Machine Learning Based Robust Access for Multimodal Biometric Recognition

For organizations requiring high security clearance, multimodal sources of biometric scans are preferred. Computational models for the unimodal biometric scans have so far been well recognized but research into multimodal scans and their models have been gaining momentum recently. For every biometric we used separately feature extraction techniques and we combined those features in efficient way to get robust combination. In this paper, a novel method for fusion of the scan images from the different modes has been introduced. The method is based on representation of data in terms of its sparsity. Feature coupling and correlation information are obtained from the biometric images. The images from each mode are fused by taking into account a quality measure. The algorithms are kernelised so as to handle nonlinear data efficiently. The result of the proposed system is compared to already existing image fusion methods to show its advantage over them.

Download Full-text

Machine Learning Applications in Breast Cancer Diagnosis

Handbook of Research on Machine Learning Innovations and Trends - Advances in Computational Intelligence and Robotics ◽

10.4018/978-1-5225-2229-4.ch020 ◽

2017 ◽

pp. 465-490

Author(s):

Syed Jamal Safdar Gardezi ◽

Mohamed Meselhy Eltoukhy ◽

Ibrahima Faye

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Feature Extraction ◽

Machine Learning Algorithms ◽

Learning Tools ◽

Extraction Techniques ◽

Cad Systems ◽

Cad System ◽

Machine Learning Applications ◽

Detection And Diagnosis

Breast cancer is one of the leading causes of death in women worldwide. Early detection is the key to reduce the mortality rates. Mammography screening has proven to be one of the effective tools for diagnosis of breast cancer. Computer aided diagnosis (CAD) system is a fast, reliable, and cost-effective tool in assisting the radiologists/physicians for diagnosis of breast cancer. CAD systems play an increasingly important role in the clinics by providing a second opinion. Clinical trials have shown that CAD systems have improved the accuracy of breast cancer detection. A typical CAD system involves three major steps i.e. segmentation of suspected lesions, feature extraction and classification of these regions into normal or abnormal class and further into benign or malignant stages. The diagnostics ability of any CAD system is dependent on accurate segmentation, feature extraction techniques and most importantly classification tools that have ability to discriminate the normal tissues from the abnormal tissues. In this chapter we discuss the application of machine learning algorithms e.g. ANN, binary tree, SVM, etc. together with segmentation and feature extraction techniques in a CAD system development. Various methods used in the detection and diagnosis of breast lesions in mammography are reviewed. A brief introduction of machine learning tools, used in diagnosis and their classification performance on various segmentation and feature extraction techniques is presented.

Download Full-text

Feature extraction and classification by machine learning methods for biometric recognition of face and iris

Proceedings ELMAR-2014 ◽

10.1109/elmar.2014.6923301 ◽

2014 ◽

Cited By ~ 8

Author(s):

Milos Oravec

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Biometric Recognition ◽

Learning Methods ◽

Machine Learning Methods

Download Full-text

A novel method for prediction of EuroLeague game results using hybrid feature extraction and machine learning techniques

Chaos Solitons & Fractals ◽

10.1016/j.chaos.2021.111119 ◽

2021 ◽

Vol 150 ◽

pp. 111119

Author(s):

Serkan Ballı ◽

Engin Özdemir

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Machine Learning Techniques ◽

Learning Techniques ◽

Hybrid Feature Extraction ◽

Novel Method

Download Full-text

A Benchmark Study of Machine Learning for Analysis of Signal Feature Extraction Techniques for Blood Pressure Estimation Using Photoplethysmography (PPG)

IEEE Access ◽

10.1109/access.2021.3117969 ◽

2021 ◽

pp. 1-1

Author(s):

Sumbal Maqsood ◽

Shuxiang Xu ◽

Matthew Springer ◽

Rami Mohawesh

Keyword(s):

Machine Learning ◽

Blood Pressure ◽

Feature Extraction ◽

Extraction Techniques ◽

Benchmark Study ◽

Pressure Estimation ◽

Blood Pressure Estimation

Download Full-text

Users' Emotions Analysis based on Hybrid Feature Extraction Techniques

International Journal of Scientific Research in Computer Science Engineering and Information Technology ◽

10.32628/cseit206658 ◽

2020 ◽

pp. 291-296

Author(s):

Sulis Sandiwarno

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Learning Systems ◽

Experimental Results ◽

Extraction Techniques ◽

Machine Learning Classifiers ◽

Feature Extraction Algorithm ◽

Extraction Algorithm ◽

E Learning ◽

Hybrid Feature Extraction

In order to solve some problems of importance of words and missing relations of semantic between words in the emotional analysis of e-learning systems, the TF-IWF algorithm weighted Word2vec algorithm model was proposed as a feature extraction algorithm. Moreover, to support this study, we employ Multinomial Naïve Bayes (MNB) to obtain more accurate results. There are three mainly steps, firstly, TF-IWF is employed used to compute the weight of word. Second, Word2vec algorithm is adopted to compute the vector of words, Third, we concatenate first and second steps. Finally, the users' opinions data is trained and classified through several machine learning classifiers especially MNB classifier. The experimental results indicate that the proposed method outperformed against previous approaches in terms of precision, recall, F-Score, and accuracy.

Download Full-text

Fuel Economy Prediction using Feature Engineering

International Journal of Advanced Research in Science, Communication and Technology ◽

10.48175/ijarsct-792 ◽

2021 ◽

pp. 149-152

Author(s):

Yash Nadkarni ◽

Siddhesh Deo ◽

Aditya Patwardhan ◽

Amey Ponkshe

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Feature Selection ◽

Fuel Economy ◽

High Performance ◽

Predictive Accuracy ◽

Machine Learning Algorithms ◽

Coolant Temperature ◽

Feature Engineering ◽

Extraction Techniques

The traditional way to calculate fuel economy is done by using odometer reading and fuel consumed by car to travel that particular distance. This is a very narrow approach as fuel economy is affected by a variety of factors in the real world. Features such as throttle response, engine temperature, coolant temperature, gross weight of vehicle, etc. have a huge influence on the fuel economy. In order to overcome this problem, we have tried to predict fuel economy based on various features extracted from telemetric data in our project. In order to achieve this, we have implemented various feature selection and feature extraction techniques by further analyzing them with the purpose of calculating the effectiveness of those features to achieve high performance of machine learning algorithms that ultimately improves the predictive accuracy of the classifier. This provides us with the information regarding the amount of influence a particular feature has on the overall fuel economy of the vehicle.

Download Full-text

Rotation Moment Invariant Feature Extraction Techniques for Image Matching

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.721.775 ◽

2014 ◽

Vol 721 ◽

pp. 775-778 ◽

Cited By ~ 1

Author(s):

Yi Qiang Lai

Keyword(s):

Feature Extraction ◽

Image Matching ◽

Image Features ◽

Extraction Techniques ◽

Moment Invariant ◽

Invariant Features ◽

Invariant Feature ◽

Novel Method ◽

Matching Field ◽

Invariant Properties

In recently years, extracting images invariance features are gaining more attention in image matching field. Various types of methods have been used to match image successfully in a number of applications. But in mostly literatures, the rotation moment invariant properties of these invariants have not been studied widely. In this paper, we present a novel method based on Polar Harmonic Transforms (PHTs) which is consisted of a set of orthogonal projection bases to extract rotation moment invariant features. The experimental results show that the kernel computation of PHTs is simple and image features is extracted accurately in image matching. Hence polar harmonic transforms have provided a powerful tool for image matching.

Download Full-text

Machine Learning-Based Epileptic Seizure Detection Methods Using Wavelet and EMD-Based Decomposition Techniques: A Review

Sensors ◽

10.3390/s21248485 ◽

2021 ◽

Vol 21 (24) ◽

pp. 8485

Author(s):

Rabindra Gandhi Thangarajoo ◽

Mamun Bin Ibne Reaz ◽

Geetika Srivastava ◽

Fahmida Haque ◽

Sawal Hamid Md Ali ◽

...

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Journal Citation Report ◽

Epileptic Seizures ◽

Seizure Detection ◽

Detection Methods ◽

High Dimensional ◽

Support Vector ◽

Extraction Techniques ◽

Eeg Data

Epileptic seizures are temporary episodes of convulsions, where approximately 70 percent of the diagnosed population can successfully manage their condition with proper medication and lead a normal life. Over 50 million people worldwide are affected by some form of epileptic seizures, and their accurate detection can help millions in the proper management of this condition. Increasing research in machine learning has made a great impact on biomedical signal processing and especially in electroencephalogram (EEG) data analysis. The availability of various feature extraction techniques and classification methods makes it difficult to choose the most suitable combination for resource-efficient and correct detection. This paper intends to review the relevant studies of wavelet and empirical mode decomposition-based feature extraction techniques used for seizure detection in epileptic EEG data. The articles were chosen for review based on their Journal Citation Report, feature selection methods, and classifiers used. The high-dimensional EEG data falls under the category of ‘3N’ biosignals—nonstationary, nonlinear, and noisy; hence, two popular classifiers, namely random forest and support vector machine, were taken for review, as they are capable of handling high-dimensional data and have a low risk of over-fitting. The main metrics used are sensitivity, specificity, and accuracy; hence, some papers reviewed were excluded due to insufficient metrics. To evaluate the overall performances of the reviewed papers, a simple mean value of all metrics was used. This review indicates that the system that used a Stockwell transform wavelet variant as a feature extractor and SVM classifiers led to a potentially better result.

Download Full-text

Twitter Sentiment Analysis Using Different Machine Learning and Feature Extraction Techniques

Al-Nahrain Journal of Science ◽

10.22401/anjs.24.3.08 ◽

2021 ◽

Vol 24 (3) ◽

pp. 50-54

Author(s):

Mohammad W.Habib ◽

◽

Zainab N. Sultani ◽

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Logistic Regression ◽

Sentiment Analysis ◽

Extraction Methods ◽

Supervised Machine Learning ◽

Support Vector ◽

Extraction Techniques ◽

Machine Learning Approach ◽

Negative Sentiment

Twitter is considered a significant source of exchanging information and opinion in today's business. Analysis of this data is critical and complex due to the size of the dataset. Sentiment Analysis is adopted to understand and analyze the sentiment of such data. In this paper, a Machine learning approach is employed for analyzing the data into positive or negative sentiment (opinion). Different arrangements of preprocessing techniques are applied to clean the tweets, and various feature extraction methods are used to extract and reduce the dimension of the tweets' feature vector. Sentiment140 dataset is used, and it consists of sentiment labels and tweets, so supervised machine learning models are used, specifically Logistic Regression, Naive Bayes, and Support Vector Machine. According to the experimental results, Logistic Regression was the best amongst other models with all feature extraction techniques.

Download Full-text