No abstract

One-class Support Vector Machine (OCSVM) is one of state-of-the-art kernel-based methods for one-class classification problem. OCSVM produces the good performance for imbalanced dataset. Nonetheless, it cannot make use of negative data samples and also cannot utilize unlabeled data to boost the classifier. In this paper, we first extend the model of OCSVM to make use of the information carried by negative data samples for classification and then propose how to integrate the semi-supervised paradigm to the extended OCSVM for utilizing the unlabeled data to increase the classifier's generalization ability. Finally, we show how to apply the fuzzy theory to the proposed semi-supervised one-class classification method for efficiently handling noises and outliers.

Support Vector Machine (SVM) is a well-known kernel-based method for binary classification problem. SVM aims at constructing the optimal middle hyperplane which induces the largest margin. It is proven that in a linearly separable case, this middle hyperplane offers the high accuracy on universal datasets. However, real world datasets often contain overlapping regions and therefore, the decision hyperplane should be adjusted according to the profiles of the datasets. In this paper, we propose Robust Support Vector Machine (RSVM), where the hyperplanes can be properly adjusted to accommodate the real world datasets. By setting the value of the adjustment factor properly, RSVM can handle well the datasets with any possible profiles. Our experiments on the benchmark datasets demonstrate the superiority of the RSVM for both binary and one-class classification problems.

No abstract

5G is the fifth generation of cellular networks and has been used in a lot of different areas. 5G often requires sudden rises in power consumption. To stabilize the power supply, a 5G system requires a lithium-ion battery (LIB) or a mechanism called AC main modernization to provide energy support during the power peak periods. The LIB approach is the best option in terms of simplicity and maintainability. Moreover, a 5G system requires not only high-performance energy but also the ability of tracking and prediction. Therefore, the requirement for a smart power supply for lithium-ion batteries with temporal monitoring and estimation is highly desirable. In this paper, we focus on artificial intelligence (AI) improvements to increase the accuracy of LIB state-of-health prediction. By observing the SeqInSeq nature of the battery data, our approach uses self-attention and fixed-point positional encoding. We also take advantage of autoregression to archive the trainable dependency from a non-linear branch and a linear branch in creating the final output. Compared with the current state-of-the-art (SOTA) method, our experimental results show that we provide better accuracy, compared with the baseline output using the NASA and CALCE datasets. From the same setting, we archive a reduction of 20.08% root mean square error (RMSE) and 29.01% mean absolute percentage error (MAPE) on NASA loss, compared to the SOTA approaches. On CALCE, the numbers are a 5.99% RMSE and 12.59% MAPE decrement, which is significant.