Indexing text and visual features for WWW images

In this paper, we present a novel indexing technique called Multi-scale Similarity Indexing (MSI) to index imagersquos multi-features into a single one-dimensional structure. Both for text and visual feature spaces, the similarity between a point and a local partitionrsquos center in individual space is used as the indexing key, where similarity values in different features are distinguished by different scale. Then a single indexing tree can be built on these keys. Based on the property that relevant images haves similar similarity values from the center of the same local partition in any feature space, certain number of irrelevant images can be fast pruned based on the triangle inequity on indexing keys. To remove the ldquodimensionality curserdquo existing in high dimensional structure, we propose a new technique called Local Bit Stream (LBS). LBS transforms imagersquos text and visual feature representations into simple, uniform and effective bit stream (BS) representations based on local partitionrsquos center. Such BS representations are small in size and fast for comparison since only bit operation are involved. By comparing common bits existing in two BSs, most of irrelevant images can be immediately filtered. Our extensive experiment showed that single one-dimensional index on multi-features improves multi-indices on multi-features greatly. Our LBS method outperforms sequential scan on high dimensional space by an order of magnitude.

Collaborative filtering on data streams

Collaborate Filtering is one of the most popular recommendation algorithms. Most Collaborative Filtering algorithms work with a static set of data. This paper introduces a novel approach to providing recommendations using Collaborative Filtering when user rating is received over an incoming data stream. In an incoming stream there are massive amounts of data arriving rapidly making it impossible to save all the records for later analysis. By dynamically building a decision tree for every item as data arrive, the incoming data stream is used effectively although an inevitable trade off between accuracy and amount of memory used is introduced. By adding a simple personalization step using a hierarchy of the items, it is possible to improve the predicted ratings made by each decision tree and generate recommendations in real-time. Empirical studies with the dynamically built decision trees show that the personalization step improves the overall predicted accuracy.

Time weight collaborative filtering

Collaborative filtering is regarded as one of the most promising recommendation algorithms. The item-based approaches for collaborative filtering identify the similarity between two items by comparing users' ratings on them. In these approaches, ratings produced at different times are weighted equally. That is to say, changes in user purchase interest are not taken into consideration. For example, an item that was rated recently by a user should have a bigger impact on the prediction of future user behaviour than an item that was rated a long time ago. In this paper, we present a novel algorithm to compute the time weights for different items in a manner that will assign a decreasing weight to old data. More specifically, the users' purchase habits vary. Even the same user has quite different attitudes towards different items. Our proposed algorithm uses clustering to discriminate between different kinds of items. To each item cluster, we trace each user's purchase interest change and introduce a personalized decay factor according to the user own purchase behaviour. Empirical studies have shown that our new algorithm substantially improves the precision of item-based collaborative filtering without introducing higher order computational complexity.

Effectiveness of document representation for classification

Conventionally, document classification researches focus on improving the learning capabilities of classifiers. Nevertheless, according to our observation, the effectiveness of classification is limited by the suitability of document representation. Intuitively, the more features that are used in representation, the more comprehensive that documents are represented. However, if a representation contains too many irrelevant features, the classifier would suffer from not only the curse of high dimensionality, but also overfitting. To address this problem of suitableness of document representations, we present a classifier-independent approach to measure the effectiveness of document representations. Our approach utilises a labelled document corpus to estimate the distribution of documents in the feature space. By looking through documents in this way, we can clearly identify the contributions made by different features toward the document classification. Some experiments have been performed to show how the effectiveness is evaluated. Our approach can be used as a tool to assist feature selection, dimensionality reduction and document classification.

Patterns in complex systems modeling

The design, development, and use of complex systems models raises a unique class of challenges and potential pitfalls, many of which are commonly recurring problems. Over time, researchers gain experience in this form of modeling, choosing algorithms, techniques, and frameworks that improve the quality, confidence level, and speed of development of their models. This increasing collective experience of complex systems modellers is a resource that should be captured. Fields such as software engineering and architecture have benefited from the development of generic solutions to recurring problems, called patterns. Using pattern development techniques from these fields, insights from communities such as learning and information processing, data mining, bioinformatics, and agent-based modeling can be identified and captured. Collections of such 'pattern languages' would allow knowledge gained through experience to be readily accessible to less-experienced practitioners and to other domains. This paper proposes a methodology for capturing the wisdom of computational modelers by introducing example visualization patterns, and a pattern classification system for analyzing the relationship between micro and macro behaviour in complex systems models. We anticipate that a new field of complex systems patterns will provide an invaluable resource for both practicing and future generations of modelers.

Searching the world wide web for local services and facilities: A review on the patterns of location-based queries

Many queries sent to search engines refer to specific locations in the world. Location-based queries try to find local services and facilities around the user’s environment or in a particular area. This paper reviews the specifications of geospatial queries and discusses the similarities and differences between location-based queries and other queries. We introduce nine patterns for location-based queries containing either a service name alone or a service name accompanied by a location name. Our survey indicates that at least 22% of the Web queries have a geospatial dimension and most of these can be considered as location-based queries. We propose that location-based queries should be treated different from general queries to produce more relevant results.