Recently, multi-view representation learning has become a rapidly growing direction in machine learning and data mining areas. This paper introduces two categories for multi-view representation learning: multi-view representation alignment and multi-view representation fusion. Consequently, we first review the representative methods and theories of multi-view representation learning based on the perspective of alignment, such as correlation-based alignment. Representative examples are canonical correlation analysis (CCA) and its several extensions. Then from the perspective of representation fusion we investigate the advancement of multi-view representation learning that ranges from generative methods including multi-modal topic learning, multi-view sparse coding, and multi-view latent space Markov networks, to neural network-based methods including multi-modal autoencoders, multi-view convolutional neural networks, and multi-modal recurrent neural networks. Further, we also investigate several important applications of multi-view representation learning. Overall, this survey aims to provide an insightful overview of theoretical foundation and state-of-the-art developments in the field of multi-view representation learning and to help researchers find the most appropriate tools for particular applications.

Precise wind energy potential assessment is vital for wind energy generation and planning and development of new wind power plants. This work proposes and evaluates a novel two-stage method for location-specific wind energy potential assessment. It combines accurate statistical modelling of annual wind direction distribution in a given location with supervised machine learning of efficient estimators that can approximate energy efficiency coefficients from the parameters of optimized statistical wind direction models. The statistical models are optimized using differential evolution and energy efficiency is approximated by evolutionary fuzzy rules.

In recent years, the analysis of surface electromyography (sEMG) signals by feature engineering and machine learning has developed rapidly. However, when feature engineering is applied to feature extraction of sEMG signals, important feature information in the signals will inevitably be omitted, which will reduce the performance of signal analysis and recognition. Therefore, this paper proposes a method to complete classification of sEMG hand movements based on convolutional neural network (CNN) and stacking ensemble learning. In this method, a primary classifier based on CNN is designed to extract sEMG data features, which avoid omission of important feature information. A secondary classifier based on the stacking method is designed to integrate three primary classifiers trained with time domain, frequency domain and time-frequency domain data of the sEMG signal respectively. Then, several experiments on NinaPro DB5 dataset is performed to evaluate the proposed models. When the window length is 200ms, primary classifier is trained and tested with the sEMG signal data divided by the 80ms, 100ms, and 125ms sliding length. The best accuracy can reach 71%. The primary classifier and the secondary classifier trained and tested with sEMG signal data divided by window lengths of 200ms and 300ms in the case of a sliding length of 100ms. When the window length is 200ms, the best primary classifier accuracy and the best secondary classifier accuracy can be 70.92% and 72.09%, respectively. On the window length of 300ms, the best primary classifier accuracy and the best secondary classifier accuracy can reach 75.02% and 76.02%, respectively. Finally, the model designed is compared with Linear Discriminant Analysis (LDA), Long Short Term Memory-CNN (LCNN), Support Vector Machine (SVM), and Random Forests. Under the same conditions, the average accuracy of the secondary classifier is 11.5%, 13.6%. and 10.1% higher than LDA, SVM, and LCNN, respectively. Also, the average accuracy rate is 3.05% higher than SVM and Random Forests.INDEX TERMS Surface electromyography, movements classification, convolutional neural network, ensemble learning.

Fog computing provides users with data storage, computing, and other services by using fog layer devices close to edge devices. Tasks and resource scheduling in fog computing has become a research hotspot. For the multi-objective task-scheduling problem in fog computing, an adaptive multi-objective optimization task scheduling method for fog computing (FOG-AMOSM) is proposed in this paper. In this method, the total execution time and the task resource cost in the fog network are taken as the optimization target of resource allocation, and a multi-objective task scheduling model is designed. Since the objective model is a Pareto optimal solution problem, the global optimal solution can be obtained by using multi-objective optimization theory and the improved multi-objective evolutionary heuristic algorithm. Moreover, to obtain a better distribution of the current task scheduling group, the neighborhood is adaptively changed according to the current situation of the task scheduling group in fog computing, which avoids the problem that the neighborhood value caused by the neighborhood policy in the multi-objective algorithm affects the distribution of the task scheduling population. This algorithm is used to solve the non-inferior solution set of the utility function index of fog computing task scheduling to try to solve the multi-objective cooperative optimization problem in fog computing task scheduling. The results show that the proposed method has better performance than other methods in terms of total task execution time, resource cost and load dimensions. INDEX TERMS Cloud computing, fog computing, task scheduling, multi-objective optimization algorithm, cyber-physical-social service.

No abstract