An efficient hyperellipsoidal clustering algorithm for resource-constrained environments

Clustering has been widely used as a fundamental data mining tool for the automated analysis of complex datasets. There has been a growing need for the use of clustering algorithms in embedded systems with restricted computational capabilities, such as wireless sensor nodes, in order to support automated knowledge extraction from such systems. Although there has been considerable research on clustering algorithms, many of the proposed methods are computationally expensive. We propose a robust clustering algorithm with low computational complexity, suitable for computationally constrained environments. Our evaluation using both synthetic and real-life datasets demonstrates lower computational complexity and comparable accuracy of our approach compared to a range of existing methods.     

Scheduling for heterogeneous systems in accelerator-rich environments

The Journal of Supercomputing - The world is creating ever more data and the applications are required to deal with ever-increasing datasets. To process such datasets heterogeneous and manycore...     

Security monitoring in heterogeneous globally distributed environments

Keeping control of a highly heterogeneous network of distributed systems in any global company is a difficult task. This problem cannot be brought under control with any single approach or technology. We must focus on the objectives and build tools into a common integrated framework to provide a security state and event monitoring concept for the entire organisation.     

Video mosaics for virtual environments

As computer-based video becomes ubiquitous with the expansion of transmission, storage, and manipulation capabilities, it will offer a rich source of imagery for computer graphics applications. This article looks at one way to use video as a new source of high-resolution, photorealistic imagery for these applications. If you walked through an environment, such as a building interior, and filmed a video sequence of what you saw you could subsequently register and composite the video images together into large mosaics of the scene. In this way, you can achieve an essentially unlimited resolution. Furthermore, since you can acquire the images using any optical technology, you can reconstruct any scene regardless of its range or scale. Video mosaics can be used in many different applications, including the creation of virtual reality environments, computer-game settings, and movie special effects. I present algorithms that align images and composite scenes of increasing complexity-beginning with simple planar scenes and progressing to panoramic scenes and, finally, to scenes with depth variation. I begin with a review of basic imaging equations and conclude with some novel applications of the virtual environments created using the algorithms presented     

Pipelining image compositing in heterogeneous networking environments

Because of intensive inter‐node communications, image compositing has always been a bottleneck in parallel visualization systems. In a heterogeneous networking environment, the variation of link bandwidth and latency adds more uncertainty to the system performance. In this paper, we present a pipelining image compositing algorithm in heterogeneous networking environments, which is able to rearrange the direction of data flow of a compositing pipeline under strict ordering constraint. We introduce a novel directional image compositing operator that specifies not only the color and α channels of the output but also the direction of data flow when performing compositing. Based on this new operator, we thoroughly study the properties of image compositing pipelines in heterogeneous environments. We develop an optimization algorithm that could find the optimal pipeline from an exponentially large searching space in polynomial time. We conducted a comprehensive evaluation on the ns‐3 network simulator. Experimental results demonstrate the efficiency of our method. Copyright © 2016 John Wiley & Sons, Ltd.     

HAT: history-based auto-tuning MapReduce in heterogeneous environments

In MapReduce model, a job is divided into a series of map tasks and reduce tasks. The execution time of the job is prolonged by some slow tasks seriously, especially in heterogeneous environments. To finish the slow tasks as soon as possible, current MapReduce schedulers launch a backup task on other nodes for each of the slow tasks. However, traditional MapReduce schedulers cannot detect slow tasks correctly since they cannot estimate the progress of tasks accurately (Hadoop home page http://hadoop.apache.org/, 2011; Zaharia et al. in 8th USENIX symposium on operating systems design and implementation, ACM, New York, pp. 29–42, 2008). To solve this problem, this paper proposes a History-based Auto-Tuning (HAT) MapReduce scheduler, which calculates the progress of tasks accurately and adapts to the continuously varying environment automatically. HAT tunes the weight of each phase of a map task and a reduce task according to the value of them in history tasks and uses the accurate weights of the phases to calculate the progress of current tasks. Based on the accurate-calculated progress of tasks, HAT estimates the remaining time of tasks accurately and further launches backup tasks for the tasks that have the longest remaining time. Experimental results show that HAT can significantly improve the performance of MapReduce applications up to 37% compared with Hadoop and up to 16% compared with LATE scheduler.     

Trustworthy-based efficient data broadcast model for P2P interaction in resource-constrained wireless environments

In a decentralised system like P2P where each individual peers are considerably autonomous, the notion of mutual trust between peers is critical. In addition, when the environment is subject to inherent resource constraints, any efficiency efforts are essentially needed. In light of these two issues, we propose a novel trustworthy-based efficient broadcast scheme in a resource-constrained P2P environment. The trustworthiness is associated with the peer?s reputation. A peer holds a personalised view of reputation towards other peers in four categories namely SpEed, Correctness, qUality, and Risk-freE (SeCuRE). The value of each category constitutes a fraction of the reliability of individual peer. Another factor that contributes to the reliability of a peer is the peer?s credibility concerning trustworthiness in providing recommendation about other peers. Our trust management scheme is applied in conjunction with our trust model in order to detect malicious and collaborative-based malicious peers. Knowledge of trustworthiness among peers is used in our proposed broadcast model named trustworthy-based estafet multi-point relays (TEMPR). This model is designed to minimise the communication overhead between peers while considering the trustworthiness of the peers such that only trustworthy peer may relay messages to other peers. With our approach, each peer is able to disseminate messages in the most efficient and reliable manner.     

异构Hadoop环境下的实时作业调度算法

为提升Hadoop集群在异构环境下处理硬实时作业的性能,提出一种基于历史进度自动调整作业优先级的调度算法（HAPS）。该算法实时监控作业进度信息,对作业进度率进行指数平滑预测,计算作业剩余执行时间,动态估算作业空闲时间。并据此实时更新作业队列中作业的优先级顺序,优先调度空闲时间小的作业。实验结果表明,HAPS有效地提高了异构环境下硬实时作业的执行成功率。     

A packaging system for heterogeneous execution environments

A packaging system that allows diverse software components to be easily interconnected within heterogeneous programming environments is described. Interface software and stubs are generated for programmers automatically once the programmers express their application's geometry in a few simple rules and module interconnection language attributes. By generating custom interface code for each application, based on analysis and extraction of interfacing requirements, the system is able to produce executables whose run-time performance is comparable to manually integrated applications. The system is implemented within the Unix environment     

Adaptive interactions in shared virtual environments for heterogeneous devices

In this research, we propose a method to adapt the interfaces and interaction processes of heterogeneous devices. The proposed method models the interaction capability of the devices. The interaction is modeled by categorizing elementary actions and measuring its effect in semantic behaviors. With this model, an interaction process can be modified to a given device by changing sequence of elementary actions for each behavior. In the pilot test, we showed the possibility of interaction adaptation for different situations. With the proposed adaptation mechanism, interface and interaction can be modeled for the device independently and can be transferred over different interaction environments. Copyright © 2010 John Wiley & Sons, Ltd.     

Time-bounded distributed QoS-aware service configuration in heterogeneous cooperative environments

The scarcity and diversity of resources among the devices of heterogeneous computing environments may affect their ability to execute services within the users’ requested Quality of Service levels, particularly in open real-time environments where the characteristics of the computational load cannot always be predicted in advance but, nevertheless, response to events still has to be provided within precise timing constraints in order to guarantee a desired level of performance.     

Using virtual reality environments to unveil the imageability of the city in homogenous and heterogeneous environments

The presented work explores the way the information conveyed by the morphology of urban artifacts affects the way we perceive the built environment. The above exploration is implemented by means of Virtual Reality Environments we have specifically developed for this purpose. We compare heterogeneous environments characterized by a heavy tailed distribution with homogeneous environments that are characterized by normal distribution and show that the former provide higher level of information and thus better imageability than the latter.     

A framework for partitioning parallel computations in heterogeneous environments

In the paper we present a framework for partitioning data parallel computations across a heterogeneous metasystem at runtime. The framework is guided by program and resource information which is made available to the system. Three difficult problems are handled by the framework: processor selection, task placement and heterogeneous data domain decomposition. Solving each of these problems contributes to reduced elapsed time. In particular, processor selection determines the best grain size at which to run the computation, task placement reduces communication cost, and data domain decomposition achieves processor load balance. We present results which indicate that excellent performance is achievable using the framework. The paper extends our earlier work on partitioning data parallel computations across a single-level network of heterogeneous workstations.     

A biologically inspired multimedia content repurposing system in heterogeneous environments

The application of biologically inspired algorithms to multimedia repurposing systems in heterogeneous network environments is gaining importance due to its ability to adapt and customize multimedia content to frequently changing network environments. This paper presents a biologically inspired proxy-based multimedia content adaptation system, which is used to repurpose multimedia content dynamically for the transmission over heterogeneous networks and end devices. We use a series of repurposing proxies’ services in a chain fashion between the sender and multiple end devices. In order to find the appropriate chain of repurposing services that satisfy the Quality of Experience (QoE) requirements, the proposed service selection algorithm uses the ant colony metaphor. During the communication session, the algorithm uses biological foraging behavior inspired from ant agents to find optimal service paths between the media sender and the destination. Experimental results demonstrate that the proposed algorithm provides significant performance gain over traditional, state of the art selection algorithms and saves the average delay.     

Experimenting with IDA* search algorithm in heterogeneous pervasive environments

Today, mobile and smart phones are often viewed as enablers of pervasive computing systems because they provide anytime and anywhere access to information services and computational resources. However, mobile devices are inherently constrained in their computational power and battery capacity making them mere “dumb terminals” connected to a resource-rich pervasive environment. If they are ever to play a more prominent role as true elements of a pervasive environment, mobile devices must be able to embed more application logic and delegate processing requests to pervasive infrastructure. In this paper we discuss distribution and offloading of computationally intensive tasks in pervasive environments populated by mobile devices. This approach is illustrated by experimenting with a distributed version of iterative deepening A* search algorithm. In our approach, the solution space of a problem being solved is partitioned and distributed among heterogeneous mobile devices, which yields a significant increase in the time of finding an optimal solution. Distributed IDA* search algorithm does not require any coordination or communication between mobile devices, but added inter-processor communication through shared memory further increases the efficiency of the algorithm. This paper presents the results of our experiments with the algorithm and discusses a number of issues related to its implementation.     

Challenges, approaches and architecture for distributed process integration in heterogeneous environments

Integration and coordination of distributed processes remains a central challenge of construction information technology research. Extant technologies, while capable, are not yet scalable enough to enable rapid customization and instantiation for specific projects. Specifically, the heterogeneity of existing legacy sources together with firms’ range of approaches to process management makes deployment of integrated information technologies impractical. This paper reports on an architecture for distributed process integration named process connectors that addresses heterogeneity in a scalable manner. The process connectors architecture incorporates two key approaches that address heterogeneity over varying time scales. The SEEK: Scalable Extraction of Enterprise Knowledge toolkit is reviewed as a mechanism to discover semantically heterogeneous source data. The SEEK approach complements existing data integration methods for persistent sharing of information. To make use of shared data on a per project basis, a schedule mapping approach is presented that integrates firms’ diverse individual schedules in a unified representation. The schedule mapping approach allows integration of process views that have different levels of detail, while allowing participants to maintain their own view of the process. Collectively, SEEK and the schedule mapping approach facilitate a broad range of analyses to support coordination of distributed schedules. While this paper focuses primarily on schedule process integration, the process connectors architecture is viewed as providing a broad solution to discovery and integration of firms’ process data.     

A physical model-based analysis of heterogeneous environments usingsonar-ENDURA method

A physical model-based analysis of unstructured environments is presented using sonar as a sensing device. Previous methods have relied only on time-of-flight (TOF) methods and have examined only homogenous environments consisting of either smooth or rough surfaces. In this paper, a forward model for the reflection from a class of surfaces with varying degrees of roughness is presented based on the Kirchhoff approximation method. This model integrates different types of environments into a single analytical framework. The echo intensity is parametrized in terms of its energy content and duration, which are functions of the surface roughness, distance, and orientation. The echo-energy and echo-duration maps are introduced to display these parameters. A systematic and robust procedure (ENDURA method) is presented to analyze the reflections and to differentiate and localize the reflecting surfaces. The methodology is verified with experimental results obtained in our laboratory. The results indicate a significant improvement over conventional TOF systems     

Dynamic proxy-assisted scalable broadcasting of videos for heterogeneous environments

Periodic broadcasting (PB) is a scalable technique for providing video-on-demand services. It significantly reduces server I/O and backbone network bandwidth requirements at the expense of high storage space and high network bandwidth requirements for clients. Traditional protocols assume homogeneous clients with identical resources. Unfortunately, in practice clients have very different bandwidths, and these are usually insufficient to provide video-on-demand (VoD) service from a PB server. Existing work on heterogeneous clients has focused on devising broadcast schedules to cater to low-bandwidth clients, which inevitably requires an extra backbone network bandwidth between the server and the clients. In our previous work, we proposed to use proxies residing at the edge of backbone network to accommodate low bandwidth clients for PB-based VoD services. The server broadcasts a video using a PB protocol while the proxy receives and stores the data in its local buffer and broadcasts the stored data to the clients in its local network. It significantly reduces the waiting time of low-bandwidth clients without requiring any extra backbone bandwidth by using a proxy buffer and channels. However, although lots of PB protocols have been proposed, the scheme can be applied only to some old PB protocols based on a pyramid protocol. In this paper, we propose a proxy-assisted PB system that can be generally applied to almost all the existing PB protocols, by dynamically managing buffer space and channels in proxy servers. Thus, with our proposed system, PB VoD system can be optimized in terms of the resource usages in backbone networks, proxy servers, and clients, by adopting more suitable PB protocols.