A hierarchical model for test-cost-sensitive decision systems

Min, Fan; Liu, Qihe

doi:10.1016/j.ins.2009.03.007

Cited by 94 publications

(43 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The information about these datasets are summarized in Table 2. Since these datasets do not provide the test cost, we apply uniform and Pareto distributions to generate random test costs in [1,10].…”

Section: Methodsmentioning

confidence: 99%

“…Example 1 Consider the clinical decision system listed in Table 1, where tc ¼ [5,6,5,5,10,7], and mc ¼ where mc ði;jÞ is the cost of classifying an object of the i-th class into the j-th class, jU 0 i j is the number of i-th class, and jU 0 j j is the number of j-th class. Similar to [11], the average misclassification cost (AMC) is given by…”

Section: The Decision System With Test Costs and Misclassification Costsmentioning

confidence: 99%

“…The test cost is money, time, or other resources while we obtain a data item of an object [10,20]. The misclassification cost is the penalty we received while deciding that an object whose real class is K belongs to class J [4,14].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An exponent weighted algorithm for minimal cost feature selection

Zhao

Zhu

2014

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

Minimal cost feature selection plays a crucial role in cost-sensitive learning. It aims to determine a feature subset for minimizing the average total cost by considering the trade-off between test costs and misclassification costs. Recently, a backtracking algorithm has been developed to tackle this problem. Unfortunately, the efficiency of the algorithm for large datasets is often unacceptable. Moreover, the run time of this algorithm significantly increases with the rise of misclassification costs. In this paper, we develop an exponent weighted algorithm for minimal cost feature selection, and the exponent weighted function of feature significance is constructed to increase the efficiency of the algorithm. The exponent weighted function is based on the information entropy, test cost, and a user-specified non-positive exponent. The effectiveness of our algorithm is demonstrated on six UCI datasets with two representative test cost distributions. Compared with the existing backtracking algorithm, the proposed algorithm significantly increases efficiency without being influenced by the misclassification cost setting.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: The Decision System With Test Costs and Misclassification Costsmentioning

confidence: 99%

See 1 more Smart Citation

An exponent weighted algorithm for minimal cost feature selection

Zhao

Zhu

2014

Int. J. Mach. Learn. & Cyber.

View full text Add to dashboard Cite

show abstract

“…In many applications, the test cost must be considered (Hunt et al 1966;Min and Liu 2009;Pazzani et al 1994;Weiss et al 2013). Test cost is money, time, or other resources we pay for collecting a data item of an object.…”

Section: Test-cost-sensitive Attribute Reduction In Heterogeneous Decmentioning

confidence: 99%

“…These algorithms roughly are divided into two categories: nominal algorithms (Lin 2003;Ma 2012;Miao et al 2009) and numerical algorithms Min and Liu 2009;Min and Zhu 2012). The nominal algorithm considers all attributes as nominal variables, the representative is attribute reduction based on rough set theory.…”

Section: Introductionmentioning

confidence: 99%

Test-cost-sensitive attribute reduction on heterogeneous data for adaptive neighborhood model

2015

View full text Add to dashboard Cite

Test-cost-sensitive attribute reduction is an important component in data mining applications, and plays a key role in cost-sensitive learning. Some previous approaches in test-cost-sensitive attribute reduction focus mainly on homogeneous datasets. When heterogeneous datasets must be taken into account, the previous approaches convert nominal attribute to numerical attribute directly. In this paper, we introduce an adaptive neighborhood model for heterogeneous attribute and deal with test-cost-sensitive attribute reduction problem. In the adaptive neighborhood model, the objects with numerical attributes are dealt with classical covering neighborhood, and the objects with nominal attributes are dealt with the overlap metric neighborhood. Compared with the previous approaches, the proposed model can avoid that objects with different values of nominal attribute are classified into one neighborhood. The number of inconsistent objects of a neighborhood reflects the discriminating capability of an attribute subset. With the adaptive neighborhood model, an inconsistent objects-based heuristic reduction algorithm is constructed. The proposed algorithm is compared with the λ-weighted heuristic reduction algorithm which nominal attribute is normalized. Experimental results demonstrate that the proposed algorithm is more effective and more practical significance than the λ-weighted heuristic reduction algorithm.

show abstract