Search

This work aims to investigate the role of the resilience of Digital Twins on the applicability of the transportation system. A literature study is conducted to review the current status of research on transportation systems and Digital Twins. It is found that the current research on Digital Twins technology has achieved different degrees of success in different aspects of transportation systems. Yet, the system performance of Digital Twins has to be optimized. First, the application of Digital Twins in intelligent transportation systems is analyzed. Then, how the changes in traveler behavior patterns reflect the extent to which the traffic network is affected by uncertain events is analyzed from the traveler's perspective. Finally, an Internet of Vehicles (IoV) system based on Digital Twins and blockchain is established to solve the data redundancy and high computational volume problems of in-vehicle data sharing common in the IoV system. Moreover, the performance of the twin system is optimized by proposing a multi-intelligence body algorithm based on local perception, and a case validation is performed. The results demonstrate that the adaptability of the transportation system to uncertain events and its response and recovery measures taken are reflected to some extent in the traveler behavior model. Besides, data sharing between vehicles and infrastructure in the transportation network can be well solved by Digital Twins Blockchain. The locally-aware multi-intelligent body algorithm saves more than 50% communication overhead and improves operational efficiency by nearly 20% over traditional algorithms by increasing intelligent body infrastructure units. It is adequately suited for large-scale vehicle traffic twins. It can be seen that improving the resilience of Digital Twins is a very obvious change in the adaptability of the traffic system. [ABSTRACT FROM AUTHOR]

MicroRNAs (miRNAs) play a crucial role in the life processes of organisms and affect the occurrence of many complex human diseases. Discovering potential links between diseases and miRNAs can aid in the prevention, diagnosis, and therapy of complex human diseases. Identifying diseases and miRNA associations through existing biological experiments is expensive, while scientific computing approaches can quickly and efficiently predict the potential links between diseases and miRNAs. We propose SODNMF-DM, a SODNMF based Disease-MiRNA matrix factorisation algorithm. The SODNMF-DM model exhibited an AUC of 0.9051 and an AUPR of 0.4774, respectively. To directly verify the effectiveness of SODNMF-DM, we studied three common human cancers. The experimental results showed that 25 of the top 30 potential miRNAs predicted by our proposed SODNMF-DM model were confirmed by HMDDv3.0 database. Conclusion: SODNMF-DM outperformed four other approaches in AUC and AUPR. In addition, our proposed approach exhibited good performance in practical cases. The approach presented in this study is thus expected to complement the field of biological research. • We fully consider disease similarity and miRNA similarity from multiple perspectives. • We use the alternating gradient descent method to ensure the stability of the solution. • The SODNMF-DM model has low overall complexity, simple operation and easy replication. [ABSTRACT FROM AUTHOR]

In recent years, UAV remote sensing has been used to estimate water quality parameters, such as suspended solids (SS), turbidity (TUB), and chlorophyll-a (chl-a) levels, due to its low cost, convenience, and high resolution. The matching pixel-by-pixel (MPP) algorithm is one of the methods to find the optimal regression equation for retrieving water quality parameters from UAV images. However, MPP has a high computational burden and commonly experiences overfitting problems. Therefore, we propose an improved MPP algorithm (called IMP-MPP) to solve the above problems by sampling pixels based on clustering results and selecting models with more filtering conditions. In this study, Qingshan Lake, Hangzhou City, Zhejiang Province, China, is taken as the study area to evaluate the suspended solids and turbidity indicators. A total of 45 in situ samples and the UAV images around the sampling points are analyzed and processed by the proposed IMP-MPP algorithm, along with the average value method and MPP for comparison purpose. The experimental results show that the determination coefficient, average relative error and comprehensive error of the best inversion model derived by the IMP-MPP algorithm for SS are 0.8255, 15.08%, and 0.1981, respectively. The determination coefficient, average relative error and comprehensive error of the best inversion model for TUB are 0.8311, 16.49% and 0.2033, respectively. The results suggest that the IMP-MPP algorithm is promising in finding more accurate inversion models for SS and TUB. Finally, based on the optimal models, suspended solids and turbidity distribution maps are generated for further research. • A method of retrieving water quality parameters based on UAV multispectral images is proposed. • This method, based on the MPP algorithm, improves the operation efficiency and can be applied to larger data sets. • Redundant calculation is avoided when sampling image pixels. • Multiple standards are set to filter out overfitting models when selecting retrieval models. [ABSTRACT FROM AUTHOR]

Effects of chitosan combined with different concentrations of nisin on quality enhancement of large yellow croaker ( Pseudosciaena crocea ) stored at 4 °C were evaluated for 8 days. Changes in sensory score and volatile spoilage products, total viable counts (TVC), and physiochemical indexes including weight loss, colour, pH, total volatile basic nitrogen (TVB-N), and K -value were examined. Results demonstrated that nisin-treated samples presented better quality preservation effects than chitosan alone. 1% chitosan combined with 0.6% nisin presented optimal quality enhancement effects, such as moisture loss control, volatile spoilage inhibition, TVB-N reduction, TVC growth control, and colour and sensory acceptability maintenance. Therefore, chitosan combined with nisin is promising in large yellow croaker shelf life extension. [ABSTRACT FROM AUTHOR]

Dilated convolution has been widely used in various computer vision tasks due to its ability to expand the receptive field while maintaining the resolution of feature maps. However, the critical challenge is the gridding problem caused by the isomorphic structure of the dilated convolution, where the holes filled in the dilated convolution destroy the integrity of the extracted information and cut off the relevance of neighboring pixels. In this work, a novel heterogeneous dilated convolution, called HDConv, is proposed to address this issue by setting independent dilation rates on grouped channels while keeping the general convolution operation. The heterogeneous structure can effectively avoid the gridding problem while introducing multi-scale kernels in the filters. Based on the heterogeneous structure of the proposed HDConv, we also explore the benefit of large receptive fields to feature extraction by comparing different combinations of dilated rates. Finally, a series of experiments are conducted to verify the effectiveness of some computer vision tasks, such as image segmentation and object detection. The results show the proposed HDConv can achieve a competitive performance on ADE20K, Cityscapes, COCO-Stuff10k, COCO, and a medical image dataset UESTC-COVID-19. The proposed module can readily replace conventional convolutions in existing convolutional neural networks (i.e., plug-and-play), and it is promising to further extend dilated convolution to wider scenarios in the field of image segmentation. [ABSTRACT FROM AUTHOR]

Increasing municipal waste generation puts more and more municipal water resources at high risk. Accurate prediction of water quality becomes critical for effective protection of the water resources. Due to the nonlinear and non-stationary characteristics of water quality data of the municipal water resources, it is challenging to achieve high prediction accuracy, especially for medium-term and long-term predictions. To address this issue, we propose a novel hybrid deep learning model to predict water quality multiple steps ahead. The proposed model adopts the encoder–decoder structure in the form of two long short-term memory (LSTM) networks, integrated with the attention mechanism and a convolutional neural network (CNN). The model extracts the complex correlation between multiple water quality features through the CNN, and uses the two LSTM networks to transfer historical information to predictions, with an attention layer assigning different weights to the different parts of the historical information. Using three years of water quality data collected from an urban river, we experimentally show that the proposed model outperforms the baseline models by 11%–34% in root mean squared error (RMSE) when predicting dissolved oxygen multiple steps ahead, and by 1%–7% when predicting total phosphorus. Similar improvement has also been found in Nash–Sutcliffeefficiency (NSE) and mean absolute error (MAE). The proposed model is a feasible solution for multi-step medium-term water quality prediction. [ABSTRACT FROM AUTHOR]