Neural Computing & Applications最新文献

This study investigated the application of a recurrent neural network for optimising pharmacological treatment for depression. A clinical dataset of 458 participants from specialist and community psychiatric services in Australia, New Zealand and Japan were extracted from an existing custom-built, web-based tool called Psynary . This data, which included baseline and self-completed reviews, was used to train and refine a novel algorithm which was a fully connected network feature extractor and long short-term memory algorithm was firstly trained in isolation and then integrated and annealed using slow learning rates due to the low dimensionality of the data. The accuracy of predicting depression remission before processing patient review data was 49.8%. After processing only 2 reviews, the accuracy was 76.5%. When considering a change in medication, the precision of changing medications was 97.4% and the recall was 71.4% . The medications with predicted best results were antipsychotics (88%) and selective serotonin reuptake inhibitors (87.9%). This is the first study that has created an all-in-one algorithm for optimising treatments for all subtypes of depression. Reducing treatment optimisation time for patients suffering with depression may lead to earlier remission and hence reduce the high levels of disability associated with the condition. Furthermore, in a setting where mental health conditions are increasing strain on mental health services, the utilisation of web-based tools for remote monitoring and machine/deep learning algorithms may assist clinicians in both specialist and primary care in extending specialist mental healthcare to a larger patient community.

Patients with deaths from COVID-19 often have co-morbid cardiovascular disease. Real-time cardiovascular disease monitoring based on wearable medical devices may effectively reduce COVID-19 mortality rates. However, due to technical limitations, there are three main issues. First, the traditional wireless communication technology for wearable medical devices is difficult to satisfy the real-time requirements fully. Second, current monitoring platforms lack efficient streaming data processing mechanisms to cope with the large amount of cardiovascular data generated in real time. Third, the diagnosis of the monitoring platform is usually manual, which is challenging to ensure that enough doctors online to provide a timely, efficient, and accurate diagnosis. To address these issues, this paper proposes a 5G-enabled real-time cardiovascular monitoring system for COVID-19 patients using deep learning. Firstly, we employ 5G to send and receive data from wearable medical devices. Secondly, Flink streaming data processing framework is applied to access electrocardiogram data. Finally, we use convolutional neural networks and long short-term memory networks model to obtain automatically predict the COVID-19 patient's cardiovascular health. Theoretical analysis and experimental results show that our proposal can well solve the above issues and improve the prediction accuracy of cardiovascular disease to 99.29%.

COVID-19 has undergone several mutations and is still spreading in most countries now. PA has positive benefits in the prevention of COVID-19 infection and counteracting the negative physical and mental effects caused by COVID-19. However, relevant evidence has indicated a high prevalence of physical inactivity among the general population, which has worsened due to the outbreak of the pandemic, and there is a severe lack of exercise guidance and mitigation strategies to advance the knowledge and role of PA to improve physical and mental health in most countries during the epidemic. This study surveyed the effects of COVID-19 on PA in Chinese residents during the pandemic and provided important reference and evidence to inform policymakers and formulate policies and planning for health promotion and strengthening residents' PA during periods of public health emergencies. ANOVA, Kolmogorov-Smirnov, the chi-square test and Spearman correlation analysis were used for statistical analysis. A total of 14,715 participants were included. The results show that nearly 70% of Chinese residents had inadequate PA (95%CI 58.0%-82.19%) during the COVID-19 outbreak, which was more than double the global level (27.5%, 95%CI 25.0%-32.2%). The content, intensity, duration, and frequency of PA were all affected during the period of home isolation, and the types of PA may vary among different ages. The lack of physical facilities and cultural environment is the main factor affecting PA. However, there was no significant correlation between insufficient PA and the infection rate. During the period of home isolation and social distance of epidemic prevention, it is necessary to strengthen the scientific remote network monitoring and guidance for the process of PA in China.

Indoor occupancy detection is essential for energy efficiency control and Coronavirus Disease 2019 traceability. The number and location of people can be accurately identified and determined through classroom surveillance video analysis. This information is used to manage environmental equipment such as HVAC and lighting systems to reduce energy use. However, the mainstream one-stage YOLO algorithm still uses an anchor-based mechanism and couples detection heads to predict. This results in slow model convergence and poor detection performance for densely occluded targets. Therefore, this paper proposed a novel decoupled anchor-free VariFocal loss convolutional network algorithm DFV-YOLOv5 for occupancy detection to tackle these problems. The proposed method uses the YOLOv5 algorithm as a baseline. It uses the anchor-free mechanism to reduce the number of design parameters needing heuristic tuning. Afterwards, to reduce the coupling of the model, speed up the model's convergence ability, and improve the model detection performance, the detection head is decoupled based on the YOLOv5 model. It can resolve the conflict between classification and regression tasks. In addition, we use the VariFocal loss to assign more weights to difficult data points to optimize the class imbalance problem and use the training target q to measure positive samples, treating positive and negative samples asymmetrically. The total loss function is redesigned, the $L_1$ loss is increased, and the ablation experiment verifies the effect of the improved loss. By applying a hybrid activation function of the sigmoid linear unit and rectified linear unit, we improved the model's nonlinear representation and reduced the model's inference time. Finally, a classroom dataset was constructed to validate the occupancy detection performance of the model. The proposed model was compared with mainstream target detection models regarding average mean precision, memory allocation, execution time, and the number of parameters on the VOC2012, CrowdHuman and self-built datasets. The experimental results show that the method significantly improves the detection accuracy and robustness, shortens the inference time, and proves the practicality of the algorithm in occupancy detection compared with the mainstream target detection model and related variants of the model.

Recently, the COVID-19 pandemic has triggered different behaviors in education, especially during the lockdown, to contain the virus outbreak in the world. As a result, educational institutions worldwide are currently using online learning platforms to maintain their education presence. This research paper introduces and examines a dataset, E-LearningDJUST, that represents a sample of the student's study progress during the pandemic at Jordan University of Science and Technology (JUST). The dataset depicts a sample of the university's students as it includes 9,246 students from 11 faculties taking four courses in spring 2020, summer 2020, and fall 2021 semesters. To the best of our knowledge, it is the first collected dataset that reflects the students' study progress within a Jordanian institute using e-learning system records. One of this work's key findings is observing a high correlation between e-learning events and the final grades out of 100. Thus, the E-LearningDJUST dataset has been experimented with two robust machine learning models (Random Forest and XGBoost) and one simple deep learning model (Feed Forward Neural Network) to predict students' performances. Using RMSE as the primary evaluation criteria, the RMSE values range between 7 and 17. Among the other main findings, the application of feature selection with the random forest leads to better prediction results for all courses as the RMSE difference ranges between (0-0.20). Finally, a comparison study examined students' grades before and after the Coronavirus pandemic to understand how it impacted their grades. A high success rate has been observed during the pandemic compared to what it was before, and this is expected because the exams were online. However, the proportion of students with high marks remained similar to that of pre-pandemic courses.

The coronavirus pandemic has been globally impacting the health and prosperity of people. A persistent increase in the number of positive cases has boost the stress among governments across the globe. There is a need of approach which gives more accurate predictions of outbreak. This paper presents a novel approach called diffusion prediction model for prediction of number of coronavirus cases in four countries: India, France, China and Nepal. Diffusion prediction model works on the diffusion process of the human contact. Model considers two forms of spread: when the spread takes time after infecting one person and when the spread is immediate after infecting one person. It makes the proposed model different over other state-of-the art models. It is giving more accurate results than other state-of-the art models. The proposed diffusion prediction model forecasts the number of new cases expected to occur in next 4 weeks. The model has predicted the number of confirmed cases, recovered cases, deaths and active cases. The model can facilitate government to be well prepared for any abrupt rise in this pandemic. The performance is evaluated in terms of accuracy and error rate and compared with the prediction results of support vector machine, logistic regression model and convolution neural network. The results prove the efficiency of the proposed model.

Phishing is an attack targeting to imitate the official websites of corporations such as banks, e-commerce, financial institutions, and governmental institutions. Phishing websites aim to access and retrieve users' important information such as personal identification, social security number, password, e-mail, credit card, and other account information. Several anti-phishing techniques have been developed to cope with the increasing number of phishing attacks so far. Machine learning and particularly, deep learning algorithms are nowadays the most crucial techniques used to detect and prevent phishing attacks because of their strong learning abilities on massive datasets and their state-of-the-art results in many classification problems. Previously, two types of feature extraction techniques [i.e., character embedding-based and manual natural language processing (NLP) feature extraction] were used in isolation. However, researchers did not consolidate these features and therefore, the performance was not remarkable. Unlike previous works, our study presented an approach that utilizes both feature extraction techniques. We discussed how to combine these feature extraction techniques to fully utilize from the available data. This paper proposes hybrid deep learning models based on long short-term memory and deep neural network algorithms for detecting phishing uniform resource locator and evaluates the performance of the models on phishing datasets. The proposed hybrid deep learning models utilize both character embedding and NLP features, thereby simultaneously exploiting deep connections between characters and revealing NLP-based high-level connections. Experimental results showed that the proposed models achieve superior performance than the other phishing detection models in terms of accuracy metric.

Specific language impairment (SLI) is one of the most common diseases in children, and early diagnosis can help to obtain better timely therapy economically. It is difficult and time-consuming for clinicians to accurately detect SLI through standard clinical assessments. Hence, machine learning algorithms have been developed to assist in the accurate diagnosis of SLI. This work aims to investigate the graph of the favipiravir molecule-based feature extraction function and propose an accurate SLI detection model using vowels. We proposed a novel handcrafted machine learning framework. This architecture comprises the favipiravir molecular structure pattern, statistical feature extractor, wavelet packet decomposition (WPD), iterative neighborhood component analysis (INCA), and support vector machine (SVM) classifier. Two feature extraction models, statistical and textural, are employed in the handcrafted feature generation methodology. A new nature-inspired graph-based feature extractor that uses the chemical depiction of the favipiravir (favipiravir became popular with the COVID-19 pandemic) is employed for feature extraction. Finally, the proposed favipiravir pattern, statistical feature extractor, and wavelet packet decomposition are used to create a feature vector. Moreover, a statistical feature extractor is used in this work. The WPD generates multilevel features, and the most meaningful features are selected using the NCA feature selector. Finally, these chosen features are fed to SVM classifier for automated classification. Two validation methods, (i) leave one subject out (LOSO) and (ii) tenfold cross-validations (CV), are used to obtain robust classification results. Our proposed favipiravir pattern-based model developed using a vowel dataset can detect SLI children with an accuracy of 99.87% and 98.86% using tenfold and LOSO CV strategies, respectively. These results demonstrated the high vowel classification ability of the proposed favipiravir pattern-based model.

Online medical consultation can significantly improve the efficiency of primary health care. Recently, many online medical question-answer services have been developed that connect the patients with relevant medical consultants based on their questions. Considering the linguistic variety in their question, social background identification of patients can improve the referral system by selecting a medical consultant with a similar social origin for efficient communication. This paper has proposed a novel fine-tuning strategy for the pre-trained transformers to identify the social origin of text authors. When fused with the existing adapter model, the proposed methods achieve an overall accuracy of 53.96% for the Arabic dialect identification task on the Nuanced Arabic Dialect Identification (NADI) dataset. The overall accuracy is 0.54% higher than the previous best for the same dataset, which establishes the utility of custom fine-tuning strategies for pre-trained transformer models.

Feature Selection (FS) aims to ameliorate the classification rate of dataset models by selecting only a small set of appropriate features from the initial range of features. In consequence, a reliable optimization method is needed to deal with the matters involved in this problem. Often, traditional methods fail to optimally reduce the high dimensionality of the feature space of complex datasets, which lead to the elicitation of weak classification models. Meta-heuristics can offer a favorable classification rate for high-dimensional datasets. Here, a binary version of a new human-based algorithm named Ali Baba and the Forty Thieves (AFT) was applied to tackle a pool of FS problems. Although AFT is an efficient meta-heuristic for optimizing many problems, it sometimes exhibits premature convergence and low search performance. These issues were mitigated by proposing three enhanced versions of AFT, namely: (1) A Binary Multi-layered AFT called BMAFT which uses hierarchical and distributed frameworks, (2) Binary Elitist AFT (BEAFT) which uses an elitist learning strategy, and, (3) Binary Self-adaptive AFT (BSAFT) which uses an adapted tracking distance parameter. These versions along with the basic Binary AFT (BAFT) were expansively assessed on twenty-four problems gathered from different repositories. The results showed that the proposed algorithms substantially enhance the performance of BAFT in terms of convergence speed and solution accuracy. On top of that, the overall results showed that BMAFT is the most competitive, which provided the best results with excellent performance scores compared to other competing algorithms.