Visual Localisation Using Deep Learning and Graph Neural Networks: Approaches and Evaluation

GROM: A generalized routing optimization method with graph neural network and deep reinforcement learning

The center of human activity and a key point of contact for social interaction between city people and the built environment is the street. With more street-level photos becoming available, urban landscape studies have more chances to examine and evaluate streetscapes closely and from various angles. This manuscript present the graph neural networks (GNN) optimized with gazelle optimization algorithm (GOA) for urban plants cape design based on large-scale street view (UPLS-GNN-GOA). Initially data is taken from ADE20K dataset. Afterward the data is fed to General Robust Subband Adaptive Filtering (GRSAF) based pre-processing process. The pre-processing output is given to Discrete Fractional Fourier Transforms (DFrFT) to extract the street greenery and openness of street canyons. After that, the extracted features are fed to Graph Neural Networks (GNN) to classify the public health, urban microclimate, human perception. The weight parameters of the GNN are optimized using Gazelle Optimization Algorithm (GOA).The UPLS-GNN-GOA method is implemented in Python, and its efficiency is determined using a series of performance evaluation metrics analysis, including accuracy, precision, recall, f1-score, and sensitivity. The proposed UPLS-GNN-GOA method shows the highest accuracy of 98%, precision of 98%, and F1-score of 97% while comparing other existing methods such as urban plantscape design based on convolutional neural network (UPLS-CNN), urban plantscape design based on deep convolutional neural network (UPLS-DCNN) and urban plantscape design based on deep learning and convolutional neural network (UPLS-DL-CNN) respectively.

To construct the risk prediction model of acute exacerbation of chronic obstructive pulmonary disease (AECOPD) and verify its effectiveness based on deep learning and back propagation algorithm neural network (BP neural network). Based on the relevant data of 1 326 patients with chronic obstructive pulmonary disease (COPD) in the team's previous clinical study, the acute exacerbation, and its risk factors during the stable period and 6 months of follow-up were recorded and analyzed. Combined with previous clinical research data and expert questionnaire results, the independent risk factors of AECOPD after screening and optimization by multivariate Logistic regression including gender, body mass index (BMI) classification, number of acute exacerbation, duration of acute exacerbation and forced expiratory volume in one second (FEV1) were used to build the BP neural network by Python 3.6 programming language and Tensorflow 1.12 deep learning framework. The patients were randomly selected according to the ratio of 4:1 to generate the training group and the test group, of which, the training group had 1 061 sample data while the test group had 265 pieces of sample data. The training group was used to establish the prediction model of neural network, and the test group was used for back-substitution test. When using the training group data to construct the neural network model, the training group was randomly divided into training set and verification set according to the ratio of 4:1. There were 849 training samples in the training set and 212 verification samples in the verification set. The optimal model was screened by adjusting the parameters of the neural network and combining the area under the receiver operator characteristic curve (AUC), and the sample data of the test group was substituted into the model for verification. The independent risk factors including gender, BMI classification, number of acute exacerbation, duration of acute exacerbation and FEV1 were collected from the team's previous clinical research, and the AECOPD risk prediction model was constructed based on deep learning and BP neural network. After 10 000 training sessions, the accuracy of the AECOPD risk prediction model in the validation set of the training group was 83.09%. When the number of training times reached 8 000, the accuracy basically tended to be stable and the prediction ability reached the upper limit. The AECOPD risk prediction model trained for 10 000 times was used to predict the risk of the validation set data, and the receiver operator characteristic curve (ROC curve) analysis showed that the AUC was 0.803. When using this model to predict the risk of the data of the test group, the accuracy rate was 81.69%. The risk prediction model based on deep learning and BP neural network has a medium level of prediction efficiency for acute exacerbation within 6 months in COPD patients, which can evaluate the risk of AECOPD and assist the clinic in making accurate treatment decisions.

Accurate prediction of small interfering RNA (siRNA) silencing efficiency is critical for accelerating nucleic acid drug development. Over the past two decades, the field has transitioned from empirical sequence-derived heuristics to data-driven methods such as deep learning and graph neural networks. In this review, we systematically discuss current research from three integrated perspectives: data resources, design rules, and computational algorithms. Firstly, we summarize strengths, biases, and gaps in existing datasets, including low-throughput saturation scanning data, high-throughput panels, and specialized repositories for chemically modified siRNAs. Next, we outline the evolution of siRNA design principles, from classical guidelines such as GC content windows, terminal thermodynamic asymmetry, and positional base preferences, to more sophisticated thermodynamic-structural features incorporating target mRNA accessibility, and finally, to advanced clinical GalNAc-siRNA strategies involving seed destabilization and stereochemically purified backbones. Regarding computational algorithms, the progression is categorized into three stages: early linear regression models, traditional machine learning approaches, and modern deep learning frameworks, alongside various specialized algorithms tailored for chemically modified siRNAs. Current studies demonstrate steadily improving prediction accuracy, yet significant challenges persist, including insufficient data coverage for disease-relevant targets and hard-to-transfect cells, limited paired measurements of bare versus modified sequences, and inadequate integration of off-target effects and immunogenicity metrics. Moving forward, there is an urgent need to establish highquality, dose- and time-resolved datasets across diverse tissues, embed biophysical priors into interpretable deep-learning architectures, and adopt multi-task modeling approaches to optimize efficiency, safety, and delivery simultaneously. Collectively, these advancements promise to propel siRNA design beyond liver-centric applications towards precision therapeutics targeting multiple tissues and diseases.

This paper presents a hybrid approach for estimating the admittance matrix of open-loop distribution networks by integrating Total Least Squares (TLS) regression with deep learning (DL) and graph neural networks (GNNs). The proposed model refines initial TLS estimates by leveraging deep learning to handle nonlinearities and graph neural networks to incorporate network topology, thereby addressing the challenges posed by noisy and incomplete data. Physical constraints-including Kirchhoff's current and voltage laws-are embedded within the optimization process to ensure that the estimated admittance matrix remains physically consistent. Extensive testing on the IEEE 33-bus and 123-bus systems demonstrates significant improvements in estimation accuracy, convergence speed, and adherence to physical principles, underscoring the model's potential for real-world applications in modern power system analysis and operation.

Autonomous driving and artificial intelligence are the most popular research projects in the field of technology today. As the high technology, autonomous driving relies on perception, decision-making, and control systems, and the performance of these systems largely depends on the application of artificial intelligence nowadays. Fortunately, there are plenty of applications of artificial intelligence in several aspects of autonomous driving. This paper aims to introduce the relationship between autonomous driving and artificial intelligence by reviewing several literatures and analyzing the applications of deep learning (DL), reinforcement learning (RL), and graph neural networks (GNN) in autonomous driving.

The main purpose of the various methods of evaluating athlete feature recognition is to monitor the current health of the athletes, thereby providing some feedback on the quality of individual training. Based on deep learning and convolutional neural networks, this paper studies athlete target recognition and proposes a feature vector extraction method based on curvature zero point. Moreover, based on the ideas of deep learning and convolutional neural networks, this paper builds an athlete feature recognition model and optimizes the algorithm. In order to verify the feasibility and efficiency of feature extraction algorithm of the sport athletes proposed by this paper and to facilitate comparison with other algorithms, this paper conducts an algorithm performance test on the sport athlete database. The research results show that the method proposed in this paper has certain advantages in the feature extraction of athletes and can be used in subsequent sports training systems.

This study presents an advanced artificial intelligence (AI) driven framework to model thermo-magnetic nanofluid convection within a wavy-top trapezoidal cavity containing internal obstacles of varying geometries. The study aims to develop an AI-enhanced model to analyze and optimize thermo-magnetic convection of nanofluids in a wavy-top trapezoidal cavity, focusing on the effects of magnetic field, nanoparticle concentration, and cavity geometry on heat transfer performance. The system is influenced by an external magnetic field, varying Rayleigh numbers (Ra), Hartmann numbers (Ha), nanoparticle volume fractions (ϕ), and obstacle shapes (square, star, triangle). Finite Element Method (FEM) simulations were conducted to generate high-fidelity datasets, capturing the variations in Nusselt number (Nu), entropy generation (ST), and effective coefficient of performance (ECOP). These outputs were then predicted using three AI models: Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). Among the models, RF consistently demonstrated superior performance across all parameters. For Nu prediction, RF achieved a Mean Absolute Error (MAE) of 0.0193, Mean Squared Error (MSE) of 0.00069, and R² of 0.9989, outperforming SVR (MAE = 0.0247) and XGBoost (MAE = 0.0215). In entropy generation prediction, RF attained an MAE of 4.48×10⁻⁶, MSE of 4.35×10⁻¹¹, and R² of 0.9992. For ECOP, RF recorded an MAE of 15.201, MSE of 386.65, and R² of 0.9986, while SVR showed a higher error margin (MAE = 21.132). The strong alignment of AI-predicted values with FEM results confirms the reliability and generalizability of the models. This research highlights the feasibility of using machine learning as a computationally efficient surrogate to solve complex multiphysics problems in thermal engineering, offering a promising tool for real-time prediction and design optimization of advanced heat transfer systems. For future work, this research can be extended by exploring hybrid or non-Newtonian nanofluids, introducing transient and time-dependent thermal analyses, and applying more advanced AI techniques, such as deep learning or physics-informed neural networks.

Chapter 2 - Machine learning for solid mechanics

Clustering is a fundamental and hot issue in the unsupervised learning area. With the rapid development of deep learning and graph neural networks (GNNs) techniques, researchers have proposed a series of effective clustering methods. However, most existing approaches adopt a conventional graph to aggregate the neighborhood information, where only the pairwise relations are considered. Moreover, the redundancy/noise in the raw data samples may result in less accurate sample relations and inferior clustering results. In this paper, we proposed a new GNNs based clustering method, which adopts the hypergraph learning approach to explore the high-order relationship for accurate relation learning. Specifically, we first construct two hypergraph representations based on the topology feature and attribute feature from data samples. Then, a self-supervised structure is integrated to learn a cross-correlation matrix from the original hypergraph to act as a higher-order neighborhood with reduced redundancy and noise. Finally the embedding representation of the clustering space is learned in the graph convolution. The proposed method has been evaluated on six public datasets for clustering tasks. Experimental results show that our proposed method outperforms the state-of-the-art ones.

The study intends to increase the marketing quantity of various commodities and promote the comprehensive development of the market. The study first discusses the principle and current situation of the emerging Immersive Marketing. Then, it analyzes the Deep Learning (DL) Neural Network (NN) model. Finally, a Personalized Recommendation System (PRS) is designed based on the Immersive Marketing environment using the Graph Neural Network (GNN) model. The proposed PRS based on the Immersive Graph Neural Network (IGNN) model has reflected higher advantages over other recommendation systems. The experiment results suggest that Immersive Marketing can fully reflect commodities’ essential attributes and characteristics, improve users’ shopping experience, and promote sales. Meanwhile, the IGNN-based PRS reported here gives users an elevated and immersive shopping experience and entertainment process. Lastly, the model comparison finds that the proposed IGNN outperforms other models. The optimal model parameters are verified as P@20 and R@20 to gain the highest composite index values. In particular, parameter R@20 gives the model a better performance over P@20. The study provides technical references for improving the marketing process of various commodities and entertainment products and contributes to marketing technology development.

The cross-fusion research of artificial intelligence technology and spinal surgery represented by machine learning and neural network model is a new research direction and hot issue in the field of artificial intelligence in recent years. The anatomy and disease symptoms of the spine are complex, and the diagnosis and treatment of spinal surgery require rich clinical experience. However, the distribution of medical resources in China is seriously uneven. How to improve the ability of primary medical services so that the most extensive patient groups can benefitis still an urgent problem to be solved. Artificial intelligence is a technical science that researches and develops theories, methods, technologies, and application systems for simulating, extending and expanding human intelligence. With the advent of the era of big data medical technology, artificial intelligence technology may solve this problem by transforming experts sinking into tech sinking . At present, technologies such as confrontation learning, weakly supervised learning, intensive learning and graph neural networks have become research hotspots in the field of artificial intelligence, and have also played an important role in many fields of clinical medicine. Based on the advantages of deep learning and neural network in disease learning, many spine surgeons combine it with the diagnosis and treatment of cervical spondylosis, low back pain, lumbar degenerative diseases, spinal deformity, spinal tumors, and other spine-related diseases. The rapid location and accurate diagnosis of the disease not only makes it an effective tool for the comprehensive diagnosis of spinal diseases but also provides the basis for the most reasonable treatment options for spinal diseases. In the domestic application of artificial intelligence in the diagnosis and treatment of spinal surgery, it can also solve the problems of difficult diagnosis and complicated treatment of spinal diseases faced by primary doctors, reduce the rate of misdiagnosis and missed diagnosis, and effectively reduce the economic and social burden of spinal diseases. This paper reviews the research progress of artificial intelligence represented by deep learning in the field of diagnosis and treatment of spinal surgery at home and abroad, and the advantages and application prospects of artificial intelligence in the diagnosis and treatment of spinal surgery.

End-to-end keyword search system based on attention mechanism and energy scorer for low resource languages

Artificial Intelligence (AI) and its tools are being widely used worldwide. In the area of agriculture, AI is being widely studied and expanding. The use of AI in agriculture is being widely studied and expanding from pre-harvest to post-harvest. The increase in world population has triggered the need to increase food production. This need has triggered a search for solutions that promote increased food production and quality. One way to increase food production and quality is pest control. AI and its tools have proven to be a growing and rising solution in controlling and combating pests. This research focuses on reviewing and demonstrating the advances in combating and controlling pests using AI tools and images. It stands out: the classification of pests; insect identification; use and capture of Unmanned aerial vehicle (UAV) footage; using Deep Learning (DL) and Convolutional Neural Network (CNN). A search engine was applied to 5 databases. Cutting criteria were applied in 3 stages, and there were 71 papers at the end. The 71 went through 3 quality assessment questions, leaving 47 works for final analysis. This study demonstrated that the DL and the CNN tool using real images have the potential for insect control and combat solutions. Another tool in recent studies associated with CNN is the attention mechanism, improving pest identification results. Identification of insects through leaf images using CNN requires.

Sleep staging is the basis of sleep evaluation and a key step in the diagnosis of sleep-related diseases. Despite being useful, the existing sleep staging methods have several disadvantages, such as relying on artificial feature extraction, failing to recognize temporal sequence patterns in the long-term associated data, and reaching the accuracy upper limit of sleep staging. Hence, this paper proposes an automatic Electroencephalogram (EEG) sleep signal staging model, which based on Multi-scale Attention Residual Nets (MAResnet) and Bidirectional Gated Recurrent Unit (BiGRU). The proposed model is based on the residual neural network in deep learning. Compared with the traditional residual learning module, the proposed model additionally uses the improved channel and spatial feature attention units and convolution kernels of different sizes in parallel at the same position. Thus, multiscale feature extraction of the EEG sleep signals and residual learning of the neural networks is performed to avoid network degradation. Finally, BiGRU is used to determine the dependence between the sleep stages and to realize the automatic learning of sleep data staging features and sleep cycle extraction. According to the experiment, the classification accuracy and kappa coefficient of the proposed method on sleep-EDF data set are 84.24% and 0.78, which are respectively 0.24% and 0.21 higher than the traditional residual net. At the same time, this paper also verified the proposed method on UCD and SHHS data sets, and the figure of classification accuracy is 79.34% and 81.6%, respectively. Compared to related existing studies, the recognition accuracy is significantly improved, which validates the effectiveness and generalization performance of the proposed method.