Enhancing accessibility: deep learning-based image description for individuals with visual impairments

The study presents the results of the development and testing of deep learning neural network architectures, which demonstrate high accuracy rates in classifying neurophysiological data, in particular hemodynamic brain activation patterns obtained by functional near-infrared spectroscopy, during solving mathematical problems on spatial-numerical associations. The analyzed signal represents a multidimensional time series of oxyhemoglobin and deoxyhemoglobin dynamics. Taking the specificity of the fNIRS signal into account, a comparative analysis of 2 types of neural network architectures was carried out: (1) architectures based on recurrent neural networks: recurrent neural network with long short-term memory, recurrent neural network with long short-term memory with fully connected layers, bidirectional recurrent neural network with long short-term memory, convolutional recurrent neural network with long short-term memory; (2) architectures based on convolutional neural networks with 1D convolutions: convolutional neural network, fully convolutional neural network, residual neural network. Trained long short-term memory recurrent neural network architectures showed worse results in accuracy in comparison with 1D convolutional neural network architectures. Residual neural network (model_Resnet) demonstrated the highest accuracy rates in three experimental conditions more than 88% in detecting age-related differences in brain activation during spatial-numerical association tasks considering the individual characteristics of the respondents’ signal.

This article aims to systematically sort out the development trajectory of artificial intelligence technology from theory to application, and clarify the evolution of its core model, the current challenges and the future development trend, in order to provide a clear reference for in-depth research in this field. For this reason, this article first traces the development process and milestone events of artificial intelligence since the mid-20th century. Then, the core concepts and architectures of four representative model types (Multi-Layer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) and Transformer) and the successful application cases in key fields such as health care and finance are analyzed. In addition, through structured analysis, this article deeply explores the three core challenges faced by the current artificial intelligence system in the process of moving towards reliable and reliable deployment: model interpretability ("black box" problem), insufficient generalization ability and security vulnerabilities. In response to these problems, this article explores how key technical paths such as artificial intelligence, migration learning and federal learning can provide a blueprint for building the next generation of reliable artificial intelligence systems. Analysis shows that the development of artificial intelligence is shifting from the simple pursuit of performance breakthroughs to the construction of robust, safe and understandable intelligent systems. This transformation requires the coordinated development of algorithm innovation and ethical, legal and social frameworks.

The integration of remote sensing (RS) and artificial intelligence (AI) has revolutionized Earth observation, enabling automated, efficient, and precise analysis of vast and complex datasets. RS techniques, leveraging satellite imagery, aerial photography, and ground-based sensors, provide critical insights into environmental monitoring, disaster response, agriculture, and urban planning. The rapid developments in AI, specifically machine learning (ML) and deep learning (DL), have significantly enhanced the processing and interpretation of RS data. AI-powered models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and reinforcement learning (RL) algorithms, have demonstrated remarkable capabilities in feature extraction, classification, anomaly detection, and predictive modeling. This paper provides a comprehensive survey of the latest developments at the intersection of RS and AI, highlighting key methodologies, applications, and emerging challenges. While AI-driven RS offers unprecedented opportunities for automation and decision-making, issues related to model generalization, explainability, data heterogeneity, and ethical considerations remain significant hurdles. The review concludes by discussing future research directions, emphasizing the need for improved model interpretability, multimodal learning, and real-time AI deployment for global-scale applications.

Recent experience in applying recurrent neural networks (RNNs) to interpreting Permannt Downhole Gauge (PDG) records has highlighted the potential utility of machine learning algorithms to learn reservoir behavior from data. The power of the RNN resides in its ability to retain information in a form of memory of previous patterns and information contained in the previous behavior of phenomena being modeled. This memory plays a role of informing the decision at the present time by using what happened in the past. This property suggests RNNs as a suitable choice to model sequences of reservoir information, even when the reservoir modeler is faced with incomplete knowledge of the underlying physical system. Convolutional Neural Networks (CNNs) are another variant of machine learning algorithms that have shown promise in sequence modeling domains, such as audio synthesis and machine translation. In this study, RNN and CNN were applied to tasks that traditionally would be modeled by a reservoir simulator. This was achieved by formulating the relationship between physical quantities of interest from subsurface reservoirs as a sequence mapping problem. In addition, the performance of a CNN layer as compared to RNN was evaluated systematically to investigate their capabilities in a variety of tasks of interest to the reservoir engineer. Preliminary results suggest that CNNs, with specific design modifications, are as capable as RNNs in modeling sequences of information and as reliable when making inferences to cases that has not been seen by the algorithm during training. Design details and reasons pertaining to the way these two seemingly different architectures process information, and handle memory are also discussed.

With several applications in various different fields, computer vision can be found everywhere in our society. A fundamental problem of artificial intelligence (AI) is to give automatic description of the content in an image. In this paper, we focus on one of the visual recognition facets of computer vision, i.e., image captioning. To give the description for visual data has been studied for a long time but in the field of videos. In the recent few years, emphasis has been lead on still image description with natural text. Due to the recent advancements in the field of object detection, the task of scene description in an image has become easier. The aim of the paper was to train convolutional neural networks (CNN) with several hundreds of hyperparameters and apply it on a huge dataset of images (ImageNet) and combine the results of this image classifier with a recurrent neural network to create a caption for the classified picture. In this paper, we systematically analyze a deep neural networks-based image caption generation method. With an image as the input, the method can output an English sentence describing the content in the image. We analyze three components of the method: convolutional neural network (CNN), recurrent neural network (RNN) and sentence generation. By replacing the CNN part with three state-of-the-art architectures, we find the VGGNet which performs best according to the BLEU score. In this paper, we present the detailed architecture of the model used by us. We achieved a BLEU score of 56 on the Flickr8k dataset while the state-of-the-art results rest at 66 on the dataset.

In recent years, Deep Learning (DL), such as the algorithms of Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN) and Generative Adversarial Networks (GAN), has been widely studied and applied in various fields including agriculture. Researchers in the fields of agriculture often use software frameworks without sufficiently examining the ideas and mechanisms of a technique. This article provides a concise summary of major DL algorithms, including concepts, limitations, implementation, training processes, and example codes, to help researchers in agriculture to gain a holistic picture of major DL techniques quickly. Research on DL applications in agriculture is summarized and analyzed, and future opportunities are discussed in this paper, which is expected to help researchers in agriculture to better understand DL algorithms and learn major DL techniques quickly, and further to facilitate data analysis, enhance related research in agriculture, and thus promote DL applications effectively. Keywords: deep learning, smart agriculture, neural network, convolutional neural networks, recurrent neural networks, generative adversarial networks, artificial intelligence, image processing, pattern recognition DOI: 10.25165/j.ijabe.20181104.4475 Citation: Zhu N Y, Liu X, Liu Z Q, Hu K, Wang Y K, Tan J L, et al. Deep learning for smart agriculture: Concepts, tools, applications, and opportunities. Int J Agric & Biol Eng, 2018; 11(4): 32-44.

Deep learning (DL) has shown explosive growth in its application to bioinformatics and has demonstrated thrillingly promising power to mine the complex relationship hidden in large-scale biological and biomedical data. A number of comprehensive reviews have been published on such applications, ranging from high-level reviews with future perspectives to those mainly serving as tutorials. These reviews have provided an excellent introduction to and guideline for applications of DL in bioinformatics, covering multiple types of machine learning (ML) problems, different DL architectures, and ranges of biological/biomedical problems. However, most of these reviews have focused on previous research, whereas current trends in the principled DL field and perspectives on their future developments and potential new applications to biology and biomedicine are still scarce. We will focus on modern DL, the ongoing trends and future directions of the principled DL field, and postulate new and major applications in bioinformatics.

A hybrid model based on neural networks for biomedical relation extraction

Deep Learning and Beyond: AI’s New Horizons” is an expansive monograph that delves into the dynamic and rapidly evolving field of deep learning, a key area of artificial intelligence. This comprehensive work provides an insightful exploration of the revolutionary developments, foundational concepts, and future directions of deep learning, positioning itself as a crucial resource for understanding this transformative technology. The monograph commences with an introductory chapter that lays the groundwork by elucidating the background of machine learning and chronicling the ascent of deep learning. This foundational perspective is vital for comprehending the underlying principles and methodologies that have propelled deep learning to the forefront of technological innovation. Subsequent chapters delve into the “Historical Evolution” of AI, tracing the origins of neural networks from their early inception to the Renaissance period of deep learning. This historical analysis is pivotal in understanding the field’s trajectory and significant milestones. The “Foundations of Deep Learning” chapter presents an in-depth analysis of neural networks, covering their basic architecture, activation functions, layers, and the critical process of backpropagation and gradient descent. This is followed by examining “Advanced Neural Network Architectures,” where the focus shifts to state-of-the-art models such as convolutional neural networks, recurrent neural networks, and groundbreaking transformers and attention mechanisms. In addressing the “Training Deep Models,” the monograph explores regularization techniques, optimization strategies, and the increasingly significant role of transfer learning and pre-trained models. The application-oriented chapter, “Applications of Deep Learning,” showcases real-world implementations in domains like image recognition, natural language viii processing, and autonomous systems, illustrating deep learning technologies’ vast potential and versatility. The monograph also tackles the “Challenges in Deep Learning,” including overfitting, interpretability, and the ethical considerations surrounding AI deployment. It then ventures into the “Future of Deep Learning,” contemplating emerging trends such as integrating quantum computing, neural architecture search, and the convergence of neuroscience and deep learning. “Case Studies” provide practical insights and empirical evidence of the impact of deep learning. At the same time, the concluding chapter synthesizes the current state of deep learning, offers predictions for the future, and provides reflective thoughts on this transformative field. “Deep Learning and Beyond: AI’s New Horizons” educates and informs readers about the vast potential and future possibilities of deep learning and artificial intelligence. Keywords: Deep Learning, Artificial Intelligence, Neural Networks, Machine Learning, Convolutional Neural Networks, Recurrent Neural Networks, Transformers, Quantum Computing, Ethical AI, Neural Architecture Search, Natural Language Processing, Autonomous Systems, AI in Healthcare, Future of AI, AI Applications, AI Challenges.

Purpose This study analyzes China’s strategic initiatives in metaverse and artificial intelligence (AI) development, examining their impact on academic research, industry innovation, and policy formulation. It aims to understand how government policies and investments have shaped research agendas and to identify challenges and opportunities in these fields. Design/methodology/approach The research employs a comprehensive analysis of government documents, funding schemes, and research output. It examines key policies, investment programs, and academic publications to track trends in metaverse and AI development in China. The study utilizes bibliometric analysis to assess publication trends, citation patterns, and international collaboration networks. Findings China’s proactive approach, characterized by strong government support and significant private sector investment, has led to a substantial increase in research output and quality in metaverse and AI fields. Chinese institutions have become major contributors to global publications, with growing citation rates and presence at international conferences. The research identifies emerging challenges in privacy, ethical AI development, and digital divide concerns. Practical implications The findings provide insights for policymakers, researchers, and industry stakeholders on the development trajectory of metaverse and AI technologies in China. They highlight the need for balanced approaches to innovation, regulation, and ethical considerations in these rapidly evolving fields. Social implications The study underscores the potential of metaverse and AI technologies to transform various sectors of society, from education and healthcare to entertainment and social interactions. It emphasizes the importance of addressing digital equity and ethical AI deployment to ensure broad societal benefits. Originality/value This research offers a comprehensive overview of China’s approach to metaverse and AI development, providing a unique perspective on the interplay between government initiatives, academic research, and industry innovation. It contributes to the broader discussion on the global development of these transformative technologies and their implications for future technological landscapes.

In recent years, convolutional neural networks have been widely used in image processing and have shown good results. Particularly useful was their ability to automatically extract image features (textures and shapes of objects). The article proposes a method that improves the accuracy and speed of recognition of an ultra-precise neural network based on image recognition of people’s faces. At first, a recurrent neural network is introduced into the convolutional neural network, thereby studying the characteristics of the image more deeply. Deep image characteristics are studied in parallel using a convolutional and recurrent neural network. In line with the idea of skipping the ResNet convolution layer, a new ShortCut3- ResNet residual module is built. A double optimization model is created to fully optimize the convolution process. A study of the influence of various parameters of a convolutional neural network on network performance is demonstrated, also analyzed using simulation experiments. As a result, the optimal parameters of the convolutional neural network are established. Ex- periments show that the method presented in this paper can study various images of people’s faces regardless of age, gender, and also improves the accuracy of feature extraction and image recognition ability.

The integration of AI is anticipated to bring a major transformation to the quality, value, and impact of radiology on patient care and population health, as well as radiologists' workflows, over the next decade.AI technologies are already being applied across various dental specialties, including orthodontics.There are various applications of AI in Oral and Maxillofacial Radiology.AI is expected to ease the daily workload of physicians and reduce the incidence of misdiagnosis or underdiagnosis in dental practice.Although AI systems are a valuable resource in both dentistry and dental education, it's crucial to recognize that these technological advancements stem from human innovation and discovery.The ability of a machine to mimic intelligent human behaviors to perform complicated tasks like problem-solving, object and word recognition, and decision-making is known as artificial intelligence or AI [1,2].AI has gained popularity recently in several areas, including dentistry, where its uses in oral and maxillofacial imaging show significant promise.Because radiology creates digitally coded images, integrating AI into medical procedures is much simpler [3].Convolutional neural networks, which are capable of handling tasks including image categorization, detection, segmentation, registration, creation, and refinement, are the main focus of recent studies in oral and maxillofacial radiology [4].In this field, artificial intelligence systems have been developed for image analysis, forensic dentistry, radiography diagnosis, and picture quality enhancement [4].However, obtaining useful results necessitates large data sets, and oral and maxillofacial radiologists play a critical role in creating reliable and consistent datasets, which can take a lot of time.The use of AI is expected to bring about a dramatic revolution in the next ten years regarding the workflows of radiologists and the impact of radiology on population health and patient care.Dentists need to use their skills to evaluate patients, choose the best course of treatment, and make clinically sound prognostic judgments.They might, however, occasionally lack the expertise needed to act swiftly and decisively in clinical decisions.Applications of AI can be useful tools for improving performance and decision-making.AI is already being used in several dental specializations, such as orthodontics.The majority of current research focuses on artificial intelligence (AI) models that use artificial neural networks (ANNs) and convolutional neural networks (CNNs) [5].AI developments are anticipated to lessen the everyday burden on healthcare professionals and lower the number of dental misdiagnoses and underdiagnoses.Radiological image research encompasses tasks such as segmenting and classifying teeth, automatically labeling anatomical structures, performing cephalometric analysis, detecting early dental diseases and periodontal conditions, and using jaw radiographs to diagnose specific diseases like osteoporosis [6].

Since IBM’s “Deep Blue” computer defeated the world champion Garry Kasparov, chess is a vital evaluation scenario to verify the learning ability of artificial intelligence algorithms. Recently, with the rapid development of this neural network technology, deep learning and reinforcement learning technology based on neural networks has completely changed the chess artificial intelligence. Several mainstream neural networks, such as Convolutional Neural Networks (CNN), are good at recognizing chess pieces and extracting game features, while Recurrent Neural Network (RNNs) analyzes complex moving sequences. AlphaZero, based on deep reinforcement learning, can even surpass human champions in the field of Go through self-supervised learning, demonstrating the great potential of artificial intelligence in intellectual games. Although artificial intelligence has greatly enhanced the competitiveness and accessibility of the game, the interpretability of the deep learning model is still a limitation, especially in high-risk or high-trust areas, where it is essential to understand the model behaviour, decision-making process and transparency. In this paper, the development of deep learning in the chess system is deeply studied, the challenge of interpretability is explored, and the potential of causal reasoning is discussed to enhance the interpretability and the overall application value of chess artificial intelligence.

Since IBM’s “Deep Blue” computer defeated the world champion Garry Kasparov, chess is a vital evaluation scenario to verify the learning ability of artificial intelligence algorithms. Recently, with the rapid development of this neural network technology, deep learning and reinforcement learning technology based on neural networks has completely changed the chess artificial intelligence. Several mainstream neural networks, such as Convolutional Neural Networks (CNN), are good at recognizing chess pieces and extracting game features, while Recurrent Neural Network (RNNs) analyzes complex moving sequences. AlphaZero, based on deep reinforcement learning, can even surpass human champions in the field of Go through self-supervised learning, demonstrating the great potential of artificial intelligence in intellectual games. Although artificial intelligence has greatly enhanced the competitiveness and accessibility of the game, the interpretability of the deep learning model is still a limitation, especially in high-risk or hightrust areas, where it is essential to understand the model behaviour, decision-making process and transparency. In this paper, the development of deep learning in the chess system is deeply studied, the challenge of interpretability is explored, and the potential of causal reasoning is discussed to enhance the interpretability and the overall application value of chess artificial intelligence.

One of the ways humans communicate is by using facial expressions. Research on technology development in artificial intelligence uses deep learning methods in human and computer interactions as an effective system application process. One example, if someone does show and tries to recognize facial expressions when communicating. The prediction of the expression or emotion of some people who see it sometimes does not understand. In psychology, the detection of emotions or facial expressions requires analysis and assessment of decisions in predicting a person's emotions or group of people in communicating. This research proposes the design of a system that can predict and recognize the classification of facial emotions based on feature extraction using the Convolution Neural Network (CNN) algorithm in real-time with the OpenCV library, namely: TensorFlow and Keras. The research design implemented in the Raspberry Pi consists of three main processes, namely: face detection, facial feature extraction, and facial emotion classification. The prediction results of facial expressions in research with the Convolutional Neural Network (CNN) method using Facial Emotion Recognition (FER-2013) were 65.97% (sixty-five point ninety-seven percent).