Relaxed Online Support Vector Machines (ROSVMs) have recently been proposed as an efficient methodology for attaining an approximate SVM solution for streaming data such as the online spam filtering task. Here, we apply ROSVMs in the TREC 2007 Spam filtering track and report results. In particular, we explore the effect of various slidingwindow sizes, trading off computation cost against classi...

In this paper, we study the problem of active learning for cost-sensitive multiclass classification. We propose selective sampling algorithms, which process the data in a streaming fashion, querying only a subset of the labels. For these algorithms, we analyze the regret and label complexity when the labels are generated according to a generalized linear model. We establish that the gains of ac...

The impulsive live streaming consumption intentions of the Southeast Asian market are examined in this study. Online transactions, a new form social media, becoming popular due to their real-time communication and innovative business concept. Though little attention has been dedicated it, theoretical knowledge Live Streaming Transaction (LST) is crucial given its broad application unique featur...

Knowledge of flow distributions from a stream of packets passing through a network link helps a network operator infer traffic demands, characterize source traffic, and detect traffic anomalies. Flow monitoring provides critical information for many network applications, and some approaches have been proposed to address flow monitoring. However, they either lack accuracy, or require intensive c...

Dynamic program analysis encompasses the development of techniques and tools for analyzing computer software by exploiting information gathered from a program at runtime. The impressive amounts of data collected by dynamic analysis tools require efficient indexing and compression schemes, as well as on-line algorithmic techniques for mining relevant information on-the-fly in order to identify f...

In this paper we give a construction of cut sparsifiers of Benczúr and Karger in the dynamic streaming setting in a single pass over the data stream. Previous constructions either required multiple passes or were unable to handle edge deletions. We use Õ(1/ǫ) time for each stream update and Õ(n/ǫ) time to construct a sparsifier. Our ǫ-sparsifiers have O(n log n/ǫ) edges. The main tools behind o...

In this study, a clustering algorithm that uses DCT transformed data is presented. The algorithm is a grid density-based clustering algorithm that can identify clusters of arbitrary shape. Streaming data are transformed and reconstructed as needed for clustering. Experimental results show that DCT is able to approximate a data distribution efficiently using only a small number of coefficients a...

In the video transcoding problem, we convert the video from one bit-rate to another which can help us design better streaming servers. This is achieved by changing the resolution as a trade-o for the bit-rate. In this work, we solve a part of the problem. The individual frames are represented in terms of 8 8 DCT blocks. We develop an algorithm for re-sampling the frame in the DCT domain, such t...