Multiple-kernel k-means (MKKM) clustering has demonstrated good clustering performance by combining pre-specified kernels. In this paper, we argue that deep relationships within data and the complementary information ...
详细信息
ISBN:
(纸本)9781509006212
Multiple-kernel k-means (MKKM) clustering has demonstrated good clustering performance by combining pre-specified kernels. In this paper, we argue that deep relationships within data and the complementary information among them can improve the performance of MKKM. To illustrate this idea, we propose a diversity-induced MKKM algorithm with extreme learning machine (ELM)-based feature extracting method. First, ELM, which has randomly chosen weights of hidden and output nodes, is applied to thoroughly extract features from data by generating different numbers of hidden nodes and using different functions. Second, an MKKM algorithm with diversity-induced regularization is utilized to explore the complementary information among kernels constructed from features. The problem could be solved efficiently by alternating optimization. Experimental results demonstrate that the proposed method outperforms state-of-the-art kernel methods.
The global open source software resources have become an Internet-scale repository,which provide abundant resources for software ***,how to locate the desired resource efficiently and accurately from such large amount...
详细信息
The global open source software resources have become an Internet-scale repository,which provide abundant resources for software ***,how to locate the desired resource efficiently and accurately from such large amounts is quite a challenge *** of recent works barely focus on the semantic similarity by analyzing the software itself,which often result in inappropriate *** this paper,we propose Dolphin,a global OSS search engine,which leverage the crowd discussions around OSS across communities for optimizing software *** employs the crowd wisdom as an important factor and combines it with the semantic similarity to optimize search results *** implement an OSS search engine based on the proposed approach,which provides online service *** experiments and user studies suggest the effectiveness of our approach.
Data distribution is the basic behavior of P2 P applications(file sharing and streaming service) and it is a key element affecting the performance of P2 P systems. However, there are few research works that focus on d...
详细信息
ISBN:
(纸本)9783037851555
Data distribution is the basic behavior of P2 P applications(file sharing and streaming service) and it is a key element affecting the performance of P2 P systems. However, there are few research works that focus on data distribution of P2 P applications from the view of whole system. In this paper we study the data distribution in P2 P applications in terms of decreasing the system distribution load. We define the distribution load of P2 P systems formally and analyze how to decrease the system load quickly by means of mathematical analysis. Moreover, we give a feasible fast distribution algorithm according to our theoretic conclusion. The experimental results show that our algorithm has significant improvement on data distribution speed and load balance.
Build system,which can convert source codes into applications,is essential for the development of *** general build systems that relying on single physical or cloud host to run bring problems such as system security,r...
详细信息
Build system,which can convert source codes into applications,is essential for the development of *** general build systems that relying on single physical or cloud host to run bring problems such as system security,resource shortage,overload,and low availability in the face of massive build *** modularizing and streamlining the steps during a build process,this paper proposes a system that introduces container technology and then builds a large-scale,real-time,and huge-concurrency supported build system based on Kubernetes[1].The system provides a highly scalable and feature-stable cloud architecture that supports huge concurrency with lower resource ***,the system controls programs' behaviors very well to avoid potential security and resource issues and shows excellent performance in concurrency,scalability,security,and load balance even when handling a large number of build tasks.
Welcome to Zhangjiajie for the 3rd International Conference on Computer Network and Mobile Computing (ICCNMC 2005). We are currently witnessing a proliferation in mobile/wireless technologies and applications. However...
详细信息
ISBN:
(数字)9783540318682
ISBN:
(纸本)9783540281023
Welcome to Zhangjiajie for the 3rd International Conference on Computer Network and Mobile Computing (ICCNMC 2005). We are currently witnessing a proliferation in mobile/wireless technologies and applications. However, these new technologies have ushered in unprecedented challenges for the research community across the range of networking, mobile computing, network security and wireless web applications, and optical network topics. ICCNMC 2005 was sponsored by the China Computer Federation, in cooperation with the Institute for Electrical and Electronics Engineers (IEEE) Computer Society. The objective of this conference was to address and capture highly innovative and stateof-the-art research and work in the networks and mobile computing industries. ICCNMC 2005 allowed sharing of the underlying theories and applications, and the establishment of new and long-term collaborative channels aimed at developing innovative concepts and solutions geared to future markets. The highly positive response to ICCNMC 2001 and ICCNMC 2003, held in Beijing and Shanghai, respectively, encouraged us to continue this international event. In its third year, ICCNMC 2005 continued to provide a forum for researchers, professionals, and industrial practitioners from around the world to report on new advances in computer network and mobile computing, as well as to identify issues and directions for research and development in the new era of evolving technologies.
OpenFlow switches in SDN use Multiple Flow Tables (MFTs) for fine-grained flow control. Commodity switches integrate hardware storage resources such as SRAM and TCAM to store flow tables to achieve high-speed lookups....
详细信息
RAM Grid is a novel grid system to share the distributed memory resources across the wide area network, and provides disk cache for other nodes which are short of memory. The resource information management system, wh...
详细信息
RAM Grid is a novel grid system to share the distributed memory resources across the wide area network, and provides disk cache for other nodes which are short of memory. The resource information management system, which monitors and manages the resources in grid environment, takes a key role for RAM Grid. Under the special requirements of RAM Grid, we propose a grid resources management system GridEye, the architecture and mechanism are also discussed. In order to improve the performance, a new caching strategy optimized for RAM Grid is *** have verified the effectiveness of the proposed method through analysis and experiments on the implemented prototype system.
Audio feature extraction is a very important technique in the field of sound processing. It extremely impacts the effectiveness and correctness of sound recognition, sound verification, etc. It is a computation intens...
详细信息
Audio feature extraction is a very important technique in the field of sound processing. It extremely impacts the effectiveness and correctness of sound recognition, sound verification, etc. It is a computation intensive stage in the whole sound recognition process, which is a challenging for acceleration. In this paper, a coarse-grained parallel feature extraction algorithm for high throughput of audio slices is proposed to improve the efficiency of audio feature extraction. Three typical audio feature extraction algorithms, Mel Frequency Cepstrum Coefficients(MFCC), Spectrogram image features(SIF), Octave-Based Spectral Contrast, are chosen to parallelize. Experiments results on different platforms show that the speedup of accelerated audio feature extraction is up to 17.23 on the platform with 16 cores 32 threads.
Zero pronoun resolution is very important in natural language processing. Identification of zero pronoun is the fundamental task of its resolution. Existing feature engineering based identification approaches are unsu...
详细信息
ISBN:
(纸本)9781510845541
Zero pronoun resolution is very important in natural language processing. Identification of zero pronoun is the fundamental task of its resolution. Existing feature engineering based identification approaches are unsuitable for big data applications due to labor-intensive work. Furthermore, as extracted from parse trees which are not unique for a certain sentence, features may be improper for zero pronoun identification. In this paper, we constructed a two-layer stacked bidirectional LSTM model to tackle identification of zero pronoun. To extract semantic knowledge, the first layer obtains the structure information of the sentence, and the second layer combines the part-of-speech information with obtained structure information. The results in two different kinds of experimental environment show that, our approach significantly outperforms the state-of-the-art method with an absolute improvement of 4.3% and 20.3% F-score in Onto Notes 5.0 corpus respectively.
High reliability is an essential factor of modern software. At the same time, as software complexity is increasing day by day, bug counts and rate inevitably rises, leading to undermine software reliability. To avoid ...
详细信息
ISBN:
(纸本)9781510830028
High reliability is an essential factor of modern software. At the same time, as software complexity is increasing day by day, bug counts and rate inevitably rises, leading to undermine software reliability. To avoid this problem, programmers always use issue-finding tools(bug detection) to discover the defects from source code in development of software. Recently, software inspection has been shown to be an effective way to speed up the process of source code verification and to move a portion of discovered defects from test to coding phase. As we know, modern software is often developed over many years. During this time, the commit metadata is becoming an important source of social characteristics. In this paper, our aim is to devise an empirical method to assess the percentage and the types of the issues found by issue finding tools are actual defects of the software.
暂无评论