Sensor networks employed by scientific applications oftenneed to support localized collaboration of sensor nodes to perform in-network data processing. This includes new quantitative synthesis andhypothesis testing in...
详细信息
ISBN:
(纸本)9783540898931
Sensor networks employed by scientific applications oftenneed to support localized collaboration of sensor nodes to perform in-network data processing. This includes new quantitative synthesis andhypothesis testing in near real time, as data streaming from distributedinstruments, to transform raw data into high level domain-dependent information. This paper investigates in-network data processing mechanismswith dynamic data requirements in resource constrained heterogeneoussensor networks. Particularly, we explore how the temporaland spatial correlation of sensor measurements can be used to trade offbetween the complexity of coordination among sensor clusters and thesavings that result from having fewer sensors involved in in-network processing,while maintaining an acceptable error threshold. Experimentalresults show that the proposed in-network mechanisms can facilitate theefficient usage of resources and satisfy data requirement in the presenceof dynamics and uncertainty.
Target tracking and localization are important applications in camera sensor networks. Although coverage is a very important research topic in wireless sensor networks, and the coverage problem for target detection ha...
详细信息
This paper presents an integrated decision support system for an automated melanoma recognition of dermoscopic images based on multiple expert fusion. In this context, the ultimate aim is to support decision making by...
详细信息
This paper presents an integrated decision support system for an automated melanoma recognition of dermoscopic images based on multiple expert fusion. In this context, the ultimate aim is to support decision making by predicting image categories (e.g., melanoma, benign and dysplastic nevi) by combining outputs from different classifiers. A fast and automatic segmentation method to detect the lesion from the background healthy skin is proposed and lesion-specific local color and texture-related features are extracted. For the classification, combining experts which are classifiers with different structures, are examined as alternative solution instead of an individual classifier. In this approach, probabilistic outputs of the experts are combined based on the combination rules that are derived by following Bayespsila theorem. The category label with the highest confidence score is considered to be the class of a test image. Experimental results on a collection of 358 dermoscopic images demonstrate the effectiveness of the proposed expert fusion-based approach.
A content delivery network (CDN) is expected to provide high performance content delivery, which requires scalable infrastructure to achieve global coverage. The provision of such infrastructure may form a substantial...
详细信息
A content delivery network (CDN) is expected to provide high performance content delivery, which requires scalable infrastructure to achieve global coverage. The provision of such infrastructure may form a substantial entry barrier for new CDN providers, as well as affecting commercial viability of the existing ones. Peering of CDNs can be a way to allow dynamic infrastructural cooperation between CDNs in a scalable manner, in order to mitigate the impact of flash crowds and to achieve better overall service times. In this paper, we present a quality of service (QoS)-driven model to evaluate the user perceived performance of CDN peering relationships. In this model, an overloaded CDN redirects a fraction of its incoming requests to peered CDNs and thereby can avoid the impact of flash crowds. The model-based approach also assists in making concrete QoS guarantee for a given CDN. Our approach endeavors to achieve scalability for a CDN in a user transparent manner.
We model the Sum and Product Riddle inpublic announcement logic, which is interpreted on an epistemic Kripke model. The model is symbolically represented as a finite state program with n agents. A model checking metho...
详细信息
Framework-based software development has been proven a useful technique to develop an application. However, the development of a large application framework itself is considered complex. There are two major causes for...
详细信息
Framework-based software development has been proven a useful technique to develop an application. However, the development of a large application framework itself is considered complex. There are two major causes for this problem, the size of a framework and the vague framework requirements. The idea of framelet a small but complete framework, can be applied to solve the former. The framelet-based approach for framework development (FAFD) has been proposed to address the later. There are some improvements in term of use case requirements description to the approach after it was first presented. This paper aims to report such improvements as well as the ongoing researches on the FAFD.
Component-based softwareengineering (CBSE) is becoming popular due to the benefits of software reuse and the availability of many alternatives of reusable components. By reusing existing software components that have...
详细信息
Component-based softwareengineering (CBSE) is becoming popular due to the benefits of software reuse and the availability of many alternatives of reusable components. By reusing existing software components that have already been tested, software engineers may reduce errors and shorten the time to market the system under development. However, software engineers still have a problem in selecting the existing reusable components as well as difficulties in determining the quality of the developed components for future reuse. Therefore, an appropriate component evaluation framework is extremely needed to harvest the full benefits of software reuse. In this paper, we present the comparative evaluation of the state-of-the-art component evaluation approaches with an emphasize on reusability. The results presented in this paper are very useful in achieving the ultimate aim of our research i.e. providing a holistic component evaluation approach that may assist software engineer both in the selection of the existing reusable components and the development of new reusable components.
In complex and dynamic environments where interdependencies cannot monotonously determine causality, data mining techniques may be employed in order to analyze the problem, extract key features and identify pivotal fa...
详细信息
In complex and dynamic environments where interdependencies cannot monotonously determine causality, data mining techniques may be employed in order to analyze the problem, extract key features and identify pivotal factors. Typical cases of such complexity and dynamicity are supply chain networks, where a number of involved stakeholders struggle towards their own benefit. These stakeholders may be agents with varying degrees of autonomy and intelligence, in a constant effort to establish beneficiary contracts and maximize own revenue. In this paper, we illustrate the benefits of data mining analysis on a well-established agent supply chain management network. We apply data mining techniques, both at a macro and micro level, analyze the results and discuss them in the context of agent performance improvement.
The process of evaluating, classifying, and assigning bugs to programmers is a difficult and time consuming task which greatly depends on the quality of the bug report itself. It has been shown that the quality of rep...
详细信息
The process of evaluating, classifying, and assigning bugs to programmers is a difficult and time consuming task which greatly depends on the quality of the bug report itself. It has been shown that the quality of reports originating from bug trackers or ticketing systems can vary significantly. In this research, we apply information retrieval (IR) and natural language processing (NLP) techniques for mining bug repositories. We focus particularly on measuring the quality of the free form descriptions submitted as part of bug reports used by open source bug trackers. Properties of natural language influencing the report quality are automatically identified and applied as part of a classification task. The results from the automated quality assessment are used to populate and enrich our existing softwareengineering ontology to support a further analysis of the quality and maturity of bug trackers.
Microarray technology has been increasingly used in cancer research because of its potential for measuring expression levels of thousands of genes simultaneously in tissue samples. It is used to collect the informatio...
详细信息
Microarray technology has been increasingly used in cancer research because of its potential for measuring expression levels of thousands of genes simultaneously in tissue samples. It is used to collect the information from tissue samples regarding gene expression differences that could be useful for cancer classification. However, this classification task faces many challenges due to availability of a smaller number of samples compared to the huge number of genes, and many of the genes are not relevant to the classification. It has been shown that selecting a small subset of genes can lead to an improved accuracy of the classification. Hence, this paper proposes a solution to the problem of gene selection by using a multi-objective approach in genetic algorithm. This approach is experimented on two microarray data sets such as lung cancer and mixed-lineage leukemia cancer. It obtains encouraging result on those data sets as compared with an approach that uses single objective approach.
暂无评论