Social networking has recently flourished in popularity through the use of social websites. Pervasive computing resources have allowed people stay well-connected to each other through access to social networking resou...
详细信息
Google's famous PageRank algorithm is widely used to determine the importance of web pages in search engines. Given the large number of web pages on theWorld Wide web, efficient computation of PageRank becomes a c...
详细信息
In the paper, we classify cancer with the Leukemia cancer of medical diagnostic data. information gain has been adapted for feature selections. A Leukemia cnacer model that utilizes information Gain based on Support V...
详细信息
GPUs are many-core processors with tremendous computational power. However, as automatic parallelization has not been realized yet, developing high-performance parallel code for GPUs is still very challenging. The pap...
详细信息
Randí et al. proposed a significant graphical representation for DNA sequences, which is very compact and avoids loss of information. In this paper, we build a fast algorithm for this graphical representation wit...
详细信息
Hot trace building plays an important role in enhancing the performance of dynamic binary translators, since in most cases 10% of code takes 90% of execution time of the whole program. Hot traces can promote the code ...
详细信息
Pervasive computing systems are begging for programming models and methodologies specifically suited to the particular cyber-physical nature of these systems. Reactive (rule-based) programming is an attractive model t...
详细信息
Pervasive computing systems are begging for programming models and methodologies specifically suited to the particular cyber-physical nature of these systems. Reactive (rule-based) programming is an attractive model to use due to its built-in safety features and intuitive application development style. Without careful optimization however, reactive programming engines could turn into monstrous power drains of the pervasive system and its sensor network. In this paper we propose two optimizations for reactivity engines. The first, which we prove to be optimal, assumes all sensors in the space are equally important to the application. The other, which is adaptive, employs and estimates a probability for each sensor based on application usage. Both optimizations use a mixed push/pull approach to achieve optimal or near optimal energy efficiency. We present an experimental evaluation of the two algorithms to quantify their performance over a range of parameters.
This paper addresses issues of safety in pervasive spaces. We show how pervasive systems are different from traditional computer systems, and how their cyber-physical nature ties intimately with the users. Errors and ...
详细信息
This paper addresses issues of safety in pervasive spaces. We show how pervasive systems are different from traditional computer systems, and how their cyber-physical nature ties intimately with the users. Errors and conflicts in such space could have detrimental, dangerous or undesired effects on the user, the space, or the devices. There are no support systems or programming models conscious of the issue of safety. Unrestrained programming is the model de jour, which is inadequate. We need a programming model that encourages and obligates various roles engaged in the development of pervasive spaces to contribute to increasing safety. We propose a model that utilizes role-specific safety knowledge, and that takes advantage of the rich sensing and actuations capabilities of pervasive systems to detect and handle “conflicting contexts” and prevent or detect/avert“impermissible contexts”. We present our model and discus show it mitigates overall safety risks in presence of uncertainty due to multiple independent roles.
Utilizing virtualization technology to combine real-time operating system (RTOS) and off-the-shelf time-sharing general purpose operating system (GPOS) is attracting much more interest recently. Such combination has t...
详细信息
Google's famous PageRank algorithm is widely used to determine the importance of web pages in search engines. Given the large number of web pages on the World Wide web, efficient computation of PageRank becomes a ...
详细信息
Google's famous PageRank algorithm is widely used to determine the importance of web pages in search engines. Given the large number of web pages on the World Wide web, efficient computation of PageRank becomes a challenging problem. We accelerated the power method for computing PageRank on AMD GPUs. The core component of the power method is the Sparse Matrix-Vector Multiplication (SpMV). Its performance is largely determined by the characteristics of the sparse matrix, such as sparseness and distribution of non-zero values. Based on careful analysis on the web linkage matrices, we design a fast and scalable SpMV routine with three passes, using a modified Compressed Sparse Row format. Our PageRank computation achieves 15x speedup on a Radeon 5870 Graphic Card compared with a PhenomII 965 CPU at 3.4GHz. Our method can easily adapt to large scale data sets. We also compare the performance of the same method on the OpenCL platform with our low-level implementation.
暂无评论