Computer
Umniah Hameed Jaid; alia karim Abdulhassan
Abstract
The voice signal carries a wide range of data about the speaker, including theirphysical characteristics, feelings, and level of health. There are several uses for the estimateof these physical characteristics from the speech in forensics, security, surveillance,marketing, and customer service. ...
Read More ...
The voice signal carries a wide range of data about the speaker, including theirphysical characteristics, feelings, and level of health. There are several uses for the estimateof these physical characteristics from the speech in forensics, security, surveillance,marketing, and customer service. The primary goal of this research is to identify the auditorycharacteristics that aid in estimating a speaker’s age. To this end, an ensemble featureselection model is proposed that selects the best features from a baseline acoustic featurevector for age estimation from speech. Using a feature vector that covers various spectral,temporal, and prosodic aspects of speech, an ensemble-based automatic feature selection isperformed by, first calculating the feature importance or ranks based on individual featureselection methods, then voting is applied to the resulting feature ranks to attain the topranked subset by all feature selection methods. The proposed method is evaluated on theTIMIT dataset and achieved a mean absolute error (MAE) of 5.58 years and 5.12 years formale and female age estimation
Computer
Shaymaa Taha Ahmed; Suhad Malallah Kadhem
Abstract
Alzheimer’s disease (AD) is caused by multiple variables. Alzheimer's disease development and progression are influenced by genetic variants. The molecular pathways causing Alzheimer's disease are still poorly understood. In Alzheimer's disease research, determining an effective and reliable diagnosis ...
Read More ...
Alzheimer’s disease (AD) is caused by multiple variables. Alzheimer's disease development and progression are influenced by genetic variants. The molecular pathways causing Alzheimer's disease are still poorly understood. In Alzheimer's disease research, determining an effective and reliable diagnosis remains a major difficulty, particularly in the early stages (i.e., Moderate Cognitive Impairment (MCI)). Researchers and technologists working in the fields of machine learning and data mining can help improve the situation, early AD diagnosis but face a hurdle when it comes to high- dimensional data processing. By reducing irrelevant and redundant data from microarray gene expression data, the technique of feature selection can save computing time, improve learning accuracy, and encourage a deeper effect on the learning system or data. The feature selection strategy described in this article reduces data noise well. In particular, Pearson's correlation coefficient is used to assess data redundancy. The efficacy of these features is assessed using the Support Vector Machine (SVM) classification approach. The proposed approach has an accuracy of up to 91.1 %. As a result, newly established approaches for early diagnosis of Alzheimer's disease(AD) are being improved.
Computer
Thabit Sulaiman Sabbah
Abstract
Feature space high dimensionality is a well-known problem in text classification and web mining domains, it is caused mainly by the large number of vocabularies contained within web documents. Several methods were applied to select the most useful and important features over the years; however, the performance ...
Read More ...
Feature space high dimensionality is a well-known problem in text classification and web mining domains, it is caused mainly by the large number of vocabularies contained within web documents. Several methods were applied to select the most useful and important features over the years; however, the performance of such methods is still improvable from different aspects such as the computational cost and accuracy. This research presents an enhanced cosine similarity-based hybridization of two efficient feature selection methods for higher classification performance. The reduced feature sets are generated using the Random Projection (RP) and the Principal Component Analysis (PCA) methods, individually, then hybridized based on the cosine similarity values between features’ vectors. The performance of the proposed method in terms of accuracy and F-measure was tested on a dataset of web pages based on several term weighting schemes. As compared to relevant methods, results of the proposed method show significantly higher accuracy and f-measure performance based on less feature set size.