A Hybrid Approach for COVID-19 Detection Using Biogeography-Based Optimization and Deep Learning

The COVID-19 pandemic has created a major challenge for countries all over the world and has placed tremendous pressure on their public health care services.An early diagnosis of COVID-19 may reduce the impact of the coronavirus.To achieve this objective,modern computation methods,such as deep learning,may be applied.In this study,a computational model involving deep learning and biogeography-based optimization(BBO)for early detection and management of COVID-19 is introduced.Specifically,BBO is used for the layer selection process in the proposed convolutional neural network(CNN).The computational model accepts images,such as CT scans,X-rays,positron emission tomography,lung ultrasound,and magnetic resonance imaging,as inputs.In the comparative analysis,the proposed deep learning model CNNis compared with other existingmodels,namely,VGG16,InceptionV3,ResNet50,and MobileNet.In the fitness function formation,classification accuracy is considered to enhance the prediction capability of the proposed model.Experimental results demonstrate that the proposed model outperforms InceptionV3 and ResNet50.

Human wetland dependency and socio-economic evaluation of wetland functions through participatory approach in rural India

Wetlands are an important source of natural resources upon which rural economies depend. They have increasingly been valuable for their goods and services, and the intrinsic ecological value they provide to local populations, as well as people living outside the periphery of the wetlands. Stakeholders＇ participation is essential to the protection and preservation of wetlands because it plays a very important role economically as well as ecologically in the wetland system. The objective of this study was to determine whether gender, educational status, mouzas （which are constituents of a block according to the land reform of the West Bengal Government in India）, and wetland functions have any influence on the annual income of the local community. Considering a floodplain wetland in rural India, the focus was extended to recognize the pattern of wetland functions according to the nature of people＇s involvement through cluster analysis of the male and female populations. Using the statistical software R-2.8.1, an ANOVA （analysis of variance） table was constructed. Since the p value （significance level） was lower than 0.05 for each case, it can be concluded that gender, educational status, mouzas, and wetland functions have a significant influence on annual income. However, S-PLUS-2000 was applied to obtain a complete scenario of the pattern of wetland functions, in terms of involvement of males and females, through cluster analysis. The main conclusion is that gender, educational status, mouzas, and wetland functions have significant impacts on annual income, while the pattern of occupation of the local community based on wetland functions is completely different for the male and female populations.

Quantifying In-Stream Processes on Phosphorus Export Using an Empirical Approach

In-stream nutrient release and retention control the timing and quantity of export at the watershed outlet by mobilization and transport of phosphorus (P) sources from land to the channel, and remobilization of transient stores of P from stream beds. We investigated the significance of stream processes in regulating P loading to the Cannonsville watershed, NY, USA. A mass balance of estimated P inputs to the stream with observed P export at the watershed outlet was used to quantify P delivery and explore the behavior of P. Stream channel transport of both dissolved and particulate P is found to be non-conservative, with dissolved P being retained during low flows and particulate P released during high flows. The results suggest that differences in the magnitude and relative importance of in-stream biogeochemical processes under different flow regimes regulate P delivery in ways that may influence ecological impacts to downstream river reaches and reservoirs.

An Advanced Analysis System for Identifying Alcoholic Brain State Through EEG Signals

This paper addresses an advanced analysis system for the identification of alcoholic brain states from electroencephalogram(EEG) data in an automatic way. This study introduces an optimum allocation based sampling(OAS) scheme to discover the most favourable representative data points from every single time-window of each EEG signal considering the minimal variability of the observations. Combining all representative samples of each time-window in a set, some statistical features are extracted from every set of each class. The Mann-Whitney U test is used to assess whether each of the features is significant between the two classes(e.g., alcoholic and control). In order to evaluate the effectiveness of the OAS-based features, four well-known machine learning methods(decision table,support vector machine(SVM), k-nearest neighbor(k-NN) and logistic regression) are considered for identification of alcoholic brain state. The experimental results on the UCI KDD(i.e., UCI knowledge discovery in databases) database demonstrate that the OAS based decision table algorithm yields the highest accuracy of 99.58% with a low false alarm rate 0.40%, which is an improvement of up to9.58% over the existing algorithms. A proposed analysis system can be used to detect alcoholism and also to determine the level of alcoholism-related changes in EEG signals.

An Integrated MCI Detection Framework Based on Spectral-temporal Analysis

Aiming to differentiate between mild cognitive impairment(MCI) patients and elderly control subjects, this study proposes an integrated framework based on spectral-temporal analysis for the automatic analysis of resting-state electroencephalogram(EEG) recordings. This framework firstly eliminates noise by employing stationary wavelet transformation(SWT). Then, a set of features is extracted through spectral-temporal analysis. Next, a new wrapper algorithm, named three-dimensional(3-D) evaluation algorithm, is proposed to derive an optimal feature subset. Finally, the support vector machine(SVM) algorithm is adopted to identify MCI patients on the optimal feature subset. Decision tree and K-nearest neighbors(KNN) algorithms are also used to test the effectiveness of the selected feature subset. Twenty-two subjects are involved in experiments, of which eleven persons were in an MCI condition and the rest were elderly control subjects. Extensive experiments show that our method is able to classify MCI patients and elderly control subjects automatically and effectively, with the accuracy of 96.94% achieved by the SVM classifier. Decision tree and KNN algorithms also achieved superior results based on the optimal feature subset extracted by the proposed framework. This study is conducive to timely diagnosis and intervention for MCI patients, and therefore to delaying cognitive decline and dementia onset.