Search

As a comprehensive and unstructured data source describing 3 dimensional (3D) objects, point cloud data has attracted wide interest from researchers. Neural networks (NNs) provide flexible, end-to-end solutions to point cloud processing tasks. Yet, one of the unavoidable problems in training the NNs is the difficulty in collecting and labeling high-quality point cloud data. Existing point cloud datasets are often collected at different scales and densities. Directly combining highly heterogeneous datasets might violate data protection regulations, but also lead to degradation of model performance. In our experiments, naive horizontal federated learning has been applied to alleviate the data privacy concern. However, when the datasets are not identically distributed, the federated model's performance falls far behind the state-of-the-art of centralized models. This paper investigates the union of highly heterogeneous point cloud datasets for the object classification task. In the proposed framework, the federated model is split into shared and personalized modules. The former improves generalizability by bringing multiple data sources into play, while the latter adapts local distribution and avoids convergence at false optima. Experiments show that the proposed framework FedPCN achieves 35.1% higher accuracy than FedAvg. At local test samples, FedPCN also outperforms the locally trained model by 0.5%.

Federated learning is a distributed deep learning method that enables parallel and distributed learning of data on multiple participants, without the need to centrally store it. In intelligent transportation system, it is impractical to gather the vehicle data from the edge devices due to data privacy concerns or network bandwidth limitation. Hence, combining with federated learning to train vehicle data processing models has become one of the popular solutions. However, such computing paradigm is subject to threats posed by malicious and abnormal nodes that greatly reduces the computing power of the neural network when performing calculations in a distributed manner. In this paper, we use the Vehicle Energy Dataset to simulate distributed vehicle data. Based on these data, we propose an unsupervised anomaly removal and neural network model based on federated learning to solve the problem of outlier data on vehicle equipment and analyze the effect of speed on fuel consumption. The results show that with the proposed anomaly removal strategy, MAE and MSE of the trained network are 29% and 36% lower than those without anomaly removal, respectively.

Proteins are linear polymers that fold into an incredible variety of three-dimensional structures that enable sophisticated functionality for biology. Predicting protein distance with high precision remains challenging, particularly for small protein families. As deep learning achieves remarkable success in many areas, deep learning also allows scientists to predict proteins' three-dimensional structure. As convolutional neural networks have a powerful ability to learn data features at multiple levels of abstraction, we deploy CNN to predict protein distance. To accelerate the training process, we apply a quantum convolutional neural network(QCNN) to improve the protein structure prediction efficiently. For QCNN, the conventional convolutional layer is transformed to a quantum convolution or quanvolutional layer. Since the protein data has large input, we explore the large dimension of these quantum transformations. And in experiments, we compare the different number of layers in QCNN during the training phase. We found the QCNN is similar to CNN that is the deeper layer can get better performance. The simulations show the proposed method can accelerate the convergence while maintaining the performance.

Many complex computational problems have to be overcome in the Computer Numerical Control (CNC) system, such as tool compensation calculation, contour interpolation, speed decomposition, position control and so on. If all the functions are accomplished by software, the corresponding execution time will affect the velocity of the CNC system. This paper has put forward a scheme of software hardening technique based on FPGA (Flied Programmable Gate Array), and developed an independent arithmetic calculating module for CNC system to improve the feed-rate of machine tool. VHSIC Hardware Description Language (VHDL) is adopted in Quartus II 9.0 development environment, based on FPGA chip of Altera company CYCLONE II series. Several algorithm operation processes relating to complex calculation are introduced in detail, such as addition, subtraction, multiplication and division operation of floating-point numbers. The simulation results prove that the proposed design methods of the arithmetic module are feasible and reasonable, which can also enhance the portability and applicability of floating-point calculating module in CNC system.

Gabor feature and gradient feature have been proven to be two most efficient features for handwritten character recognition recently. However, few comprehensive comparative researches on the performance of these two methods in large scale handwritten Chinese character recognition (HCCR) were reported in the literature. In this paper, we compare these two methods for large scale HCCR. Some new interesting conclusions were obtained through this study. The result showed that the performance of gradient feature significantly outperforms gabor feature. Multi-channel Gabor feature can improve the performance of single-channel gabor feature. We also observed that the recognition accuracy hardly get obvious increasing after the number of directions of gabor feature achieves 5. That means only 5 directional parameters of gabor features are necessary to achieve a good enough performance, rather than 8 directions which are widely used in the literature.