Search

The solving of dynamic matrix square root (DMSR) problems is frequently encountered in many scientific and engineering fields. Although the original zeroing neural network is powerful for solving the DMSR, it cannot vanish the influence of the noise perturbations, and its constant‐coefficient design scheme cannot accelerate the convergence speed. Therefore, a noise‐tolerate and adaptive coefficient zeroing neural network (NTACZNN) is raised to enhance the robust noise immunity performance and accelerate the convergence speed simultaneously. Then, the global convergence and robustness of the proposed NTACZNN are theoretically analysed under an ideal environment and noise‐perturbed circumstances. Furthermore, some illustrative simulation examples are designed and performed in order to substantiate the efficacy and advantage of the NTACZNN for the DMSR problem solution. Compared with some existing ZNNs, the proposed NTACZNN possesses advanced performance in terms of noise tolerance, solution accuracy, and convergence rate. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) and machine learning (ML) are revolutionizing human activities in various fields, with medicine and infectious diseases being not exempt from their rapid and exponential growth. Furthermore, the field of explainable AI and ML has gained particular relevance and is attracting increasing interest. Infectious diseases have already started to benefit from explainable AI/ML models. For example, they have been employed or proposed to better understand complex models aimed at improving the diagnosis and management of coronavirus disease 2019, in the field of antimicrobial resistance prediction and in quantum vaccine algorithms. Although some issues concerning the dichotomy between explainability and interpretability still require careful attention, an in-depth understanding of how complex AI/ML models arrive at their predictions or recommendations is becoming increasingly essential to properly face the growing challenges of infectious diseases in the present century. AI and ML are revolutionizing human activities in various fields, and infectious diseases are not exempt from their rapid and exponential growth. Despite some notable challenges, explainable AI/ML could provide insights into the decision-making process, making the outcomes of models more transparent. Improved transparency can help to build trust among healthcare professionals, policymakers, and the general public in leveraging AI/ML-based systems to face the growing challenges of infectious diseases in the present century. [ABSTRACT FROM AUTHOR]

Cell counting and segmentation are critical tasks in biology and medicine. The traditional methods for cell counting are labor‐intensive, time‐consuming, and prone to human errors. Recently, deep learning‐based cell counting methods have become a trend, including point‐based counting methods, such as cell detection and cell density prediction, and non‐point‐based counting, such as cell number regression prediction. However, the point‐based counting method heavily relies on well‐annotated datasets, which are scarce and difficult to obtain. On the other hand, nonpoint‐based counting is less interpretable. The task of cell counting by dividing it into two subtasks is approached: cell number prediction and cell distribution prediction. To accomplish this, a deep learning network for spatial‐based super‐resolution reconstruction (SSRNet) is proposed that predicts the cell count and segments the cell distribution contour. To effectively train the model, an optimized multitask loss function (OM loss) is proposed that coordinates the training of multiple tasks. In SSRNet, a spatial‐based super‐resolution fast upsampling module (SSR‐upsampling) is proposed for feature map enhancement and one‐step upsampling, which can enlarge the deep feature map by 32 times without blurring and achieves fine‐grained detail and fast processing. SSRNet uses an optimized encoder network. Compared with the classic U‐Net, SSRNet's running memory read and write consumption is only 1/10 of that of U‐Net, and the total number of multiply and add calculations is 1/20 of that of U‐Net. Compared with the traditional sampling method, SSR‐upsampling can complete the upsampling of the entire decoder stage at one time, reducing the complexity of the network and achieving better performance. Experiments demonstrate that the method achieves state‐of‐the‐art performance in cell counting and segmentation tasks. The method achieves nonpoint‐based counting, eliminating the need for exact position annotation of each cell in the image during training. As a result, it has demonstrated excellent performance on cell counting and segmentation tasks. The code is public on GitHub (https://github.com/Roin626/SSRnet). [ABSTRACT FROM AUTHOR]

Facial expression recognition (FER) is widely used in many fields. To further improve the accuracy of FER, this paper proposes a method based on double‐code LBP‐layer spatial‐attention network (DLSANet). The backbone model for the DLSANet is an emotion network (ENet), which is modified with a double‐code LBP (DLBP) layer and a spatial attention module. The DLBP layer is at the front of the first convolutional layer. More valuable features can be extracted by inputting the image processed by DLBP into convolutional layers. The JAFFE and CK+ datasets are used, which contain seven expressions: happiness, anger, disgust, neutral, fear, sadness, and surprise. The average of fivefold cross‐validation shows that DLSANet achieves a recognition accuracy of 93.81% and 98.68% on the JAFFE and CK+ datasets. The experiment reveals that the DLSANet can produce better classification results than state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

Simple Summary: Deep learning has succeeded greatly in medical image-based cancer diagnosis. To help readers better understand the current research status and ideas, this article provides a detailed overview of the working mechanisms and use cases of commonly used radiological imaging and histopathology, the basic architecture of deep learning, classical pretrained models, common methods to overcome overfitting, and the application of deep learning in medical image-based cancer diagnosis. Finally, the data, label, model, and radiomics were discussed specifically and the current challenges and future research hotspots were discussed and analyzed. (1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one of the research hotspots in the field of artificial intelligence and computer vision. Due to the rapid development of deep learning methods, cancer diagnosis requires very high accuracy and timeliness as well as the inherent particularity and complexity of medical imaging. A comprehensive review of relevant studies is necessary to help readers better understand the current research status and ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission computed tomography (PET), and histopathological images, are reviewed in this paper. The basic architecture of deep learning and classical pretrained models are comprehensively reviewed. In particular, advanced neural networks emerging in recent years, including transfer learning, ensemble learning (EL), graph neural network, and vision transformer (ViT), are introduced. Five overfitting prevention methods are summarized: batch normalization, dropout, weight initialization, and data augmentation. The application of deep learning technology in medical image-based cancer analysis is sorted out. (3) Results: Deep learning has achieved great success in medical image-based cancer diagnosis, showing good results in image classification, image reconstruction, image detection, image segmentation, image registration, and image synthesis. However, the lack of high-quality labeled datasets limits the role of deep learning and faces challenges in rare cancer diagnosis, multi-modal image fusion, model explainability, and generalization. (4) Conclusions: There is a need for more public standard databases for cancer. The pre-training model based on deep neural networks has the potential to be improved, and special attention should be paid to the research of multimodal data fusion and supervised paradigm. Technologies such as ViT, ensemble learning, and few-shot learning will bring surprises to cancer diagnosis based on medical images. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) technologies have been powerful solutions used to improve food yield, quality, and nutrition, increase safety and traceability while decreasing resource consumption, and eliminate food waste. Compared with several qualitative reviews on AI in food safety, we conducted an in-depth quantitative and systematic review based on the Core Collection database of WoS (Web of Science). To discover the historical trajectory and identify future trends, we analysed the literature concerning AI technologies in food safety from 2012 to 2022 by CiteSpace. In this review, we used bibliometric methods to describe the development of AI in food safety, including performance analysis, science mapping, and network analysis by CiteSpace. Among the 1855 selected articles, China and the United States contributed the most literature, and the Chinese Academy of Sciences released the largest number of relevant articles. Among all the journals in this field, PLoS ONE and Computers and Electronics in Agriculture ranked first and second in terms of annual publications and co-citation frequency. The present character, hot spots, and future research trends of AI technologies in food safety research were determined. Furthermore, based on our analyses, we provide researchers, practitioners, and policymakers with the big picture of research on AI in food safety across the whole process, from precision agriculture to precision nutrition, through 28 enlightening articles. [ABSTRACT FROM AUTHOR]

The complexity of AI-related theories may impede the applications of AI to MBD healthcare Deep learning (DL) is currently the most popular AI category. There are roughly six main categories of common AI methods [[21]]: deep learning, machine learning, neural networks, computer vision, robotics, and natural language processing, as shown in Figure 2. Big data have altered the way we manage, explore, evaluate, analyze, and leverage data across many different industries [[1]]. However, most MBD research thus far still focuses on either (i) traditional AI methods [[38]] due to the complexity of AI categories and sub-categories; or (ii) small-sized healthcare datasets involving the expensive collection of healthcare-related samples [[39]]. [Extracted from the article]

Purpose: In this article, the elementary notions and aggregation operations of single-valued neutrosophic parameterized complex fuzzy hypersoft set (sv-NPCFHSS) are characterized initially. Then by using matrix version of sv-NPCFHSS, a decision-support system is constructed for the evaluation of real estate residential projects by observing various risk factors. Design/methodology/approach: Two approaches are utilized in this research: set-theoretic approach and algorithmic approach. The first approach is used to investigate the notions of sv-NPCFHSS and its some aggregations whereas the second approach is used to propose an algorithm for designing its decision-support system by using the aggregation operations like reduced fuzzy matrix, decision matrix, etc. of sv-NPCFHSS. The adopted algorithm is validated in real estate scenario for the selection of residential project by observing various risk factors to avoid any expected investment loss. Findings: The proposed approach is more flexible and reliable as it copes with the shortcomings of literature on sv-neutrosophic set, sv-neutrosophic soft set and other fuzzy soft set-like structures by considering hypersoft setting, complex setting and neutrosophic setting collectively. Research limitations/implications: It has limitations for complex intuitionistic fuzzy hypersoft set, complex neutrosophic hypersoft set and other complex neutrosophic hypersoft set-like models. Practical implications: The scope of this research may cover a wide range of applications in several fields of mathematical sciences like artificial intelligence, optimization, MCDM, theoretical computer science, soft computing, mathematical statistics etc. Originality/value: The proposed model bears the characteristics of most of the relevant existing fuzzy soft set-like models collectively and fulfills their limitations. [ABSTRACT FROM AUTHOR]

With the increasing requirements for aerodynamic performance, aerodynamic configuration design of aircraft based on traditional design experience has gradually failed to meet the needs of the future. Therefore, the new concept aerodynamic shape design will be the development trend for future aircraft, but the current new concept aerodynamic shape design is still based on the designer's understanding of the existing flow physics. One novel technology that can be useful is topology design. Compared with traditional design, topology design not only has more undetermined parameters, but also its topology variables have a greater impact on the design goals. In this perspective, we propose the concept of Artificial Intelligent Topology Design (AITD) for aerodynamic configuration design based on topology design and artificial intelligence technology and discuss its potential in the application of the new concept of aerodynamic configuration design. [ABSTRACT FROM AUTHOR]

• We analysed over 350 references from all well-famed databases. • We provided a comprehensive survey on deep learning in food category recognition. • This review encompassed current challenges & applications, strengths & limitations. • Fundamental deep learning rules and performance assessment methods were reviewed. • Convolutional neural networks, transfer and semi-supervised learning were reviewed. Integrating artificial intelligence with food category recognition has been a field of interest for research for the past few decades. It is potentially one of the next steps in revolutionizing human interaction with food. The modern advent of big data and the development of data-oriented fields like deep learning have provided advancements in food category recognition. With increasing computational power and ever-larger food datasets, the approach's potential has yet to be realized. This survey provides an overview of methods that can be applied to various food category recognition tasks, including detecting type, ingredients, quality, and quantity. We survey the core components for constructing a machine learning system for food category recognition, including datasets, data augmentation, hand-crafted feature extraction, and machine learning algorithms. We place a particular focus on the field of deep learning, including the utilization of convolutional neural networks, transfer learning, and semi-supervised learning. We provide an overview of relevant studies to promote further developments in food category recognition for research and industrial applications. [ABSTRACT FROM AUTHOR]

One of the concerns people have is how to get the diagnosis online without privacy being jeopardized. In this paper, we propose a privacy-preserving intelligent medical diagnosis system (IMDS), which can efficiently solve the problem. In IMDS, users submit their health examination parameters to the server in a protected form; this submitting process is based on Paillier cryptosystem and will not reveal any information about their data. And then the server retrieves the most likely disease (or multiple diseases) from the database and returns it to the users. In the above search process, we use the oblivious keyword search (OKS) as a basic framework, which makes the server maintain the computational ability but cannot learn any personal information over the data of users. Besides, this paper also provides a preprocessing method for data stored in the server, to make our protocol more efficient. [ABSTRACT FROM AUTHOR]

It relies on the synergy between artificial intelligence (AI) and software engineering, improving both software productivity and quality, for example, providing coding suggestions for better productivity or locating defects to avoid poor quality. Intelligent software engineering is an emerging topic that has attracted great attention in both academia and industry. The first paper, titled 'Syntax-based metamorphic relation prediction via the bagging framework' by Li et al., proposes a multi-dimensional program structure-based metamorphic relation prediction approach, which is composed of feature extraction and prediction model building. [Extracted from the article]

The approaches based on vision transformers (ViTs) are advancing the field of medical artificial intelligence (AI) and cancer diagnosis. Recently, many researchers have developed artificial intelligence methods for cancer diagnosis based on ViTs. In this paper, 98 pertinent articles since 2020 were carefully chosen from digital databases, including Google scholar, Elsevier, and Springer Link, to review the research progress of artificial intelligence methods for cancer imaging based on ViT. Method : The basic structure of ViT is introduced, and corresponding modules such as patch embedding, positional embedding, transformer encoder, multi-head self-attention (MSA), layer normalization (LN), and residual connections, multilayer perceptron (MLP) are elaborated; a comprehensive review of improved ViT models in the medical field is presented. The application of ViT technology in cancer analysis based on medical images was reviewed. Results : ViT has achieved great success in cancer diagnosis based on medical images, showing its advantages in image classification, image reconstruction, image detection, image segmentation, image registration, image fusion, and other tasks. In these task studies, the most common task is cancer image classification and segmentation. There is still a lot of room for improvement in the aspects of multi-task learning, multi-modal learning, model generality, generalization ability, and explainability, and it also faces the mutual restriction of model scale and performance. Conclusion : The ViT training model for cancer diagnosis can potentially improve. The ViT model of self-supervised learning and semi-supervised learning mechanism is promising research. The lightweight attention module design, ViTs based on mobile networks, and the development of 3DViT will promote cancer diagnosis based on medical images to be more accurate and efficient. [ABSTRACT FROM AUTHOR]

• This paper summarizes 181 studies on artificial intelligence used to help the visually impaired. • DL can help diagnose eye diseases, including cataracts, diabetic retinopathy, and glaucoma. • DL can help build assisted reading and obstacle avoidance systems. The eyes are an essential tool for human observation and perception of the world, helping people to perform their tasks. Visual impairment causes many inconveniences in the lives of visually impaired people. Therefore, it is necessary to focus on the needs of the visually impaired community. Researchers work from different angles to help visually impaired people live normal lives. The advent of the digital age has profoundly changed the lives of the visually impaired community, making life more convenient. Deep learning, as a promising technology, is also expected to improve the lives of visually impaired people. It is increasingly being used in the diagnosis of eye diseases and the development of visual aids. The earlier accurate diagnosis of the eye disease by the doctor, the sooner the patient can receive the appropriate treatment and the better chances of a cure. This paper summarises recent research on the development of artificial intelligence-based eye disease diagnosis and visual aids. The research is divided according to the purpose of the study into deep learning methods applied in diagnosing eye diseases and smart devices to help visually impaired people in their daily lives. Finally, a summary is given of the directions in which artificial intelligence may be able to assist the visually impaired in the future. In addition, this overview provides some knowledge about deep learning for beginners. We hope this paper will inspire future work on the subjects.. [ABSTRACT FROM AUTHOR]