Multi-modal regression is important in forecasting nonstationary processes or with a complex mixture of distributions. It can be tackled with multiple hypotheses frameworks but with the difficulty of combining them efficiently in a learning model. A Structured Radial Basis Function Network is presented as an ensemble of multiple hypotheses predictors for regression problems. The predictors are regression models of any type that can form centroidal Voronoi tessellations which are a function of their losses during training. It is proved that this structured model can efficiently interpolate this tessellation and approximate the multiple hypotheses target distribution and is equivalent to interpolating the meta-loss of the predictors, the loss being a zero set of the interpolation error. This model has a fixed-point iteration algorithm between the predictors and the centers of the basis functions. Diversity in learning can be controlled parametrically by truncating the tessellation formation with the losses of individual predictors. A closed-form solution with least-squares is presented, which to the authors’ knowledge, is the fastest solution in the literature for multiple hypotheses and structured predictions. Superior generalization performance and computational efficiency is achieved using only two-layer neural networks as predictors controlling diversity as a key component of success. A gradient-descent approach is introduced which is loss-agnostic regarding the predictors. The expected value for the loss of the structured model with Gaussian basis functions is computed, finding that correlation between predictors is not an appropriate tool for diversification. The experiments show outperformance with respect to the top competitors in the literature.
Nonlinear system identification is considered using a generalized kernel regression model. Unlike the standard kernel model, which employs a fixed common variance for all the kernel regressors, each kernel regressor in the generalized kernel model has an individually tuned diagonal covariance matrix that is determined by maximizing the correlation between the training data and the regressor using a repeated guided random search based on boosting optimization. An efficient construction algorithm based on orthogonal forward regression with leave-one-out (LOO) test statistic and local regularization (LR) is then used to select a parsimonious generalized kernel regression model from the resulting full regression matrix. The proposed modeling algorithm is fully automatic and the user is not required to specify any criterion to terminate the construction procedure. Experimental results involving two real data sets demonstrate the effectiveness of the proposed nonlinear system identification approach.
The role of cell-cell communications (CCCs) is increasingly recognized as being important to differentiation, invasion, metastasis, and drug resistance in tumoral tissues. Developing CCC inference methods using traditional experimental methods are time-consuming, labor-intensive, cannot handle large amounts of data. To facilitate inference of CCCs, we proposed a computational framework, called CellMsg, which involves two primary steps: identifying ligand-receptor interactions (LRIs) and measuring the strength of LRIs-mediated CCCs. Specifically, CellMsg first identifies high-confident LRIs based on multimodal features of ligands and receptors and graph convolutional networks. Then, CellMsg measures the strength of intercellular communication by combining the identified LRIs and single-cell RNA-seq data using a three-point estimation method. Performance evaluation on four benchmark LRI datasets by five-fold cross validation demonstrated that CellMsg accurately captured the relationships between ligands and receptors, resulting in the identification of high-confident LRIs. Compared with other methods of identifying LRIs, CellMsg has better prediction performance and robustness. Furthermore, the LRIs identified by CellMsg were successfully validated through molecular docking. Finally, we examined the overlap of LRIs between CellMsg and five other classical CCC databases, as well as the intercellular crosstalk among seven cell types within a human melanoma tissue. In summary, CellMsg establishes a complete, reliable, and well-organized LRI database and an effective CCC strength evaluation method for each single-cell RNA-seq data. It provides a computational tool allowing researchers to decipher intercellular communications. CellMsg is freely available at https://github.com/pengsl-lab/CellMsg.
To formulate the classification criteria of disability weight for Alzheimer's disease (AD) and Parkinson's disease (PD) in China and to evaluate the disability weight of AD and PD in population over 60 years old in Beijing.Based on the criteria of Global Burden of Disease (GBD), a seven-grade disability classification was used to develop a new disability classification criteria for AD and PD in terms of Delphi method in China. Using the data from epidemiological survey for AD and PD in Beijing in 1997 and new criteria, mean disability weights of AD and PD in population over 60 years old in Beijing were obtained.The mean disability weights of Alzheimer's disease was 0.40 in population over 60 years old who received treatment in Beijing and 0.52 in those without treatment while the mean disability weights of Parkinson's disease were 0.30 in the patient receiving treatment and 0.23 in those without treatment.Difference between the result of this study and the data of GBD study in the mean disability weight for AD and PD was noticed.
BACKGROUND:Although most unstable C1 fractures can be effectively treated either by conservative treatment with external immobilization or by surgical procedure of C1-ring osteosynthesis, those fractures involving the lateral mass are likely to lead to traumatic arthritis and persistent neck pain. Specific reports of treatment of unstable C1 fractures involving the lateral mass are still scarce. We therefore present this report to evaluate the effectiveness of posterior C1-C2 screw-rod fixation and fusion for unstable C1 fractures involving the lateral mass. MATERIAL AND METHODS:From June 2009 to June 2016 in our hospital, 16 cases were diagnosed with C1 fractures involving the lateral mass and treated by posterior C1-C2 screw-rod fixation and fusion. The patients’ clinical data were retrospectively analyzed. Preoperative and postoperative images were taken to evaluate cervical sequence, location of screws, and bone fusion. Neurological status and neck pain levels were evaluated clinically on follow-up. RESULTS:All patients underwent surgery successfully. The mean follow-up duration was 15.3±4.9 months (range 9-24 months). All patients obtained satisfying clinical outcomes with good neck pain alleviation, appropriate screw placement, and reliable bone fusion. None of the patients developed vascular or neurological complications during the operation or follow-up. CONCLUSIONS:Posterior C1-C2 screw-rod fixation and fusion is an effective management for unstable C1 fractures involving the lateral mass. This operation can provide reliable stabilization and satisfactory bone fusion.
This paper describes a novel on-line learning approach for radial basis function (RBF) neural network. Based on an RBF network with individually tunable nodes and a fixed small model size, the weight vector is adjusted using the multi-innovation recursive least square algorithm on-line. When the residual error of the RBF network becomes large despite of the weight adaptation, an insignificant node with little contribution to the overall system is replaced by a new node. Structural parameters of the new node are optimized by proposed fast algorithms in order to significantly improve the modeling performance. The proposed scheme describes a novel, flexible, and fast way for on-line system identification problems. Simulation results show that the proposed approach can significantly outperform existing ones for nonstationary systems in particular.
It is a significant problem how we select step-size of adaptive filtering algorithm so as to solve effectively the conflict between convergence speed and steady misalignment in echo cancellation. This paper presents a novel echo cancellation scheme which integrates a diverse set of adaptive filtering methods and different choices of step-size, such that their advantages can be integrated and the improved performance can be achieved. In the proposed scheme, the performance of different methods are analyzed, thus being able to keep selecting the best methods for output. An empiri-cal study on the integration of four methods, namely, LMS, NLMS, PNLMS and IPNLMS, indicates that the proposed scheme is effective in terms of both convergence speed and good steadiness.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)