ALBERT

Description: In cloud data centers, different virtual machine placement strategies will affect the resource utilization efficiency of the whole system. How to improve the overall resource utilization of the system by adjusting the virtual machine placement strategy under limited resources is the focus of current researchers. In this paper, a new virtual machine placement strategy is proposed, which is based on the comprehensive constraints of various system resources. In the process of solving the problem, a multi-objective ant colony optimization algorithm is used. Simulation results show that this method can effectively reduce the number of physical machines activated in the data center, and the accuracy is high.

Description: The application of video and image segmentation is carried out from the aspects of improving the accuracy of segmentation and reducing the calculation time, but the segmentation result is affected by the initial curve position, so this paper proposes a new method. As an important part of the Internet, pictures are usually used to help visitors understand. The image contains a lot of deep-level video information, which is an important basis for video content retrieval and data analysis. In this paper, combining the texture and edge features of the image in the process of text location, a multi-scale Gabor filter bank is proposed to transform the original image, and a priori knowledge of the text region is used to process the non-text object in the transform result. In the part of extracting text from pictures, and improved TF-IDF algorithm, BC-TF-IDF algorithm, is proposed to extract text from pictures. To ensure the integrity of the extracted image, the Sobel algorithm is used to process the image in the edge extraction step. Finally, the above method is applied to the Weibo network, and a system of collecting and recognizing the character content of the Weibo image is set up, which completes the function of collecting and gradually recognizing the Weibo image, and verifies the proposed localization method.

Description: The problems caused by network dimension disasters and computational complexity have become an important issue to be solved in the field of social network research. The existing methods for network feature learning are mostly based on static and small-scale assumptions, and there is no modified learning for the unique attributes of social networks. Therefore, existing learning methods cannot adapt to the dynamic and large-scale of current social networks. Even super large scale and other features. This paper mainly studies the feature representation learning of large-scale dynamic social network structure. In this paper, the positive and negative damping sampling of network nodes in different classes is carried out, and the dynamic feature learning method for newly added nodes is constructed, which makes the model feasible for the extraction of structural features of large-scale social networks in the process of dynamic change. The obtained node feature representation has better dynamic robustness. By selecting the real datasets of three large-scale dynamic social networks and the experiments of dynamic link prediction in social networks, it is found that DNPS has achieved a large performance improvement over the benchmark model in terms of prediction accuracy and time efficiency. When the α value is around 0.7, the model effect is optimal.

Description: This special issue of the Journal of Intelligent & Fuzzy Systems contains selected articles of computational human performance modelling for human-in-the-loop machine systems.

Description: The main reason that currently hinders the commercialization of electric vehicles is a bottleneck in battery, motor and electronic control technology, however, an In-depth study of electronic control technology is one of the most effective means to break through this bottleneck at present. The purpose of this paper is to solve the problem that the pure electric vehicle is difficult to meet the driver’s acceleration intention in the urban road cycle acceleration work condition and the brake energy recovery process does not consider the battery state of charge during the deceleration work condition. Proposed a control strategy that can meet the requirements of road cycle conditions and driver’s driving intentions and take account of the vehicle operating status. Use a fuzzy control algorithm to develop a fuzzy controller that taking the motor demand speed change rate and battery state of charge as input, the motor demand torque compensation coefficient as output. The experimental results show that the modified control strategy can improve the actual output power, the actual output torque of the motor and actual driving force of the wheel under the premise of maintaining economy; it also improved the acceleration performance and climbing performance of pure electric vehicles, and can recycle braking energy efficiently. The experimental results show that the secondary development control strategy can meet the requirements of the cycle work condition CYC_ECE_EUDC for the speed and driving force and the driver’s driving intention under the premise of not sacrificing economics.

Description: Hyperspectral remote sensing combines spectrum, ground space and images organically to provide humans with unprecedented rich information. However, a prominent problem faced in the extraction and identification of hyperspectral remote sensing information is mixed pixels, and the method to solve mixed pixels is mixed pixel decomposition. The purpose of this paper is to study the swarm intelligence algorithm of spatial-spectral feature extraction and mixed pixel decomposition of hyperspectral remote sensing images. This paper first introduces two different methods for extracting spatial spectrum features, then studies linear and non-linear spectral hybrid models, and then studies end element extraction methods based on quantum particle swarm optimization. The degree inversion method, the experimental part is based on the accuracy of the quantum particle swarm optimization-based end-element extraction method and two spatial-spectrum feature extraction methods. The experimental results show that the algorithm proposed in this paper improves the effect of group pixel decomposition based on the swarm intelligence algorithm. The classification accuracy of the 3DLBP spatial spectrum feature proposed in this paper is 94.22%.

Description: Welding is an important method for modern material processing. In actual processing, due to the influence of processing accuracy and welding thermal deformation, various defects often appear in the appearance of the weld. At present, visual inspection is mainly used for the appearance inspection of welds. The detection of weld defects mainly depends on the work experience of the staff. Based on the above background, the purpose of this article is to visually inspect the weld surface quality. This article uses visually obtained fringe images of weld contours as information sources to explore a visual-based weld appearance detection algorithm, including the measurement of weld formation dimensions and the detection of weld appearance defects. This algorithm overcomes manual measurements of the misjudgments and omissions caused by eye fatigue and experience differences. It improves the efficiency and accuracy of welding appearance inspection, and meets the needs of automation and intelligence of the entire welding process. In this paper, a subpixel stripe centerline extraction algorithm based on the combination of the Hessian matrix method and the center of gravity method is used; to further improve the accuracy of the extraction of the centerline of the weld seam, this article also performs the work of removing the wrong points and the compensation of the broken seam. Obtain a fringe centerline with better connectivity. Comparing the extraction algorithms of each centerline, the centerline obtained by this method has high accuracy, less time-consuming and high stability. It laid the foundation for the subsequent inspection of weld appearance. Through the training of the model, the accurate classification and recognition of surface defects of tube and plate welds have been achieved. The experimental results show that the improved vision-based welding surface defect recognition and classification proposed in this paper has better performance and accuracy. Up to 96.34%.

Description: Aiming at the image features of stock data, considering the picture features of stock data and the characteristics of CNN’s good at extracting picture features, the paper proposed a stock price trend prediction model CNN-M based on a Convolutional Neural Network. At the same time, based on the excellent image feature extraction ability of the residual network, this paper proposed a residual network-based stock price trend prediction model ResNet-M based on the Conventional Neural Network. The experimental results showed that the prediction ability of the improved residual network-based prediction model Resnet-M is superior to the CNN model.

Description: In smart city wireless network infrastructure, network node deployment directly affects network service quality. This problem can be attributed to deploying a suitable ordinary AP node as a wireless terminal access node on a given geometric plane, and deploying a special node as a gateway to aggregate. Traffic from ordinary nodes is to the wired network. In this paper, Pareto multi-objective optimization strategy is introduced into the wireless sensor network node security deployment, and an improved multi-objective particle swarm coverage algorithm based on secure connection is designed. Firstly, based on the mathematical model of Pareto multi-objective optimization, the multi-target node security deployment model is established, and the security connectivity and node network coverage are taken as the objective functions, and the problems of wireless sensor network security and network coverage quality are considered. The multi-objective particle swarm optimization algorithm is improved by adaptively adjusting the inertia weight and particle velocity update. At the same time, the elite archive strategy is used to dynamically maintain the optimal solution set. The high-frequency simulation software Matlab and simulation platform data interaction are used to realize the automatic modeling, simulation analysis, parameter prediction and iterative optimization of wireless network node deployment in smart city based on adaptive particle swarm optimization. Under the premise of meeting the performance requirements of wireless network nodes in smart cities, the experimental results show that although the proposed algorithm could not achieve the accuracy of using only particle swarm optimization algorithm to optimize the parameters of wireless network nodes in smart cities, the algorithm is completed. The antenna parameter optimization process takes less time and the optimization efficiency is higher.

Description: Nowadays, moving object detection in sequence images has become a hot topic in computer vision research, and has a very wide range of practical applications in many fields of military and daily life. In this paper, fast detection of moving objects in complex background is studied, and fast detection methods for moving objects in static and dynamic scenes are proposed respectively. Firstly, based on image preprocessing, aiming at the difficulty of feature extraction of moving targets in low illumination at night, Gamma change is used to process. Secondly, for the fast detection of moving objects in static scenes, this paper designs a detection method combining background difference and edge frame difference. Finally, aiming at the fast detection of moving objects in dynamic scenes, a feature matching detection method based on the SIFT algorithm is designed in this paper. Simulation experiments show that the method designed in this paper has good detection performance.