Explore the vast range of titles available.

Most of the existing laser welding process monitoring technologies focus on the detection of post-engineering defects, but in the mass production of electronic equipment, such as laser welding metal plates, the real-time identification of defect detection has more important practical significance. The data set of laser welding process is often difficult to build and there is not enough experimental data, which hinder the applications of the data-driven laser welding defect detection method. In this paper, an intelligent welding defect diagnosis method based on auxiliary classifier generative adversarial networks (ACGAN) has been proposed. Firstly, a ten-class dataset consisting of 6467 samples, was constructed, which originate from the optical and thermal sensory parameters in the welding process. A new structured ACGAN network model is proposed to generate fake data similar to the true defect feature distributions. In addition, in order to make the difference between different defects categories more obvious after data expansion, a data filtering and data purification scheme was proposed based on ensemble learning and an SVM (support vector machine), which is used to filter the bad generated data. In the experiments, the classification accuracy can reach 96.83% and 85.13%, for the CNN (convolutional neural network) algorithm model and ACGAN model, respectively. However, the accuracy can further improve to 97.86% and 98.37% for the fusion models of ACGAN-CNN and ACGAN-SVM-CNN models, respectively. The results show that ACGAN can not only be used as an algorithm model for classification, but also be used to achieve superior real-time classification and recognition through data enhancement and multi-model fusion.

In order to address the shortcomings of the traditional bidirectional RRT* algorithm, such as its high degree of randomness, low search efficiency, and the many inflection points in the planned path, we institute improvements in the following directions. Firstly, to address the problem of the high degree of randomness in the process of random tree expansion, the expansion direction of the random tree growing at the starting point is constrained by the improved artificial potential field method; thus, the random tree grows towards the target point. Secondly, the random tree sampling point grown at the target point is biased to the random number sampling point grown at the starting point. Finally, the path planned by the improved bidirectional RRT* algorithm is optimized by extracting key points. Simulation experiments show that compared with the traditional A*, the traditional RRT, and the traditional bidirectional RRT*, the improved bidirectional RRT* algorithm has a shorter path length, higher path-planning efficiency, and fewer inflection points. The optimized path is segmented using the dynamic window method according to the key points. The path planned by the fusion algorithm in a complex environment is smoother and allows for excellent avoidance of temporary obstacles.

In view of the fact that the global planning algorithm cannot avoid unknown dynamic and static obstacles and the local planning algorithm easily falls into local optimization in large-scale environments, an improved path planning algorithm based on the integration of A* and DWA is proposed and applied to driverless ferry vehicles. Aiming at the traditional A* algorithm, the vector angle cosine value is introduced to improve the heuristic function to enhance the search direction; the search neighborhood is expanded and optimized to improve the search efficiency; aiming at the problem that there are many turning points in the A* algorithm, a cubic quasi-uniform B-spline curve is used to smooth the path. At the same time, fuzzy control theory is introduced to improve the traditional DWA so that the weight coefficient of the evaluation function can be dynamically adjusted in different environments, effectively avoiding the problem of a local optimal solution. Through the fusion of the improved DWA and the improved A* algorithm, the key nodes in global planning are used as sub-target punctuation to guide the DWA for local planning, so as to ensure that the ferry vehicle avoids obstacles in real time. Simulation results show that the fusion algorithm can avoid unknown dynamic and static obstacles efficiently and in real time on the basis of obtaining the global optimal path. In different environment maps, the effectiveness and adaptability of the fusion algorithm are verified.

For the RRT* algorithm, there are problems such as greater randomness, longer time consumption, more redundant nodes, and inability to perform local obstacle avoidance when encountering unknown obstacles in the path planning process of autonomous vehicles. And the artificial potential field method (APF) applied to autonomous vehicles is prone to problems such as local optimality, unreachable targets, and inapplicability to global scenarios. A fusion algorithm combining the improved RRT* algorithm and the improved artificial potential field method is proposed. First of all, for the RRT* algorithm, the concept of the artificial potential field and probability sampling optimization strategy are introduced, and the adaptive step size is designed according to the road curvature. The path post-processing of the planned global path is carried out to reduce the redundant nodes of the generated path, enhance the purpose of sampling, solve the problem where oscillation may occur when expanding near the target point, reduce the randomness of RRT* node sampling, and improve the efficiency of path generation. Secondly, for the artificial potential field method, by designing obstacle avoidance constraints, adding a road boundary repulsion potential field, and optimizing the repulsion function and safety ellipse, the problem of unreachable targets can be solved, unnecessary steering in the path can be reduced, and the safety of the planned path can be improved. In the face of U-shaped obstacles, virtual gravity points are generated to solve the local minimum problem and improve the passing performance of the obstacles. Finally, the fusion algorithm, which combines the improved RRT* algorithm and the improved artificial potential field method, is designed. The former first plans the global path, extracts the path node as the temporary target point of the latter, guides the vehicle to drive, and avoids local obstacles through the improved artificial potential field method when encountered with unknown obstacles, and then smooths the path planned by the fusion algorithm, making the path satisfy the vehicle kinematic constraints. The simulation results in the different road scenes show that the method proposed in this paper can quickly plan a smooth path that is more stable, more accurate, and suitable for vehicle driving.

Purpose: the distribution routing plans of multi-depots vehicle scheduling problem will increase exponentially along with the adding of customers. So, it becomes an important studying trend to solve the vehicle scheduling problem with heuristic algorithm. On the basis of building the model of multi-depots vehicle scheduling problem, in order to improve the efficiency of the multiple depots vehicle routing, the paper puts forward a fusion algorithm on multiple depots vehicle routing based on the ant colony algorithm with genetic algorithm. Design/methodology/approach: to achieve this objective, the genetic algorithm optimizes the parameters of the ant colony algorithm. The fusion algorithm on multiple depots vehicle based on the ant colony algorithm with genetic algorithm is proposed. Findings: simulation experiment indicates that the result of the fusion algorithm is more excellent than the other algorithm, and the improved algorithm has better convergence effective and global ability. Research limitations/implications: in this research, there are some assumption that might affect the accuracy of the model such as the pheromone volatile factor, heuristic factor in each period, and the selected multiple depots. These assumptions can be relaxed in future work. Originality/value: In this research, a new method for the multiple depots vehicle routing is proposed. The fusion algorithm eliminate the influence of the selected parameter by optimizing the heuristic factor, evaporation factor, initial pheromone distribute, and have the strong global searching ability. The Ant Colony algorithm imports cross operator and mutation operator for operating the first best solution and the second best solution in every iteration, and reserves the best solution. The cross and mutation operator extend the solution space and improve the convergence effective and the global ability. This research shows that considering both the ant colony and genetic algorithm together can improve the efficiency multiple depots vehicle routing.

Human activity recognition (HAR) is becoming increasingly important, especially with the growing number of elderly people living at home. However, most sensors, such as cameras, do not perform well in low-light environments. To address this issue, we designed a HAR system that combines a camera and a millimeter wave radar, taking advantage of each sensor and a fusion algorithm to distinguish between confusing human activities and to improve accuracy in low-light settings. To extract the spatial and temporal features contained in the multisensor fusion data, we designed an improved CNN-LSTM model. In addition, three data fusion algorithms were studied and investigated. Compared to camera data in low-light environments, the fusion data significantly improved the HAR accuracy by at least 26.68%, 19.87%, and 21.92% under the data level fusion algorithm, feature level fusion algorithm, and decision level fusion algorithm, respectively. Moreover, the data level fusion algorithm also resulted in a reduction of the best misclassification rate to 2%~6%. These findings suggest that the proposed system has the potential to enhance the accuracy of HAR in low-light environments and to decrease human activity misclassification rates.

We present an algorithm for regional snow mapping that combines snow maps derived from Advanced Very High Resolution Radiometer (AVHRR) and Special Sensor Microwave/Imager (SSM/I) data. This merging algorithm combines AVHRR’s moderate spatial resolution with SSM/I’s ability to penetrate clouds and, thus, benefits from the advantages of the two sensors while minimizing their limitations. First, each of the two detection algorithms were upgraded before developing the methodology to merge the snow mapping results obtained using both algorithms. The merging methodology is based on a membership function calculated over a temporal running window of ±4 days from the actual date. The studied algorithms were developed and tested over Eastern Canada for the period from 1988 to 1999. The snow mapping algorithm focused on the spring melt season (1 April to 31 May). The snow maps were validated using snow depth observations from meteorological stations. The overall accuracy of the merging algorithm is about 86%, which is between that of the new versions of the two individual algorithms: AVHRR (90%) and SSM/I (83%). Furthermore, the algorithm was able to locate the end date of the snowmelt season with reasonable accuracy (bias = 0 days; SD = 11 days). Comparison of mapping results with high spatial resolution snow cover from Landsat imagery demonstrates the feasibility of clear-sky snow mapping with relatively good accuracy despite some underestimation of snow extent inherited from the AVHRR algorithm. It was found that the detection limit of the algorithm is 80% snow cover within a 1 × 1 km pixel.

Micro-expressions, which are spontaneous and difficult to suppress, reveal a person’s true emotions. They are characterized by short duration and low intensity, making the task of micro-expression recognition challenging in the field of emotion computing. In recent years, deep learning-based feature extraction and fusion techniques have been widely used for micro-expression recognition, particularly methods based on Vision Transformer that have gained popularity. However, the Vision Transformer-based architecture used in micro-expression recognition involves a significant amount of invalid computation. Additionally, in the traditional two-stream architecture, although separate streams are combined through late fusion, only the output features from the deepest level of the network are utilized for classification, thus limiting the network’s ability to capture subtle details due to the lack of fine-grained information. To address these issues, we propose a new two-level spatio-temporal feature fused with a two-stream architecture. This architecture includes a spatial encoder (modified ResNet) for learning texture features of the face, a temporal encoder (Swin Transformer) for learning facial muscle motor features, a feature fusion algorithm for integrating multi-level spatio-temporal features, a classification head, and a weighted average operator for temporal aggregation. The two-stream architecture has the advantage of extracting richer features compared to the single-stream architecture, leading to improved performance. The shifted window scheme of Swin Transformer restricts self-attention computation to non-overlapping local windows and allows cross-window connections, significantly improving the performance and reducing the computation compared to Vision Transformer. Moreover, the modified ResNet is computationally less intensive. Our proposed feature fusion algorithm leverages the similarity in output feature shapes at each stage of the two streams, enabling the effective fusion of multi-level spatio-temporal features. This algorithm results in an improvement of approximately 4% in both the F1 score and the UAR. Comprehensive evaluations conducted on three widely used spontaneous micro-expression datasets (SMIC-HS, CASME II, and SAMM) consistently demonstrate the superiority of our approach over comparative methods. Notably, our approach achieves a UAR exceeding 0.905 on CASME II, making it one of the few frameworks in the published micro-expression recognition literature to achieve such high performance.

Melanoma is one of the most lethal and rapidly growing cancers, causing many deaths each year. This cancer can be treated effectively if it is detected quickly. For this reason, many algorithms and systems have been developed to support automatic or semiautomatic detection of neoplastic skin lesions based on the analysis of optical images of individual moles. Recently, full-body systems have gained attention because they enable the analysis of the patient’s entire body based on a set of photos. This paper presents a prototype of such a system, focusing mainly on assessing the effectiveness of algorithms developed for the detection and segmentation of lesions. Three detection algorithms (and their fusion) were analyzed, one implementing deep learning methods and two classic approaches, using local brightness distribution and a correlation method. For fusion of algorithms, detection sensitivity = 0.95 and precision = 0.94 were obtained. Moreover, the values of the selected geometric parameters of segmented lesions were calculated and compared for all algorithms. The obtained results showed a high accuracy of the evaluated parameters (error of area estimation <10%), especially for lesions with dimensions greater than 3 mm, which are the most suspected of being neoplastic lesions.

To solve the problems that the existing mobile robots cannot complete autonomous learning in the path planning, as well as the slow convergence of path planning and poor smoothness of planned paths, the neural networks are utilized to perceive the environment and perform feature extraction to achieve the fitness of environment to state action function. Through the mapping of the current state to the action through Hierarchical Reinforcement Learning (HRL), the mobile needs of mobile robots are met, a path planning model for mobile robots based on neural networks and HRL is finally constructed. The proposed algorithm is compared with different algorithms in path planning and underwent performance evaluation to obtain the optimal learning algorithm system. Finally, the optimal algorithm system is tested in different environments and scenarios to obtain the optimal learning conditions, thereby verifying the effectiveness of the proposed algorithm. The experimental results show that the Actor-Critic (A3C) algorithm based on reinforcement learning is more effective than the traditional Q-Learning algorithm. After using the neural network algorithm, the path planning ability of robots is significantly improved. Compared with the Double Deep Q-Learning (DDQN) algorithm, under the Actor-Critic Deep Q-Learning (DDPG) algorithm based on neural network and HRL, the path planning time is increased by 22.48%, the number of path steps is increased by 8.69%, the convergence time is increased by 55.52%, and the cumulative rewards are increased significantly. When the action set is 4, the number of grids is 3, and the state set is 40*40*8, with the introduction of the force value, the algorithm can reduce the convergence time by 91% compared with the traditional Q-learning algorithm, and the smoothness of the path is increased by 79%. The algorithm has good generalization effect in different scenarios. The above results have important theoretical value and guiding significance for the research on the precise positioning and path planning of mobile robots.