Neural Computing & Applications最新文献

Corona Virus Disease 2019 (COVID-19) is a continuing extensive incident globally affecting several million people's health and sometimes leading to death. The outbreak prediction and making cautious steps is the only way to prevent the spread of COVID-19. This paper presents an Adaptive Neuro-fuzzy Inference System (ANFIS)-based machine learning technique to predict the possible outbreak in India. The proposed ANFIS-based prediction system tracks the growth of epidemic based on the previous data sets fetched from cloud computing. The proposed ANFIS technique predicts the epidemic peak and COVID-19 infected cases through the cloud data sets. The ANFIS is chosen for this study as it has both numerical and linguistic knowledge, and also has ability to classify data and identify patterns. The proposed technique not only predicts the outbreak but also tracks the disease and suggests a measurable policy to manage the COVID-19 epidemic. The obtained prediction shows that the proposed technique very effectively tracks the growth of the COVID-19 epidemic. The result shows the growth of infection rate decreases at end of 2020 and also has delay epidemic peak by 40-60 days. The prediction result using the proposed ANFIS technique shows a low Mean Square Error (MSE) of 1.184 × 10^-3 with an accuracy of 86%. The study provides important information for public health providers and the government to control the COVID-19 epidemic.

The success of the supervised learning process for feedforward neural networks, especially multilayer perceptron neural network (MLP), depends on the suitable configuration of its controlling parameters (i.e., weights and biases). Normally, the gradient descent method is used to find the optimal values of weights and biases. The gradient descent method suffers from the local optimal trap and slow convergence. Therefore, stochastic approximation methods such as metaheuristics are invited. Coronavirus herd immunity optimizer (CHIO) is a recent metaheuristic human-based algorithm stemmed from the herd immunity mechanism as a way to treat the spread of the coronavirus pandemic. In this paper, an external archive strategy is proposed and applied to direct the population closer to more promising search regions. The external archive is implemented during the algorithm evolution, and it saves the best solutions to be used later. This enhanced version of CHIO is called ACHIO. The algorithm is utilized in the training process of MLP to find its optimal controlling parameters thus empowering their classification accuracy. The proposed approach is evaluated using 15 classification datasets with classes ranging between 2 to 10. The performance of ACHIO is compared against six well-known swarm intelligence algorithms and the original CHIO in terms of classification accuracy. Interestingly, ACHIO is able to produce accurate results that excel other comparative methods in ten out of the fifteen classification datasets and very competitive results for others.

With the emergence of COVID-19, mobile health applications have increasingly become crucial in contact tracing, information dissemination, and pandemic control in general. Apps warn users if they have been close to an infected person for sufficient time, and therefore potentially at risk. The distance measurement accuracy heavily affects the probability estimation of being infected. Most of these applications make use of the electromagnetic field produced by Bluetooth Low Energy technology to estimate the distance. Nevertheless, radio interference derived from numerous factors, such as crowding, obstacles, and user activity can lead to wrong distance estimation, and, in turn, to wrong decisions. Besides, most of the social distance-keeping criteria recognized worldwide plan to keep a different distance based on the activity of the person and on the surrounding environment. In this study, in order to enhance the performance of the COVID-19 tracking apps, a human activity classifier based on Convolutional Deep Neural Network is provided. In particular, the raw data coming from the accelerometer sensor of a smartphone are arranged to form an image including several channels (HAR-Image), which is used as fingerprints of the in-progress activity that can be used as an additional input by tracking applications. Experimental results, obtained by analyzing real data, have shown that the HAR-Images are effective features for human activity recognition. Indeed, the results on the k-fold cross-validation and obtained by using a real dataset achieved an accuracy very close to 100%.

This study proposes a novel interpretable framework to forecast the daily tourism volume of Jiuzhaigou Valley, Huangshan Mountain, and Siguniang Mountain in China under the impact of COVID-19 by using multivariate time-series data, particularly historical tourism volume data, COVID-19 data, the Baidu index, and weather data. For the first time, epidemic-related search engine data is introduced for tourism demand forecasting. A new method named the composition leading search index-variational mode decomposition is proposed to process search engine data. Meanwhile, to overcome the problem of insufficient interpretability of existing tourism demand forecasting, a new model of DE-TFT interpretable tourism demand forecasting is proposed in this study, in which the hyperparameters of temporal fusion transformers (TFT) are optimized intelligently and efficiently based on the differential evolution algorithm. TFT is an attention-based deep learning model that combines high-performance forecasting with interpretable analysis of temporal dynamics, displaying excellent performance in forecasting research. The TFT model produces an interpretable tourism demand forecast output, including the importance ranking of different input variables and attention analysis at different time steps. Besides, the validity of the proposed forecasting framework is verified based on three cases. Interpretable experimental results show that the epidemic-related search engine data can well reflect the concerns of tourists about tourism during the COVID-19 epidemic.

Deep learning techniques, in particular generative models, have taken on great importance in medical image analysis. This paper surveys fundamental deep learning concepts related to medical image generation. It provides concise overviews of studies which use some of the latest state-of-the-art models from last years applied to medical images of different injured body areas or organs that have a disease associated with (e.g., brain tumor and COVID-19 lungs pneumonia). The motivation for this study is to offer a comprehensive overview of artificial neural networks (NNs) and deep generative models in medical imaging, so more groups and authors that are not familiar with deep learning take into consideration its use in medicine works. We review the use of generative models, such as generative adversarial networks and variational autoencoders, as techniques to achieve semantic segmentation, data augmentation, and better classification algorithms, among other purposes. In addition, a collection of widely used public medical datasets containing magnetic resonance (MR) images, computed tomography (CT) scans, and common pictures is presented. Finally, we feature a summary of the current state of generative models in medical image including key features, current challenges, and future research paths.

Capturing time and frequency relationships of time series signals offers an inherent barrier for automatic human activity recognition (HAR) from wearable sensor data. Extracting spatiotemporal context from the feature space of the sensor reading sequence is challenging for the current recurrent, convolutional, or hybrid activity recognition models. The overall classification accuracy also gets affected by large size feature maps that these models generate. To this end, in this work, we have put forth a hybrid architecture for wearable sensor data-based HAR. We initially use Continuous Wavelet Transform to encode the time series of sensor data as multi-channel images. Then, we utilize a Spatial Attention-aided Convolutional Neural Network (CNN) to extract higher-dimensional features. To find the most essential features for recognizing human activities, we develop a novel feature selection (FS) method. In order to identify the fitness of the features for the FS, we first employ three filter-based methods: Mutual Information (MI), Relief-F, and minimum redundancy maximum relevance (mRMR). The best set of features is then chosen by removing the lower-ranked features using a modified version of the Genetic Algorithm (GA). The K-Nearest Neighbors (KNN) classifier is then used to categorize human activities. We conduct comprehensive experiments on five well-known, publicly accessible HAR datasets, namely UCI-HAR, WISDM, MHEALTH, PAMAP2, and HHAR. Our model significantly outperforms the state-of-the-art models in terms of classification performance. We also observe an improvement in overall recognition accuracy with the use of GA-based FS technique with a lower number of features. The source code of the paper is publicly available here https://github.com/apusarkar2195/HAR_WaveletTransform_SpatialAttention_FeatureSelection.

The purpose of this work is to compare predictive performance of neural networks trained using the relatively novel technique of training single hidden layer feedforward neural networks (SFNN), called Extreme Learning Machine (ELM), with commonly used backpropagation-trained recurrent neural networks (RNN) as applied to the task of financial market prediction. Evaluated on a set of large capitalisation stocks on the Australian market, specifically the components of the ASX20, ELM-trained SFNNs showed superior performance over RNNs for individual stock price prediction. While this conclusion of efficacy holds generally, long short-term memory (LSTM) RNNs were found to outperform for a small subset of stocks. Subsequent analysis identified several areas of performance deviations which we highlight as potentially fruitful areas for further research and performance improvement.

Diabetes Mellitus (DM) is a widespread condition that is one of the main causes of health disasters around the world, and health monitoring is one of the sustainable development topics. Currently, the Internet of Things (IoT) and Machine Learning (ML) technologies work together to provide a reliable method of monitoring and predicting Diabetes Mellitus. In this paper, we present the performance of a model for patient real-time data collection that employs the Hybrid Enhanced Adaptive Data Rate (HEADR) algorithm for the Long-Range (LoRa) protocol of the IoT. On the Contiki Cooja simulator, the LoRa protocol's performance is measured in terms of high dissemination and dynamic data transmission range allocation. Furthermore, by employing classification methods for the detection of diabetes severity levels on acquired data via the LoRa (HEADR) protocol, Machine Learning prediction takes place. For prediction, a variety of Machine Learning classifiers are employed, and the final results are compared with the already existing models where the Random Forest and Decision Tree classifiers outperform the others in terms of precision, recall, F-measure, and receiver operating curve (ROC) in the Python programming language. We also discovered that using k-fold cross-validation on k-neighbors, Logistic regression (LR), and Gaussian Nave Bayes (GNB) classifiers boosted the accuracy.