Towards Grading Chest X-rays of COVID-19 Patients Using a Dynamic Radial Basis Function Network Classifier

The high volume of COVID-19 Chest X-rays and less number of radiologists to interpret those is a challenge for the highly populous developing nations. Moreover, correct grading of the COVID-19 stage by interpreting the Chest X-rays manually is time-taking and could be biased. It often delays the treatment. Given the scenario, the purpose of this study is to develop a deep learning classifier for multiple classifications (e.g., mild, moderate, and severe grade of involvement) of COVID-19 Chest X-rays for faster and accurate diagnosis. To accomplish the goal, the raw images are denoised with a Gaussian filter during pre-processing followed by the Regions of Interest, and Edge Features are identified using Canny’s edge detector algorithm. Standardized Edge Features become the training inputs to a Dynamic Radial Basis Function Network classifier, developed from scratch. Results show that the developed classifier is 88% precise and 86% accurate in classifying the grade of illness with a much faster processing speed. The contribution lies in the dynamic allocation of the (i) number of Input and Hidden nodes as per the shape and size of the image, (ii) Learning rate, (iii) Centroid, (iv) Spread, and (v) Weight values during squared error minimization; (vi) image size reduction (37% on average) by standardization, instead of dimensionality reduction to prevent data loss; and (vii) reducing the time complexity of the classifier by 26% on average. Such a classifier could be a reliable assistive tool to human doctors in screening and grading COVID-19 patients and in turn, would help faster management of the patients as per the stages of COVID-19.

Resting State fMRI Speech, Language, and Executive Function Network Connectivity in Children with and without Listening Difficulties

Listening Difficulties (LiD) are characterized by a child having reported issues with listening despite exhibiting normal hearing thresholds. LiD can often overlap with other developmental disorders, including speech and language disorders, and involve similar higher-order auditory processing. This study used resting-state functional MRI to examine functional brain networks associated with receptive and expressive speech and language and executive function in children with LiD and typically developing (TD) peers (average age of 10 years). We examined differences in region-of-interest (ROI)-to-ROI functional connectivity between: (1) the LiD group and the TD group and (2) within the LiD group, those participants who had seen a Speech-Language Pathologist and those who had not. The latter comparison was examined as a way of comparing children with and without speech and language disorders. Connections that differed between groups were analyzed for correlations with behavioral test data. The results showed functional connectivity differences between the LiD group and TD group in the executive function network and trends in the speech perception network. Differences were also found in the executive network between those LiD participants who had seen an SLP and those who had not. Several of these connectivity differences, particularly frontal-striatal connections, correlated with performance on behavioral tests: including tests that measure attention, executive function, and episodic memory, as well as speech, vocabulary, and sentence structure. The results of this study suggest that differences in functional connectivity in brain networks associated with speech perception and executive function may underlie and contribute to listening difficulties.

White Matter Correlates of Hostility and Aggression in the Visuospatial Function Network in Patients With Schizophrenia

Background: Violent acts in patients with schizophrenia are often associated with their hostility and aggression levels. Poor visuospatial processing has been suggested as a possible risk factor of violence in schizophrenia. However, studies investigating the relationship between hostility, aggression, and the visuospatial function have been lacking. Here, we aimed to investigate brain dysconnectivity associated with hostility and aggression in schizophrenia, particularly focusing on the visuospatial function network.Methods: Eighty-eight participants with schizophrenia and 42 healthy controls were enrolled. The visuospatial function network regions of interest were analyzed using Tract-Based Spatial Statistics. The hostility item from the Positive and Negative Syndrome Scale (PANSS), aggressive, and agitated behavior item from the Scale for the Assessment of Positive Symptoms (SAPS), and the Rey Complex Figure Test (R-CFT) were measured.Results: Among the participants with schizophrenia, the SAPS aggressive and agitated behavior scores were significantly correlated with fractional anisotropies (FAs) of the white matter regions in the splenium of the corpus callosum (CC), left posterior thalamic radiations (PTR), and left posterior corona radiata (PCR). Exploratory correlational analysis revealed significant negative correlations between FAs of the splenium of the CC and R-CFT copy and immediate recall scores. In addition, three regions including CC, PTR, and PCR that significantly correlated with the aggression scores showed significant correlations with the total PANSS scores.Conclusion: Our main finding suggests that aggression of patients with schizophrenia may be associated with poor visuospatial ability and underlying white matter dysconnectivity. These may help enhance understanding aggression in patients with schizophrenia.

A federated data-driven evolutionary algorithm for expensive multi-/many-objective optimization

Data-driven optimization has found many successful applications in the real world and received increased attention in the field of evolutionary optimization. Most existing algorithms assume that the data used for optimization are always available on a central server for construction of surrogates. This assumption, however, may fail to hold when the data must be collected in a distributed way and are subject to privacy restrictions. This paper aims to propose a federated data-driven evolutionary multi-/many-objective optimization algorithm. To this end, we leverage federated learning for surrogate construction so that multiple clients collaboratively train a radial-basis-function-network as the global surrogate. Then a new federated acquisition function is proposed for the central server to approximate the objective values using the global surrogate and estimate the uncertainty level of the approximated objective values based on the local models. The performance of the proposed algorithm is verified on a series of multi-/many-objective benchmark problems by comparing it with two state-of-the-art surrogate-assisted multi-objective evolutionary algorithms.

Prediction of the Loss of Feed Water Fault Signatures Using Machine Learning Techniques

Fault diagnosis occurrence and its precise prediction in nuclear power plants are extremely important in avoiding disastrous consequences. The inherent limitations of the current fault diagnosis methods make machine learning techniques and their hybrid methodologies possible solutions to remedy this challenge. This study sought to develop, examine, compare, and contrast three robust machine learning methodologies of adaptive neurofuzzy inference system, long short-term memory, and radial basis function network by modeling the loss of feed water event using RELAP5. The performance indices of residual plots, mean absolute percentage error, root mean squared error, and coefficient of determination were used to determine the most suitable algorithms for accurately diagnosing the loss of feed water transient signatures. The study found out that the adaptive neurofuzzy inference system model outperformed the other schemes when predicting the temperature of the steam generator tubes, the radial basis function network scheme was best suited in forecasting the mass flow rate at the core inlet, while the long short-term memory algorithm was best suited for the estimation of the severities of the loss of the feed water fault.