Feature Selection using an SVM learning machine

Ferchichi, Sabra El; Laabidi, Kaouther; Zidi, Salah; Maouche, S.

doi:10.1109/icscs.2009.5412341

Cited by 14 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVMs have been extensively used as a classification tool with associated learning algorithms to analyze data and recognize patterns [11]. Besides high classification accuracy, SVMs also have a number of advantages: firstly, SVM has a superior generalization capability for small training sets [12].…”

Section: A Data Analysis Methodsmentioning

confidence: 99%

Attacking Random Keypads through Click Timing Analysis

Fleming

Cui²,

Liu

et al. 2014

2014 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery

View full text Add to dashboard Cite

This paper introduces a new method for attacking Personal Identification Numbers(PINs) through analysis of time delay between clicks. While click timing attacks are not new, they previously relied on known spacings between keys. In our method, we do not focus on flaws or weaknesses in the system itself, but on the flaws inherent in the human aspect of the system. Our attack exploits unconscious patterns in PIN input that are a side-effect of the human memorization process to narrow the PIN down to a specific class, such as date, greatly reducing the possible set of passcodes. To identify these patterns, we use a series of Support Vector Machines(SVM) as a multi-class classifier. Through analysis of our collected data set we demonstrate that this attack is very effective.

show abstract

Section: A Data Analysis Methodsmentioning

confidence: 99%

Attacking Random Keypads through Click Timing Analysis

Fleming

Cui²,

Liu

et al. 2014

2014 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery

View full text Add to dashboard Cite

show abstract

“…The main objective of the feature selection can be described by [18]. However, the classification error can be increased by the elimination of certain very relevant informations, considering this information if they are used can prove to be informative [19]. Our goal is to design efficient algorithms to select a solid set of pertinent features.…”

Section: Feature Selection and Validationmentioning

confidence: 99%

Effective Detection of Parkinson’s Disease at Different Stages using Measurements of Dysphonia

Benmalek¹,

Elmhamdi²,

Jilbab³

2018

IJEEI

View full text Add to dashboard Cite

This paper addressees the problem of multiclass of Parkinson's disease by the characteristic features of person's voice. So we computed 22 dysphonia measures from 375 voice samples of healthy and people suffering from Parkinson's disease. We used the particle swarm optimization (PSO) feature selection method, with random forest and the linear discriminant analysis (LDA) along with the 4-fold cross validation analysis to classify the subjects in 4 classes according to the severity of symptoms. With a classification accuracy score of 95.2%, promisingly the proposed diagnosis system might serve as a powerful tool for diagnosing PD, and could also extended for other voice pathologies.

show abstract

“…Two typical approaches exist to achieve this objective: feature selection and feature extraction. Feature selection methods search for the optimal subset of original features [8] [9].…”

Section: Introductionmentioning

confidence: 99%

Feature extraction for atmospheric pollution detection

Ferchichi¹,

Zidi

Laabidi³

et al. 2011

2011 International Conference on Communications, Computing and Control Applications (CCCA)

Self Cite

View full text Add to dashboard Cite

Atmospheric data sets are represented by an amount of heterogeneous and redundant data. As number of measurements grows, a strategy is needed to select and efficiently analyze the useful information from the whole data set. The aim of this work is to propose a feature extraction technique based on construction of clusters of similar features. The main objective of the proposed process is to attempt to reach a more accurate classification task and to achieve a more compact representation of the underlying structure of the data. The paper reports the results obtained using the above extraction and analysis procedure of a real data set on atmospheric pollution. It is shown that the proposed approach is able to detect underlying relationship between features and thus get to ameliorate classification accuracy rate.

show abstract

Feature Selection using an SVM learning machine

Cited by 14 publications

References 4 publications

Attacking Random Keypads through Click Timing Analysis

Attacking Random Keypads through Click Timing Analysis

Effective Detection of Parkinson’s Disease at Different Stages using Measurements of Dysphonia

Feature extraction for atmospheric pollution detection

Contact Info

Product

Resources

About