Search

In the process of facial expression recognition, face detection is the prerequisite, image preprocessing is the foundation, facial expression feature extraction is the key, and facial expression classification is the target. Effective feature extraction in this process can improve the accuracy of facial expression classifications. On the other hand, traditional facial expression recognition methods are not only complicated in the feature extraction process, but also unable to obtain more in-depth high-semantic features and deep features from the original image. To solve the above problems, this paper proposes a facial expression recognition method based on multi-channel fusion and lightweight neural network. First, a cascade classifier based on Haar features is used to detect the face region of the facial expression image. Second, the local binary pattern (LBP) is used to extract the local texture features from the face region. Third, face edge features are simultaneously obtained by performing edge detection in the face region based on the Canny edge detection algorithm. Fourth, the obtained face image, LBP texture feature image, and edge detection Canny image are fused, and the fused image is input into the constructed lightweight neural network for training and recognition. Experiments are carried out on the public image databases Facial Expression Recognition 2013 (Fer2013) and extended Cohn–Kanade (CK +) using the hold-out cross-validation method. The experimental results show that the proposed method effectively extracts more complete image features by combining traditional feature extraction algorithms with deep learning feature extraction algorithms, improves the accuracy and robustness of facial expression recognition, and has better recognition rate and generalization ability compared to other mainstream methods. [ABSTRACT FROM AUTHOR]

Due to the heterogeneity of program language and natural language query, it is difficult to identify the semantic relationship between them, which leads to the low efficiency of code recommendation. In order to solve the problems of the above code recommendation technology, a code recommendation method based on joint embedded attention network (JEAN) is proposed in this paper. The method uses GRU Network to embed code snippets and describe queries into vector representation, which solves the problem of heterogeneous code snippets and natural language queries. The Attention mechanism is then used to distribute totally different weights to different components of every mode of the code snippet. The reason for the Attention mechanism is that different components of every mode of the code snippet contribute differently to the semantic vector of the final code snippet, making it interpretable. Finally, two commonly used evaluation indexes of information retrieval, SuccessRate@k and MRR, are used for experimental comparison with other baseline models. The experimental results show that the code recommendation method based on joint embedded attention network proposed in this paper can effectively recommend appropriate code snippets according to the needs of developers, and its performance is better than other baseline methods. [ABSTRACT FROM AUTHOR]

In order to solve the problems of low learning efficiency and slow convergence speed when mobile robot uses reinforcement learning method for path planning in complex environment, a reinforcement learning method based on each round path planning result is proposed. Firstly, the algorithm adds obstacle learning matrix to improve the success rate of path planning; and introduces heuristic reward to speed up the learning process by reducing the search space; then proposes a method of dynamically adjusting the exploration factor to balance the exploration and utilization in path planning, so as to further improve the performance of the algorithm. Finally, the simulation experiment in grid environment shows that compared with Q-learning algorithm, the improved algorithm not only shortens the average path length of the robot to reach the target position, but also speeds up the learning efficiency of the algorithm, so that the robot can find the optimal path more quickly. The code of EPRQL algorithm proposed in this paper has been published to GitHub: https://github.com/panpanpanguoguoqian/mypaper1.git. [ABSTRACT FROM AUTHOR]

Many real-world datasets consist of multiple views of data items. The rough method of combining multiple views directly through feature concatenation cannot uncover the optimal latent structure shared by multiple views, which would benefit many data analysis applications. Recently, multi-view clustering methods have emerged and been applied to solving many machine learning problems. However, most multi-view clustering methods ignore the joint information of multi-view data or neglect the quality difference between different views of data, resulting in decreased learning performance. In this paper, we discuss a multi-view clustering algorithm based on concept factorization that effectively fuses useful information to derive a better representation for more effective clustering. We incorporate two regularizers into the concept factorization framework. Specifically, one regularizer is adopted to force the coefficient matrix to move smoothly on the underlying manifold. The other regularizer is used to learn the latent clustering structure from different views. Both of these regularizers are incorporated into the concept factorization framework to learn the latent representation matrix. Optimization problems are solved efficiently via an iterative algorithm. The experimental results on seven real-world datasets demonstrate that our approach outperforms the state-of-the-art multi-view clustering algorithms. [ABSTRACT FROM AUTHOR]

Iris image-based biometric systems are commonly used in applications that demand security, authentication, recognition and faster login access. In solving these real-time problems, the impact of soft computing techniques which employ cognitive skills is very high. Although this system has been commercialized, the scope for improvement is still plenty. This paper introduces the reader to different segments of an iris recognition system and reviews the techniques involved with each segment. It reports on how research articles validate the robustness of an iris-based recognition system. As these systems are fallible, it also shows the vulnerabilities associated with each segment and provides insights to develop much better intelligent and robust techniques which will make the system more accurate. This paper also shows that in spite of versatility of soft computing techniques, it is not fully exploited for iris recognition systems. The present challenges and directions for future research are also discussed. [ABSTRACT FROM AUTHOR]

The qualities of new data used in the sequential learning phase of the online sequential extreme learning machine algorithm (OS-ELM) have a significant impact on the performance of OS-ELM. This paper proposes a novel data filter mechanism for OS-ELM from the perspective of fuzziness and a fuzziness-based online sequential extreme learning machine algorithm (FOS-ELM). In FOS-ELM, when new data arrive, a fuzzy classifier first picks out the meaningful data according to the fuzziness of each sample. Specifically, the new samples with high-output fuzziness are selected and then used in sequential learning. The experimental results on eight binary classification problems and three multiclass classification problems have shown that FOS-ELM updated by the new samples with high-output fuzziness has better generalization performance than OS-ELM. Since the unimportant data are discarded before sequential learning, FOS-ELM can save more memory and have higher computational efficiency. In addition, FOS-ELM can handle data one-by-one or chunk-by-chunk with fixed or varying sizes. The relationship between the fuzziness of new samples and the model performance is also studied in this paper, which is expected to provide some useful guidelines for improving the generalization ability of online sequential learning algorithms. [ABSTRACT FROM AUTHOR]

Human inertial thinking schemes can be formed through learning, which are then applied to quickly solve similar problems later. However, when problems are significantly different, inertial thinking generally presents the solutions that are definitely imperfect. In such cases, people will apply creative thinking, such as reverse thinking, to solve problems. Similarly, machine learning methods also form inertial thinking schemes through learning the knowledge from a large amount of data. However, when the testing samples are vastly different, the formed inertial thinking schemes will inevitably generate errors. This kind of inertial thinking is called illusion inertial thinking. Because all machine learning methods do not consider the illusion inertial thinking, in this paper we propose a new method that uses the reverse thinking to correct the illusion inertial thinking, which increases the generalization ability of machine learning methods. Experimental results on benchmark data sets validated the proposed method. [ABSTRACT FROM AUTHOR]

Focusing on non-iterative approaches in training feed-forward neural networks, this special issue includes 12 papers to share the latest progress, current challenges, and potential applications of this topic. This editorial presents a background of the special issue and a brief introduction to the 12 contributions. [ABSTRACT FROM AUTHOR]

Learning from categorical data is a critical yet challenging task. Current research focuses on either leveraging the complex interaction between and within categorical values to generate a numerical representation, or designing a model that can tackle this types of data directly. However, both of these paradigms overlook the relation between the data characteristics and learning model hypothesis. In this paper, we propose a model-aware categorical data embedding framework that jointly reveals the intrinsic categorical data characteristics and optimizes the fitness of the representation for the follow-up learning model. An ELM-aware and a SVM-aware representation methods have been instantiated under this framework. Extensive experiments of classification with the embedded representation on 17 data sets demonstrate that the proposed framework can significantly improve the categorical data representation performance compared with state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Considering restricted Boltzmann machine (RBM) as an unsupervised pre-training phase, this paper delivers a study on predetermined model parameters in extreme learning machine (ELM). Because of the non-iterative attribute in fine-tuning phase, the property of hidden layer output plays an important part in model performance. For ELM, we give a theoretical analysis on the hidden layer parameters related to matrix perturbation and continuity of generalized inverse. Then by empirically analyzing the proposed RBM-ELM algorithm, we find that the impact of hidden layer parameters on generalization ability varies among the experimental datasets. By exploring the training process and comparing the model parameters between random assignment and RBM, we identify the special pattern of hidden layer output discussed in theoretical part and empirically show that such pattern could harm the model performance. [ABSTRACT FROM AUTHOR]

A cohort refers to a group of candidates interacting and competing with one another. The basic idea of cohort is inspired from the social tendency of following/learning from one another and adapting the qualities of certain candidate. Based upon this approach, seven variations of cohort intelligence (CI) are presented in this paper. The seven variations of CI are: follow best, follow better, follow worst, follow itself, follow median, follow roulette wheel selection and alienate-and-random selection. The proposed variations are tested on seven multimodal and three uni-modal unconstrained test functions, and the numerical results are analyzed to decide which variation works best for a particular type of problem. The performance of these variations is compared with some well-known algorithms namely PSO, CMAES, ABC, JDE, CLPSO, SADE and BSA. The analysis of variations gives very important insight about the strategy that should be followed while working in a cohort. The variations proposed may provide insight into variegated applicability domain of the CI methodology. The choice of the right variation may also further open doors for CI to solve different real-world problems. [ABSTRACT FROM AUTHOR]

Large-scale problems have been a very active topic in machine learning area. In the time of big data, it is a challenge and meaningful work to solve such problems. Standard SVM can make linear classification on large-scale problems effectively, with acceptable training time and excellent prediction accuracy. However, nonparallel SVM (NPSVM) and ramp loss nonparallel SVM (RNPSVM) are proposed with better performance than SVM on benchmark datasets. It is motivated to introduce NPSVMs into the area of large-scale issues. In this paper, we propose large-scale linear NPSVMs, solved by the alternating direction method of multipliers (ADMM), to handle large-scale classification problems. ADMM breaks large problems into smaller pieces, avoiding solving intractable problems and leading to higher training speed. The primal problems of NPSVM are convex and differentiable, and they can be managed directly by ADMM. But the objective functions of RNPSVM, composed of convex ones and concave ones, should first be processed by CCCP algorithm and transformed as a series of convex programs. Then, we apply ADMM to solve these programs in every iteration. Experiments of NPSVMs on large-scale problems verify that the algorithms can classify large-scale tasks effectively. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) has become one of the new research hotspots in the field of pattern recognition and machine learning. However, the existing extreme learning machine algorithms cannot better use identification information of data. Aiming at solving this problem, we propose a regularized extreme learning machine (algorithm) based on discriminative information (called IELM). In order to evaluate and verify the effectiveness of the proposed method, experiments use widely used image data sets. The comparative experimental results show that the proposed algorithm in the paper can significantly improve the classification performance and generalization ability of ELM. [ABSTRACT FROM AUTHOR]