A Novel Unsupervised Feature Selection Method for Bioinformatics Data Sets
through Feature Clustering
Guangrong Li1, 2, Xiaohua Hu3, 4, Xiajiong Shen4, Xin Chen3, Zhoujun Li5
1School of Computer, Wuhan University, Wuhan, China
2College of Accounting, Hunan University, Changsha, China
3College of Information Science and Technology
Drexel University, Philadelphia, PA 19104
4College of Computer and Information Engineering,
Henan University, Henan, China
5Dept. of Computer Science, Beihang University, Beijing, China
Abstract
Many feature selection methods have been proposed and most of them are in the supervised learning paradigm. Recently unsupervised feature selection has attracted a lot of attention especially in bioinformatics and text mining. So far, supervised feature selection and unsupervised feature selection method are studied and developed separately. A subset selected by a supervised feature selection method may not be a good one for unsupervised learning and vice verse. In bioinformatics research, however it is very common to perform clustering and classification iteratively for the same data sets, especially in gene expression analysis, thus it is very desirable to have a feature selection method which works well for both unsupervised learning and supervised learning. In this paper we propose a novel feature selection algorithm through feature clustering. Our algorithm does not need the class label information in the data set and is suitable for both supervised learning and unsupervised learning. Our algorithm groups the features into different clusters based on feature similarity, so that the features in the same clusters are similar to each other. A representative feature is selected from each cluster, thus reduces the feature redundancy. Our feature selection algorithm uses feature similarity for feature redundancy reduction but requires no feature search, works very well for high dimensional data set. We test our algorithm on some biological data sets for both clustering and classification analysis and the results indicates that our FSFC algorithm can significantly reduce the original data sets without scarifying the quality of clustering and classification . 1. Introduction
Feature selection (also known as variable selection, subspace selection, or dimensionality reduction) is a procedure to select a subset from the original feature set by eliminating redundant and less informative features so that the subset has only the best discriminative features [15]. There are three major benefits of feature selection (FS): (1) improves the prediction performance of the predictors; (2) helps predictors do faster and more cost-effective prediction; and (3) provides a better understanding of the underlying process that generated data [9]. Therefore FS has been an essential tool for many applications, especially bioinformatics, text mining, and combinatorial chemistry [9] where high dimensional data is very common.
Feature selection research has been studied extensively in the supervised learning paradigm in various disciplines such as machine learning, data mining, pattern recognition, etc for very long time. Recently unsupervised feature selection (UFS) received some attentions in data mining and machine learning as clustering high dimensional data sets becomes an essential and routine task in bioinformatics and text mining. UFS is becoming an essential preprocessing step because UFS can not only reduce computational time greatly due to reduced feature subset but also improve clustering quality because no redundant features that could act as noises are involved
in unsupervised learning.
Feature selection as heuristic search consists of four modules; the selection of starting point in feature search, the organization of the search (search strategy), the evaluation of feature subsets, and search halting criterion [2]. With this guideline it seems that UFS could be designed in the same way with some modifications as supervised feature selection. However, the traditional feature selection approach cannot be directly applied to UFS. This is because, due
to the absence of class label in data set, two of the four
required modules are recondite to fulfill in UFS; the evaluation of feature subsets, generated through feature search, and search halting criterion, because it mostly depends on feature subset evaluation, are abstruse. Also it is impossible to measure the correlations between the class and each feature by using distance, information or dependence measures, which is an essential processing in FS. In addition to that, due to the unknown number of clusters, it is very hard to evaluate feature subsets in UFS. That is why supervised feature selection and unsupervised feature selection and studied and developed separately.
The subsets selected based on supervised feature selection may not a good one for clustering task and vice verse [3]. In some real applications, various data mining analysis may need to apply to the same data, which is very popular in bioinformatics study, especially in gene expression analysis. It is very common to perform clustering to group genes and then perform classification to identify important genes to distinguish different genes type in different groups. Thus, it is necessary to design a feature selection method that works for both supervised and unsupervised learning. In this paper we present a novel feature selection approach based on feature clustering. Since our method does not rely on the classification label information in the data set, it works for both supervised and unsupervised learning. In our method, we use maximal information compression index (MICI) [14] to evaluate the similarity of the feature and then use a novel distance measure to cluster the feature into different clusters. In each cluster, a representative feature is selected, thus the number of feature is reduced significantly.
The rest of this paper is organized as follows. In Section 2 we first discuss filter and wrapper method in feature selection since most UFS works are based on these methods, then discuss several feature selection methods based on feature clustering in text mining and a UFS approach based on feature clustering. We explain our method (FSFC) in details in Section 3. In Section 4, extensive experiment results of various biological data sets for both clustering and classification based on our FSFC approach are presented. In Section 5 we conclude the paper.
2. Related Work
Traditionally, filter and wrapper feature selection approaches have been widely used in supervised feature selection [12]. Wrapper approach uses learning (or induction) algorithm for both the FS and the evaluation of each feature set while filter approach uses intrinsic properties of data (e.g. the correlation with the class) for FS. Both wrapper and filter approaches need to search the feature space to get a feature subset. For feature search greedy algorithms, instead of exhaustive search, like forward or backward sequential selection is widely used. For exhaustive search, the whole search space is O(2D), where D is the number of features and for forward or backward sequential search, the search space is O(D2).
In wrapper approach, every feature set must be evaluated by learning algorithm instead of intrinsic properties of data. However, it requires huge amount of computational time. Even if scalable and efficient learning algorithms and greedy algorithm for feature search are used in wrapper approach, it is very expensive in terms of computational cost. A huge number (at least D2) of iterative running of the algorithms make it infeasible to be applied in high-dimensional data set.
On the other hand, in bioinformatics, the number of features in the data sets tends to be very large, feature clustering method has been used frequently for the initial exploration analysis. It was found that this method outperforms traditional feature selection methods [1] [16] and it also reduces more redundant features with high classification accuracy than feature selection methods [1]. Distributional clustering method and information bottleneck method are used for feature clustering [1] [16]. However, these two methods require high computational time, compared with [6] that uses information theoretic framework. The framework is similar to information bottleneck but it uses a new divisive algorithm (similar to k-means algorithm) that uses Kullback Leibler divergences as distance, which makes it faster. Recently an unsupervised feature selection method based on clustering method was introduced in [14]. However, the method requires user input parameter k, where k is used to control the neighborhood size of the feature clusters. It is very difficult to pick up the proper k value and it normally needs to try different k value many times before a desirable k value is determined. For different k value, the whole procedure to calculate the distance and clustering the data need to start over. 3. Our Algorithm (FSFC)
One of the reasons why UFS is very challenging is because it is very hard to distinguish informative features from less informative features due to the absence of class label. Unlike traditional UFS methods [13] [4] [18] [5] [17] [7], we propose a clustering based feature selection algorithm which uses feature similarity for redundancy reduction but requiring no feature search.
Our feature selection method consists of two major steps: first the entire feature set is partitioned into different homogeneous subsets (clusters) based on the feature similarity, and then a representative feature is selected from each cluster. Partitioning the features is done using hierarchical clustering based on MICI. A representative feature of each cluster is selected based on our cost distance function. Such representatives (features) constitute the optimal feature subset. The algorithm is summarized as below:
Algorithm: Feature Selection through Feature Clustering (FSFC)
Input: Data set D = {F n, n = 1, …, D} (D is the number of features), the number of feature k
Output: the reduced feature subset FS k
Method
Step1: FS k = ?
Calculate MICI for each feature pair
Step2: Repeat
Select S i, S j if C(S i, S j) is the minimum
Merge S i & S j
Until all the objects are merged into one cluster
Step3: Select the top k clusters from the hierarchical cluster tree
For each cluster S k
The center CF k(the feature with the smallest sum of MICI all other features in
the cluster) is selected as a representative
feature of the cluster.
FS k = FS k∪ CF k
EndFor
The complexity of the FSFC algorithm is O(D2), where is the dimension. Even though the sequential forward selection and backward elimination also have complexity O(D2), but the each evaluation of the searched based approach is more item consuming than ours.
var()var()
x y
+, where “var” means a sample variance and “cov” means a sample covariance. MICI as a similarity measure between features in our method has many benefits over correlation coefficient and least square regression error; first, MICI is symmetric regardless of the feature order on distance calculation (i.e. Distance(F1,F2) = Distance(F2,F1), where F n is the n th feature); secondly it is strong for data translation since the formula includes mean, variance, and covariance; finally it is insensitive to rotation of the variable.
The distance function used in our clustering adapted from [20], it was successfully used for in cluster ensemble approach [10]. It is defined as
(,)min((),())
i j i j j i
c S S D S S D S S
=→→
, where
1,
1
()(,)
m in
i
j j
i i
m
i j i j
x S
i x S
i
D S S M IC I x x
m∈
=∈
→=∑
S i and S j are the i th and j th clusters in the clustering hierarchy. In hierarchical clustering S i or S j contains only one object (a feature in our case) in the beginning. S i and S j are merged based on the distance. As the clustering step progresses, the number of unclustered objects decreases one by one. The process stops until all the clusters are merged into one cluster. For each cluster a representative feature is selected from the features in the cluster. Our definition of the representative feature of a cluster is the center of the features which has the shortest sum of distance to all other features in the cluster. For example in the “1D” and “2D” example as shown below, The star should be the representative of both clusters because it is in the middle; the distance of the star for every other object in the cluster is the shortest.
▲▼★??
A cluster in 1D space A cluster in 2D space
A hierarchical clustering tree is formed after running the algorithm once in the data set. Different feature subsets can be easily formed from this tree. To generate a feature subset with size k, k representative features are selected from the top K clusters in the cluster tree. Since our feature selection approach is based on hierarchical clustering, it is very easy to generate various feature subsets without much computational overhead. We only need to do clustering once. This is a significant advantages compared with other approaches. For example, in [14] for different k, the whole clustering procedure needs to be done over again.
Our clustering based FSFC method does not require any feature search, it is expected that our algorithm is considerably fast, compared with traditional UFS. The biggest differences of our approach from [14] is that in our method we only need to do feature clustering once and then can choose different numbers of features for the exploration analysis with very little computation overhead for clustering, which is considered crucial in
real applications. Another difference is that our k is exactly the number of cluster; the exact number of features reduced is expected in the result.
4. Experiment Results
We conduct extensive experiments to demonstrate that our approach works well for both clustering and classification tasks. We want to demonstrate that our FSFC can significantly reduce the original data sets without scarifying the quality of clustering and classification. We first apply our FSFC method on the original data set to reduce the number of feature and then apply either clustering or classification algorithm. We want to demonstrate that our method can significantly reduce the number of redundant features
in high dimensional data set and retain highly informative features, which is essential for clustering and/or classification. In our experiments we use various biological data sets (protein sequence, microarray gene expression data sets) for clustering and classification.
Before applying our FSFC method to data sets for clustering analysis, we remove the class label from the original data sets and use the class label only on generating the true clusters for MS measurement purpose (MS definition is explained in the experimental subsection). For clustering analysis, K-means, SOM, and Fuzzy C-means are used and MS is used as an evaluation measurement for the clustering result. For classification analysis, SVM light is used [11]. This software is available at https://www.doczj.com/doc/0d17641073.html,/. For each data set, the features are decreased by 20 percents each time so each data set generate 4 additional data sets with 20% features removed each time. For example, if a data set has 100 features, data sets with 20, 40, 60, and 80 features are generated using FSFC algorithm. Graphs based on MS or the accuracy of SVM are provided; y axis indicates MS or SVM accuracy while x axis indicates the number of features used. Please note the small is better in MS while the bigger is better in the accuracy of SVM.
4.1 Clustering analysis with FSFC a pre-processing step for data reduction
In these tests, we demonstrate that FSFC can significantly reduce the original data sets without scarifying the clustering quality.
To evaluate the clustering results, we adopt the Minkowski score. A clustering solution for a set of n elements can be represented by an nxn matrix C where
C ij=1 iff x i and x j are in the same cluster according to the solution and C ij=0 otherwise. A measure of Minkowski Score (MS) between the clustering results C(h) from a particular clustering algorithm CA h with a reference clustering T (or alternatively, the true clusters if the cluster information in the data set is known in advance) is defined as MS (T, C(h)) = ||T-
C(h)||/||T||, where ||T|| = sqrt(∑i∑j T ij)
The Minkowski score is the normalized distance between the two matrices. Hence a perfect solution will obtain a score zero, and the smaller the score, the better solution.
We use 5 public gene datasets for our clustering analysis.
(1) Yeast gene data set contains 7129 tuples and 80 attributes. But 2465 genes are classified. Such genes are classified into 108 function family. All Yeast data sets used here have 80 attributes. In our experiment, each family is treated as a cluster. Yeast1, Yeast2, and Yeast3 data sets are extracted from those genes. Yeast1 data set with 3 clusters contains 101 tuples and Yeast2 data set with 2 clusters contains 80 tuples. Yeast3 data set with 4 classes contains 669 tuples. The original data set is available here (https://www.doczj.com/doc/0d17641073.html,/EisenData.htm).
Yeast1
(MS index)
K-means SOM
Fuzzy C-
mean
16 features 1.086 1.066 1.102
32 features 1.027 0.945 1.064
48 features 1.014 0.912 1.043 64 features 1.028 0.929 1.054
80 features 1.04
0.956 1.054
Yeast2
(MS index)
K-means SOM
Fuzzy C-
mean
16
features 0.926 0.879 0.879 32
features 0.759 0.817 0.799 48
features 0.780 0.713 0.737 64 features 0.737 0.688 0.713 80 features 0.759 0.737 0.713
Yeast3 (MS index) K-means SOM
Fuzzy C-
mean
16 features 1.198 1.185 1.373
32 features 1.136 1.167 1.540
48 features 1.123 1.114 1.265 64 features 1.110 1.119 1.303 80 features 1.124 1.118
1.305
(2) Leukemia data set has 7129 genes but 52 genes are classified into 2 clusters. Our experiment data set has 52 genes and 38 features. The data set is available from https://www.doczj.com/doc/0d17641073.html,/colondata.
Leukemia (MS index) K-means SOM
Fuzzy C-
mean
8 features 0.917 0.768 0.933
15 features 0.933 0.768 0.933
23 features 0.933 0.768 0.898
30 features 0.933 0.768 0.877 38 features
0.877 0.768 0.877
(3) B-cell Lymphoma dataset has 4026 genes and 96 features. 43 genes are classified into 4 clusters. The
https://www.doczj.com/doc/0d17641073.html,/lymphoma.
B-cell
Lymphoma (MS index) K-means SOM
Fuzzy C-
mean
19 features 0.831 0.965 1.087
38 features 0.512 0.841 1.106 58 features 0.569 0.816 0.569
77 features 0.577 0.768 0.821
96 features 0.779 0.882 0.569
(4) RTK (Receptor Tyrosine Kinase) data set has 6312 genes and 16 attributes but 137 genes are classified into 7 classes. We used this classified gene so our experiment data set with 7 classes has 137 genes and 16 features. The data set is available from https://www.doczj.com/doc/0d17641073.html,/RTK/.
RTK
(MS index)
K-means SOM
Fuzzy C-
mean 3
features 1.354 1.350 1.354 6
features 1.347 1.285 1.375 10 features 1.354 1.256 1.354
13 features 1.435 1.275 1.351
16 features 1.291 1.277 1.359
(5) BRCA1 (related with breast cancer) data set has 373 genes and 12 attributes. 337 genes are classified into 51 classes (each class has 1~43genes). Our experimental data set with 6 clusters has 164 tuples and 12 features. For more information about this gene data set, refer to [21].
BRCA1
(MS index)
K-means SOM
Fuzzy C-
mean
2 features 1.308 1.277 1.363
5 features 1.354 1.317 1.348
7 features 1.353 1.292 1.358
10 features 1.351 1.304 1.360
12 features 1.355 1.302 1.347
4.2 Classification analysis with FSFC as pre-processing step for data reduction.
4.2.1UCI data sets are used for classification testing
Data Set Name
# of
Class
# of
Tuples
# of
Features
Spambase 2 4601 57 Ionosphere 2 351 34 Multiple
Features
10 2000 649
Spambase SVM
11 features 71.67%
23 features 81.30%
34 features 86.01%
46 features 91.30%
57 features
73.12%
Ionosphere SVM
7 features 61.90%
14 features 62.86%
20 features 61.90%
27 features 63.81%
34 features
61.90%
Multiple Features SVM
130 features 85.33%
260 features 85.17%
389 features 85.83%
519 features 87.00%
649 features
81.83% 4.2.2 Protein Data:
The first data set has 315 features and 38009 tuples [3]. We use 10 fold cross validation for the accuracy result.
Protein interaction SVM
63 features 65.86%
126 features 66.92%
189 features 67.52%
252 features 67.88%
315 features
70.53%
The second data set with 2 classes has 300 features and 94466 tuples [3]. We use 10 fold cross validation for the accuracy result.
Solvent SVM
60 features 68.72%
120 features 75.64%
180 features 77.47%
240 features 77.61%
300 features
78.05%
5. Discussions and Conclusion
The difference of our algorithm from traditional unsupervised feature selection is two fold; it is clustering base so it does not require feature search. In
our algorithm k is the number of the features in the selection output. We only need to do the feature clustering once and get different feature subsets with various dimension numbers without extra computational cost. This characteristic is useful in data mining where multiscale representation of the data is often necessary. In our algorithm, k acts as a scale parameter which controls the degree of details in a more direct manner. These make it suitable for a wide variety of data mining tasks involving large dimensional data set.
The novelty of our method is the absence of search process which contributes to the high-computational time requirement of those features selection algorithms. Our algorithm is based on pairwise feature similarity measures, which are fast to compute. Unlike other approaches, which are based on optimizing either classification accuracy or clustering performance explicitly. In our method, we determine a set of maximally independent features by discarding the redundant ones; this improves the applicability of the resulting features to other data mining task such as data reduction, summarization, and association mining in addition to clustering/classification.
The experimental results on various biological data sets indicate our algorithm work well both for supervised learning and unsupervised learning. As our future plan, we would like to test our feature selection approach on biomedical literature mining and hope to report our findings in the near future.
Acknowledgement: This work is supported partially by NSF CCF 0514679, and the NSF Career grant (IIS-0448023) and PA Dept of Health Grants (#239667).
6. References
[1] L. D. Baker and A. McCallum, “Distributional clustering
of words for text classification”, in SIGIR’98: Proceedings of the 21st Annual International ACM SIGIR, Melbourne, Australia, 1998, pp. 96–103.
[2] A. Blum, and P. Langley, “Selection of relevant features and examples in machine learning”, Artificial Intelligence, vol. 97, pp. 245-271, 1997.
[3] H. Chen, H. Zhou H., X. Hu, and I. Yoo, “Classification Comparison of Prediction of Solvent Accessibility from Protein Sequences”, in the 2nd Asia-Pacific Bioinformatics Conference, New Zealand, Jan 18-22, 2004.
[4] M. Dash, H. Liu, and J. Yao, “Dimensionality Reduction
of Unsupervised Data”, in 9th IEEE Int'l Conf. Tools with Artificial Intelligence, 1997, pp. 532-539. [5] M. Devaney and A. Ram, “Efficient Feature Selection in Conceptual Clustering”, in 14th Int'l Conf. Machine Learning, 1997.
[6] I. S. Dhillon, S. Mallela, and R. Kumar, “A Divisive Information-Theoretic Feature Clustering Algorithm for Text Classification”, JMLR, vol. 3, pp.1265-1287, 2003.
[7] J. G. Dy and C. E. Brodley, “Feature Subset Selection and Order Identification for Unsupervised Learning”, ICML, 2000, pp. 247-254.
[8] D. H. Fisher, “Knowledge acquisition via incremental conceptual clustering, Machine Learning”, Machine Learning, vol. 2, pp.139-172, 1987.
[9] I. Guyon and A. Elisseeff, “An Introduction to Variable and Feature Selection JMLR Special Issue on Variable and Feature Selection”, Kernel Machines Section, Mar, pp. 1157-1182, 2003.
[10] X. Hu and Y. Yoo, “Cluster Ensemble and Its Applications in Gene Expression Analysis”, in BIBE, 2006. [11] T. Joachims, “Making large-Scale SVM Learning Practical”, Advances in Kernel Methods - Support Vector Learning, MIT-Press, 1999.
[12] G. H. John, R. Kohavi, and K. Pfleger, “Irrelevant features and the subset selection problem”, in 11th International conference on Machine Learning, New Brunswick, NJ, 1994, pp. 121-129.
[13] Y.S. Kim, N. Street, and F. Menczer, “Evolutionary model selection in unsupervised learning”, Intelligent Data Analysis, vol. 6, pp. 531-556, 2002.
[14] P. Mitra, C. A. Murthy, and Sankar K. Pal, “Unsupervised Feature Selection Using Feature Similarity”, IEEE Transactions on Pattern Analysis and Machine Intelligenc, vol. 24, pp. 301-312, 2002.
[15] M.E Morita, R. Sabourin, F. Bortolozzi, and C.Y. Suen, “Unsupervised Feature Selection Using Multi-Objective Genetic Algorithm for Handwritten Word Recognition”, in the 7th International Conference on Document Analysis and Recognition, Edinburgh, Scotland, 2003, pp.666-670.
[16] N. Slonim and N. Tishby. “The power of word clusters for text classification.” In 23rd European Colloquium on Information Retrieval Research (ECIR), 2001.
[17] L. Talavera, “Feature Selection as a Preprocessing Step for Hierarchical Clustering”, in 16th Int'l Conf. on Machine Learning, 1999, pp. 389-397.
[18] L. Talavera, “Dependency-Based Feature Selection for Clustering Symbolic Data”, Intelligent Data Analysis, vol. 4, pp. 19-28, 2000.
[19] P.L. Welcsh, M.K. Lee, R.M. Gonzalez-Hernandez, D.J. Black, M. Mahadevappa, E.M. Swisher, J.A. Warrington, and M.C. King, “BRCA1 transcriptionally regulates genes involved in breast tumorigenesis”, in Natl Acad Sci U S A 99, 2002, pp. 7560-7565.
[20] Y. Zeng, J. Tang, J. Garcia-Frias, and G.R. Gao, “An Adaptive Meta-Clustering Approach: Combining The Information From Different Clustering Results”, in IEEE Computer Society Bioinformatics Conference, Stanford University, pp. 276-287.
[21] “Machine Learning Repository”
https://www.doczj.com/doc/0d17641073.html,/~mlearn/MLRepository.html
URL:https://www.doczj.com/doc/0d17641073.html,/14072.html 特征选择(排序)对于数据科学家、机器学习从业者来说非常重要。好的特征选择能够提升模型的性能，更能帮助我们理解数据的特点、底层结构，这对进一步改善模型、算法都有着重要作用。 特征选择主要有两个功能： 1.减少特征数量、降维，使模型泛化能力更强，减少过拟合 2.增强对特征和特征值之间的理解 拿到数据集，一个特征选择方法，往往很难同时完成这两个目的。通常情况下，选择一种自己最熟悉或者最方便的特征选择方法（往往目的是降维，而忽略了对特征和数据理解的目的）。 在许多机器学习的书里，很难找到关于特征选择的容，因为特征选择要解决的问题往往被视为机器学习的一种副作用，一般不会单独拿出来讨论。本文将介绍几种常用的特征选择方法，它们各自的优缺点和问题。 1 去掉取值变化小的特征Removing features with low variance 这应该是最简单的特征选择方法了：假设某种特征的特征值只有0和1，并且在所有输入样本中，95%的实例的该特征取值都是1，那就可以认为这个特征作用不大。如果100%都是1，那这个特征就没意义了。当特征值都是离散型变量的时候这种方法才能用，如果是连续型变量，就需要将连续变量离散化之后才能用，而且实际当中，一般不太会有95%以上都取某个值的特征存在，所以这种方法虽然简单但是不太好用。可以把它作为特征选择的预处理，先去掉那些取值变化小的特征，然后再从接下来提到的特征选择方法中选择合适的进行进一步的特征选择。
2 单变量特征选择Univariate feature selection 单变量特征选择能够对每一个特征进行测试，衡量该特征和响应变量之间的关系，根据得分扔掉不好的特征。对于回归和分类问题可以采用卡方检验等方式对特征进行测试。 这种方法比较简单，易于运行，易于理解，通常对于理解数据有较好的效果（但对特征优化、提高泛化能力来说不一定有效）；这种方法有许多改进的版本、变种。 2.1 Pearson相关系数Pearson Correlation 皮尔森相关系数是一种最简单的，能帮助理解特征和响应变量之间关系的方法，该方法衡量的是变量之间的线性相关性，结果的取值区间为[-1，1]，-1表示完全的负相关(这个变量下降，那个就会上升)，+1表示完全的正相关，0表示没有线性相关。 Pearson Correlation速度快、易于计算，经常在拿到数据(经过清洗和特征提取之后的)之后第一时间就执行。 Pearson相关系数的一个明显缺陷是，作为特征排序机制，他只对线性关系敏感。如果关系是非线性的，即便两个变量具有一一对应的关系， Pearson相关性也可能会接近0。 2.2 互信息和最大信息系数Mutual information and maximal information coefficient (MIC)
特征选择方法在建模中的应用 ——以CHAID树模型为例 华东师范大学邝春伟
特征选择是指从高维特征集合中根据某种评估标准选择输出性能最优的特征子集,其目的是寻求保持数据集感兴趣特性的低维数据集合,通过低维数据的分析来获得相应的高维数据特性,从而达到简化分析、获取数据有效特征以及可视化数据的目标。 目前，许多机构的数据均已超载，因此简化和加快建模过程是特征选择的根本优势。通过将注意力迅速集中到最重要的字段（变量）上，可以降低所需的计算量，并且可以方便地找到因某种原因被忽略的小而重要的关系，最终获得更简单、精确和易于解释的模型。通过减少模型中的字段数量，可以减少评分时间以及未来迭代中所收集的数据量。 减少字段数量特别有利于Logistic 回归这样的模型。
SPSS Modeler是一个非常优秀的数据挖掘软件。它的前身是SPSS Clementine及PASW Modeler。该软件 的特征选择节点有助于识别用于预测特定结果的最重要的字段。特征选择节点可对成百乃至上千个预测变量进行筛选、排序，并选择出可能是最重要的预测变量。最后，会生成一个执行地更快且更加有效的模型—此模型使用较少的预测变量，执行地更快且更易于理解。 案例中使用的数据为“上海高中生家庭教育的调查”，包含有关该CY二中的304名学生参与环保活动的信息。 该数据包含几十个的字段（变量），其中有学生年龄、性别、家庭收入、身体状况情况等统计量。其中有一个“目标”字段，显示学生是否参加过环保活动。我们想利用这些数据来预测哪些学生最可能在将来参加环保活动。
案例关注的是学生参与环保活动的情况，并将其作为目标。案例使用CHAID树构建节点来开发模型，用以说明最有可能参与环保活动的学生。其中对以下两种方法作了对比： ?不使用特征选择。数据集中的所有预测变量字段 均可用作CHAID 树的输入。 ?使用特征选择。使用特征选择节点选择最佳的4 个预测变量。然后将其输入到CHAID 树中。 通过比较两个生成的树模型，可以看到特征选择如何产生有效的结果。
基因工程中限制酶的选择及的筛选方法 摘要:基因工程是现代生物科技专题的重要内容，基因工程四部曲中的核心内容是基因表达载体的构建，在构建表达载体过程涉及的限制酶的种类以及筛选方法成为考试的热点内容。本文结合三道例题将限制酶的选择和筛选方法结合在一起进行比较分析。 关键词:限制酶筛选 1 单酶切及筛选 若用同一种限制酶切割质粒和目的基因形成相同的四个黏性末端，因而可能出现多种连接方式如①质粒和质粒②目的基因和目的基因③质粒的自身环化，目的基因的自身连接④质粒与目的基因的连接。质粒与目的基因的连接又会出现正向连接和反向连接两种。若启动子在质粒上，目的基因与质粒的反向连接则导致三联体密码顺序改变，起始密码子和终止密码子位置改变，使得翻译不能正常进行而无法得到正常的表达产物。 例1: (2012江苏生物高考33题部分)图2表示一种质粒的结构和部分碱基序列。现有Msp I、BamH I、Mbo I、Sma I4种限制性核酸内切酶，它们识别的碱基序列和酶切位点分别为 C↓CGG、G↓GATCC、↓GATC、CCC↓GGG。请回答下列问题 若将图2中质粒和目的基因D通过同种限制酶处理后进行连接，形成重组质粒，那么应选用的限制酶是。在导入重组质粒后，为了筛选出含重组质粒的大肠杆菌，一般需要用添加的培养基进行培养。经检测，部分含有重组质粒的大肠杆菌菌株中目的基因D不能正确表达，其最可能的原因是。答案: BamH I 抗生素B 同种限制酶切割形成的末端相同，部分目的基因D与质粒反向链接 笔者认为可通过免疫学方法检测目的基因的表达产物排除反向连接的重组质粒，或分别在质粒和目的基因上设计相同的限制酶识别位点，然后用该酶去切割重组质粒，正向连接和反向连接便会得到不同长度的DNA片段，再根据已知的限制酶在目的基因的位置进行比对，找到正确连接的重组质粒。 2 双酶切及筛选 因为用单酶切会出现质粒与目的基因的任意连接，所以在实际操作中多使用双酶切。双酶切可以避免质粒的自身环化，目的基因的自身连接和目的基因和质粒的反向连接，而目的基因与目的基因的连接因为没有抗生素抗性基因所以可以在含有该抗生素的培养基上去除，故只剩下质粒与质粒，以及质粒与目的基因的重组体。 2.1插入失活筛选法 例2：（苏锡常镇2012届高三教学调研测试）MseI，EcoRI，PstI识别的碱基序列和切割位点分别为GAAT↓TAATTC，G↓AATTC，C↓TGCAG。请回答下列问题：
医疗质量和安全监测指标的监测 住院患者医疗质量指标 (一)住院重点疾病包括：1. 急性心肌梗塞2. 充血性心力衰竭3. 脑出血和脑梗塞.4.创伤性颅脑损伤5. 消化道出血(无并发症) 6. 累及身体多个部位的损伤7. 细菌性肺炎(成人、无并发症8. 慢性阻塞性肺疾病9. 糖尿病伴短期与长期并发症10.结节性甲状腺肿11.急性阑尾炎伴弥漫性腹膜炎及脓肿12.前列腺增生13.肾功能衰竭14.败血症（成人)15.高血压病(成人) 16.急性胰腺炎17.恶性肿瘤术后化疗18.恶性肿瘤维持性化学治疗。 对上述18种疾病的死亡数、二周与一月内再住院例数进行质量监测。 (二)住院重点手术包括：1.甲状腺切除术 2.半月板摘除术3.子宫摘除术4.剖宫产术 5.腹股沟斜疝修补术 6.阑尾切除术7.乳腺手术 对上述7种重点手术的总例数、死亡例数、术后非预期的重返手术室再手术例数进行监测。 (三)手术并发症及患者安全监测指标包括：1..择期手术并发症（肺栓塞、深静脉血栓、败血症、出血或血肿、伤口裂开、猝死、呼吸衰竭、骨折、生理/代谢紊乱、肺部感染、人工气道意外脱出）发生率。2..产伤发生率 3..因用药错误导致患者死亡率 4. 输血/输液反应 5.手术过程中异物遗留发生率 6..医源性气胸7..医源性意外穿刺伤或撕裂伤(第二诊断) 8. 住院患者压疮9.医院内跌倒/坠床对上述7类并发症与安全事件的发生率(%)*、严重程度进行监测。 （四）麻醉监测指标包括：1.麻醉总例数 2.由麻醉医师实施镇痛治疗数3.由麻醉医师实施心肺复苏治疗例数 4.麻醉复苏管理数 5.麻醉非预期的相关例数 6.麻醉分级（ASA病情分级）管理例数进行监测。
Computer Engineering and Applications 计算机工程与应用 基金项目：山西省实验动物专项资金(the Special Foundation for Laboratory Animals of Shanxi Province, China under Grant No.2010K12);山西医科大学青年基金(Shanxi Medical University Foundation for Young Scientists under Grant No.02201023)。 作者简介: 杨俊丽(1978－),女,硕士研究生,讲师,主要研究领域为生物信息学,医学数据整合;刘田福(1954－),男, 教授；李祥生(1961－), 男, 教授。E-mail: hplkyjl@https://www.doczj.com/doc/0d17641073.html, 样本类型无关的多类特征基因选择方法 杨俊丽1, 刘田福2, 李祥生1 YANG Junli 1, LIU Tianfu 2, LI Xiang-sheng 1 1.山西医科大学 计算机教学部,山西 太原 030001 2.山西医科大学 实验动物中心,山西 太原 030001 1. Department of Computer Teaching, Shanxi Medical University, Taiyuan 030001, China 2. Laboratory Animal Center, Shanxi Medical University, Taiyuan 030001, China Feature selection rules for classifying any multi-class samples Abstract ：Feature gene for classification is one of important problems in gene expression data analysis. Current methods ignored that gene expression were unbalanced in different classes. The paper introduces a new feature selection method for any sample. The method presents a new heuristic algorithm that was composed of a improved difference between classes and a original undulation inside the class. The experimental results showed that the method was effective on selecting feature genes for unbalanced multi-class sample and advancing classification capability of classifiers. Key words ：feature selection; multi-class; classifier; gene expression profile 摘 要：分类特征基因是基因表达谱数据分析中的重点，目前的特征基因选择方法均没有考虑到基因在不同类别中分布失衡给特征基因选择算法带来的影响。提出一种样本无关的特征基因选择方法，该方法利用改进地类间差异函数和类内波动函数，并根据两个函数的一致性选择每个类别的鉴别基因。该方法不仅适用于多类样本，对于各类样本数量不均衡以及基因在各类中分布失调的样本同样有效。实验结果表明，该方法确保了特征矢量的均衡性，提高了分类器的分类性能。 关键词：特征选择; 多类; 分类器; 基因表达谱 文献标识码: A 中图分类号: TP391.4 1 引言 基因表达水平是衡量基因功能发挥作用的重要指标，通过基因表达水平的高低，可以揭示生物体的状态和基因在生物体内的活性[1] ，对医学基础研究以及疾病的临床诊断和治疗具有重要的意义。基因表达谱就是描述基因在某一特定状态下表达水平的数据。通过对基因表达谱数据的分析可以获得基因功能和基因表达的潜在信息，为生物学和医学研究提供准确有力的科学依据。然而，基因表达谱数据集中的每个 样本的可测基因数一般达到几千甚至上万个，而实际上只有 几十个甚至几个基因才真正与样本类别相关，包含了样本分类信息，大部分基因与样本类别无关。因此，如何发现对样本分类起决定性作用的一组分类特征基因，即分类特征基因提取与选择的方法至关重要。它不仅是建立有效地分类模型的关键，也是发现疾病分类与分型的基因标记物以及药物治疗潜在靶点的重要手段[2]。 目前科研工作者已从不同角度提出多种特征基因选择方法。其中大多数特征基因选择方法都是针对两类分类问题 网络出版时间：2012-04-25 17:21 网络出版地址：https://www.doczj.com/doc/0d17641073.html,/kcms/detail/11.2127.TP.20120425.1721.060.html
文本分类中的特征提取和分类算法综述 摘要：文本分类是信息检索和过滤过程中的一项关键技术，其任务是对未知类别的文档进行自动处理，判别它们所属于的预定义类别集合中的类别。本文主要对文本分类中所涉及的特征选择和分类算法进行了论述，并通过实验的方法进行了深入的研究。 采用kNN和Naive Bayes分类算法对已有的经典征选择方法的性能作了测试，并将分类结果进行对比，使用查全率、查准率、F1值等多项评估指标对实验结果进行综合性评价分析.最终，揭示特征选择方法的选择对分类速度及分类精度的影响。 关键字：文本分类特征选择分类算法 A Review For Feature Selection And Classification Algorithm In Text Categorization Abstract:Text categorization is a key technology in the process of information retrieval and filtering,whose task is to process automatically the unknown categories of documents and distinguish the labels they belong to in the set of predefined categories. This paper mainly discuss the feature selection and classification algorithm in text categorization, and make deep research via experiment. kNN and Native Bayes classification algorithm have been applied to test the performance of classical feature detection methods, and the classification results based on classical feature detection methods have been made a comparison. The results have been made a comprehensive evaluation analysis by assessment indicators, such as precision, recall, F1. In the end, the influence feature selection methods have made on classification speed and accuracy have been revealed. Keywords:Text categorization Feature selection Classification algorithm
常用训练监控与评价的指标 一、生理学指标： 1）心率（HR）：是评定运动性疲劳最简易的指标，一般常用基础心率、运动后即刻心率和恢复期心率对疲劳进行评价。 ①基础心率(晨脉)：基础心率是基础状态下的心率，即清晨、清醒、起床前、静卧时的心率，一般用脉搏表示，机体机能正常时基础心率相对稳定。大运动负荷训练后，若经一夜的休息基础心率较平时增加5-10次/分以上，则认为有疲劳累积现象，若续几天持续增加，则应调整运动负荷。在选用基础心率作为评定疲劳指标时，应排除惊吓、恶梦、睡眠等其它因素的影响。 ②运动中心率：可采用遥测心率方法测定运动中的心率变化，或用运动后即刻心率代替运动中的心率。按照训练-适应理论，随着训练水平的提高，完成同样运动负荷时，运动中心率有逐渐减少的趋势。若一段时期内从事同样强度的定量负荷，运动中心率增加，则表示身体机能状态不佳。 ③运动后心率恢复：运动后心率包括运动后即刻心率和恢复期心率.恢复期心率下降越快,恢复时间越短,心血管机能越好·相同运动负荷后,运动员心率恢复加快,提示运动员对训练负荷适应或机能状况良好。运动后心率的恢复速度和程度,可衡量运动员对训练负荷的适应水平或者身体机能状况。运动后心率一般从第2分钟开始测6s、10s或30s的心率,用于观察运动员对运动负荷和训练强度的反应和恢复情况。通过对运动后心率的观测运用,以探求运动员取得最大化训练效果的适宜运动负荷。 ①膝跳反射阈值：随着疲劳的增加，膝跳反射的敏感性发生变化，引起膝跳反射所需的叩击力量增加。因此，可根据运动前后膝跳反射的敏感性评价疲劳。 ②反应时：反应时是指刺激信号（光、声音等）出现后机体迅速做出反应的最短时间，分为简单反应时和选择反应时。疲劳时反应时明显延长，特别是选择反应时延长更明显，表明大脑皮层分析机能下降。 ③血压体位反射：测定心血管系统调节机能(植物神经)。受试者坐位静息5分钟后，测安静时血压，随即仰卧3分钟，然后将受试者扶成坐姿(推受试者背部，使其被动坐起)，立即测血压，每30秒测一次，共测2分钟。若2分钟以内完全恢复，说明没有疲劳，恢复一半以上为轻度疲劳，完全不能恢复为重度疲劳。 4)测试感觉机能评价疲劳 ①皮肤空间阈: 皮肤空间阈，也称两点阈，是指能引起皮肤产生两点感觉的两刺激间的最小距离。运动后皮肤空间阈较安静时增加1.5-2倍为轻度疲劳, 2倍以上为重度疲劳。 ②闪光融合频率: 受试者坐位，注视频率仪的光源，直到将光调至明显断续闪光融合频率为止，即临界闪光融合频率，测三次取平均值。轻度疲劳时约减少1.0-3.9Hz;中度疲劳时约减少4.0-7.9Hz;重度疲劳时减少8Hz以上。 5)用生物电评价疲劳
K -split Lasso ：有效的肿瘤特征基因选择方法* 张靖+，胡学钢，张玉红，施万锋 合肥工业大学计算机与信息学院，合肥230009 K -split Lasso:An Effective Feature Selection Method for Tumor Gene Expression Data ZHANG Jing +,HU Xuegang,ZHANG Yuhong,SHI Wanfeng School of Computer and Information,Hefei University of Technology,Hefei 230009,China +Corresponding author:E-mail:hfzjwjl@https://www.doczj.com/doc/0d17641073.html, ZHANG Jing,HU Xuegang,ZHANG Yuhong,et al.K -split Lasso:an effective feature selection method for tumor gene expression data.Journal of Frontiers of Computer Science and Technology,2012,6(12)：1136-1143. Abstract:With the advent of DNA microarray technology,a large number of open-access tumor gene expression datasets are searchable online and can be https://www.doczj.com/doc/0d17641073.html,rmative gene selection and tumor subtype classification have been becoming one of primary research fields in Bioinformatics.This paper proposes K -split Lasso (least absolute shrinkage and selection operator)method for gene selection,whose main idea is to divide the feature sets into K parts,and then select the genes from each feature subset using Lasso,finally merge the selected genes into one feature subset to get the informative https://www.doczj.com/doc/0d17641073.html,ing the support vector machine as classification tool,the experimental results indicate that K -split Lasso reduces data redundancy,improves sample classification accuracy,and has good stability.In addition,K -split Lasso overcomes the large computation and overfitting problems due to the decrease of dimension.K -split Lasso is an effective method for gene selection of tumor. Key words:tumor gene expression profiles;Lasso;feature selection;support vector machine 摘要：随着DNA 微阵列技术的出现，大量关于不同肿瘤的基因表达谱数据集被发布到网络上，从而使得对肿瘤特征基因选择和亚型分类的研究成为生物信息学领域的热点。基于Lasso （least absolute shrinkage and selection operator ）方法提出了K -split Lasso 特征选择方法，其基本思想是将数据集平均划分为K 份，分别使用*The National Natural Science Foundation of China under Grant No.60975034(国家自然科学基金);the Natural Science Foundation of Anhui Province of China under Grant No.1208085QF122(安徽省自然科学基金);the Fundamental Research Funds for the Cen-tral Universities of China under Grant Nos.2011HGBZ1329,2011HGQC1013(中央高校基本科研业务费专项资金). Received 2012-05,Accepted 2012-07.ISSN 1673-9418CODEN JKYTA8 Journal of Frontiers of Computer Science and Technology 1673-9418/2012/06(12)-1136-08DOI:10.3778/j.issn.1673-9418.2012.12.008E-mail:fcst@https://www.doczj.com/doc/0d17641073.html, https://www.doczj.com/doc/0d17641073.html, Tel: +86-10-51616056
Dota打电脑最强模式选择方法 -----pandahero 简单介绍一下： dota打电脑模式分为以下几种： 第一种： 电脑最简单模式：-apneng (电脑普通经验普通金钱模式） 第二种: 电脑稍微厉害：-ap （电脑双倍经验双倍金钱模式） 第三种： 电脑比较厉害：-aphehg （电脑高倍经验高倍金钱模式） 第四种：超级电脑模式：-apxm 或者-apxmstfr （电脑打钱，升级速度超快，后文重点详细介绍该模式） 备注：个人觉得打电脑可以附加3个命令例如： -apnengstfrdu -apstfrdu -aphehgstfrdu st ：超级塔模式：就是塔可以慢慢自动回血，这种模式适合玩家持久娱乐 fr ：快速复活模式：英雄死亡之后，复活时间减少一半，也是适合玩家娱乐 du : 复选英雄模式：英雄可以重复多次选择，适合娱乐 这三种模式是最常见dota打电脑模式： -apnengstfrdu -apstfrdu -aphehgstfrdu (备注：玩家根据自己爱好，可以输入命令，需要就可以全部输入，不需要则输入部分命令即可，建议大家可以在开始游戏之前界面先把命令打一遍，复制下来进入游戏之后，直接复制很方便,因为有时候命令比较长，打字速度慢，容易打错） 如下图最下边对话框：可以先输入写出命令例如：-apnengstfrdu 用鼠标全部选中下面的命令，然后按住Ctrl+C组合键就是复制。然后直接再按住Ctrl+V检查是不是可以粘贴出结果，接着就可以开始游戏，进入游戏之后，直接Ctrl+V 很快
下来开始详细介绍打dota超级电脑模式： 超级模式第一种：-apxm 或者-apxmstfr 或者-apxmstfrdu (如下图：最好游戏开始之前先复制，进入游戏直接粘贴方便） 超级模式第二种：-apxmstfrdu （命令和第一种一模一样，但是玩家可以为电脑手选英雄，为电脑选择很牛逼的英雄，这对于游戏难度就是进一步提升） 重点讲一下如何为电脑手选英雄？ 进入游戏，输入命令：-apxmstfrdu ,如下图所示：稍微一会 等一会就会出现下面屏幕如下图： 看清楚下面这张图片展示内容，屏幕明显显示了：可以为AI选择英雄：-pa/-pe
污染源自动监控数据传输有效率 指标解释及考核要求 （初稿） 1.指标定义 (1) 2.拟定依据 (1) 3.计算公式 (2) 3.1 数据传输有效率 (2) 3.2 数据传输率 (2) 3.3 数据有效率 (3) 4.指标解释 (3) 4.1 考核时段 (3) 4.2 国控重点污染源自动监控名单 (3) 4.3 直出数据 (4) 4.4 有效数据 (4) 4.5 无效数据 (4) 4.6 数据缺失 (5) 5.规则设定 (5) 5.1 数据标识规则 (5) 5.2 数据修约补遗规则 (6) 5.3 限期上传文件凭证规则 (7) 5.4 系统自动修补排放量规则 (7) 6.考核要求 (7) 6.1 数据传输有效率核算源唯一性 (7) 6.2 现场端、信息及时性和完整性 (8) 6.3 数据有效性审核信息规范性、完整性 (8) 6.4 数据人工修补的合法性 (8) 6.5 自动监控系统工作程序性、完整性和及时性 (8) 7.考核方法 (9)
根据国务院办公厅转发的《“十二五”主要污染物总量减排考核办法》（国办发〔2013〕4号）中“依据国家重点监控企业名单核实主要污染物自动监测设备的建设和联网情况，以国务院环境保护主管部门污染源自动监控平台数据核实各地污染物自动监测设备运行情况和主要污染物监控数据传输有效率”的规定，按照环境保护部有关污染源自动监控（测）工作的部门规章、文件、技术标准和规范的要求，制定数据传输有效率考核指标。各级环保部门须使用环境保护部统一发放的国控重点污染源自动监控核心应用软件（以下简称“国发软件”）向环境保护部污染源监控中心传送污染源自动监控数据并如实记录相关信息，环境保护部以部污染源自动监控平台接收的数据核实各地污染物自动监测设备运行情况和主要污染物监控数据传输有效率，向国务院报告并向社会公示。 1.指标定义 数据传输有效率：对考核时段内可实施自动监控的国家重点监控企业（以下简称为可控国控企业），其有效自动监控数据上报至环境保护部污染源自动监控平台的数据完整性和数据有效性两方面进行考核的指标，定义为数据传输率和数据有效率的乘积。 数据传输率为考核时段内实收数据个数与应收数据个数的比值。考核数据为可控国控企业自动监控设备直出数据中主要污染物的浓度、流量和排放量数据，考核数据类型为小时数据和日数据。 数据有效率为考核时段内实收有效数据组数量与应收数据组数量的比值。考核的数据组为可监国控企业自动监控设备直出数据中的主要污染物排放浓度(废气污染物包含折算浓度)、流量、排放量等数据组成的数据组，考核数据类型为小时数据。数据组中任一数据无效则该数据组无效。 2.拟定依据 《“十二五”主要污染物总量减排考核办法》（国办发〔2013〕4号） 《污染源自动监控管理办法》（国家环境保护总局令第28号）
特征选择方法综述 控制与决策2012.2 问题的提出 特征选择框架基于搜索策略划分特征选择方法基于评价准则划分特征选择方法结论 一、问题的提出特征选择是从一组特征中挑选出一些最有效的特征以降低特征空间维数的过程，是模式识别的关键问题之一。对于模式识别系统，一个好的学习样本是训练分类器的关键，样本中是否含有不相关或冗余信息直接影响着分类器的性能。因此研究有效的特征选择方法至关重要。 特征选择算法的目的在于选择全体特征的一个较少特征集合，用以对原始数据进行有效表达按照特征关系度量划分，可分为依赖基尼指数、欧氏距离、信息熵。 、特征选择框架 由于子集搜索是一个比较费时的步骤，一些学者基于相关和冗余分析，给出了下面一种特征选择框架，避免了子集搜索，可以高效快速地寻找最优子集。 从特征选择的基本框架看出，特征选择方法中有4 个基本步骤：候选特征子集的生成（搜索策略）、评价准则、停止准则和验证方法。目前对特征选择方法的研究主要集中于搜索策略和评价准则。因而，本文从搜索策略和评价准则两个角度对特征选择方法进行分类。 三、基于搜索策略划分特征选择方法 基本的搜索策略按照特征子集的形成过程，形成的特征选择方法如下：
图3 基于搜索策略划分特征选择方法 其中，全局搜索如分支定界法，存在问题： 1）很难确定优化特征子集的数目； 2）满足单调性的可分性判据难以设计； 3）处理高维多类问题时，算法的时间复杂度较高。 随机搜索法如模拟退火、遗传算法、禁忌搜索算法等，存在问题： 1）具有较高的不确定性，只有当总循环次数较大时，才可能找到较好的结果。 2）在随机搜索策略中，可能需对一些参数进行设置，参数选择的合适与否对最终结果的好坏起着很大的作用。 启发式搜索如SFS、SBS、SFFS、SFBS等，存在问题： 1）虽然效率高，但是它以牺牲全局最优为代价。 每种搜索策略都有各自的优缺点，在实际应用过程中，根据具体环境和准则函数来寻找一个最佳的平衡点。例如，特征数较少，可采用全局最优搜索策略；若不要求全局最优，但要求计算速度快，可采用启发式策略；若需要高性能的子集，而不介意计算时间，则可采用随机搜索策略。 四、基于评价准则划分特征选择方法
各科室： 按照原卫生部《三级综合医院评审标准及实施细则（2011年版）》、《卫生部办公厅关于印发<三级综合医院医疗质量管理与控制指标（2011年版）>的通知》（卫办医政函〔2011〕54号）、国家卫计委《三级医院医疗服务能力标准（2015年版）》及《国家卫计委<关于印发麻醉等6个专业质控指标（2015年版）>的通知》（国卫办医函〔2015〕252号）的要求，现结合医院实际，对我院的医疗质量与安全监测指标进行了修订和完善。现印发给各科室，请各科室组织学习并严格执行。 该指标有九部分，第一部分医院运行基本监测指标；第二部分住院患者医疗质量与安全监测指标；第三部分单病种质量指标；第四部分重症医学（ＩＣＵ）质量监测指标；第五部分急诊科监测指标；第六部分临床检验监测指标；第七部分病理科监测指标；第八部分合理用药监测指标；第九节医院感染控制质量监测指标。以上指标由信息科牵头负责进行数据的收集，分析由相关科室负责。各科室必须按照监测指标开展定期评价活动，解读评价结果，持续改进医疗管理工作（有显示持续改进效果的记录）。医院将不定期的对科室执行情况进行监督检查，并将检查结果纳入综合目标考核。
附件：医疗质量与安全监测指标（2016年修订） 附件 第一部分医院运行基本监测指标 一、资源配置
二、工作负荷 三、治疗质量
四、工作效率
七、科研成果 第二部分住院患者医疗质量与安全监测指标 一、住院重点疾病(监测指标包含总例数、死亡例数、2周与1月再住院例数、平均住院日和平均住院费用)
二、住院重点手术（监测指标包含总例数、死亡例数、术后非预期再手术例数、平均住院日与平均住院费用）
URL:https://www.doczj.com/doc/0d17641073.html,/14072.html 特征选择(排序)对于数据科学家、机器学习从业者来说非常重要。好的特征选择能够提升模型的性能，更能帮助我们理解数据的特点、底层结构，这对进一步改善模型、算法都有着重要作用。 特征选择主要有两个功能： 1.减少特征数量、降维，使模型泛化能力更强，减少过拟合 2.增强对特征和特征值之间的理解 拿到数据集，一个特征选择方法，往往很难同时完成这两个目的。通常情况下，选择一种自己最熟悉或者最方便的特征选择方法（往往目的是降维，而忽略了对特征和数据理解的目的）。 在许多机器学习的书里，很难找到关于特征选择的内容，因为特征选择要解决的问题往往被视为机器学习的一种副作用，一般不会单独拿出来讨论。本文将介绍几种常用的特征选择方法，它们各自的优缺点和问题。 1 去掉取值变化小的特征 Removing features with low variance 这应该是最简单的特征选择方法了：假设某种特征的特征值只有0和1，并且在所有输入样本中，95%的实例的该特征取值都是1，那就可以认为这个特征作用不大。如果100%都是1，那这个特征就没意义了。当特征值都是离散型变量的时候这种方法才能用，如果是连续型变量，就需要将连续变量离散化之后才能用，而且实际当中，一般不太会有95%以上都取某个值的特征存在，所以这种方法虽然简单但是不太好用。可以把它作为特征选择的预处理，先去掉那些取值变化小的特征，然后再从接下来提到的特征选择方法中选择合适的进行进一步的特征选择。 2 单变量特征选择 Univariate feature selection
特征选择常用算法综述 一.什么是特征选择(Featureselection ) 特征选择也叫特征子集选择 ( FSS , Feature SubsetSelection ) 。是指从已有的M个特征(Feature)中选择N个特征使得系统的特定指标最优化。 需要区分特征选择与特征提取。特征提取 ( Feature extraction )是指利用已有的特征计算出一个抽象程度更高的特征集，也指计算得到某个特征的算法。 特征提取与特征选择都能降低特征集的维度。 评价函数 ( Objective Function )，用于评价一个特征子集的好坏的指标。这里用符号J ( Y )来表示评价函数，其中Y是一个特征集，J( Y )越大表示特征集Y 越好。 评价函数根据其实现原理又分为2类，所谓的Filter和Wrapper 。 Filter（筛选器）：通过分析特征子集内部的信息来衡量特征子集的好坏，比如特征间相互依赖的程度等。Filter实质上属于一种无导师学习算法。 Wrapper（封装器）：这类评价函数是一个分类器，采用特定特征子集对样本集进行分类，根据分类的结果来衡量该特征子集的好坏。Wrapper实质上是一种有导师学习算法。 二.为什么要进行特征选择？ 获取某些特征所需的计算量可能很大，因此倾向于选择较小的特征集特征间的相关性，比如特征A完全依赖于特征B，如果我们已经将特征B选入特征集，那么特征A 是否还有必要选入特征集？我认为是不必的。特征集越大，分类器就越复杂，其后果就是推广能力（generalization capability）下降。选择较小的特征集会降低复杂度，可能会提高系统的推广能力。Less is More ! 三.特征选择算法分类 精确的解决特征子集选择问题是一个指数级的问题。常见特征选择算法可以归为下面3类： 第一类：指数算法 ( Exponential algorithms ) 这类算法对特征空间进行穷举搜索（当然也会采用剪枝等优化），搜索出来的特征集对于样本集是最优的。这类算法的时间复杂度是指数级的。
水质监测与分析
适合现场监测的指标 感官物理性质指标
1
适合现场监测的指标
经过保存、运输的过程，指标性质会发生物理、化学或 生化变化，监测结果无法反应现场真实的水质状况。 适合现场监测的指标
z z z
温度 浊度与透明度
电导率 z pH值
z
溶解氧
2
一、温度(temperature)
水温对水的许多物理性质，如密度、粘度、蒸汽压等 有直接的影响。 水温对水的pH值、盐度及碳酸钙饱和度等化学性质也 存在明显影响。 水温影响水中溶解度。在1个大气压下，氧在淡水中的 溶解度10℃时为11.33mg/L，20℃时为9.17mg/L，30℃时为 7.63 mg/L。
3
水温的影响：
1. 化学和生物化学反应速度 化学和生化反应的速度随温度的升高而加快。通常 温度每升高10℃，反应速率约可增加一倍。 2. 生物和微生物的活动 温度的变化能引起在水中生存的鱼类品种的改变， 稍高的水温还可使一些藻类和污水霉菌的繁殖增加，影 响水体的景观。 水的温度因水源不同而有很大差异。
地下水温度较稳定，一般为8～12℃左右。 地表水的温度随季节和气候而变化(0～30℃左右)。 生活污水水温通常为10～15℃。 工业废水的温度因工业类型、生产工艺的不同而差别较大。
4
温度的测量
温度为必须在现场测定的项目之一，采用 温度计法测量（GB13195-91）。 浅水水温：水银温度计 半导体热敏电阻温度计 较深水温：深水温度计
5
第一节医院运行基本监测指标一、解读 通过医院运行基本监测指标，监测与了解医院日常运行的基本情况。 二、监测指标 （一）资源配置 1．实际开放床位、重症医学科实际开放床位、急诊留观实际开放床位。 2．全院员工总数、卫生技术人员数（医师数、护理人员数、医技人数）。 3．医院医用建筑面积。 （二）工作负荷 1．年门诊人次、健康体检人次、年急诊人次、留观人次。 2．年住院患者入院、出院例数，出院患者实际占用总床日。 3．职业健康体检人次。 4. 职业病诊断人次。 （三）诊疗质量 1．住院患者死亡与自动出院例数。 2．住院危重抢救例数、死亡例数。 3．急诊室危重抢救例数、死亡例数。
4. 诊断质量指标。 5. 治疗质量指标。 （四）工作效率（项目及数据引自医院财务报表）1．出院患者平均住院日。 2．平均每张床位工作日。 3．床位使用率（%）。 4．床位周转次数。 （五）患者负担（项目及数据引自医院财务报表）1．每门诊人次费用（元），其中药费（元）。2．每住院人次费用（元），其中药费（元）。（六）资产运营（项目及数据引自医院财务报表）1．流动比率、速动比率。 2．医疗收入/百元固定资产。 3．业务支出/百元业务收入。 4．资产负债率。 5．固定资产总值。 6．医疗收入中药品收入、医用材料收入比率。（七）科研成果（评审前三年）
1．国内论文数ＩＳＳＮ、国内论文数及被引用数次（以中国科技核心期刊发布信息为准）、ＳＣＩ收录论文数/每百张开放床位。2．承担与完成国家、省级科研课题数/每百张开放床位。 3．获得国家、省级科研基金额度/每百张开放床位。
第二节住院患者医疗质量与安全监测指标 一、解读 为了解住院患者医疗质量与安全的总体情况，是以重返率、死亡率、安全指标三类结果质量为重点 （一）住院重点疾病：总例数、死亡例数、2 周与 1 月内再住院例数、平均住院日与平均住院费用。 （二）住院患者安全类指标。 在本标准中引用的疾病名称与ＩＣＤ10 编码采用《疾病和有关健康问题的国际统计分类》第十次修订本第二版（北京协和医院、世界卫生组织、国际分类家族合作中心编译）。 以下每一项目与数据指标可通过住院病历首页采集，现分别作简要说明。 二、监测指标 住院重点疾病总例数、死亡例数、2 周与 1 月内再住院例数、平均住院日与平均住院费用。 【解读】 按每季、每年，统计每种病种期内总例数、死亡例数、15 日内再住院率、31 日内再住院率等监测指标，了解住院患者医疗质量的总体情况。 分母：年龄≥18 岁的全部因某疾病出院总例数。 分子（符合分母的标准，且符合以下一项者）：①某病种的“死亡”出院患者；②属于同一疾病出院后 2 周与 1 月内再住院患者。 有以下八种重点疾病及ＩＣＤ10 编码： （一）矽肺ＩＣＤ10：J62.800 （二）尘肺待诊ＩＣＤ10：J64.X01