Explore the vast range of titles available.

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in the field of ML, thus achieving outstanding results on several complex cognitive tasks, matching or even beating those provided by human performance. One of the benefits of DL is the ability to learn massive amounts of data. The DL field has grown fast in the last few years and it has been extensively used to successfully address a wide range of traditional applications. More importantly, DL has outperformed well-known ML techniques in many domains, e.g., cybersecurity, natural language processing, bioinformatics, robotics and control, and medical information processing, among many others. Despite it has been contributed several works reviewing the State-of-the-Art on DL, all of them only tackled one aspect of the DL, which leads to an overall lack of knowledge about it. Therefore, in this contribution, we propose using a more holistic approach in order to provide a more suitable starting point from which to develop a full understanding of DL. Specifically, this review attempts to provide a more comprehensive survey of the most important aspects of DL and including those enhancements recently added to the field. In particular, this paper outlines the importance of DL, presents the types of DL techniques and networks. It then presents convolutional neural networks (CNNs) which the most utilized DL network type and describes the development of CNNs architectures together with their main features, e.g., starting with the AlexNet network and closing with the High-Resolution network (HR.Net). Finally, we further present the challenges and suggested solutions to help researchers understand the existing research gaps. It is followed by a list of the major DL applications. Computational tools including FPGA, GPU, and CPU are summarized along with a description of their influence on DL. The paper ends with the evolution matrix, benchmark datasets, and summary and conclusion.

Data scarcity is a major challenge when training deep learning (DL) models. DL demands a large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate data to train DL frameworks. Usually, manual labeling is needed to provide labeled data, which typically involves human annotators with a vast background of knowledge. This annotation process is costly, time-consuming, and error-prone. Usually, every DL framework is fed by a significant amount of labeled data to automatically learn representations. Ultimately, a larger amount of data would generate a better DL model and its performance is also application dependent. This issue is the main barrier for many applications dismissing the use of DL. Having sufficient data is the first step toward any successful and trustworthy DL application. This paper presents a holistic survey on state-of-the-art techniques to deal with training DL models to overcome three challenges including small, imbalanced datasets, and lack of generalization. This survey starts by listing the learning techniques. Next, the types of DL architectures are introduced. After that, state-of-the-art solutions to address the issue of lack of training data are listed, such as Transfer Learning (TL), Self-Supervised Learning (SSL), Generative Adversarial Networks (GANs), Model Architecture (MA), Physics-Informed Neural Network (PINN), and Deep Synthetic Minority Oversampling Technique (DeepSMOTE). Then, these solutions were followed by some related tips about data acquisition needed prior to training purposes, as well as recommendations for ensuring the trustworthiness of the training dataset. The survey ends with a list of applications that suffer from data scarcity, several alternatives are proposed in order to generate more data in each application including Electromagnetic Imaging (EMI), Civil Structural Health Monitoring, Medical imaging, Meteorology, Wireless Communications, Fluid Mechanics, Microelectromechanical system, and Cybersecurity. To the best of the authors’ knowledge, this is the first review that offers a comprehensive overview on strategies to tackle data scarcity in DL.

The WRKY transcription factor family has more than 70 members in the Arabidopsis (Arabidopsis thaliana) genome, and some of them are involved in plant responses to biotic and abiotic stresses. This study evaluated the role of WRKY45 in regulating phosphate (Pi) uptake in Arabidopsis. WRKY45 was localized in the nucleus and mainly expressed in roots. During Pi starvation, WRKY45 expression was markedly induced, typically in roots. WRKY45 overexpression in Arabidopsis increased Pi content and uptake, while RNA interference suppression of WRKY45 decreased Pi content and uptake. Furthermore, the WRKY45-overexpressing lines were more sensitive to arsenate, the analog of Pi, compared with wild-type seedlings. These results indicate that WRKY45 positively regulates Arabidopsis Pi uptake. Quantitative real-time polymerase chain reaction and β-glucuronidase staining assays showed that PHOSPHATE TRANSPORTER1;1 (PHT1;1) expression was enhanced in the WRKY45-overexpressing lines and slightly repressed in the WRKY45 RNA interference line. Chromatin immunoprecipitation and eclectrophoretic mobility shift assay results indicated that WRKY45 can bind to two W-boxes within the PHT1;1 promoter, confirming the role of WRKY45 in directly up-regulating PHT1;1 expression. The pht1;1 mutant showed decreased Pi content and uptake, and overexpression of PHT1;1 resulted in enhanced Pi content and uptake. Furthermore, the PHT1;1-overexpressing line was much more sensitive to arsenate than WRKY45-overexpressing and wild-type seedlings, indicating that PHT1;1 overexpression can enhance Arabidopsis Pi uptake. Moreover, the enhanced Pi uptake and the increased arsenate sensitivity of the WRKY45-overexpressing line was impaired by pht1;1 (35S:WRKY45-18::pht1;1), demonstrating an epistatic genetic regulation between WRKY45 and PHT1;1. Together, our results demonstrate that WRKY45 is involved in Arabidopsis response to Pi starvation by direct up-regulation of PHT1;1 expression.

China’s rapid economic growth and improving quality of life have led to severe air pollution, primarily due to the country’s development model. This pollution not only raises public health risks but also shortens life expectancy, drawing significant attention from both the public and the government. This study focuses on 31 provincial-level regions within China, utilizing data collected annually from 2000 to 2021. It begins by examining the spatial relationships between air pollution and public health, then delves into how air pollution and various influencing factors affect public health outcomes. Lastly, the research investigates how these effects vary across different regional contexts. The findings show a clear connection between the medical visits for diagnosis and treatment and the levels of air pollution across different provinces. The spatial econometric model reveals that PM 2.5 levels, industrial SO 2 emissions, and smoke and dust emissions from industries all significantly increase medical visits for diagnosis and treatment. A 1% rise in PM 2.5 , SO 2 , or industrial smoke and dust emissions leads to increases of 0.2884%, 0.0563%, and 0.1365%, respectively, in medical visits. This suggests that air pollution contributes to a decline in public health. The impact of air pollution on public health shows considerable variation across different regions, including the eastern, central, and western parts of the country. The results of this study offer fresh insights into how air pollution affects public health, providing important guidance for policies aimed at improving air quality and protecting the health of citizens.

Background Cryo-electron microscopy (Cryo-EM) is widely used in the determination of the three-dimensional (3D) structures of macromolecules. Particle picking from 2D micrographs remains a challenging early step in the Cryo-EM pipeline due to the diversity of particle shapes and the extremely low signal-to-noise ratio of micrographs. Because of these issues, significant human intervention is often required to generate a high-quality set of particles for input to the downstream structure determination steps. Results Here we propose a fully automated approach (DeepCryoPicker) for single particle picking based on deep learning. It first uses automated unsupervised learning to generate particle training datasets. Then it trains a deep neural network to classify particles automatically. Results indicate that the DeepCryoPicker compares favorably with semi-automated methods such as DeepEM, DeepPicker, and RELION, with the significant advantage of not requiring human intervention. Conclusions Our framework combing supervised deep learning classification with automated un-supervised clustering for generating training data provides an effective approach to pick particles in cryo-EM images automatically and accurately.

One of the main challenges of employing deep learning models in the field of medicine is a lack of training data due to difficulty in collecting and labeling data, which needs to be performed by experts. To overcome this drawback, transfer learning (TL) has been utilized to solve several medical imaging tasks using pre-trained state-of-the-art models from the ImageNet dataset. However, there are primary divergences in data features, sizes, and task characteristics between the natural image classification and the targeted medical imaging tasks. Therefore, TL can slightly improve performance if the source domain is completely different from the target domain. In this paper, we explore the benefit of TL from the same and different domains of the target tasks. To do so, we designed a deep convolutional neural network (DCNN) model that integrates three ideas including traditional and parallel convolutional layers and residual connections along with global average pooling. We trained the proposed model against several scenarios. We utilized the same and different domain TL with the diabetic foot ulcer (DFU) classification task and with the animal classification task. We have empirically shown that the source of TL from the same domain can significantly improve the performance considering a reduced number of images in the same domain of the target dataset. The proposed model with the DFU dataset achieved F1-score value of 86.6% when trained from scratch, 89.4% with TL from a different domain of the targeted dataset, and 97.6% with TL from the same domain of the targeted dataset.

Optimizing the layout of major productive forces is key in the advancement of high-quality economic development and will inevitably drive significant changes in the spatial pattern of China’s iron and steel enterprises. This study selects 2005, 2010, 2014, 2020, and 2023 as time nodes during the period from the Tenth to the Fourteenth Five-Year Plan, analyzing the spatial evolution pattern and agglomeration characteristics from multiple scales of China’s iron and steel industry over the past 20 years by adopting various mathematical and theoretical methods. The results show that the distribution characteristics of “gradient” are reduced in the east, middle, and west from the perspective of the belt scale. There are notable differences in the spatial agglomeration of different types of iron and steel member units, except for the trade-type iron and steel member units; for example, on the national scale, iron and steel member units as a whole show a spatial distribution trend of “Northeast–Southwest”. There are a large number of production-type enterprise units displaying obvious relative concentrations and geographies; the movement trend of the regional centre of gravity can first be found in the southwest, moving then to the northeast and finally to the southwest. Based on this study, coastal and existing production bases should further improve environmental regulations, increase structural adjustment, and better play the role of demonstration and drive.

To achieve high power conversion efficiency in perovskite/silicon tandem solar cells, it is necessary to develop a promising wide-bandgap perovskite absorber and processing techniques in relevance. To date, the performance of devices based on wide-bandgap perovskite is still limited mainly by carrier recombination at their electron extraction interface. Here, we demonstrate assembling a binary two-dimensional perovskite by both alternating-cation-interlayer phase and Ruddlesden−Popper phase to passivate perovskite/C 60 interface. The binary two-dimensional strategy takes effects not only at the interface but also in the bulk, which enables efficient charge transport in a wide-bandgap perovskite solar cell with a stabilized efficiency of 20.79% (1 cm 2 ). Based on this absorber, a monolithic perovskite/silicon tandem solar cell is fabricated with a steady-state efficiency of 30.65% assessed by a third party. Moreover, the tandem devices retain 96% of their initial efficiency after 527 h of operation under full spectral continuous illumination, and 98% after 1000 h of damp-heat testing (85 °C with 85% relative humidity). The performance of wide bandgap perovskite solar cells is limited by the carrier recombination at their electron extraction interface. Here, the authors assemble binary 2D perovskites for efficient charge transport and realizing stable perovskite/silicon tandems with device efficiency over 30%.

Nowadays medical imaging plays a vital role in diagnosing the various types of diseases among patients across the healthcare system. Robust and accurate analysis of medical data is crucial to achieving a successful diagnosis from physicians. Traditional diagnostic methods are highly time-consuming and prone to handmade errors. Cost is reduced and performance is improved by adopting computer-aided diagnosis methods. Usually, the performance of traditional machine learning (ML) classification methods much depends on both feature extraction and selection methods that are sensitive to colors, shapes, and sizes, which conveys a complex solution when facing classification tasks in medical imaging. Currently, deep learning (DL) tools have become an alternative solution to overcome the drawbacks of traditional methods that make use of handmade features. In this paper, a new DL approach based on a hybrid deep convolutional neural network model is proposed for the automatic classification of several different types of medical images. Specifically, gradient vanishing and over-fitting issues have been properly addressed in the proposed model in order to improve its robustness by means of different tested techniques involving residual links, global average pooling layers, dropout layers, and data augmentation. Additionally, we employed the idea of parallel convolutional layers with the aim of achieving better feature representation by adopting different filter sizes on the same input and then concatenated as a result. The proposed model is trained and tested on the ICIAR 2018 dataset to classify hematoxylin and eosin-stained breast biopsy images into four categories: invasive carcinoma, in situ carcinoma, benign tumors, and normal tissue. As the experimental results show, our proposed method outperforms several of the state-of-the-art methods by achieving rate values of 93.2% and 89.8% for both image- and patch-wise image classification tasks, respectively. Moreover, we fine-tuned our model to classify foot images into two classes in order to test its robustness by considering normal and abnormal diabetic foot ulcer (DFU) image datasets. In this case, the model achieved an F1 score value of 94.80% on the public DFU dataset and 97.3% on the private DFU dataset. Lastly, transfer learning (TL) has been adopted to validate the proposed model with multiple classes with the aim of classifying six different wound types. This approach significantly improves the accuracy rate from a rate of 76.92% when trained from scratch to 87.94% when TL was considered. Our proposed model has proven its suitability and robustness by addressing several medical imaging tasks dealing with complex and challenging scenarios.

Rural tourism is a new point of growth for tourism and the economy in the context of the new normalization of the economy and is of great significance in achieving the complementary coordination and integration of urban and rural areas, promoting rural transformation, and increasing farmers’ incomes. The trends of rural tourism development mechanisms studied on a spatial scale can be used to interpret the sustainable development of rural tourism from different perspectives. Based on the data of key rural tourism villages in China’s Yellow River Basin (hereinafter referred to as the Yellow River Basin), kernel density estimation and spatial hot spot clustering methods were used in the present study to analyze the spatial distribution pattern and sustainable development mechanisms of these villages. The results showed that the spatial distribution of the key villages presents greater concentrations in the west and south than in the east and north, respectively. The spatial distribution of the key villages was found to be primarily affected by factors such as historical culture, transportation locations, economic level, and topography. Finally, the sustainable development mechanisms of rural tourism are proposed, and corresponding suggestions are provided from the perspectives of sustainable livelihoods, operation management, and marketing.