Three-dimensional (3D) liver tumor segmentation from Computed Tomography (CT) images is a prerequisite for computer-aided diagnosis, treatment planning, and monitoring of liver cancer. Despite many years of research, 3D liver tumor segmentation remains a challenging task. In this paper, an efficient semiautomatic method was proposed for liver tumor segmentation in CT volumes based on improved fuzzy C-means (FCM) and graph cuts. With a single seed point, the tumor volume of interest (VOI) was extracted using confidence connected region growing algorithm to reduce computational cost. Then, initial foreground/background regions were labeled automatically, and a kernelized FCM with spatial information was incorporated in graph cuts segmentation to increase segmentation accuracy. The proposed method was evaluated on the public clinical dataset (3Dircadb), which included 15 CT volumes consisting of various sizes of liver tumors. We achieved an average volumetric overlap error (VOE) of 29.04% and Dice similarity coefficient (DICE) of 0.83, with an average processing time of 45 s per tumor. The experimental results showed that the proposed method was accurate for 3D liver tumor segmentation with a reduction of processing time.

In this paper, a fault diagnosis method that is based on the deep structure and the sparse least squares support vector machine (SLSSVM) is proposed. This method constructs the structure of a multi-layer support vector machine (SVM). First, the SVM on the first layer is trained by using the training samples, and it learns the shallow features of the data. Then, the ''feature extraction formula'' is used to generate a new expression of the sample, which is used as input of the next layer. The new layer of the SVM trains on the new sample, and it extracts and learns the deep features of the signal layer by layer; eventually, after multiple feature mapping, it outputs the diagnostic results on the last layer. Because of the deep structure, the algorithm complexity and operation time increase. Therefore, in this paper, the least squares support vector machine (LSSVM) is combined with the sparse theory. By constructing the approximate maximal linearly independent vector set in the feature space, we conduct the sparse expression of samples and obtain the discriminant function for classification, which effectively solves the problem of sparsity deficiency for the LSSVM. Last, the method is used to diagnose centrifugal pump faults and rolling bearing faults and compares with the several methods of the SVM, the SLSSVM, deep SVM, and convolutional neural networks. The diagnostic results indicate that the method in this paper has good performance. INDEX TERMS Fault diagnosis, deep structure, support vector machine, sparsity.

No abstract

No abstract

Intelligent personal assistants on mobile devices such as Apple’s Siri and Microsoft Cortana are increasingly important. Instead of passively reacting to queries, they provide users with brand new proactive experiences that aim to offer the right information at the right time. It is, therefore, crucial for personal assistants to understand users’ intent, that is, what information users need now. Intent is closely related to context. Various contextual signals, including spatio-temporal information and users’ activities, can signify users’ intent. It is, however, challenging to model the correlation between intent and context. Intent and context are highly dynamic and often sequentially correlated. Contextual signals are usually sparse, heterogeneous, and not simultaneously available. We propose an innovative collaborative nowcasting model to jointly address all these issues. The model effectively addresses the complex sequential and concurring correlation between context and intent and recognizes users’ real-time intent with continuously arrived contextual signals. We extensively evaluate the proposed model with real-world data sets from a commercial personal assistant. The results validate the effectiveness the proposed model, and demonstrate its capability of handling the real-time flow of contextual signals. The studied problem and model also provide inspiring implications for new paradigms of recommendation on mobile intelligent devices.

No abstract

No abstract

No abstract