1.This method preserves the strong power of bigram to distinguish class, while reduces the extent of data sparseness.
该方法保留了二元词串的较强类型分辨能力的特点，同时降低了特征的数据稀疏程度。
2.Accuracy of the 4 methods was compared for sparseness and defect of anterior wall with reference to the results of coronary angiography.
以冠状动脉造影结果为标准，比较4种方法判断前壁稀疏缺损的准确性。
3.Conclusion Wall motion and wall thickening by G-MPI can improve accuracy of diagnosing sparseness and defect of anterior wall.
结论G-MPI、室壁运动及室壁增厚率检测可提高前壁稀疏缺损的诊断准确性。
4.Based on the clustering method, the mixing matrix was first estimated by a new potential function using the sparseness of sources.
首先，利用变换后信源的稀疏特征，采用一新的势函数通过聚类算法估计混叠矩阵。
5.Because the data it used was not users' rating but users' browse route, the problem of data sparseness and initial rating was resolved.
由于数据不是简单的用户评分，而是用户浏览网页的路径，这样就解决了数据稀疏问题和最初评价问题。
6.This algorithm not only improves search speed, but also needs a smaller space for data store than others and reduces the data sparseness .
实验证明该算法不仅提高了查询速度，而且占用的存储空间也较少，进一步减少了数据的稀疏。
7.New Measurements of Uniformity-Compression Discrepancy and Sparseness Discrepancy
均匀性度量中的密集性偏差与稀疏性偏差
8.Wavelet-based Non-negative Matrix Factorization with Sparseness Constraints for Face Recognition
基于小波和非负稀疏矩阵分解的人脸识别方法
9.High sparseness least squares support vector machine classifier
最小二乘支持向量机分类器的高稀疏化及应用
10.Uniform Sparseness of Huge Discrete Data Point
海量数据的均匀稀化