenarios, and continuously drive and evaluate the progress of feature designing and supervised learning models. Recently, the million scale labelled image dataset further contributes to the rebirth of deep convolutional neural network and bypass manual designing handcraft features. However, the construction process of image dataset is mainly manual-based and quite labor intensive, which often take years' efforts to construct a million scale dataset with high quality. In this paper, we propose a deep learning based method to construct large scale image dataset in an automatic way. Specifically, word representation and image representation are learned in a deep neural network from large amount of click-through logs, and further used to define word-word similarity and image-word similarity. These two similarities are used to automatize the two labor intensive steps in manual-based image dataset construction: query formation and noisy image removal. With a new proposed cross convolutional filter regularizer, we can construct a million scale image dataset in one week. Finally, two image datasets are constructed to verify the effectiveness of the method. In addition to scale, the automatically constructed dataset has comparable accuracy, diversity and cross-dataset generalization with manually labelled image datasets.

Networks in real world usually have multiple layers. Most of the current works concentrate on the single-layer network. Visualization of double-layer networks using 2.5D method is proposed in this paper to reveal the network structure and interdependent relations within network layers. A context-preserving layout method and matrix transformation is adopted to preserve node positions and reduce visual clutters within network layers. Visual analysis is conducted based on the 2.5D visualization, focusing on the interdependent relations and node importance evaluation. The proposed method ensures satisfying readability of the network structural features and demonstrates the relations in the network.

The increasing availability of location-acquisition technologies (GPS, GSM networks, etc.) enables people to log the location histories with spatio-temporal data. Such real-world location histories imply, to some extent, users' interests in places, and bring us opportunities to understand the correlation between users and locations. In this article, we move towards this direction and report on a personalized friend and location recommender for the geographical information systems (GIS) on the Web. First, in this recommender system, a particular individual's visits to a geospatial region in the real world are used as their implicit ratings on that region. Second, we measure the similarity between users in terms of their location histories and recommend to each user a group of potential friends in a GIS community. Third, we estimate an individual's interests in a set of unvisited regions by involving his/her location history and those of other users. Some unvisited locations that might match their tastes can be recommended to the individual. A framework, referred to as a hierarchical-graph-based similarity measurement (HGSM), is proposed to uniformly model each individual's location history, and effectively measure the similarity among users. In this framework, we take into account three factors: 1) the sequence property of people's outdoor movements, 2) the visited popularity of a geospatial region, and 3) the hierarchical property of geographic spaces. Further, we incorporated a content-based method into a user-based collaborative filtering algorithm, which uses HGSM as the user similarity measure, to estimate the rating of a user on an item. We evaluated this recommender system based on the GPS data collected by 75 subjects over a period of 1 year in the real world. As a result, HGSM outperforms related similarity measures, namely similarity-by-count, cosine similarity, and Pearson similarity measures. Moreover, beyond the item-based CF method and random recommendations, our system provides users with more attractive locations and better user experiences of recommendation.

User mobility has given rise to a variety of Web applications, in which the global positioning system (GPS) plays many important roles in bridging between these applications and end users. As a kind of human behavior, transportation modes, such as walking and driving, can provide pervasive computing systems with more contextual information and enrich a user's mobility with informative knowledge. In this article, we report on an approach based on supervised learning to automatically infer users' transportation modes, including driving, walking, taking a bus and riding a bike, from raw GPS logs. Our approach consists of three parts: a change point-based segmentation method, an inference model and a graph-based post-processing algorithm. First, we propose a change point-based segmentation method to partition each GPS trajectory into separate segments of different transportation modes. Second, from each segment, we identify a set of sophisticated features, which are not affected by differing traffic conditions (e.g., a person's direction when in a car is constrained more by the road than any change in traffic conditions). Later, these features are fed to a generative inference model to classify the segments of different modes. Third, we conduct graph-based postprocessing to further improve the inference performance. This postprocessing algorithm considers both the commonsense constraints of the real world and typical user behaviors based on locations in a probabilistic manner. The advantages of our method over the related works include three aspects. (1) Our approach can effectively segment trajectories containing multiple transportation modes. (2) Our work mined the location constraints from user-generated GPS logs, while being independent of additional sensor data and map information like road networks and bus stops. (3) The model learned from the dataset of some users can be applied to infer GPS data from others. Using the GPS logs collected by 65 people over a period of 10 months, we evaluated our approach via a set of experiments. As a result, based on the change-point-based segmentation method and Decision Tree-based inference model, we achieved prediction accuracy greater than 71 percent. Further, using the graph-based post-processing algorithm, the performance attained a 4-percent enhancement.

The popularity of mobile devices, such as PDAs and SmartPhones, has grown rapidly over the last couple of years. Though most users still perform searches using desktop computers, it is expected that more and more people will also search the Web while they are on the move. In addition to text-based keyword queries, mobile devices can support richer and hybrid queries such as images, audio, video, and their combinations. In this paper, we will discuss mobile search systems that support image queries and audio queries, covering typical designs for mobile visual and audio search, as well as the opportunities and challenges. Specifically, we will present an in-depth study of two real systems we have developed: product image categorization and mobile ringtone search, which use image queries and audio queries, respectively. Experimental results on real-life data demonstrate their effectiveness and efficiency.

In recent years, relevance feedback has been studied extensively as a way to improve performance of content-based image retrieval (CBIR). Since users are usually unwilling to provide much feedback, the insufficiency of training samples limits the success of relevance feedback. In this paper, we propose two strategies to tackle this problem: (i) to make relevance feedback more informative by presenting representative images for users to label; (ii) to make use of unlabeled data in the training process. As a result, an active feedback framework is proposed, consisting of two components, representative image selection and label propagation. For practical implementation of this framework, we develop two coupled algorithms corresponding to the two components, namely, overlapped subspace clustering and multi-subspace label propagation. Experimental results on a very large-scale image collection demonstrated the high effectiveness of the proposed active feedback framework.

Although it has been studied for years by the computer vision and machine learning communities, image annotation is still far from practical. In this paper, we propose a novel attempt at model-free image annotation, which is a data-driven approach that annotates images by mining their search results. Some 2.4 million images with their surrounding text are collected from a few photo forums to support this approach. The entire process is formulated in a divide-and-conquer framework where a query keyword is provided along with the uncaptioned image to improve both the effectiveness and efficiency. This is helpful when the collected data set is not dense everywhere. In this sense, our approach contains three steps: 1) the search process to discover visually and semantically similar search results, 2) the mining process to identify salient terms from textual descriptions of the search results, and 3) the annotation rejection process to filter out noisy terms yielded by Step 2. To ensure real-time annotation, two key techniques are leveraged - one is to map the high-dimensional image visual features into hash codes, the other is to implement it as a distributed system, of which the search and mining processes are provided as Web services. As a typical result, the entire process finishes in less than 1 second. Since no training data set is required, our approach enables annotating with unlimited vocabulary and is highly scalable and robust to outliers. Experimental results on both real Web images and a benchmark image data set show the effectiveness and efficiency of the proposed algorithm. It is also worth noting that, although the entire approach is illustrated within the divide-and- conquer framework, a query keyword is not crucial to our current implementation. We provide experimental results to prove this.

Although much work has been done on duplicate document detection (DDD) and its applications, we observe the absence of a systematic study on the performance and scalability of large-scale DDD algorithms. It is still unclear how various parameters in DDD correlate mutually, such as similarity threshold, precision/recall requirement, sampling ratio, and document size. This paper explores the correlations among several most important parameters in DDD and the impact of sampling ratio is of most interest since it heavily affects the accuracy and scalability of DDD algorithms. An empirical analysis is conducted on a million HTML documents from the TREC .GOV collection. Experimental results show that even when using the same sampling ratio, the precision of DDD varies greatly on documents with different sizes. Based on this observation, we propose an adaptive sampling strategy for DDD, which minimizes the sampling ratio with the constraint of a given precision requirement. We believe that the insights from our analysis are helpful for guiding the future large-scale DDD work.

Topic distillation is one of the main information needs when users search the Web. Previous approaches for topic distillation treat single page as the basic searching unit, which has not fully utilized the structure information of the Web. In this paper, we propose a novel concept for topic distillation, named sub-site retrieval, in which the basic searching unit is sub-site instead of single page. A sub-site is the subset of a website, consisting of a structural collection of pages. The key of sub-site retrieval includes (1) extracting effective features for the representation of a sub-site using both the content and structure information, (2) delivering the sub-site-based retrieval results with a friendly and informative user interface. For the first point, we propose Punished Integration algorithm, which is based on the modeling of the growth of websites. For the second point, we design a user interface to better illustrate the search results of sub-site retrieval. Testing on the topic distillation task of TREC 2003 and 2004, sub-site retrieval leads to significant improvement of retrieval performance over the previous methods based on single pages. Furthermore, time complexity analysis shows that sub-site retrieval can be integrated into the index component of search engines.

In order to improve the retrieval accuracy of content-based image retrieval systems, research focus has been shifted from designing sophisticated low-level feature extraction algorithms to reducing the 'semantic gap' between the visual features and the richness of human semantics. This paper attempts to provide a comprehensive survey of the recent technical achievements in high-level semantic-based image retrieval. Major recent publications are included in this survey covering different aspects of the research in this area, including low-level image feature extraction, similarity measurement, and deriving high-level semantic features. We identify five major categories of the state-of-the-art techniques in narrowing down the 'semantic gap': (1) using object ontology to define high-level concepts; (2) using machine learning methods to associate low-level features with query concepts; (3) using relevance feedback to learn users' intention; (4) generating semantic template to support high-level image retrieval; (5) fusing the evidences from HTML text and the visual content of images for WWW image retrieval. In addition, some other related issues such as image test bed and retrieval performance evaluation are also discussed. Finally, based on existing technology and the demand from real-world applications, a few promising future research directions are suggested.

Inner product transform principle reveals that the basis functions most relevant or similar to the fault features are pivotal to the meaningful fault detection. Customized multiwavelet methods and practices have continued to improve over the recent years, focused on two-scale similarity transform (TST), lifting transform (LT), and lifting scheme (LS). Due to the respective advantages and disadvantages, a comparative study on the multiwavelet construction methods by TST, symmetric and dissymmetric LT, and LS is discussed in the paper, covering the differences of construction theories, the synthetic analyses of construction strategies, and the comparison of waveform characteristics along with their applicable occasions. Comprehensively utilizing the capabilities of the construction methods, a novel customized multiwavelet library is established for the accurate fault detection. The proposed method is applied to incipient fault detection of rolling bearing for electric locomotive to verify the effectiveness and feasibility.

Pictures have become increasingly common and popular in mobile communications. However, due to the limitation of mobile devices, there is a need to develop new technologies to facilitate the browsing of large pictures on the small screen. In this paper, we propose a set of novel approaches which are able to aid or automate common image browsing tasks on mobile devices. All of these approaches are based on an image attention model which is employed to illustrate the information structure within an image. An efficient algorithm to generate the optimal browsing path based on the information foraging theory is presented. Experimental evaluations of the proposed mechanism indicate that our approach is an effective way for viewing large images on small displays

Algorithms on streaming data have attracted increasing attention in the past decade. Among them, dimensionality reduction algorithms are greatly interesting due to the desirability of real tasks. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are two of the most widely used dimensionality reduction approaches. However, PCA is not optimal for general classification problems because it is unsupervised and ignores valuable label information for classification. On the other hand, the performance of LDA is degraded when encountering limited available low-dimensional spaces and singularity problem. Recently, Maximum Margin Criterion (MMC) was proposed to overcome the shortcomings of PCA and LDA. Nevertheless, the original MMC algorithm could not satisfy the streaming data model to handle large-scale high-dimensional data set. Thus an effective, efficient and scalable approach is needed. In this paper, we propose a supervised incremental dimensionality reduction algorithm and its extension to infer adaptive low-dimensional spaces by optimizing the maximum margin criterion. Experimental results on a synthetic dataset and real datasets demonstrate the superior performance of our proposed algorithm on streaming data.

Selecting optimization ship form scheme is an important content in the process of concept design of ship. Multi-objective fuzzy decision-making model for ship form demonstration is set up according to the fuzzy pattern-recognition theory. Weight coefficients of each target of ship form scheme are determined by information entropy and individual subjective partiality. This model is used to select the optimal ship form scheme, the example shows that the model is exact and the result is credible. It can provide a reference for choosing the optimization scheme of ship form.

The limited display size of current small Internet devices is becoming a serious obstacle to information access. In this paper, we introduce a Document REpresentation for Scalable Structures (DRESS) to help information providers make composite documents, typically web pages, scalable in both logic and layout structure to support effective information acquisition in heterogeneous environments. Through this novel document representation structure based on binary slicing trees, the document can dynamically adapt its presentation according to display sizes by maximizing the information throughput to users. We discuss the details of this structure with its key attributes. An automatic approach for generating this structure for existing web pages is also presented. A branch-and-bound algorithm and a capacity ratio-based slicing method are proposed to select proper content representation and aesthetic document layouts respectively. A set of user study experiments have been carried out and the results show that compared with the thumbnail-based approach, the DRESS-based interface can reduce browsing time by 23.5%.

Multiclass classification has been investigated for many years in the literature. Recently, the scales of real-world multiclass classification applications have become larger and larger. For example, there are hundreds of thousands of categories employed in the Open Directory Project (ODP) and the Yahoo! directory. In such cases, the scalability of classification methods turns out to be a major concern. To tackle this problem, hierarchical classification is proposed and widely adopted to get better trade-off between effectiveness and efficiency. Unfortunately, many data sets are not explicitly organized in hierarchical forms and, therefore, hierarchical classification cannot be used directly. In this paper, we propose a novel algorithm to automatically mine a hierarchical structure from the flat taxonomy of a data corpus as a preparation for the adoption of hierarchical classification. In particular, we first compute matrices to represent the relations among categories, documents, and terms. And, then, we cocluster the three substances at different scales through consistent bipartite spectral graph copartitioning, which is formulated as a generalized singular value decomposition problem. At last, a hierarchical taxonomy is constructed from the category clusters. Our experiments showed that the proposed algorithm could discover very reasonable taxonomy hierarchy and help improve the classification accuracy.

Very large-scale classification taxonomies typically have hundreds of thousands of categories, deep hierarchies, and skewed category distribution over documents. However, it is still an open question whether the state-of-the-art technologies in automated text categorization can scale to (and perform well on) such large taxonomies. In this paper, we report the first evaluation of Support Vector Machines (SVMs) in web-page classification over the full taxonomy of the Yahoo! categories. Our accomplishments include: 1) a data analysis on the Yahoo! taxonomy; 2) the development of a scalable system for large-scale text categorization; 3) theoretical analysis and experimental evaluation of SVMs in hierarchical and non-hierarchical settings for classification; 4) an investigation of threshold tuning algorithms with respect to time complexity and their effect on the classification accuracy of SVMs. We found that, in terms of scalability, the hierarchical use of SVMs is efficient enough for very large-scale classification; however, in terms of effectiveness, the performance of SVMs over the Yahoo! Directory is still far from satisfactory, which indicates that more substantial investigation is needed.

We propose a page-adaptation technique that splits existing Web pages into smaller, logically related units. To do this, we must first solve two technical problems: how to detect an existing Web page's semantic structure, and how to split a Web page into smaller blocks based on that structure. To date, we've implemented our technique in Web browsers for mobile devices, in a proxy server for adapting Web pages on the fly, and as an authoring tool plug-in for converting existing Web pages. The Web page can then be adapted to form a two-level hierarchy with a thumbnail representation at the top level for providing a global view and an index to a set of subpages at the bottom level for detailed information.

Previous work shows that a web page can be partitioned into multiple segments or blocks, and often the importance of those blocks in a page is not equivalent. It has also been proven that differentiating noisy and unimportant blocks from pages can facilitate web mining, search and accessibility. However, no uniform approach and model has been presented to measure the importance of different blocks in a web page. Through a user study, we found that people do have a consistent view about the importance of blocks in a web page. Thus, we investigate how to find a model to automatically assign importance values to blocks in a web page. We formulate the block importance estimation as a learning problem. First, we use a vision-based page segmentation technique to partition a web page into semantic blocks with a hierarchical structure. Then spatial features (such as position and size) and content features (such as the number of images and links) are extracted to construct a feature vector for each block. Then, learning algorithms are used to train a model to assign importance to each block in the web page. In our experiments, the best model can achieve the performance with Micro-F1 80.2% and Micro-Accuracy 86.8%.

A novel idea and framework of ubiquitous media agents is presented for managing personal multimedia objects. Media agents are intelligent systems that can autonomously do the following tasks. They automatically collect and build personalized semantic indices of multimedia data on behalf of the user whenever and wherever he accesses/uses these multimedia data. The sources of these semantic descriptions are the textual context of the same documents that contain these multimedia data. The URLs of these multimedia data are indexed using these textual features. When the user wants to use these multimedia data again, the media agents can help the user find relevant multimedia data and provide proper suggestions based on the semantic indices. The media agents learn from the user's interaction records to refine the semantic indices and to model user intentions and preferences. Various algorithms can be used to implement the framework, and a few of them are described in this paper. As shown in the experiments, the media agents are effective in gathering relevant semantics for media objects and learning to provide precise suggestions when the user wants to reuse relevant media objects again

As current methods for content-based retrieval are incapable of capturing the semantics of images, we experiment with using spectral methods to infer a semantic space from user's relevance feedback, so that our system will gradually improve its retrieval performance through accumulated user interactions. In addition to the long-term learning process, we also model the traditional approaches to query refinement using relevance feedback as a short-term learning process. The proposed short- and long-term learning frameworks have been integrated into an image retrieval system. Experimental results on a large collection of images have shown the effectiveness and robustness of our proposed algorithms.

Image retrieval using relevance feedback can be treated as a two-class learning and classification process. The user-labelled relevant and irrelevant images are regarded as positive and negative training samples, based on which a classifier is trained dynamically. Then the classifier in turn classifies all images in the database. In practice, the number of training samples is very small because the users are often impatient. On the other hand, the positive samples usually are not representative since they are the nearest ones to the query and thus less informative. The insufficiency of training samples both in quantities and varieties constrains the generalization ability of the classifier significantly. In this paper, we propose a novel relevance feedback approach, which aims to collect more representative samples and hence improve the performance of classifier. Image labeling and classifier training are conducted in two complementary image feature spaces. Since the samples distribute differently in two spaces, the positive samples may be more informative in one feature space than in another. The two complementary feature spaces are alternated iteratively during the feedback process. To choose appropriate complementary feature spaces, we present two methods to measure the complementarities between two feature spaces quantitatively. Our experimental result on 10,000 images indicates that the proposed feedback approach significantly improves image retrieval performance.

With the advance of high-speed network technologies, the availability and popularity of streaming media content over the Internet has grown rapidly in recent years. The delivery and caching of streaming media must be handled in a different fashion than that of traditional non-streaming objects such as HTML or image files, because of its distinct characteristics and user viewing patterns. We propose a novel scheme that provides users with the video summary (a number of key-frame images) before they download the file, and options for them to select the starting playback position. We introduce the content analysis service to achieve these functionalities. The video content analysis performs shot boundary detection, key-frame selection, and face detection and tracking. The results of the processing are a segmented video sequence and an XML-based meta-data describing the video content. We also design a caching system that utilizes our video abstraction and summarization technique. Our integrated video delivery and caching system combines content-aware segmentation, prefix caching, prefetching, and cooperative caching. We describe how our scheme can be applied in three proposed caching architectures.

The problem of inferring a user's intentions in Machine–Human Interaction has been the key research issue for providing personalized experiences and services. In this paper, we propose novel approaches on modeling and inferring user's actions in a computer. Two linguistic features – keyword and concept features – are extracted from the semantic context for intention modeling. Concept features are the conceptual generalization of keywords. Association rule mining is used to find the proper concept of corresponding keyword. A modified Naive Bayes classifier is used in our intention modeling. Experimental results have shown that our proposed approach achieved 84% average accuracy in predicting user's intention, which is close to the precision (92%) of human prediction.

Recent technological advances have made it possible to process and store large amounts of image data. Perhaps the most impressive example is the accumulation of image data in scientific applications such as medical or satellite imagery. However, in order to realize their full potential, tools for efficient extraction of information and for intelligent searches in image databases need to be developed. This paper describes a new approach to image data retrieval which allows queries to be composed of local intensity patterns. The intensity pattern is converted into a feature representation of reduced dimensionality which can be used for searching similar-looking patterns in the database. This representation is obtained by filtering the pattern with a bank of scale and orientation selective filters modeled using Gabor functions. Experimental results are presented which illustrate that the proposed representation preserves the perceptual similarities, and provides a powerful tool for content-based image retrieval.

The laboratory management department in higher schools is faced with the problem of assessing the management of computer laboratory objectively. The BP network can be established by selecting limited indexes and adopting appropriate samples. This paper obtains the evaluation model by using 13 evaluating indicators and training network.. The results show that the management of computer laboratory can be better assessed by it.

This paper brings up a mobile learning system, which can be used to collaborative learning, learning evaluation, information distribution, resource sharing and so on. This system is developed by using Java ME technology, the Web application server is powered by Tomcat 6.0, and the background database uses SQL Server database. To support the WAP 2.0 protocols, all documents of this system follow the XHTML MP specification. Therefore, the users can access the system by using a wireless communication device which supports the WAP 2.0 protocols.

Although it has been studied for years by computer vision and machine learning communities, image annotation is still far from practical. In this chapter, the authors propose a novel attempt of modeless image annotation, which investigates how effective a data-driven approach can be, and suggest annotating an uncaptioned image by mining its search results. The authors collected 2.4 million images with their surrounding texts from a few photo forum Web sites as our database to support this data-driven approach. The entire process contains three steps: (1) the search process to discover visually and semantically similar search results; (2) the mining process to discover salient terms from textual descriptions of the search results; and (3) the annotation rejection process to filter noisy terms yielded by step 2. To ensure real time annotation, two key techniques are leveraged – one is to map the high dimensional image visual features into hash codes, the other is to implement it as a distributed system, of which the search and mining processes are provided as Web services. As a typical result, the entire process finishes in less than 1 second. Since no training dataset is required, our proposed approach enables annotating with unlimited vocabulary, and is highly scalable and robust to outliers. Experimental results on real Web images show the effectiveness and efficiency of the proposed algorithm.

Corpus callosum is very important for interhemispheric communication. A new corpus callosum segmentation scheme based on MR image is proposed in this paper. Firstly, the live-wire algorithm is adopted to compute the initial contour of ACM, which have small user interaction time and higher flexibility. Secondly, based on an improve GAC model, this scheme takes Neumann boundary condition as the termination condition of the curve evolution. Through test and comparison, the scheme's high performance for the CC segmentation shows much promise for further clinical applications.

Based on research on currently prevalent WEB application project attributes and analysis on the influence factors on development effort of the project, an estimation methodology based on page is present, in which, when the user WEB pages DEMO developed after requirements development, project effort can be estimated by evaluating pages' complexity and corresponding team productivity which can be obtained by referring to historical data in organization measurement analysis repository. Instance shows that the method is practical and facile with a comparative high precision and is visual and helpful for project planning and controlling.

The development of virtual roaming system is an important application of virtual reality technology. The purpose of this paper is to implement a three-dimensional virtual environment to display the campus of the College as a reference. During the process we made various models of the campus by using 3ds Max and set up the virtual roaming system by using Cortona VRML. We also discussed a general design and development process of a virtual roaming system based on the virtual reality technology.

Facing the 21st century the age of exploration-increasing of all kinds of knowledge and quickly development of information, how to promote the competition potential of our citizens becomes a critical issue. How to deepen the quality of education obviously becomes an important mission for the government. As we know, the initial stage of children education is main portion of profound education work and ought to be carefully concerned. Parents should offer perfect educational environment as well as material environment for next generation instead of purchasing better living condition all day long. A well-learning attitude and habit should be cultivated from childhood, especially from the initial stage of children. For example, the learning age of children is provided earlier than before in most Asian countries to upgrade the best learning effect. Therefore, in this study we tried to combine advanced technology of speech-recognition techniques with Sun-Plus microprocessor SPCE061A with wireless communication technique of Bluetooth and Flash software to construct “Full-purposed Learning Machine for Initial stage education”, which posses techniques speech-recognition, wireless communication interface, and multi-media management, to offer an ever brand-new learning environment and experience for children. The experimental result of this brand-new learning machine with testing from 251 children finally proved that learning activities could achieve much better effect through encouraged design and attractive factors with multi-media and promote the interest for students to learn boring language.