Tinghuai Ma

Real time services for future cloud computing enabled vehicle networks

Cloud computing technique is gaining more and more popularity recently. It can be applied to the vehicle applications to ensure real time performance as well as to improve accuracy and comfort degree for drivers. In this paper, we propose our novel vehicle cloud architecture which includes device level, communication level and service level. Each of these levels is explained in further detail with flow chart and taxonomy definition. Some innovative and real time vehicle cloud services are introduced to show the wide potential applications of vehicles and some discussion about research challenges, context classification is also provided.

Review of Sensor-based Activity Recognition Systems

Abstract Activity recognition (AR) has become a hot research topic due to its strength in providing personalized sup port for many diverse applications such as healthcare and security. Due to its importance, a considerable amount of AR systems have been developed. In general, these systems utilize diverse sensors to obtain the activity related information, which are then used by machine learning techniques to infer human’s ongoing activity. According to the types of sensors used, existing AR systems can be roughly divided into two catego ries: 1. Video sensor based AR. It remotely observes human activity using video sensors; 2. Physical sensor based AR (PSAR). It attaches physical sensors to the body of human or objects (appliances) to infer human activity. Based on the location of attached sensors, PSAR consists of two subcategories: Wearable sensor based AR and object usage based AR. In this work, different types of AR are reviewed. We think this review is significant because no existing review papers include all the different types of AR as a whole. For each type of AR, its main techniques, characteristics, strengths and limitations are discussed and summarized. We also make a comparative analysis for them. Finally the main research challenges in AR are pointed out.

Grid Task Scheduling: Algorithm Review

Abstract As a new distributed heterogeneous computing platform, grid aims at achieving Internet-wide resource sharing and collaborative computing. Grid task scheduling (GTS) is the key issue of grid computing, and its algorithm has a direct effect on the performance of the whole system. In this paper, two key entities in GTS, applications and target systems, are defined first. And then two types of the most popular GTS algorithms, namely, meta-task GTS algorithm and directed acyclic graph GTS algorithm, are discussed in details in accordance with the classification of the traditional deterministic algorithm and heuristic intelligent algorithm. In addition, the comparative analysis is made among them. Finally, some main research directions of GTS are pointed out.

Resource Allocation and Scheduling in Cloud Computing: Policy and Algorithm

ABSTRACT Cloud computing is a new distributed commercial computing model that aims at providing computational resources or services to users over a network in a low-cost manner. Resource allocation and scheduling (RAS) is the key focus of cloud computing, and its policy and algorithm have a direct effect on cloud performance and cost. This paper presents five major topics in cloud computing, namely locality-aware task scheduling; reliability-aware scheduling; energy-aware RAS; Software as a Service (SaaS) layer RAS; and workflow scheduling. These five topics are then classified into three parts: performance-based RAS; cost-based RAS; and performance- and cost-based RAS. A number of existing RAS policies and algorithms are discussed in detail accordingly with regard to their given parameters. In addition, a comparative analysis of five identified problems with their representative algorithms is performed. Finally, some future research directions of cloud RAS are pointed out.

A Hybrid Evolutionary Algorithm for Numerical Optimization Problem

The hybrid artificial bee colony (ABC) algorithm with differential evolution (DE) techniques (HABCwDE) is proposed for numerical optimization in this paper. The HABCwDE adopts multiple candidate solution generation strategies (CSGSes) from DE techniques to generate new solutions in the framework of the ABC algorithm. In the HABCwDE algorithm, three CSGSes and three groups of parameter settings are employed. The performance of HABCwDE and some other evolutionary algorithms are tested on 26 state-of-the-art benchmark functions. Experimental results demonstrate that HABCwDE is very competitive, and that it is an effective way to improve the performance of ABC algorithm by employing CSGSes from DE techniques.

Detecting potential labeling errors for bioinformatics by multiple voting

Classification techniques are important in bioinformatics analysis as they can separate various bioinformatical data into distinct groups. To obtain good classifiers, accurate labeling of the training data is required. However labeling in practical bioinformatics applications might be erroneous due to various reasons. To identify those mislabeled data, an ensemble learning based scheme, single-voting has been widely used. It generates multiple classifiers and makes use of their voting to detect mislabeled data. Single-voting scheme mainly consists of two components: data partitioning component to generate multiple classifiers, and mislabeled detection component to identify mislabeled data. Existing works in this field mainly focus on mislabeled detection part and neglect data partitioning. However, our analysis shows that data partitioning plays an important role in single-voting scheme. This analysis helps us proposing a novel multiple-voting scheme. It is superior to traditional single-voting by reducing the unreliable influence from data partitioning. Empirical and theoretical evaluations on a set of bioinformatics datasets illustrate the utility of our proposed scheme.

Privacy preserving based on association rule mining

Privacy has become an important issue in Data Mining. Many methods have been brought out to solve this problem. This paper deals with the problem of association rule mining which preserves the confidentiality of each database. In order to find the association rule, each participant has to share their own data. Thus, much privacy information may be broadcast or been illegal used. These issues can be divided into two categories: data hiding and knowledge hiding. This paper reviews the major method of privacy preserving on each category and choose some of them to complete our system. At the end, an improvement of sensitive rules hiding is proposed to make it more accuracy and security.

Review on Grid Resource Discovery: Models and Strategies

Abstract As grid technique is growing rapidly in recent years, large-scale grid systems usually have the capability of providing flexible, secure, coordinated resource-sharing and problem solving among dynamic virtual organizations. Grid resource discovery (GRD) is one of the crucial issues in the whole system and the discovery models and strategies have a vital influence on the performance of grid systems. In this paper, the definition and principles of GRD are explained first. Then, several existing GRD models, namely centralized, hierarchical, Peer-to-Peer (P2P)-based, group-clustering, and semantic-based models, are introduced in detail from both system architecture and resource matching pattern aspects. In particular, the strategies to increase the searching performance in these models are presented. Moreover, trust mechanism to ensure secure communications in P2P-based GRD models is emphasized. Besides, the comparative analysis among the GRD models is made. Finally, several promising research directions of GRD are provided.

Cost-sensitive elimination of mislabeled training data

Accurately labeling training data plays a critical role in various supervised learning tasks. Since labeling in practical applications might be erroneous due to various reasons, a wide range of algorithms have been developed to eliminate mislabeled data. These algorithms may make the following two types of errors: identifying a noise-free data as mislabeled, or identifying a mislabeled data as noise free. The effects of these errors may generate different costs, depending on the training datasets and applications. However, the cost variations are usually ignored thus existing works are not optimal regarding costs. In this work, the novel problem of cost-sensitive mislabeled data filtering is studied. By wrapping a cost-minimizing procedure, we propose the prototype cost-sensitive ensemble learning based mislabeled data filtering algorithm, named CSENF. Based on CSENF, we further propose two novel algorithms: the cost-sensitive repeated majority filtering algorithm CSRMF and cost-sensitive repeated consensus filtering algorithm CSRCF. Compared to CSENF, these two algorithms could estimate the mislabeling probability of each training data more confidently. Therefore, they produce less cost compared to CSENF and cost-blind mislabeling filters. Empirical and theoretical evaluations on a set of benchmark datasets illustrate the superior performance of the proposed methods.

A survey on grid task scheduling

Grid is a new distributed heterogeneous computing platform, which attracts many researchers. The allocation of tasks to distributed resources is crucial to grid application. So, Grid Task Scheduling (GTS) becomes the key issue of grid computing, and its algorithm has a direct effect on the performance of the whole grid system. In this paper, we summarise the most popular GTS algorithms, including traditional GTS, heuristic intelligent GTS and DAG-based GTS, separately. Furthermore, the comparative analysis is made among them. Finally, some main research directs of GTS are pointed out.