A thorough analysis and cross-comparison of recent relevant works was provided, outlining a closed-loop process for EEG data analysis based on deep learning. EEG data were introduced, and the application of deep learning in three key stages: preprocessing, feature extraction, and model generalization was unfolded. The research ideas and solutions provided by deep learning algorithms in the respective stages were delineated, including the challenges and issues encountered at each stage. The main contributions and limitations of different algorithms were comprehensively summarized. The challenges faced and future directions of deep learning technology in handling EEG data at each stage were discussed.

The research progress of direct air capture CO₂ adsorbents was reviewed. The advantages and disadvantages of alkali/alkaline metal based adsorbents, metal organic framework adsorbents, amine loaded adsorbents and moisture swing adsorbents were compared. Meanwhile, the properties of adsorbents from the aspects of adsorption capacity and amine efficiency, kinetics and supporters, regeneration mode and energy consumption, thermal stability and resistance to degradation were evaluated. Additionally, the related engineering demonstration projects and economic evaluation were briefly discussed. Finally, the problems existing in the current research were summarized, and the future research direction was prospected.

A multi-agent reinforcement learning algorithm based on priority experience replay and decomposed reward function was proposed in multi-agent pursuit and evasion games. Firstly, multi-agent twin delayed deep deterministic policygradient algorithm (MATD3) algorithm based on multi-agent deep deterministic policy gradient algorithm (MADDPG) and twin delayed deep deterministic policy gradient algorithm (TD3) was proposed. Secondly, the priority experience replay was proposed to determine the priority of experience and sample the experience with high reward, aiming at the problem that the reward function is almost sparse in the multi-agent pursuit and evasion problem. In addition, a decomposed reward function was designed to divide multi-agent rewards into individual rewards and joint rewards to maximize the global and local rewards. Finally, a simulation experiment was designed based on DEPER-MATD3. Comparison with other algorithms showed that DEPER-MATD3 algorithm solved the over-estimation problem, and the time consumption was improved compared with MATD3 algorithm. In the decomposed reward function environment, the global mean rewards of the pursuers were improved, and the pursuers had a greater probability of chasing the evader.

An improved method for the blockchain Kademlia network based on small world theory was proposed aiming at the issue of sacrificing security to improve scalability in the current research of the blockchain Kademlia network. The idea of the small world theory was followed, and a probability formula for replacing expansion nodes was proposed. The probability was inversely proportional to the distance between nodes. The number of node replacements and additional nodes could be flexibly adjusted according to actual conditions. The theoretical analysis and experimental verification demonstrate that the network transformed by this method can reach a stable state. The experimental results showed that the transmission hierarchy required for broadcasting transaction messages throughout the network was reduced by 15.0% to 30.8% and the rate of locating nodes was increased. The level of network structure was reduced and network security was enhanced compared to other optimization algorithms that modify the network structure.

Ensuring that the flue gas in the furnace stays within the temperature range of no less than 850 ℃ for at least 2 s contributes to the steady municipal solid waste (MSW) incineration, and the reduction of secondary pollution. However, at present, it is difficult to quantitatively calculate and predict the residence time of flue gas in the high temperature area by only using the thermocouple for qualitative evaluation. Based on the thermodynamic calculation, correlation analysis of practical operation parameters, and a variety of machine learning algorithms (backpropagation neural network, recurrent neural network, and random forest regression), the residence time of flue gas in high-temperature areas (>850 ℃) was calculated, correlation analysis of key operation parameters was conducted, and the prediction model of residence time was constructed, aiming at a typical MSW circulating fluidized bed boiler in China. Results revealed that 10 key operating parameters, e.g. section temperature of the furnace, temperature and pressure of primary air and secondary air, etc., had a strong correlation and predictability with the high-temperature flue gas residence time. Moreover, the model of the recurrent neural network was relatively optimal, with a higher fitting degree and accuracy. Specifically, the mean square error (MSE) was 0.11626, and the average absolute error between the predicted value and real value was 1.174%. Research enabled the prediction of flue gas temperature variation in high-temperature areas, helped optimize the MSW incineration, and contributed to the advanced control of pollutant emission reduction.

Physical information was divided into rule information and numerical information, in order to explore the role of physical information in training neural network when solving differential equations with physics-informed neural network (PINN). The logic of PINN for solving differential equations was explained, as well as the data-driven approach of physical information and neural network interpretability. Synthetic loss function of neural network was designed based on the two types of information, and the training balance degree was established from the aspects of training sampling and training intensity. The experiment of solving the Burgers-Fisher equation by PINN showed that PINN can obtain good solution accuracy and stability. In the training of neural networks for solving the equation, numerical information of the Burgers-Fisher equation can better promote neural network to approximate the equation solution than rule information. The training effect of neural network was improved with the increase of training sampling, training epoch, and the balance between the two types of information. In addition, the solving accuracy of the equation was improved with the increasing of the scale of neural network, but the training time of each epoch was also increased. In a fixed training time, it is not true that the larger scale of the neural network, the better the effect.

A surface water quality prediction model based on graph neural network (GNN) was proposed to solve the problem that water quality data has complex dependencies in both temporal and spatial dimensions. GNN was utilized to model the complex spatial dependencies of monitoring stations, and long short-term memory (LSTM) was used to model the complex temporal dependencies of historical water quality sequences. Then the encoded vector was input into the decoder to get the water quality prediction output. The experimental results show that the model can achieve 23.3%, 26.6% and 14.8% performance improvements compared with time series analysis methods, general regression methods and existing deep learning methods.

A method for creating binocular dataset and a 6D pose estimation network called Binocular-RNN were proposed, in response to the problem of low accuracy in the current task of 6D pose estimation for objects. The existing images in the YCB-Video Dataset were used as the content captured by the left camera of the binocular system. The corresponding 3D object models in the YCB-Video Dataset were imported using Open GL, and the parameters related to each object were input to generate synthetic images captured by the virtual right camera of the binocular system. A monocular prediction network was utilized in the Binocular-RNN to extract geometric features from the left and right images in the binocular dataset, and recurrent neural network was used to fuse these geometric features and predict the 6D pose of the objects. The evaluation of Binocular-RNN and other pose estimation methods was based on the average distance of model points (ADD), average nearest point distance (ADDS), translation error and angle error. The results show that when the network was trained on a single object, the ADD or ADDS score of Binocular-RNN was 2.66 times that of PoseCNN and 1.15 times that of GDR-Net. Furthermore, the Binocular-RNN trained by the physics-based real-time rendering (Real+PBR) outperformed the DeepIM method based on deep neural network iterative 6D pose matching.

The researches on data security management and privacy protection technologies at home and abroad were analyzed and summarized aiming at current problems in blockchain security, such as unreasonable data management mode, unreliable data sharing scheme, smart contract vulnerabilities not easily fixed and incomplete privacy protection of multiple types of data. Various security problems and reasonable solutions in current blockchain systems were outlined from four aspects: data storage security, data privacy security, data access security and data sharing security. The challenges and future research directions of data security in blockchain were discussed. Some reference for the future work of researchers was provided in the field of blockchain security.

A comprehensive evaluation and categorization of text-to-image generation tasks were conducted. Text-to-image generation tasks were classified into three major categories based on the principles of image generation: text-to-image generation based on the generative adversarial network architecture, text-to-image generation based on the autoregressive model architecture, and text-to-image generation based on the diffusion model architecture. Improvements in different aspects were categorized into six subcategories for text-to-image generation methods based on the generative adversarial network architecture: adoption of multi-level hierarchical architectures, application of attention mechanisms, utilization of siamese networks, incorporation of cycle-consistency methods, deep fusion of text features, and enhancement of unconditional models. The general evaluation indicators and datasets of existing text-to-image methods were summarized and discussed through the analysis of different methods.

For the poor real-time detection capability of the current object detection model in the production environment of electronic components, GhostNet was used to replace the backbone network of YOLOv5. And for the existence of small objects and objects with large scale changes on the surface defects of electronic components, a coordinate attention module was added to the YOLOv5 backbone network, which enhanced the sensory field while avoiding the consumption of large computational resources. The coordinate information was embedded into the channel attention to improve the object localization of the model. The feature pyramid networks (FPN) structure in the YOLOv5 feature fusion module was replaced with a weighted bi-directional feature pyramid network structure, to enhance the fusion capability of multi-scale weighted features. Experimental results on the self-made defective electronic component dataset showed that the improved GCB-YOLOv5 model achieved an average accuracy of 93% and an average detection time of 33.2 ms, which improved the average accuracy by 15.0% and the average time by 7 ms compared with the original YOLOv5 model. And the improved model can meet the requirements of both accuracy and speed of electronic component surface defect detection.

A dynamic multi-objective optimization algorithm based on individual prediction (IPS) was proposed to quickly track the Pareto optimal front of the dynamic multi-objective optimization problem that changed with the environment. Firstly, the special points with good convergence and diversity were selected by the reference point relation algorithm, and the environment changes can be quickly responded to by predicting the special points set. Secondly, a feedback correction mechanism for population center point predication was proposed, and in the process of predicting the non-dominant solution set, the prediction step size was corrected to make the prediction more accurate. Finally, to avoid the algorithm falling into local optimal, a hybrid diversity maintenance mechanism was proposed, which introduced random individuals generated by Latin hypercube sampling and a precision controllable mutation strategy to improve the diversity of the population. The proposed algorithm was compared with the other four dynamic multi-objective optimization algorithms. Experimental results show that IPS can balance the diversity and convergence of the population, and the experimental results are better than that of the other four algorithms on the FDA, DMOP, and F5~F10 test suite.

A front multi-vehicle target tracking algorithm optimized by DeepSort was proposed in order to improve the awareness of autonomous vehicles to the surrounding environment. Gaussian YOLO v3 model was adopted as the front-end target detector, and training was based on DarkNet-53 backbone network. Gaussian YOLO v3-Vehicle, a detector specially designed for vehicles was obtained, which improved the vehicle detection accuracy by 3%. The augmented VeRi data set was proposed to conduct the re-recognition pre-training in order to overcome the shortcomings that the traditional pre-training model doesn't target vehicles. A new loss function combining the central loss function and the cross entropy loss function was proposed, which can make the target features extracted by the network become better in-class aggregation and inter-class resolution. Actual road videos in different environments were collected in the test part, and CLEAR MOT evaluation index was used for performance evaluation. Results showed a 1% increase in tracking accuracy and a 4% reduction in identity switching times compared with the benchmark DeepSort YOLO v3.

A video object detection algorithm which was built upon the YOLOX-S single-stage detector based on mixed weighted reference-frame sampler and multi-level feature aggregation attention was proposed aiming at the problems of existing deep learning-based video object detection algorithms failing to simultaneously meet accuracy and efficiency requirements. Mixed weighted reference-frame sampler (MWRS) included weighted random sampling and local consecutive sampling to fully utilize effective global information and inter-frame local information. Multi-level feature aggregation attention (MFAA) module refined the classification features extracted by YOLOX-S based on self-attention mechanism, encouraging the network to learn richer feature information from multi-level features. The experimental results demonstrated that the proposed algorithm achieved an average precision AP50 of 77.8% on the ImageNet VID dataset with an average detection speed of 11.5 milliseconds per frame. The object classification and location performance are significantly better than that of YOLOX-S, indicating that the proposed algorithm achieves higher accuracy and faster detection speed.

There has been a trend of intelligent development using artificial intelligence technology in order to improve the efficiency of software development. It is important to understand program semantics to support intelligent development. A series of research work on program representation learning has emerged to solve the problem. Program representation learning can automatically learn useful features from programs and represent the features as low-dimensional dense vectors in order to efficiently extract program semantic and apply it to corresponding downstream tasks. A comprehensive review to categorize and analyze existing research work of program representation learning was provided. The mainstream models for program representation learning were introduced, including the frameworks based on graph structure and token sequence. Then the applications of program representation learning technology in defect detection, defect localization, code completion and other tasks were described. The common toolsets and benchmarks for program representation learning were summarized. The challenges for program representation learning in the future were analyzed.

A feature fusion emotion recognition method based on modality attention multi-path convolutional neural network was proposed, extracting the connection between the signals of each channel from the electroencephalogram (EEG) and functional near infrared spectroscopy (fNIRS) data induced by emotional video to improve the accuracy of emotion recognition. The EEG and fNIRS data were constructed as graph structure data, and the feature of each mode signal was extracted by multi-path graph convolution. The information of connection between different modal channels was fused by modality attention graph convolution. The modality attention mechanism can give different weights to different modal nodes, thus the graph convolution layer can more fully extract the connection relationship between different modal nodes. Experimental tests were carried out on four types of emotional data collected from 30 subjects. Compared with the results of EEG only and fNIRS only, the recognition accuracy of the proposed graph convolution fusion method was higher, which increased by 8.06% and 22.90% respectively. Compared with the current commonly used EEG and fNIRS fusion method, the average recognition accuracy of the proposed graph convolution fusion method was improved by 2.76%~7.36%. The recognition rate of graph convolution fusion method increased by 1.68% after adding modality attention.

For selective laser melting (SLM) forming of Ti6Al4V, a three-dimensional (3D) mesoscopic model of random distribution of powder particles was established based on the discrete element method (DEM). The volume of fluid method (VOF) was used to track the 3D dynamic free surface in SLM forming process. Various factors were considered in the numerical model, such as the TC4 powder bed with randomly distributed particles, the thermophysical parameters changing nonlinearly with temperature, the free surface evolution of the molten pool, the surface tension caused by temperature gradients, and the evaporation effect. The heat transfer, melting, flow and solidification in the interaction between laser and powder particles were studied according to the numerical simulation. Results show that the Marangoni convection induced by temperature gradient and surface tension gradient is the main factor affecting the heat and mass transfer within the melt pool and the 3D morphology of the melt pool. The line energy density (LED) is positively correlated with the Marangoni effect. The quality of single track surface was good when the optimized LED ranged from 92.9 J/m to 183.0 J/m. The three-dimensional size and the morphology of the molten pool and the molten track were observed and analyzed by the single track forming experiment, by which the numerical results were validated.

A multimodal image retrieval model based on semantic-enhanced feature fusion (SEFM) was proposed to establish the correlation between text features and image features in multimodal image retrieval tasks. Semantic enhancement was conducted on the combined features during feature fusion by two proposed modules including the text semantic enhancement module and the image semantic enhancement module. Firstly, to enhance the text semantics, a multimodal dual attention mechanism was established in the text semantic enhancement module, which associated the multimodal correlation between text and image. Secondly, to enhance the image semantics, the retain intensity and update intensity were introduced in the image semantic enhancement module, which controlled the retaining and updating degrees of the query image features in combined features. Based on the above two modules, the combined features can be optimized, and be closer to the target image features. In the experiment part, the SEFM model was evaluated on MIT-States and Fashion IQ datasets, and experimental results show that the proposed model performs better than the existing works on recall and precision metrics.

The process architecture, software and hardware systems, core algorithms, and the validation of the autonomous docking guidance system for a modular flying vehicle were investigated. The remote, medium range, and short range multi segment fusion guidance was adopted based on the transition of guidance methods. The point density clustering algorithm and the kernel correlation filter algorithm were used to provide smooth fusion information in response to the false detections and missed detections in the actual use of YOLOv4-tiny. A correction factor method was proposed to achieve fusion correction of AprilTag measurement data in the short range guidance stage, and the pose compensation algorithm was used to solve the camera pose problem of fixed connection between the camera and the drone. The dark light image enhancement algorithm was introduced and combined with the visual guidance algorithm to meet the docking requirements in low-light environment. A simulation platform and an engineering application platform were built, and the process, the system architecture and the algorithms were verified step by step. Experimental results showed that the engineering application flight platform could safely, stably and accurately guide the landing into a conical docking mechanism with an allowable error of only 6 cm and an angle error of 5°. The results prove that the developed autonomous docking technology has good accuracy and reliability.

A news recommendation method based on Transformer and knowledge graph was proposed to increase the auxiliary information and improve the prediction accuracy. The self-attention mechanism was used to obtain the connection between news words and news entities in order to combine news semantic information and entity information. The additive attention mechanism was employed to capture the influence of words and entities on news representation. Transformer was introduced to pick up the correlation information between clicked news of user and capture the change of user interest over time by considering the time-series characteristics of user preference for news. High-order structural information in knowledge graphs was used to fuse adjacent entities of the candidate news and enhance the integrity of the information contained in the candidate news embedding vector. The comparison experiments with five typical recommendation methods on two versions of the MIND news dataset show that the introduction of attention mechanism, Transformer and knowledge graph can improve the performance of the algorithm on news recommendation.