Support vector machine for predicting protein interactions using domain scores

Protein-protein interactions play a crucial role in the cellular process such as metabolic pathways and immunological recognition. This paper presents a new domain score-based support vector machine (SVM) to infer protein interactions, which can be used not only to explore all possible domain interactions by the kernel method, but also to reflect the evolutionary conservation of domains in proteins by using the domain scores of proteins. The experimental result on the Saccharomyces cerevisiae dataset demonstrates that this approach can predict protein-protein interactions with higher performances compared to the existing approaches.     

Deep forest

Current deep-learning models are mostly built upon neural networks, i.e. multiple layers of parameterized differentiable non-linear modules that can be trained by backpropagation. In this paper, we explore the possibility of building deep models based on non-differentiable modules such as decision trees. After a discussion about the mystery behind deep neural networks, particularly by contrasting them with shallow neural networks and traditional machine-learning techniques such as decision trees and boosting machines, we conjecture that the success of deep neural networks owes much to three characteristics, i.e. layer-by-layer processing, in-model feature transformation and sufficient model complexity. On one hand, our conjecture may offer inspiration for theoretical understanding of deep learning; on the other hand, to verify the conjecture, we propose an approach that generates deep forest holding these characteristics. This is a decision-tree ensemble approach, with fewer hyper-parameters than deep neural networks, and its model complexity can be automatically determined in a data-dependent way. Experiments show that its performance is quite robust to hyper-parameter settings, such that in most cases, even across different data from different domains, it is able to achieve excellent performance by using the same default setting. This study opens the door to deep learning based on non-differentiable modules without gradient-based adjustment, and exhibits the possibility of constructing deep models without backpropagation.     

短期电力负荷时间序列预测的极限学习机方法

提出将一种进化的神经网络模型——极限学习机应用于短期电力负荷时间序列预测中,该方法具有模型参数设置少、训练速度快和良好的泛化能力等明显优点。通过实例分析表明该模型的预测精度要优于BP神经网络模型,同时也验证了该模型应用于短期负荷预测的有效性和可行性。     

基于并行决策树的微博互动数预测

社交网络的快速发展,微博成为主要的社交媒体平台,针对如何预测微博文本的未来互动数,对微博进行有效的分发控制的问题,提出一种基于并行决策树的微博互动数所属级数预测的方法。首先,对用户以往发表的微博进行用户特征和微博文本特征的处理;然后,使用并行决策树分类算法对训练数据进行分类模型的构建;最后使用得到的分类模型对新微博文本的互动数所属级数进行分类预测。通过对比算法的实验,验证了所提方法具有较高的分类精度和较好的可扩展性,能够对微博所属级数进行有效的分类预测。     

车辆网络中基于网络编码机会的调度算法

证明在车辆网络中应用网络编码,其广播容量最大化问题是NP难的;提出一种基于最大编码机会的优化调度算法. 该算法结合网络编码与车辆缓存提供的编码机会,有效提高了广播容量. 结果表明,与贪婪算法相比,该算法获得更大网络编码增益,保证了一定的传输公平性.     

冲孔程序设计在生产过程中的应用

本文通过研究和分析数控冲加工的工艺特点,提出了在冲孔机的程序设计中应当注意的一些事项,将数控冲程序设计在生产过程应用中常见的问题进行剖析,并以相应的实例阐述了完成各项工作和解决具体问题的办法。     

基于分类的机器学习方法中的决策树算法

阐述数据挖掘的分类及目的,总结分类器的构造方法,讲述分类中决策树的构建和修剪.     

3D finite element simulation of tunnel boring machine construction processes in deep water conveyance tunnel

Applying stiffness migration method, a 3D finite element mechanical model is established to simulate the excavation and advance processes. By using 3D nonlinear finite element method, the tunnel boring machine (TBM) excavation process is dynamically simulated to analyze the stress and strain field status of surrounding rock and segment. The maximum tensile stress of segment ring caused by tunnel construction mainly lies in arch bottom and presents zonal distribution. The stress increases slightly and limitedly in the course of excavation. The maxi-mum and minimum displacements of segment, manifesting as zonal distribution, distribute in arch bottom and vault respectively. The displacements slightly increase with the advance of TBM and gradually tend to stability.     

Motion classification of EMG signals based on wavelet packet transform and LS-SVMs ensemble

This paper presents an effective method for motion classification using the surface electromyographic (sEMG) signal collected from the forearm. Given the nonlinear and time-varying nature of EMG signal, the wavelet packet transform (WPT) is introduced to extract time-frequency joint information. Then the multi-class classifier based on the least squares support vector machine (LS-SVM) is constructed and verified in the various motion classification tasks. The results of contrastive experiments show that different motions can be identified with high accuracy by the presented method. Furthermore, compared with other classifiers with different features, the performance indicates the potential of the SVM techniques combined with WPT in motion classification.     

用户态并行文件系统性能优化

用户态文件系统框架(filesystem in user space,FUSE)因其相对简单快捷的开发特性被广泛应用于新型文件系统的开发过程中.但是FUSE框架在处理应用的I/O请求时存在多次用户态和内核态切换、上下文切换以及额外的内存拷贝操作,造成一定的性能开销.为减小FUSE对I/O性能的影响,提出一种绕过FUSE...