A compression algorithm is proposed in this paper for reducing the size of sensor data. By using a dictionary-based lossless compression algorithm, sensor data can be compressed efficiently and interpreted without dec...A compression algorithm is proposed in this paper for reducing the size of sensor data. By using a dictionary-based lossless compression algorithm, sensor data can be compressed efficiently and interpreted without decompressing. The correlation between redundancy of sensor data and compression ratio is explored. Further, a parallel compression algorithm based on MapReduce [1] is proposed. Meanwhile, data partitioner which plays an important role in performance of MapReduce application is discussed along with performance evaluation criteria proposed in this paper. Experiments demonstrate that random sampler is suitable for highly redundant sensor data and the proposed compression algorithms can compress those highly redundant sensor data efficiently.展开更多
基金supported by the National Natural Science Foundation of China(60933011,61170258)
文摘A compression algorithm is proposed in this paper for reducing the size of sensor data. By using a dictionary-based lossless compression algorithm, sensor data can be compressed efficiently and interpreted without decompressing. The correlation between redundancy of sensor data and compression ratio is explored. Further, a parallel compression algorithm based on MapReduce [1] is proposed. Meanwhile, data partitioner which plays an important role in performance of MapReduce application is discussed along with performance evaluation criteria proposed in this paper. Experiments demonstrate that random sampler is suitable for highly redundant sensor data and the proposed compression algorithms can compress those highly redundant sensor data efficiently.
