More and more advanced technologies have become available to collect and integrate an unprecedented amount of data from multiple sources, including GPS trajectories about the traces of moving objects. Given the fact t...
详细信息
More and more advanced technologies have become available to collect and integrate an unprecedented amount of data from multiple sources, including GPS trajectories about the traces of moving objects. Given the fact that GPS trajectories are vast in size while the information carried by the trajectories could be redundant, we focus on trajectory compression in this article. As a systematic solution, we propose a comprehensive framework, namely, COMPRESS (Comprehensive Paralleled Road-Network- Based Trajectory Compression), to compress GPS trajectory data in an urban road network. In the preprocessing step, COMPRESS decomposes trajectories into spatial paths and temporal sequences, with a thorough justification for trajectory decomposition. In the compression step, COMPRESS performs spatial compression on spatial paths, and temporal compression on temporal sequences in parallel. It introduces two alternative algorithms with different strengths for lossless spatial compression and designs lossy but error-bounded algorithms for temporal compression. It also presents query processing algorithms to support error-bounded location-based queries on compressed trajectories without full decompression. All algorithms under COMPRESS are efficient and have the time complexity of O(|T|), where |T| is the size of the input trajectory T. We have also conducted a comprehensive experimental study to demonstrate the effectiveness of COMPRESS, whose compression ratio is significantly better than related approaches.
This paper presents a new method for constructing an optimal feature set from sequential data. It creates a dictionary of n-grams of variable length (we call them v-grams), based on the minimum description length prin...
详细信息
ISBN:
(纸本)9781450360142
This paper presents a new method for constructing an optimal feature set from sequential data. It creates a dictionary of n-grams of variable length (we call them v-grams), based on the minimum description length principle. The proposed method is a dictionary coder and works simultaneously as both a compression algorithm and as unsupervised feature extraction. The length of constructed v-grams is not limited by any bound and exceeds 100 characters in provided experiments. Constructed v-grams can be used for any sequential data analysis and allows transfer bag-of-word techniques to non-text data types. The method demonstrates a high compression rate on various real-life datasets. Extracted features generate a practical basis for text classification, that shows competitive results on standard text classification collections without using the text structure. Combining extracted character v-grams with the words from the original text we achieved substantially better classification quality than on words or v-grams alone.
In this paper, we first review the lossless coding mode in the version 1 of the HEVC standard that has recently finalized. We then provide a performance comparison between the lossless coding mode in the HEVC and MPEG...
详细信息
ISBN:
(纸本)9780819494399
In this paper, we first review the lossless coding mode in the version 1 of the HEVC standard that has recently finalized. We then provide a performance comparison between the lossless coding mode in the HEVC and MPEG-AVC/H.264 standards and show that the HEVC lossless coding has limited coding efficiency. To improve the performance of the lossless coding mode, several new coding tools that were contributed to JCT-VC but not adopted in version 1 of HEVC standard are introduced. In particular, we discuss sample based intra prediction and coding of residual coefficients in more detail. At the end, we briefly address a new class of coding tools, i.e., a dictionary-based coder, that is efficient in encoding screen content including graphics and text.
暂无评论