No abstract

Research on spam email filtering is drawing experts from all over the world, as these junk email messages continue to affect people's daily lives, whether consciously or unconsciously. The overwhelming use of irritating, destructive, and misleading emails appears to have damaged the values of email which prompted us to perform this research to construct a model for spam filtering with faster training time and enhanced accuracy. We have proposed two voting architectures built upon machine learning models and ensemble classifiers, respectively. In our work, we have also analyzed the performance of several individually applied classifiers and ensemble techniques with various feature retrieval strategies. Additionally, we have compared the training time of the proposed models with the deep LSTM-CNN hybrid model. Both of our suggested models have performed adequately, while the MLbased voting model (Type 1) produces the most accurate filtering (98%) taking bag of words for feature extraction and can be trained above 200 times faster than the LSTM-CNN model.

No abstract

The recognition of pathological voice is considered a difficult task for speech analysis. Moreover, otolaryngologists needed to rely on oral communication with patients to discover traces of voice pathologies like dysphonia that are caused by voice alteration of vocal folds and their accuracy is between 60%-70%. To enhance detection accuracy and reduce processing speed of dysphonia detection, a novel approach is proposed in this paper. We have leveraged Linear Discriminant Analysis (LDA) to train multiple Machine Learning (ML) models for dysphonia detection. Several ML models are utilized like Support Vector Machine (SVM), Logistic Regression, and K-nearest neighbor (K-NN) to predict the voice pathologies based on features like Mel-Frequency Cepstral Coefficients (MFCC), Fundamental Frequency (F 0 ), Shimmer (%), Jitter (%), and Harmonic to Noise Ratio (HNR). The experiments were performed using Saarbrucken Voice Database (SVD) and a privately collected dataset. The K-fold cross-validation approach was incorporated to increase the robustness and stability of the ML models. According to the experimental results, our proposed approach has a 70% increase in processing speed over Principal Component Analysis (PCA) and performs remarkably well with a recognition accuracy of 95.24% on the SVD dataset surpassing the previous best accuracy of 82.37%. In the case of the private dataset, our proposed method achieved an accuracy rate of 93.37%. It can be an effective non-invasive method to detect dysphonia.

No abstract