Learning is the heart of intelligence. The focus in machine learning is to automate methods that achieve objectives, improve predictions or encourage informed behavior. Feature selection is a vital step in data analysis that often reduces dataset dimensionality by eliminating irrelevant and/or redundant attributes to simplify the learning process or improve outcomes' quality. This research critically analyses different filter methods based on ranking procedures (Information Gain (IG), Chi-square (CHI), V-score, Fisher Score, mRMR, Va and ReliefF) and identifies possible challenges that arise. We particularly concentrate on how threshold determination can affect results of different filter methods based on ranked scores. We show that this issue is vital, especially in the era of big data in which users deal with attributes in the magnitudes of tens of thousands with only a limited number of instances.
1 July 2017 in Computer Methods and Programs in Biomedicine
Gene expression profiles can be utilized in the diagnosis of critical diseases such as cancer. The selection of biomarker genes from these profiles is significant and crucial for cancer detection. This paper presents a framework proposing a two-stage multifilter hybrid model of feature selection for colon cancer classification. Colon cancer is being extremely common nowadays among other types of cancer. There is a need to find fast and an accurate method to detect the tissues, and enhance the diagnostic process and the drug discovery. This paper reports on a study whose objective has been to improve the diagnosis of cancer of the colon through a two-stage, multifilter model of feature selection. The model described deals with feature selection using a combination of Information Gain and a Genetic Algorithm. The next stage is to filter and rank the genes identified through this method using the minimum Redundancy Maximum Relevance (mRMR) technique. The final phase is to further analyze the data using correlated machine learning algorithms. This two-stage approach, which involves the selection of genes before classification techniques are used, improves success rates for the identification of cancer cells. It is found that Decision Tree, K-Nearest Neighbor, and Naïve Bayes classifiers had showed promising accurate results using the developed hybrid framework model. It is concluded that the performance of our proposed method has achieved a higher accuracy in comparison with the existing methods reported in the literatures. This study can be used as a clue to enhance treatment and drug discovery for the colon cancer cure.
This paper reports (1) the latest development and application of a modified hyperbolic sine law for minimum creep strain rate and stress for both low Cr and high Cr steels, and (2) the development of a creep fracture criterion based on cavity area fraction along grain boundaries for high Cr steel. This work is part of the fundamental development of creep damage constitutive equations which were identified through a critical literature review. In the former the application of the new law results in an improved fitting; in the latter, a new creep fracture criterion based on cavity area fraction along grain boundaries was derived and quantitatively calibrated using the latest detailed cavity nucleation and growth kinetics models for high Cr steel. Furthermore, this paper revealed the trend of nucleation rate coefficient with stress, and the trend of creep life time coefficient with stress, which provide reliable and universal prediction capabilities. This paper contributes to the specific knowledge on the minimum creep strain rate and stress function, the development of a scientifically sound and novel creep rupture criterion based on the cavity area fraction along grain boundaries for high Cr steel, and the provision of creep damage/life prediction tools.
9 November 2012 in Engineering, Construction and Architectural Management
Purpose: The aim of the research presented in this paper is to develop a new methodology for the comparative analysis and quantification of the impact of delay factors in construction projects.Design/methodology/approach: A framework of delay analysis system (DAS) is developed using the findings from the literature review and industry survey. Frequency and severity index method are used to identify and compare the delay factors in Libya and the UK. Statistical experiments are used to test the relationship and confidence level of survey results. A case study of a building project is used to evaluate the functions of the DAS.Findings: The survey illustrated that construction projects suffered more delays in Libya than the UK. The survey results indicated that critical delay factors are quite different in both countries. The case study found that a building project might be delayed by 41 to 46 days in Libya, or 34 to 38 days in the UK, when considering the most critical delay factors.Practical implications: The outcome of the study is expected to help policymakers, decision makers and others stakeholders within the construction industry to improve the industry's processes and reduce the impact of delay in the construction operations.Originality/value: This paper provides a new methodology and a delay analysis system that assists construction managers to analyse and quantify the impact of delay factors in building projects. The system is also expected to provide timely information about possible delays so that necessary measures can be taken to reduce the impact of delays and improve project delivery.