Search

The research groups in computer vision, graphics, and machine learning have dedicated a substantial amount of attention to the areas of 3D object reconstruction, augmentation, and registration. Deep learning is the predominant method used in artificial intelligence for addressing computer vision challenges. However, deep learning on three-dimensional data presents distinct obstacles and is now in its nascent phase. There have been significant advancements in deep learning specifically for three-dimensional data, offering a range of ways to address these issues. This study offers a comprehensive examination of the latest advancements in deep learning methodologies. We examine many benchmark models for the tasks of 3D object registration, augmentation, and reconstruction. We thoroughly analyse their architectures, advantages, and constraints. In summary, this report provides a comprehensive overview of recent advancements in three-dimensional deep learning and highlights unresolved research areas that will need to be addressed in the future.

Quality assessment in industrial applications is often carried out through visual inspection, usually performed or supported by human domain experts. However, the manual visual inspection of processes and products is error-prone and expensive. It is therefore not surprising that the automation of visual inspection in manufacturing and maintenance is heavily researched and discussed. The use of artificial intelligence as an approach to visual inspection in industrial applications has been considered for decades. Recent successes, driven by advances in deep learning, present a possible paradigm shift and have the potential to facilitate automated visual inspection, even under complex environmental conditions. For this reason, we explore the question of to what extent deep learning is already being used in the field of automated visual inspection and which potential improvements to the state of the art could be realized utilizing concepts from academic research. By conducting an extensive review of the openly accessible literature, we provide an overview of proposed and in-use deep-learning models presented in recent years. Our survey consists of 196 open-access publications, of which 31.7% are manufacturing use cases and 68.3% are maintenance use cases. Furthermore, the survey also shows that the majority of the models currently in use are based on convolutional neural networks, the current de facto standard for image classification, object recognition, or object segmentation tasks. Nevertheless, we see the emergence of vision transformer models that seem to outperform convolutional neural networks but require more resources, which also opens up new research opportunities for the future. Another finding is that in 97% of the publications, the authors use supervised learning techniques to train their models. However, with the median dataset size consisting of 2500 samples, deep-learning models cannot be trained from scratch, so it would be beneficial to use other training paradigms, such as self-supervised learning. In addition, we identified a gap of approximately three years between approaches from deep-learning-based computer vision being published and their introduction in industrial visual inspection applications. Based on our findings, we additionally discuss potential future developments in the area of automated visual inspection.

Abstract Integrating energy systems with information systems in smart grids offers a promising avenue for combating electricity theft by leveraging real-time data insights. Suspicious activity indicative of theft can be identified through anomalous consumption patterns observed in smart networks. However, a smart model is required for capturing and analysing the data intelligently to accurately detect electricity theft. In the paper, electricity theft has been detected using an encoder-decoder-based classifier that integrates two models of convolutional neural networks (CNN). The aim is to scan the strength of the data and built a smart model that analysed the connections in complex data and determine the pattern of theft. The model comprises three compartments: the auto-encoder, the wide convolutional neural network (1-D CNN model), and the deep convolutional neural network (2-D CNN model). The auto-encoder has been trained on the complex and in-depth linkage between the theft data and the normal data as it removes noise and unnecessary information. The 1-D CNN model gathers relevant connections and general features, while the 2-D CNN model determines the rate at which energy theft occurs and differentiates between the energy-stealing consumers and normal consumers. The efficacy of the approach is underscored by its superiority over traditional deep learning and machine learning techniques. This paper elucidates the distinct advantages and applications of the proposed model in combating electricity theft within smart grid environments.

Abstract Accurate atom mapping, which establishes correspondences between atoms in reactants and products, is a crucial step in analyzing chemical reactions. In this paper, we present a novel end-to-end approach that formulates the atom mapping problem as a deep graph matching task. Our proposed model, AMNet (Atom Matching Network), utilizes molecular graph representations and employs various atom and bond features using graph neural networks to capture the intricate structural characteristics of molecules, ensuring precise atom correspondence predictions. Notably, AMNet incorporates the consideration of molecule symmetry, enhancing accuracy while simultaneously reducing computational complexity. The integration of the Weisfeiler-Lehman isomorphism test for symmetry identification refines the model’s predictions. Furthermore, our model maps the entire atom set in a chemical reaction, offering a comprehensive approach beyond focusing solely on the main molecules in reactions. We evaluated AMNet’s performance on a subset of USPTO reaction datasets, addressing various tasks, including assessing the impact of molecular symmetry identification, understanding the influence of feature selection on AMNet performance, and comparing its performance with the state-of-the-art method. The result reveals an average accuracy of 97.3% on mapped atoms, with 99.7% of reactions correctly mapped when the correct mapped atom is within the top 10 predicted atoms. Scientific contribution The paper introduces a novel end-to-end deep graph matching model for atom mapping, utilizing molecular graph representations to capture structural characteristics effectively. It enhances accuracy by integrating symmetry detection through the Weisfeiler-Lehman test, reducing the number of possible mappings and improving efficiency. Unlike previous methods, it maps the entire reaction, not just main components, providing a comprehensive view. Additionally, by integrating efficient graph matching techniques, it reduces computational complexity, making atom mapping more feasible.

Abstract Recent studies have proven that data analytics may assist in predicting events before they occur, which may impact the outcome of current situations. In the medical sector, it has been utilized for predicting the likelihood of getting a health condition such as chronic kidney disease (CKD). This paper aims at developing a CKD prediction framework, which forecasts CKD occurrence over a specific time using deep learning and deep ensemble learning approaches. While a great deal of research focuses on disease detection, few studies contribute to disease prediction before it may occur. However, the performance of previous work was not competitive. This paper tackles the under-explored area of early CKD prediction through a high-performing deep learning and ensemble framework. We bridge the gap between existing detection methods and preventive interventions by: developing and comparing deep learning models like CNN, LSTM, and LSTM-BLSTM for 6–12 month CKD prediction; addressing data imbalance, feature selection, and optimizer optimization; and building an ensemble model combining the best individual models (CNN-Adamax, LSTM-Adam, and LSTM-BLSTM-Adamax). Our framework achieves significantly higher accuracy (98% and 97% for 6 and 12 months) than previous work, paving the way for earlier diagnosis and improved patient outcomes.

Abstract With a significant number of mechanical products approaching the retirement phase, the batch recycling of discarded mechanical parts necessitates a preliminary assessment of their surface condition. However, the presence of surface rust poses a challenge to defect identification. Therefore, this paper proposes a method for detecting heavily rusted surface defects based on an improved YOLOv8n network. In the Backbone, the C2f-DBB module of re-parameterized deep feature extraction was introduced, and the attention module was designed to improve the accuracy of information extraction. In the Neck part, a Bi-Afpn multiscale feature fusion strategy is designed to facilitate information exchange between features at different scales. Finally, Focal-CIoU is employed as the bounding box loss function to enhance the network’s localization performance and accuracy for defects. Experimentally, it is proved that the improved network in this paper improves the Recall, Precision, and mAP0.5 by 1.2%, 2.1%, and 1.9%, respectively, on the original basis, which is better than other network models.

Abstract Learning is to use algorithms to enable machines to learn rules from a large amount of historical data, so as to intelligently identify new samples or predict the future. Deep learning can promote students’ understanding of knowledge, conduct in-depth processing of new knowledge, integrate it with the original knowledge, and apply it to new situations, solve intelligent audio–visual listening from the perspective of deep learning, and focus on cultivating students’ in-depth learning ability and individual differences in innovative thinking. As the main position of ecological education, schools should effectively strengthen the publicity and education of ecological ideas and low-carbon concepts, and integrate them into education and teaching to effectively improve students’ awareness of environmental protection. This study aims to explore the effectiveness of flipped classroom teaching model based on deep learning. Therefore, from the perspective of deep learning, this paper combs the theory of deep learning, constructs a new model of smart classroom, and provides ideas and directions for model reform. In this study, the flipped classroom teaching model based on deep learning was applied to English teaching, and an 8-week teaching experiment was conducted. In addition, this paper believes that it is of great practical significance to carry out environmental protection education with the help of English teaching.

How to preserve the complementary information in multiple images to represent the scene in one image is a challenging topic. Based on this topic, various image fusion methods have been proposed. As an important branch of image fusion, infrared and visible image fusion (IVIF) has a wide range of applications in segmentation, target detection and military reconnaissance fields. In recent years, deep learning has led the development direction of image fusion. Researchers have explored the field of IVIF using deep learning. Relevant experimental work has proven that applying deep learning to achieving IVIF has significant advantages compared with traditional methods. This paper provides a detailed analysis on the advanced algorithms for IVIF based on deep learning. Firstly, this paper reports on the current research status from the aspects of network architecture, method innovation, and limitations. Secondly, this paper introduces the commonly used datasets in IVIF methods and provides the definition of commonly used evaluation metrics in quantitative experiments. Qualitative and quantitative evaluation experiments of fusion and segmentation and fusion efficiency analysis experiments are conducted on some representative methods mentioned in the paper to comprehensively evaluate the performance of the methods. Finally, this paper provides conclusions and prospects for possible future research directions in the field.

The impact of air pollution on public health is substantial, and accurate long-term predictions of air quality are crucial for early warning systems to address this issue. Air quality prediction has drawn significant attention, bridging environmental science, statistics, and computer science. This paper presents a comprehensive review of the current research status and advances in air quality prediction methods. Deep learning, a novel machine learning approach, has demonstrated remarkable proficiency in identifying complex, nonlinear patterns in air quality data, yet its application in air quality prediction is still relatively nascent. This paper also conducts a systematic analysis and summarizes how cutting-edge deep learning models are applied in air quality prediction. Initially, the historical evolution of air quality prediction methods and datasets is presented. This is followed by an examination of conventional air quality prediction techniques. A thorough comparative analysis of progress made with both traditional and deep learning-based prediction methods is provided. This review particularly focuses on three aspects: temporal modeling, spatiotemporal modeling, and attention mechanisms. Finally, emerging trends in the field of air quality prediction are identified and discussed.

The use of Artificial Intelligence is currently being observed in many areas of life. In addition to assisting in intellectual work, solving complex computational problems, or analyzing various types of data, the aforementioned techniques can also be applied in the process of providing security to people. The paper proposes an emergency identification system based on Artificial Intelligence that aims to provide timely detection and notification of dangerous situations. The proposed solution consider the position of a person "hands up" as an emergency situation that will indicate a potential danger for a person. Because people in the face of potential danger are mostly forced to raise their hands up and this pose attracts attention, emphasizes the emotional reaction to certain events and is usually used as a sign of risk or as a means of subjugation. The system should recognize the pose of a person, detect it, and consequently inform about the threat. In this paper, an AI based emergency identification system was proposed to detect the human pose "hands up" for emergency identification using the PoseNet Machine Learning Model. The assumption consists that the utilization only of 6 key points made allows reducing the computing resources of the system since the conclusion is made taking into account a smaller amount of data. For the study, a dataset of 1510 images was created for training an Artificial Intelligence model, and the decisions were verified. Supervised Machine Learning methods are used to classify the definition of an emergency. Alternative methods: Support Vector Machine, Logistic Regression, Naïve Bayes Classifier, Discriminant Analysis Classifier, and K-nearest Neighbours Classifier based on the accuracy were evaluated. Overall, the paper presents a comprehensive and innovative approach to emergency identification for quick response to them using the proposed system.