Multilayer perceptron neural network model development for mechanical ventilator parameters prediction by real time system learning

Anti-Biofilm: Machine Learning Assisted Prediction of IC50 Activity of Chemicals Against Biofilms of Microbes Causing Antimicrobial Resistance and Implications in Drug Repurposing

Biofilms are one of the leading causes of antibiotic resistance. It acts as a physical barrier against the human immune system and drugs. The use of anti-biofilm agents helps in tackling the menace of antibiotic resistance. The identification of efficient anti-biofilm chemicals remains a challenge. Therefore, in this study, we developed 'anti-Biofilm', a machine learning technique (MLT) based predictive algorithm for identifying and analyzing the biofilm inhibition of small molecules. The algorithm is developed using experimentally validated anti-biofilm compounds with half maximal inhibitory concentration (IC₅₀) values extracted from aBiofilm resource. Out of the five MLTs, the Support Vector Machine performed best with Pearson's correlation coefficient of 0.75 on the training/testing data set. The robustness of the developed model was further checked using an independent validation dataset. While analyzing the chemical diversity of the anti-biofilm compounds, we observed that they occupy diverse chemical spaces with parent molecules like furanone, urea, phenolic acids, quinolines, and many more. Use of diverse chemicals as input further signifies the robustness of our predictive models. The three best-performing machine learning models were implemented as a user-friendly 'anti-Biofilm' web server (https://bioinfo.imtech.res.in/manojk/antibiofilm/) with different other modules which make 'anti-Biofilm' a comprehensive platform. Therefore, we hope that our initiative will be helpful for the scientific community engaged in identifying effective anti-biofilm agents to target the problem of antimicrobial resistance.

A Step Towards Preserving Speakers' Identity While Detecting Depression Via Speaker Disentanglement

Preserving a patient's identity is a challenge for automatic, speech-based diagnosis of mental health disorders. In this paper, we address this issue by proposing adversarial disentanglement of depression characteristics and speaker identity. The model used for depression classification is trained in a speaker-identity-invariant manner by minimizing depression prediction loss and maximizing speaker prediction loss during training. The effectiveness of the proposed method is demonstrated on two datasets - DAIC-WOZ (English) and CONVERGE (Mandarin), with three feature sets (Mel-spectrograms, raw-audio signals, and the last-hidden-state of Wav2vec2.0), using a modified DepAudioNet model. With adversarial training, depression classification improves for every feature when compared to the baseline. Wav2vec2.0 features with adversarial learning resulted in the best performance (F1-score of 69.2% for DAIC-WOZ and 91.5% for CONVERGE). Analysis of the class-separability measure (J-ratio) of the hidden states of the DepAudioNet model shows that when adversarial learning is applied, the backend model loses some speaker-discriminability while it improves depression-discriminability. These results indicate that there are some components of speaker identity that may not be useful for depression detection and minimizing their effects provides a more accurate diagnosis of the underlying disorder and can safeguard a speaker's identity.

Stockwell transform and semi-supervised feature selection from deep features for classification of BCI signals

Over the past few years, the processing of motor imagery (MI) electroencephalography (EEG) signals has been attracted for developing brain-computer interface (BCI) applications, since feature extraction and classification of these signals are extremely difficult due to the inherent complexity and tendency to artifact properties of them. The BCI systems can provide a direct interaction pathway/channel between the brain and a peripheral device, hence the MI EEG-based BCI systems seem crucial to control external devices for patients suffering from motor disabilities. The current study presents a semi-supervised model based on three-stage feature extraction and machine learning algorithms for MI EEG signal classification in order to improve the classification accuracy with smaller number of deep features for distinguishing right- and left-hand MI tasks. Stockwell transform is employed at the first phase of the proposed feature extraction method to generate two-dimensional time–frequency maps (TFMs) from one-dimensional EEG signals. Next, the convolutional neural network (CNN) is applied to find deep feature sets from TFMs. Then, the semi-supervised discriminant analysis (SDA) is utilized to minimize the number of descriptors. Finally, the performance of five classifiers, including support vector machine, discriminant analysis, k-nearest neighbor, decision tree, random forest, and the fusion of them are compared. The hyperparameters of SDA and mentioned classifiers are optimized by Bayesian optimization to maximize the accuracy. The presented model is validated using BCI competition II dataset III and BCI competition IV dataset 2b. The performance metrics of the proposed method indicate its efficiency for classifying MI EEG signals.

FRAUG: A FRAME RATE BASED DATA AUGMENTATION METHOD FOR DEPRESSION DETECTION FROM SPEECH SIGNALS

In this paper, a data augmentation method is proposed for depression detection from speech signals. Samples for data augmentation were created by changing the frame-width and the frame-shift parameters during the feature extraction process. Unlike other data augmentation methods (such as VTLP, pitch perturbation, or speed perturbation), the proposed method does not explicitly change acoustic parameters but rather the time-frequency resolution of frame-level features. The proposed method was evaluated using two different datasets, models, and input acoustic features. For the DAIC-WOZ (English) dataset when using the DepAudioNet model and mel-Spectrograms as input, the proposed method resulted in an improvement of 5.97% (validation) and 25.13% (test) when compared to the baseline. The improvements for the CONVERGE (Mandarin) dataset when using the x-vector embeddings with CNN as the backend and MFCCs as input features were 9.32% (validation) and 12.99% (test). Baseline systems do not incorporate any data augmentation. Further, the proposed method outperformed commonly used data-augmentation methods such as noise augmentation, VTLP, Speed, and Pitch Perturbation. All improvements were statistically significant.