Particle filters have been widely used in various fields due to their advantages in dealing with non-linear and/or non-Gaussian systems. A large number of particles are needed to guarantee the convergence of particle filters for the state estimation, especially for large-scale complex systems. Therefore, parallel/distributed particle filters were adopted to improve the performance, in which different paradigms of resampling were proposed, including the centralized resampling, the decentralized resampling, and the hybrid resampling. To ease their adoptions, we analyze time consumptions and speedup factors of parallel/distributed particle filters with various resampling algorithms, state sizes, system complexities, numbers of processing units, and model dimensions in this study. The experimental results indicate that the decentralized resampling achieves the highest speedup factors due to the local transfer of particles, the centralized resampling always has the lowest speedup factors because of the global transfer of particles, and the hybrid resampling attains the speedup factors between. Moreover, we define the complexity-state ratio, as the ratio between the system complexity and the system state size to study how it impacts the speedup factor. The experiments show that the higher complexity-state ratio results in the increase of the speedup factors. This is one of the earliest attempts to analyze and compare the performance of parallel/distributed particle filters with different resampling algorithms. The analysis can provide potential solutions for further performance improvements and guide the appropriate selection of the resampling algorithm for parallel/distributed particle filters.
Since protein 3D structure prediction is very important for biochemical study and drug design, researchers have developed many machine learning algorithms to predict protein 3D structures using the sequence information only. Understanding the sequence-to-structure relationship is key for the successful structure prediction. Previous approaches including the single shallow learning model, the single deep learning model and clustering algorithms all have disadvantages to understand precise sequence-to-structure relationship. In order to further improve the performance of the local protein structure prediction, a novel deep learning model called Clustering Recurrent Neural Network (CRNN) is proposed. In this model, the whole protein dataset is divided into multiple cluster subtrees. A RNN is trained for each cluster in the subtrees so that each RNN can be used to learn the computationally simpler local sequence-to-structure relationship instead of attempting to capture the global sequence-to-structure relationship. After learning the local sequence-to-structure relationship using RNN, CRNN is designed to predict distance matrices, torsion angles and secondary structures for backbone -carbon atoms of protein sequence segments. Our experimental analysis indicates that 3D structure prediction accuracy is comparable or better than other state-of-art approaches.
Most computational algorithms mainly focus on detecting highly connected subgraphs in PPI networks as protein complexes but ignore their inherent organization. Furthermore, many of these algorithms are computationally expensive. However, recent analysis indicates that experimentally detected protein complexes generally contain Core/attachment structures.
Recent studies have shown that gene selection is a crucial technology in microarray data analysis as a result of its large number of genes and relatively small number of samples. Filter methods are fast convergent algorithms with low time complexity. However, filter methods neglect correlation among genes. Other methods for gene selection also have disadvantages. For example, the measurement used to calculate the correlation in other methods can not effectively reflect function similarity among genes, the time complexity will be high based on the whole gene set. Therefore, we propose a novel selection model called mutual information based minimum spanning trees (MIMST) which considers both gene interaction and complementary genes. In this new model, we first use filter methods to remove non-relevant genes, and then compute the interdependence of top-ranked genes. Finally, we construct MST to remove the redundant genes. The experiment results show that MIMST can find the smallest siMIMSTgnificant genes subset with higher classification accuracy compared with other methods.