Search

Relocation is one of the most common problems in Simultaneous Localization and Mapping (SLAM). This paper presents a novel relocation method, using unsupervised deep learning algorithm to extract the feature of Light Detection and Ranging (LiDAR) data, and narrows the scope of relocation by classifying these features to reduce the randomness of the relocation. Compared with the other methods which is based on matching the manual feature points, this method avoids some limitations of manual features. We modify the Particle Filter SLAM (PF-SLAM), and use our relocation method to replace the original method for experimentation. The experimental results demonstrate that this method can be relocation whit high success rate only use a small amount of computational resource in a short time. Training neural network will consume a lot of computing resources, we also propose a cloud computing framework to the implementation of this method for the mobile robot which computational resources are limited. [ABSTRACT FROM AUTHOR]

• Proposing a novel hybrid SVR based model for the market price forecasting considering the risk error in the analysis and evaluation. • Proposing the firefly algorithm as a swarm based solution for optimizing the SVR hyperparameters according to the market price. • Proposing a two-stage modification approach for the FA (MFA) to enhance the search capabilities and boost the diversity of solutions. This paper proposes a novel artificial intelligence based approach for the accurate forecasting of the market cost incorporating the error risk. The proposed model makes use of a hybrid evolving solution based on firefly algorithm and support vector regression (SVR) for getting to the highest accuracy and precision. In contrast to the artificial neural network models which face the overfitting problem, the SVR would keep a limit on the forecast model complexity and thus would escape from the overfitting concerns. In order to get into the maximum performance of the SVR, one need to adjust the hyperparameters optimally. This article proposes the firefly algorithm which mimics the social behavior of these insects in their colony. In addition, a new modification method is introduced which would add up the algorithm population diversity and thus enhance the search results. The appropriate performance of the proposed hybrid AI base model is assessed on the typical market price datasets. [Display omitted] [ABSTRACT FROM AUTHOR]

As an essential subproblem in the face recognition field, occluded face recognition has received considerable attention in recent years. However, satisfactory recognition accuracy for occluded faces has not been achieved. Therefore, in order to solve this problem, this paper proposes a convolutional neural network that has multidimensional serial feature extraction modules for occluded faces and uses the deep learning method to improve the recognition rate. In order to improve the expression ability of the network, the method extracts features from two dimensions — space and channel — and built a multidimensional serial feature extraction module. By "multiscale" and "dependence" processing features, the generalization ability was significantly improved. Through the experimental test, the recognition accuracy of the multidimensional feature network (MFNet) reached 90.35%. This accuracy is 17.89% (72.36%) better than that of the traditional algorithm. Meanwhile, compared with other convolutional neural networks, this network has different degrees of improvement, which are 0.68% (ArcFace), 2.14% (Visual Geometry Group Face), and 4.83% (DeepID3). [ABSTRACT FROM AUTHOR]