Optimal positioning of read/write heads in mirrored disks

This work is concerned with finding the expected-travel-distance-minimizing anticipatory positions of disk arms in mirrored disk systems. In such systems, data is duplicated across two or more disk drives. A ‘read’ request may choose to read from any copy, and thus do so from the disk whose arm is closest to the request location. Since a ‘write’ must update all copies, the response time for such a request will depend on the distance of the arm which is furthest away from the request's location. Some problems of optimally positioning emergency service units on a line and of positioning idle elevators can be viewed mathematically as a special case of the mirrored disks scenario in which there are ‘read’ requests only. We show that, for any request location distribution, if there are more write than read requests then both arms should be located as if read requests did not exist — both at the median of the distribution. For situations where most requests are of ‘read’ type, we derive necessary conditions for optimal locations.     

A multigranularity locking model for RDF

The advent of Linked Data is spurring the deployment of applications that use the RDF data model at the information tier. In addition to querying RDF data, there is also the requirement for online updates with suitable concurrency control. Client sessions in Web applications are organized as transactions involving requests that read and write shared data. Executing concurrently, these sessions may invalidate each other’s data. This paper presents a locking model, which is a variant of multigranularity locking protocol (MGL), to address isolation between transactions that manipulate RDF data. Four “hierarchically” related granules are defined, as well as new read/write operations and their corresponding lock modes, specifically created for the RDF data model. These new operations allow greater concurrency than the classical read/write operations in relational databases. We assessed the performance of the proposed locking model through model simulation.     

Associative search in peer to peer networks: Harnessing latent semantics

The success of a P2P file-sharing network highly depends on the scalability and versatility of its search mechanism. Two particularly desirable search features are scope (ability to find infrequent items) and support for partial-match queries (queries that contain typos or include a subset of keywords). While centralized-index architectures (such as Napster) can support both these features, existing decentralized architectures seem to support at most one: prevailing unstructured P2P protocols (such as Gnutella and FastTrack) deploy a “blind” search mechanism where the set of peers probed is unrelated to the query; thus they support partial-match queries but have limited scope. On the other extreme, the recently-proposed distributed hash tables (DHTs) such as CAN and CHORD, couple index location with the item’s hash value, and thus have good scope but can not effectively support partial-match queries. Another hurdle to DHTs deployment is their tight control of the overlay structure and the information (part of the index) each peer maintains, which makes them more sensitive to failures and frequent joins and disconnects.We develop a new class of decentralized P2P architectures. Our design is based on unstructured architectures such as Gnutella and FastTrack, and retains many of their appealing properties including support for partial match queries, and relative resilience to peer failures. Yet, we obtain orders of magnitude improvement in the efficiency of locating rare items. Our approach exploits associations inherent in human selections to steer the search process to peers that are more likely to have an answer to the query. We demonstrate the potential of associative search using models, analysis, and simulations.     

WeBeVis: analyzing user web behavior through visual metaphors

Large wikis such as Wikipedia attract large numbers of editors continuously editing content. It is difficult to observe what editing activity goes on at any given moment, what editing patterns can be observed, and which are the currently active editors and articles. We introduce the design and implementation of an information visualization tool for data streams of recent changes in wikis that aims to address this difficulty. We also show examples of our visualizations from English Wikipedia, and present several patterns of editing activity that we have visually identified using our tool. We have evaluated our tool’s usability, accuracy and speed of task performance in comparison with Wikipedia’s recent changes page, and have obtained qualitative feedback from users on the pros and cons of our tool. We also present a review of the related literature.     

An Analysis of Topical Coverage of Wikipedia

Many have questioned the reliability and accuracy of Wikipedia. Here a different issue, but one closely related: how broad is the coverage of Wikipedia? Differences in the interests and attention of Wikipedia’s editors mean that some areas, in the traditional sciences, for example, are better covered than others. Two approaches to measuring this coverage are presented. The first maps the distribution of topics on Wikipedia to the distribution of books published. The second compares the distribution of topics in three established, field‐specific academic encyclopedias to the articles found in Wikipedia. Unlike the top‐down construction of traditional encyclopedias, Wikipedia’s topical coverage is driven by the interests of its users, and as a result, the reliability and completeness of Wikipedia is likely to be different depending on the subject‐area of the article.     

I/O-aware bandwidth allocation for petascale computing systems

In the Big Data era, the gap between the storage performance and an application’s I/O requirement is increasing. I/O congestion caused by concurrent storage accesses from multiple applications is inevitable and severely harms the performance. Conventional approaches either focus on optimizing an application’s access pattern individually or handle I/O requests on a low-level storage layer without any knowledge from the upper-level applications. In this paper, we present a novel I/O-aware bandwidth allocation framework to coordinate ongoing I/O requests on petascale computing systems. The motivation behind this innovation is that the resource management system has a holistic view of both the system state and jobs’ activities and can dynamically control the jobs’ status or allocate resource on the fly during their execution. We treat a job’s I/O requests as periodical sub-jobs within its lifecycle and transform the I/O congestion issue into a classical scheduling problem. Based on this model, we propose a bandwidth management mechanism as an extension to the existing scheduling system. We design several bandwidth allocation policies with different optimization objectives either on user-oriented metrics or system performance. We conduct extensive trace-based simulations using real job traces and I/O traces from a production IBM Blue Gene/Q system at Argonne National Laboratory. Experimental results demonstrate that our new design can improve job performance by more than 30%, as well as increasing system performance.     

基于自校正分散控制的Web服务器比例延迟保证

Apache Web服务器一般采用单变量模型,处理多优先级延迟保证时需多次建模,可扩展性不佳。为此提出一种Web服务器多输入多输出(MIMO)模型,并结合分散控制理论和自校正控制(STC)理论设计分散自校正控制器。该控制器动态调节处理不同优先级请求的工作线程数目,能保证较高优先级请求更快得到处理且维持不同优先级请求的平均延迟比为设定值,模型和控制器参数根据在线辨识结果实时更新。仿真表明,过载情况下即使并发客户连接数目急剧变化,闭环系统中的服务器仍能维持较好的比例延迟保证。     

Decentralized supervisory control with conditional decisions: supervisor existence

Most of the results on decentralized supervisory control are based on supervisors that make unconditional decisions: "enable" and "disable." In this paper, we introduce and study the properties of decentralized supervisory control architectures where supervisors are allowed to make conditional decisions in addition to unconditional decisions. The conditional decisions we consider are of the form: "enable if nobody disables" and "disable if nobody enables." We characterize the notion of conditional coobservability that appears in the necessary and sufficient conditions for the existence of supervisors in the context of such control architectures. This condition relaxes the previous notions of coobservability for unconditional architectures. The key properties of conditional coobservability are studied. We develop a polynomial-time algorithm for verifying the notion of conditional coobservability. A polynomial-time method of partitioning the controllable events between "enable by default" and "disable by default" is presented.     

Multi-decision diagnosis: decentralized architectures cooperating for diagnosing the presence of faults in discrete event systems

This article deals with decentralized diagnosis, where a set of diagnosers cooperate for detecting faults in a discrete event system. We propose a new framework, called multi-decision diagnosis, whose basic principle consists in using several decentralized diagnosis architectures working in parallel. We first present a generic form of multi-decision diagnosis, where several decentralized diagnosis architectures work in parallel and combine their global decisions disjunctively or conjunctively. We then study in more detail the inference-based multi-decision diagnosis, that is, in the case where each of the decentralized architectures in parallel is based on the inference-based framework. We develop a method that checks if a given specification is diagnosable under the inference-based multi-decision architecture. We also show that with our method, the worst-case computational complexity for checking codiagnosability for our inference-based multi-decision architecture is in the same order of complexity as checking codiagnosability for the inference-based architecture designed by Kumar and Takai. In fact, multi-decision diagnosis is fundamentally undecidable and we have formulated a decidable variant of it. Multi-decision diagnosis is formally based on language decomposition, but it is worth noting that our objective is not to answer the existential question of language decomposition in the general case. Our objective is rather to propose a decentralized diagnosis architecture that generalizes the decidable existing ones.     

Comparative Analysis of Text Representation Methods Using Classification

In our work, we review and empirically evaluate five different raw methods of text representation that allow automatic processing of Wikipedia articles. The main contribution of the article—evaluation of approaches to text representation for machine learning tasks—indicates that the text representation is fundamental for achieving good categorization results. The analysis of the representation methods creates a baseline that cannot be compensated for even by sophisticated machine learning algorithms. It confirms the thesis that proper data representation is a prerequisite for achieving high-quality results of data analysis. Evaluation of the text representations was performed within the Wikipedia repository by examination of classification parameters observed during automatic reconstruction of human-made categories. For that purpose, we use a classifier based on a support vector machines method, extended with multilabel and multiclass functionalities. During classifier construction we observed parameters such as learning time, representation size, and classification quality that allow us to draw conclusions about text representations. For the experiments presented in the article, we use data sets created from Wikipedia dumps. We describe our software, called Matrix’u, which allows a user to build computational representations of Wikipedia articles. The software is the second contribution of our research, because it is a universal tool for converting Wikipedia from a human-readable form to a form that can be processed by a machine. Results generated using Matrix’u can be used in a wide range of applications that involve usage of Wikipedia data.     

Attribute-based data access control in mobile cloud computing: Taxonomy and open issues

With the thriving growth of the cloud computing, the security and privacy concerns of outsourcing data have been increasing dramatically. However, because of delegating the management of data to an untrusted cloud server in data outsourcing process, the data access control has been recognized as a challenging issue in cloud storage systems. One of the preeminent technologies to control data access in cloud computing is Attribute-based Encryption (ABE) as a cryptographic primitive, which establishes the decryption ability on the basis of a user’s attributes. This paper provides a comprehensive survey on attribute-based access control schemes and compares each scheme’s functionality and characteristic. We also present a thematic taxonomy of attribute-based approaches based on significant parameters, such as access control mode, architecture, revocation mode, revocation method, revocation issue, and revocation controller. The paper reviews the state-of-the-art ABE methods and categorizes them into three main classes, such as centralized, decentralized, and hierarchal, based on their architectures. We also analyzed the different ABE techniques to ascertain the advantages and disadvantages, the significance and requirements, and identifies the research gaps. Finally, the paper presents open issues and challenges for further investigations.     

Automatic acquisition of a taxonomy of microblogs users’ interests

Modeling users’ interests plays an important role in the current web since it is at the basis of many services such as recommendation and customization. Using semantic technologies to represent users’ interests may help to reduce problems such as sparsity, over-specialization and domain-dependency, which are known to be critical issues of state of the art recommenders. In this paper we present a method for high-coverage modeling of Twitter users supported by a hierarchical representation of their interests, which we call a Twixonomy. In order to automatically build a population, community, or single-user Twixonomy we first identify “topical” friends in users’ friendship lists (i.e., friends representing an interest rather than a social relation between peers). We classify as topical those users with an associated page on Wikipedia. A word-sense disambiguation algorithm is used to select the appropriate Wikipedia page for each topical friend. Next, starting from the set of wikipages representing the main topics of interests of the considered Twitter population, we extract all paths connecting these pages with topmost Wikipedia category nodes, and we then prune the resulting graph efficiently so as to induce a direct acyclic graph and significantly reduce over ambiguity, a well known problem of the Wikipedia category graph. We release the Twixonomy produced in this work under creative common license.     

Hybrid simulation models for spare parts supply chain considering 3D printing capabilities

In the era of Industry 4.0, 3D printing unlocks a wide array of solutions to rapidly-produce spare parts for maintenance operations. In this research, we propose a hybrid simulation approach, combining agent-based and discrete event simulation methods, to investigate how the adoption of 3D printing technologies to manufacture spare parts for maintenance operations will improve operational efficiency and effectiveness. Specifically, our framework is applied to the United States Navy’s fighter jet maintenance operations to study various network configurations, where 3D printing facilities may be centralized, decentralized, or hub configured. System performance in terms of the total cost, timeliness of delivery, and vulnerability under disruptions such as cyber-attacks and emergencies are evaluated. Lastly, the impact of 3D printing technological advancements on operational performance is investigated to obtain managerial insights.     

一种基于维基百科的中文词语相关度学习算法

词语相关程度计算是语义计算的基础。维基百科是目前最大、更新最快的在线开放式百科全书,涵盖概念广,概念解释详细,蕴含了大量概念间关联关系,为语义计算提供了丰富的背景知识。然而,中文维基百科中存在严重的数据稀疏问题,降低了中文词语相关度计算方法的有效性。针对这一问题,该文利用机器学习技术,提出一种新的基于多种维基资源的词语相关度学习算法。在三个标准数据集上的实验结果验证了新算法的有效性,在已知最好结果的基础上提升了20%—40%。
     

The Descent of Pluto: Interactive dynamics,specialisation and reciprocity of roles in a Wikipedia debate

This research focuses on analysing collective activity in Wikipedia, conceptualised as an Online Epistemic Community (“OEC”). Previous research on Wikipedia has shown that widespread participation, coupled with the principle of neutrality of viewpoint, has led to ‘editing wars’ and associated high coordination costs. The question that we address is therefore that of how to analyse the interactive dynamics of conflictual OEC discussions. To address this issue, we performed a longitudinal analysis of a specific case-study within the French-speaking “astronomy” Wikipedia OEC, revolving around the renaming of the article on the celestial body “Pluto”, given the ‘descent’ of its scientific status from that of a planet to an asteroid. Our choice was to focus on the analysis of dialogic and epistemic roles, as an appropriate meso-level unit of analysis. We present a qualitative-quantitative method for analysis of roles, based on filtering major participants and analysing the dialogic functions and epistemic contents of their communicative acts. Our analyses showed that online epistemic communities can be communities in the true sense of their involving cooperation, in that roles become gradually specialised and reciprocal over sequences of the discussion: when one participant changes role from one sequence to another, other participants ‘fill in’ for the vacant role. Secondly, we show that OECs, in the case of Wikipedia, do not function purely on a knowledge-level, but also involve, crucially, negotiation of images of participants’ competences with respect to the knowledge domain. In that sense, OECs can be seen as socio-cognitive communities. The originality of our research resides in the qualitative-quantitative method for analysing interactive roles, and the results of its application to an extended longitudinal case study.     

A Wikipedia Matching Approach to Contextual Advertising

Contextual advertising is an important part of today’s Web. It provides benefits to all parties: Web site owners and an advertising platform share the revenue, advertisers receive new customers, and Web site visitors get useful reference links. The relevance of selected ads for a Web page is essential for the whole system to work. Problems such as homonymy and polysemy, low intersection of keywords and context mismatch can lead to the selection of irrelevant ads. Therefore, a simple keyword matching technique gives a poor accuracy. In this paper, we propose a method for improving the relevance of contextual ads. We propose a novel “Wikipedia matching” technique that uses Wikipedia articles as “reference points” for ads selection. We show how to combine our new method with existing solutions in order to increase the overall performance. An experimental evaluation based on a set of real ads and a set of pages from news Web sites is conducted. Test results show that our proposed method performs better than existing matching strategies and using the Wikipedia matching in combination with existing approaches provides up to 50% lift in the average precision. TREC standard measure bpref-10 also confirms the positive effect of using Wikipedia matching for the effective ads selection.     

Performance characterization of multi-thread and multi-core processors based XML application oriented networking systems

There is a growing trend to insert application intelligence into network devices. Processors in this type of Application Oriented Networking (AON) devices are required to handle both packet-level network I/O intensive operations as well as XML message-level CPU intensive operations. In this paper, we investigate the performance effect of symmetric multi-processing (SMP) via (1) hardware multi-threading, (2) uni-processor to dual-processor architectures, and (3) single to dual and quad core processing, on both packet-level and XML message-level traffic. We use AON systems based on Intel Xeon processors with hyperthreading, Pentium M based dual-core processors, and Intel’s dual quad-core Xeon E5335 processors. We analyze and cross-examine the SMP effect from both highlevel performance as well as processor microarchitectural perspectives. The evaluation results will not only provide insight to microprocessor designers, but also help system architects of AON types of device to select the right processors.     

Efficient computation of distance labeling for decremental updates in large dynamic graphs

Since today’s real-world graphs, such as social network graphs, are evolving all the time, it is of great importance to perform graph computations and analysis in these dynamic graphs. Due to the fact that many applications such as social network link analysis with the existence of inactive users need to handle failed links or nodes, decremental computation and maintenance for graphs is considered a challenging problem. Shortest path computation is one of the most fundamental operations for managing and analyzing large graphs. A number of indexing methods have been proposed to answer distance queries in static graphs. Unfortunately, there is little work on answering such queries for dynamic graphs. In this paper, we focus on the problem of computing the shortest path distance in dynamic graphs, particularly on decremental updates (i.e., edge deletions). We propose maintenance algorithms based on distance labeling, which can handle decremental updates efficiently. By exploiting properties of distance labeling in original graphs, we are able to efficiently maintain distance labeling for new graphs. We experimentally evaluate our algorithms using eleven real-world large graphs and confirm the effectiveness and efficiency of our approach. More specifically, our method can speed up index re-computation by up to an order of magnitude compared with the state-of-the-art method, Pruned Landmark Labeling (PLL).     

Performance vs. cost of redundant arrays of inexpensive disks

Data redundancy has been widely used to increase data availability in critical applications and several methods have been proposed to organize redundant data across a disk array. Data redundancy consists of either total data replication or the spreading of the data across the disk array along with parity information which can be used to recover missing data in the event of disk failure. In this paper we present an extended comparative analysis, carried out by using discrete event simulation models, between two disk array architectures: the Redundant Arrays of Inexpensive Disks (RAID) level 1 architecture, based on data replication; and the RAID level 5 architecture, based on the use of parity information. The comparison takes both performance and cost aspects into account. We study the performance of these architectures simulating two application environments characterized by different sizes of the data accessed by I/O operations. In addition, several scheduling policies for I/O requests are considered and the impact of non-uniform access to data on performance is investigated.