Exploiting multimodal information like acceleration and heart rate is a promising method to achieve human action recognition. A Semi-Supervised action recognition approach AUCC (Action Understanding with Combinational Classifier) using the diversity of base classifiers to create a high-quality ensemble for multimodal human action recognition is proposed in this paper. Furthermore, both labeled and unlabeled data are applied to obtain the diversity measure from multimodal human action recognition. Any classifiers can be applied by AUCC as its base classifier to create the human action recognition model, and the diversity of classifier ensemble is embedded in the error function of the model. The model’s error is decayed and back-propagated to the basic classifiers through each iteration. The basic classifiers’ weights are acquired during creation of the ensemble to guarantee the appropriate total accuracy of the model. Considerable experiments have been done during creation of the ensemble. Extensive experiments show the effectiveness of the offered method and suggest its superiority of exploiting multimodal signals.

This study explores a Semi-Supervised classification approach using random forest as a base classifier to classify the low-back disorders (LBDs) risk associated with the industrial jobs. Semi-Supervised classification approach uses unlabeled data together with the small number of labelled data to create a better classifier. The results obtained by the proposed approach are compared with those obtained by a backpropagation neural network. Comparison indicates an improved performance by the Semi-Supervised approach over the random forest classifier as well as neural network approach. Highest classification accuracy of 78.20% was achieved by the used Semi-Supervised approach with random forest as base classifier in comparison to an accuracy of 72.4% and 74.7% obtained by random forest and back propagation neural network approaches respectively. Thus results suggest that the proposed approach can successfully classify jobs into the low and high risk categories of low-back disorders based on lifting task characteristics.

The increment of computer technology usage and rapid development of the Internet and electronic business lead to an increase in financial transactions. With the increase of these banking activities, fraudsters also use different methods to boost their fraudulent activities. One of the ways to cope their damages is fraud detection. Although, in this field, some methods have been proposed, there are essential challenges on the way. For example, it is necessary to propose methods that detect fraud accurately and fast, simultaneously. Lack of non-fraud labeled data and little fraud labeled data for Learning is another challenge in this field particularly in banking. Therefore, we propose a new fraud detection method for bank accounts called SSLBM. In this method, after preprocessing phase, a helpful Learning method called SSEV is used that is based on Semi-Supervised Learning and evolutionary algorithm. The results imply improvement of detection by using SSLBM with 68% accuracy and acceptable speed.

On many occasions, the evaluation of a phenomenon based on a single feature could not solely be resulted in comprehensive and accurate results. Moreover, even if we have several features, we don’ t know in advance, which feature offers a better description of the phenomenon. Thus, selecting the best features and especially their combination could lead to better results. An affinity graph is a tool that can describe the relationship between the samples. In this paper, we proposed a graph-based sample-based ranking method that sorts the graphs based on six proposed parameters. The sorting is performed such that the graphs at the top of the list have better performance compared to the graphs at the bottom. Furthermore, we propose a fusion method to merge the information of various features and improve the accuracy of label propagation. Moreover, a method is proposed for parameter optimizations and the ultimate decision fusion. The experimental results indicate that the proposed scheme, apart from correctly ranking the graphs according to their accuracy, in the fusion step, increases the accuracy compared to the use of a single feature.