In the past decades,advances in high-throughput technologies have led to the generation of huge amounts of biological data that require analysis and ***,nonnegative matrix factorization (NMF) has been introduced as ...
详细信息
In the past decades,advances in high-throughput technologies have led to the generation of huge amounts of biological data that require analysis and ***,nonnegative matrix factorization (NMF) has been introduced as an efficient way to reduce the complexity of data as well as to interpret them,and has been applied to various fields of biological *** this paper,we present CloudNMF,a distributed open-source implementation of NMF on a MapReduce *** evaluation demonstrated that CloudNMF is scalable and can be used to deal with huge amounts of data,which may enable various kinds of a high-throughput biological data analysis in the *** is freely accessible at http://***/projects/***.
This paper describes a method for reducing the information contained in an image sequence, while retaining the information necessary for the interpretation of the sequence by a human observer. The method consists of f...
详细信息
This paper describes a method for reducing the information contained in an image sequence, while retaining the information necessary for the interpretation of the sequence by a human observer. The method consists of first locating the redundant information, reducing the degree of redundancy, and coding the result. The sequence is treated as a single 3-D data volume, the voxels of which are grouped into several regions, obtained by a 3-D split and merge algorithm. To find these regions, we first obtain an initial region space by splitting the image sequence until the gray-level variation over each region can be approximated by a 3-D polynomial, to a specified accuracy. This results in a set of parallelepipedic regions of various sizes. To represent the gray-level variation over these regions, the coefficients of the approximating polynomial are used as features. The most similar regions are then merged, using a region adjacency graph. The information is coded by representing the borders of the regions using a pyramidal structure in the x, y, t space. The coefficients of the approximating polynomials are coded in a straightforward manner. For 256 x 256 pixel, 25 frames/s image sequences, compressions allowing transmission rates near 64 kbit/s are obtained.
Controls, especially effficiency controls on dynamical processes, have become major challenges in many complex systems. We study an important dynamical process, random walk, due to its wide range of applications for m...
详细信息
Controls, especially effficiency controls on dynamical processes, have become major challenges in many complex systems. We study an important dynamical process, random walk, due to its wide range of applications for modeling the transporting or searching process. For lack of control methods for random walks in various structures, a control technique is presented for a class of weighted treelike scale-free networks with a deep trap at a hub node. The weighted networks are obtained from original models by introducing a weight parameter. We compute analytically the mean first passage time (MFPT) as an indicator for quantitatively measurinM the et^ciency of the random walk process. The results show that the MFPT increases exponentially with the network size, and the exponent varies with the weight parameter. The MFPT, therefore, can be controlled by the weight parameter to behave superlinearly, linearly, or sublinearly with the system size. This work provides further useful insights into controllinM eftlciency in scale-free complex networks.
The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a ver...
详细信息
The performance of a machine translation system heavily depends on the quantity and quality of the bilingual language resource. However,getting a parallel corpus,which has a large scale and is of high quality,is a very difficult task especially for low resource languages such as Chinese-Vietnamese. Fortunately,multilingual user generated contents( UGC),such as bilingual movie subtitles,provide us access to automatic construction of the parallel corpus. Although the amount of UGC parallel corpora can be considerable,the original corpus is not suitable for statistical machine translation( SMT) systems. The corpus may contain translation errors,sentence mismatching,free translations,etc. To improve the quality of the bilingual corpus for SMT systems,three filtering methods are proposed: sentence length difference,the semantic of sentence pairs,and machine learning. Experiments are conducted on the Chinese to Vietnamese translation *** results demonstrate that all the three methods effectively improve the corpus quality,and the machine translation performance( BLEU score) can be improved by 1. 32.
Many recent state-of-the-art image retrieval approaches are based on Bag-of-Visual-Words model and represent an image with a set of visual words by quantizing local SIFT(scale invariant feature transform) features. ...
详细信息
Many recent state-of-the-art image retrieval approaches are based on Bag-of-Visual-Words model and represent an image with a set of visual words by quantizing local SIFT(scale invariant feature transform) features. Feature quantization reduces the discriminative power of local features and unavoidably causes many false local matches between images, which degrades the retrieval accuracy. To filter those false matches, geometric context among visual words has been popularly explored for the verification of geometric consistency. However, existing studies with global or local geometric verification are either computationally expensive or achieve limited accuracy. To address this issue, in this paper, we focus on partialduplicate Web image retrieval, and propose a scheme to encode the spatial context for visual matching verification. An efficient affine enhancement scheme is proposed to refine the verification results. Experiments on partial-duplicate Web image search, using a database of one million images, demonstrate the effectiveness and efficiency of the proposed *** on a 10-million image database further reveals the scalability of our approach.
Optimal location query in road networks is a basic operation in the location intelligence *** a set of clients and servers on a road network,the purpose of optimal location query is to obtain a location for a new serv...
详细信息
Optimal location query in road networks is a basic operation in the location intelligence *** a set of clients and servers on a road network,the purpose of optimal location query is to obtain a location for a new server,so that a certain objective function calculated based on the locations of clients and servers is *** works assume no labels for servers and that a client only visits the nearest *** assumptions are not realistic and it renders the existing work not useful in many *** this paper,we relax these assumptions and consider the k nearest neighbours(KNN)of *** introduce the problem of KNN-based optimal location query(KOLQ)which considers the k nearest servers of clients and labeled *** also introduce a variant problem called relocation KOLQ(RKOLQ)which aims at relocating an existing server to an optimal *** main analysis algorithms are proposed for these *** experiments on the real road networks illustrate the efficiency of our proposed solutions.
Now object detection based on deep learning tries different *** uses fewer data training networks to achieve the effect of large dataset ***,the existing methods usually do not achieve the balance between network para...
详细信息
Now object detection based on deep learning tries different *** uses fewer data training networks to achieve the effect of large dataset ***,the existing methods usually do not achieve the balance between network parameters and training *** makes the information provided by a small amount of picture data insufficient to optimize model parameters,resulting in unsatisfactory detection *** improve the accuracy of few shot object detection,this paper proposes a network based on the transformer and high-resolution feature extraction(THR).High-resolution feature extractionmaintains the resolution representation of the *** and spatial attention are used to make the network focus on features that are more useful to the *** addition,the recently popular transformer is used to fuse the features of the existing *** compensates for the previous network failure by making full use of existing object *** on the Pascal VOC and MS-COCO datasets prove that the THR network has achieved better results than previous mainstream few shot object detection.
It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are critic...
详细信息
It has been widely recognized that the efficient training of neural networks (NNs) is crucial to classification performance. While a series of gradient-based approaches have been extensively developed, they are criticized for the ease of trapping into local optima and sensitivity to hyperparameters. Due to the high robustness and wide applicability, evolutionary algorithms (EAs) have been regarded as a promising alternative for training NNs in recent years. However, EAs suffer from the curse of dimensionality and are inefficient in training deep NNs (DNNs). By inheriting the advantages of both the gradient-based approaches and EAs, this article proposes a gradient-guided evolutionary approach to train DNNs. The proposed approach suggests a novel genetic operator to optimize the weights in the search space, where the search direction is determined by the gradient of weights. Moreover, the network sparsity is considered in the proposed approach, which highly reduces the network complexity and alleviates overfitting. Experimental results on single-layer NNs, deep-layer NNs, recurrent NNs, and convolutional NNs (CNNs) demonstrate the effectiveness of the proposed approach. In short, this work not only introduces a novel approach for training DNNs but also enhances the performance of EAs in solving large-scale optimization problems.
This paper addressed the problem of Out-Of-Vocabulary (OOV) utterance detection in small vocabulary telephone keyword spotting system. We propose a new approach for modeling OOV words in the scenario of a small vocabu...
详细信息
ISBN:
(纸本)7801501144
This paper addressed the problem of Out-Of-Vocabulary (OOV) utterance detection in small vocabulary telephone keyword spotting system. We propose a new approach for modeling OOV words in the scenario of a small vocabulary of telephone keyword spotting system. The paper adopt the semi-continuous Hidden Markov Model with multiple codebooks to modeling the keywords. We propose a two pass procedure to spot the real keyword occurrence. In the first pass, the normal viterbi search procedure is applied, with the appropriate defined and trained garbage models and silence models. The output of this stage produces the N-best word hypothesis The second pass, which can be seen as a verification procedure, take the first pass output as focuses. This approach is mainly constructing a "dynamic anti-model" based on the detected hypothesis keyword model and the current input acoustic information.
Nowadays, cloud providers of 'Infrastructure as a service' require datacenter networks to support virtualization and multi-tenancy at large scale, while it brings a grand challenge to datacenters. Traditional ...
详细信息
暂无评论