2007
Conference article
Restricted
Spatio-temporal aggregations in trajectory data warehouses
Orlando S., Orsini R., Raffaetà A., Roncato A., Silvestri C.
In this paper we investigate some issues related to the design of a simple Data Warehouse (DW), storing several aggregate measures about trajectories of moving objects. First we discuss the loading phase of our DW which has to deal with overwhelming streams of trajectory observations, possibly produced at different rates, and arriving in an unpredictable and unbounded way. Then, we focus on the measure presence, the most complex measure stored in our DW. Such a measure returns the number of trajectories that lie in a spatial region during a given temporal interval. We devise a novel way to compute an approximate, but very accurate, presence aggregate function, which algebraically combines a bounded amount of measures stored in the base cells of the data cube.Source: Data Warehousing and Knowledge Discovery . 9th International Conference on Data Warehousing and Knowledge Discovery, DaWaK '07, pp. 66–77, Regensburg, Germany, 3-7 September 2007
Orlando S., Orsini R., Raffaetà A., Roncato A., Silvestri C.
In this paper we investigate some issues related to the design of a simple Data Warehouse (DW), storing several aggregate measures about trajectories of moving objects. First we discuss the loading phase of our DW which has to deal with overwhelming streams of trajectory observations, possibly produced at different rates, and arriving in an unpredictable and unbounded way. Then, we focus on the measure presence, the most complex measure stored in our DW. Such a measure returns the number of trajectories that lie in a spatial region during a given temporal interval. We devise a novel way to compute an approximate, but very accurate, presence aggregate function, which algebraically combines a bounded amount of measures stored in the base cells of the data cube.Source: Data Warehousing and Knowledge Discovery . 9th International Conference on Data Warehousing and Knowledge Discovery, DaWaK '07, pp. 66–77, Regensburg, Germany, 3-7 September 2007
See at:
www.springerlink.com 
| CNR ExploRA
2008
Conference article
Restricted
Multi-set DHT for range queries on dynamic data for grid information service
Da Costa G., Orlando S., Dikaiakos M. D.
Scalability is a fundamental problem for information systems when the amount of managed data increases. Peer to Peer systems are usually used to solve scalability problems as centralized approaches do not scale without large dedicated infrastructure. But most current Peer to Peer systems do not take into account that indexed data can be dynamic. Thus, we propose the Multi-set approach, which aims to find the best trade-off between DHT-based network and total replication. This approach is built over classical DHT Peer to Peer system. It can improve most of pure DHT Peer to Peer system by taking into account the dynamism of indexed data. Evaluation is done by modeling, simulation and experimentation on PlanetLab. The use case is an information service for Grid, where resource attributes are indexed.Source: Globe 2008 - Data Management in Grid and Peer-to-Peer Systems. First International Conference, pp. 93–104, Torino, Italia, 3 Settembre 2008
DOI: 10.1007/978-3-540-85176-9_9
Metrics:
Da Costa G., Orlando S., Dikaiakos M. D.
Scalability is a fundamental problem for information systems when the amount of managed data increases. Peer to Peer systems are usually used to solve scalability problems as centralized approaches do not scale without large dedicated infrastructure. But most current Peer to Peer systems do not take into account that indexed data can be dynamic. Thus, we propose the Multi-set approach, which aims to find the best trade-off between DHT-based network and total replication. This approach is built over classical DHT Peer to Peer system. It can improve most of pure DHT Peer to Peer system by taking into account the dynamism of indexed data. Evaluation is done by modeling, simulation and experimentation on PlanetLab. The use case is an information service for Grid, where resource attributes are indexed.Source: Globe 2008 - Data Management in Grid and Peer-to-Peer Systems. First International Conference, pp. 93–104, Torino, Italia, 3 Settembre 2008
DOI: 10.1007/978-3-540-85176-9_9
Metrics:
See at:
doi.org | link.springer.com | CNR ExploRA
2010
Contribution to conference
Open Access
Parallel and distributed data management
Sakellariou R., Orlando S., Larriba-Pey J. L., Parthasarathy S., Zeinalipour-Yazti D.
Introduction to Topic 5 of Europar 2010Source: Euro-Par 2010 - Parallel Processing. 16th International Euro-Par Conference, pp. 316–316, Ischia, Italy, 31 Agosto - 3 Settembre 2010
DOI: 10.1007/978-3-642-15277-1_30
Metrics:
Sakellariou R., Orlando S., Larriba-Pey J. L., Parthasarathy S., Zeinalipour-Yazti D.
Introduction to Topic 5 of Europar 2010Source: Euro-Par 2010 - Parallel Processing. 16th International Euro-Par Conference, pp. 316–316, Ischia, Italy, 31 Agosto - 3 Settembre 2010
DOI: 10.1007/978-3-642-15277-1_30
Metrics:
See at:
link.springer.com 
| doi.org | www.springerlink.com | CNR ExploRA
2007
Journal article
Closed Access
Approximate mining of frequent patterns on streams
Silvestri C., Orlando S.
Many critical applications, like intrusion detection or stock market analysis, require a nearly immediate result based on a continuous and infinite stream of data. In most cases finding an exact solution is not compatible with limited availability of resources and real time constraints, but an approximation of the exact result is enough for most purposes. This paper introduces a new algorithm for approximate mining of frequent itemsets from streams of transactions using a limited amount of memory. The proposed algorithm is based on the computation of frequent itemsets in recent data and an effective method for inferring the global support of previously infrequent itemsets. Both upper and lower bounds on the support of each pattern found are returned along with the interpolated support. An extensive experimental evaluation shows that AP_Stream, the proposed algorithm, yields a good approximation of the exact global result considering both the set of patterns found and their supports.Source: Intelligent data analysis 11 (2007): 49–73.
Silvestri C., Orlando S.
Many critical applications, like intrusion detection or stock market analysis, require a nearly immediate result based on a continuous and infinite stream of data. In most cases finding an exact solution is not compatible with limited availability of resources and real time constraints, but an approximation of the exact result is enough for most purposes. This paper introduces a new algorithm for approximate mining of frequent itemsets from streams of transactions using a limited amount of memory. The proposed algorithm is based on the computation of frequent itemsets in recent data and an effective method for inferring the global support of previously infrequent itemsets. Both upper and lower bounds on the support of each pattern found are returned along with the interpolated support. An extensive experimental evaluation shows that AP_Stream, the proposed algorithm, yields a good approximation of the exact global result considering both the set of patterns found and their supports.Source: Intelligent data analysis 11 (2007): 49–73.
See at:
dl.acm.org | CNR ExploRA
2007
Journal article
Restricted
The many faces of the integration of instruments and the grid
Lelli F., Frizziero E., Gulmini M., Maron G., Orlando S., Petrucci A., Squizzato S.
Current grid technologies offer unlimited computational power and storage capacity for scientific research and business activities in heterogeneous areas all over the world. Thanks to the grid, different virtual organisations can operate together in order to achieve common goals. However, concrete use cases demand a closer interaction between various types of instruments accessible from the grid on the one hand and the classical grid infrastructure, typically composed of Computing and Storage Elements, on the other. We cope with this open problem by proposing and realising the first release of the Instrument Element (IE), a new grid component that provides the computational/data grid with an abstraction of real instruments, and grid users with a more interactive interface to control them. In this paper we discuss in detail the implemented software architecture for this new component and we present concrete use cases where the IE has been successfully integrated.Source: International journal of web and grid services (Print) 3 (2007): 239–266. doi:10.1504/IJWGS.2007.014953
DOI: 10.1504/ijwgs.2007.014953
Metrics:
Lelli F., Frizziero E., Gulmini M., Maron G., Orlando S., Petrucci A., Squizzato S.
Current grid technologies offer unlimited computational power and storage capacity for scientific research and business activities in heterogeneous areas all over the world. Thanks to the grid, different virtual organisations can operate together in order to achieve common goals. However, concrete use cases demand a closer interaction between various types of instruments accessible from the grid on the one hand and the classical grid infrastructure, typically composed of Computing and Storage Elements, on the other. We cope with this open problem by proposing and realising the first release of the Instrument Element (IE), a new grid component that provides the computational/data grid with an abstraction of real instruments, and grid users with a more interactive interface to control them. In this paper we discuss in detail the implemented software architecture for this new component and we present concrete use cases where the IE has been successfully integrated.Source: International journal of web and grid services (Print) 3 (2007): 239–266. doi:10.1504/IJWGS.2007.014953
DOI: 10.1504/ijwgs.2007.014953
Metrics:
See at:
International Journal of Web and Grid Services | www.inderscience.com | CNR ExploRA
2007
Journal article
Unknown
Trajectory data warehouses: design and implementation issues
Orlando S., Orsini R., Raffaetà A., Roncato A., Silvestri C.
In this paper we investigate some issues and solutions related to the design of a Data Warehouse (DW), storing several aggregate measures about trajectories of moving objects. First we discuss the loading phase of our DW which has to deal with overwhelming streams of trajectory observations, possibly produced at different rates, and arriving in an unpredictable and unbounded way. Then, we focus on the measure presence, the most complex measure stored in our DW. Such a measure returns the number of distinct trajectories that lie in a spatial region during a given temporal interval. We devise a novel way to compute an approximate, but very accurate, presence aggregate function, which algebraically combines a bounded amount of measures stored in the base cells of the data cube. We conducted many experiments to show the effectiveness of our method to compute such an aggregate function. In addition, the feasibility of our innovative trajectory DW was validated with an implementation based on Oracle. We investigated the most challenging issues in realizing our trajectory DW using standard DW technologies: namely, the preprocessing and loading phase, and the aggregation functions to support OLAP operations.Source: Journal of computing science and engineering (Seoul) 1 (2007): 240–261.
Orlando S., Orsini R., Raffaetà A., Roncato A., Silvestri C.
In this paper we investigate some issues and solutions related to the design of a Data Warehouse (DW), storing several aggregate measures about trajectories of moving objects. First we discuss the loading phase of our DW which has to deal with overwhelming streams of trajectory observations, possibly produced at different rates, and arriving in an unpredictable and unbounded way. Then, we focus on the measure presence, the most complex measure stored in our DW. Such a measure returns the number of distinct trajectories that lie in a spatial region during a given temporal interval. We devise a novel way to compute an approximate, but very accurate, presence aggregate function, which algebraically combines a bounded amount of measures stored in the base cells of the data cube. We conducted many experiments to show the effectiveness of our method to compute such an aggregate function. In addition, the feasibility of our innovative trajectory DW was validated with an implementation based on Oracle. We investigated the most challenging issues in realizing our trajectory DW using standard DW technologies: namely, the preprocessing and loading phase, and the aggregation functions to support OLAP operations.Source: Journal of computing science and engineering (Seoul) 1 (2007): 240–261.
See at: CNR ExploRA
2007
Conference article
Unknown
Nine months in the life of EGEE: a look from the South
Da Costa G., Dikaiakos M. D., Orlando S.
Grids have emerged as wide-scale, distributed infrastructures providing enough resources for always more demanding scientific experiments. EGEE is one of the largest scientific Grids in production operation today, with over 220 sites and more than 30,000 CPU all over the world. A further evolution of EGEE needs to be based on knowledge of deficiencies and bottleneck of the current infrastructure and software. To provide this knowledge we analyzed nine months of job submissions on the South-East federation of EGEE. We provide information on how users submit their jobs: throughput, bursts, requirements, VO. We study the current behavior of EGEE middleware too, by evaluating its performance and the retry policy. We finally show that even if the middleware provides advanced functionality, most submissions are still embarrassingly parallel jobs.Source: International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, pp. 281–287, Istanbul, Turkey, 24-26 October 2007
Da Costa G., Dikaiakos M. D., Orlando S.
Grids have emerged as wide-scale, distributed infrastructures providing enough resources for always more demanding scientific experiments. EGEE is one of the largest scientific Grids in production operation today, with over 220 sites and more than 30,000 CPU all over the world. A further evolution of EGEE needs to be based on knowledge of deficiencies and bottleneck of the current infrastructure and software. To provide this knowledge we analyzed nine months of job submissions on the South-East federation of EGEE. We provide information on how users submit their jobs: throughput, bursts, requirements, VO. We study the current behavior of EGEE middleware too, by evaluating its performance and the retry policy. We finally show that even if the middleware provides advanced functionality, most submissions are still embarrassingly parallel jobs.Source: International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, pp. 281–287, Istanbul, Turkey, 24-26 October 2007
See at: CNR ExploRA
2007
Conference article
Unknown
Towards response time estimation in Web services
Lelli F., Maron G., Orlando S.
Monitor and control operations demand deep interaction between users and devices, while they require the adoption of high interoperable solutions that only SOA-based Web Services can offer. When the access is performed via Internet using Web Services calls, the remote invocation time becomes crucial in order to understand if a service can be controlled properly, or the delays introduced by the wire and the serialization/deserialization process are unacceptable. We propose methodologies, based on a 2^k factorial analysis and a Gaussian Majorization of previous service execution times, which enable the estimation of a generic remote method execution time.Source: ICWS 2007, Salt Lake City, Utah, USA, 9-13 July 2007
Lelli F., Maron G., Orlando S.
Monitor and control operations demand deep interaction between users and devices, while they require the adoption of high interoperable solutions that only SOA-based Web Services can offer. When the access is performed via Internet using Web Services calls, the remote invocation time becomes crucial in order to understand if a service can be controlled properly, or the delays introduced by the wire and the serialization/deserialization process are unacceptable. We propose methodologies, based on a 2^k factorial analysis and a Gaussian Majorization of previous service execution times, which enable the estimation of a generic remote method execution time.Source: ICWS 2007, Salt Lake City, Utah, USA, 9-13 July 2007
See at: CNR ExploRA
2007
Conference article
Restricted
Client side estimation of a remote service execution
Lelli F., Maron G., Orlando S.
Monitor and control operations demand deep interaction between users and devices, while they require the adoption of high interoperable solutions that only SOA-based Web Services can offer. When the access is performed via Internet using Web Services calls, the remote invocation time becomes crucial in order to understand if a service can be controlled properly, or the delays introduced by the wire and the serialization/deserialization process are unacceptable. We propose methodologies, based on a 2^k factorial analysis and a Gaussian Majorization of previous service execution times, which enable the estimation of a generic remote method execution time.Source: International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, pp. 295–302, Istanbul, Turkey, 24-26 October 2007
Lelli F., Maron G., Orlando S.
Monitor and control operations demand deep interaction between users and devices, while they require the adoption of high interoperable solutions that only SOA-based Web Services can offer. When the access is performed via Internet using Web Services calls, the remote invocation time becomes crucial in order to understand if a service can be controlled properly, or the delays introduced by the wire and the serialization/deserialization process are unacceptable. We propose methodologies, based on a 2^k factorial analysis and a Gaussian Majorization of previous service execution times, which enable the estimation of a generic remote method execution time.Source: International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, pp. 295–302, Istanbul, Turkey, 24-26 October 2007
See at:
ieeexplore.ieee.org | CNR ExploRA
2011
Contribution to conference
Restricted
Introduction to Topic 5: Parallel and Distributed Data Management
Orlando Salvatore, Antoniu Gabriel, Ghoting Amol, Perez Maria S.
The manipulation and handling of an ever increasing volume of data by current data-intensive applications require novel techniques for efficient data management. Despite recent advances in every aspect of data management (storage, access, querying, analysis, mining), future applications are expected to scale to even higher degrees, not only in terms of volumes of data handled but also in terms of users and resources, often making use of multiple, pre-existing autonomous, distributed or heterogeneous resources. The notion of parallelism and concurrent execution at all levels remains a key element in achieving scalability and managing efficiently such data-intensive applications, but the changing nature of the underlying environments requires new solutions to cope with such changes. In this context, this topic sought papers in all aspects of data management (including databases and data-intensive applications) that focus on some form of parallelism and concurrency. Each paper was reviewed by four reviewers and, after discussion, we were able to select four regular papers. The accepted papers address relevant issues on various topics such as effective data compression, GPU-based data indexing, distributed collaborative data filtering and parallel query processing.Source: Euro-Par 2011 Parallel Processing. 17th International Conference, Euro-Par 2011, pp. 351–352, Bordeaux, France, 29 Agosto - 2 Settembre 2011
DOI: 10.1007/978-3-642-23400-2_32
Metrics:
Orlando Salvatore, Antoniu Gabriel, Ghoting Amol, Perez Maria S.
The manipulation and handling of an ever increasing volume of data by current data-intensive applications require novel techniques for efficient data management. Despite recent advances in every aspect of data management (storage, access, querying, analysis, mining), future applications are expected to scale to even higher degrees, not only in terms of volumes of data handled but also in terms of users and resources, often making use of multiple, pre-existing autonomous, distributed or heterogeneous resources. The notion of parallelism and concurrent execution at all levels remains a key element in achieving scalability and managing efficiently such data-intensive applications, but the changing nature of the underlying environments requires new solutions to cope with such changes. In this context, this topic sought papers in all aspects of data management (including databases and data-intensive applications) that focus on some form of parallelism and concurrency. Each paper was reviewed by four reviewers and, after discussion, we were able to select four regular papers. The accepted papers address relevant issues on various topics such as effective data compression, GPU-based data indexing, distributed collaborative data filtering and parallel query processing.Source: Euro-Par 2011 Parallel Processing. 17th International Conference, Euro-Par 2011, pp. 351–352, Bordeaux, France, 29 Agosto - 2 Settembre 2011
DOI: 10.1007/978-3-642-23400-2_32
Metrics:
See at:
www.springerlink.com | CNR ExploRA
2014
Conference article
Restricted
GPU-based computing of repeated range queries over moving objects
Orlando S., Francesco L., Silvestri C., Jensen C. S.
In this paper we investigate the use of GPUs to solve a data-intensive problem that involves huge amounts of moving objects. The scenario which we focus on regards objects that continuously move in a 2D space, where a large percentage of them also issues range queries. The processing of these queries entails a large quantity of objects falling into the range queries to be returned. In order to solve this problem by maintaining a suitable throughput, we partition the time into ticks, and defer the parallel processing of all the objects events (location updates and range queries) occurring in a given tick to the next tick, thus slightly delaying the overall computation. We process in parallel all the events of each tick by adopting an hybrid approach, based on the combined use of CPU and GPU, and show the suitability of the method by discussing performance results. The exploitation of a GPU allow us to achieve a speedup of more than 20× on several datasets with respect to the best sequential algorithm solving the same problem. More importantly, we show that the adoption of new bitmap-based intermediate data structure we propose to avoid memory access contention entails a 10× speedup with respect to naive GPU based solutions. © 2014 IEEE.Source: PDP 2014 - 22nd Euromicro International Conference on Parallel, Distributed and Network-Based Processing, pp. 640–647, Torino, Italy, 12-14 February 2014
DOI: 10.1109/pdp.2014.27
Metrics:
Orlando S., Francesco L., Silvestri C., Jensen C. S.
In this paper we investigate the use of GPUs to solve a data-intensive problem that involves huge amounts of moving objects. The scenario which we focus on regards objects that continuously move in a 2D space, where a large percentage of them also issues range queries. The processing of these queries entails a large quantity of objects falling into the range queries to be returned. In order to solve this problem by maintaining a suitable throughput, we partition the time into ticks, and defer the parallel processing of all the objects events (location updates and range queries) occurring in a given tick to the next tick, thus slightly delaying the overall computation. We process in parallel all the events of each tick by adopting an hybrid approach, based on the combined use of CPU and GPU, and show the suitability of the method by discussing performance results. The exploitation of a GPU allow us to achieve a speedup of more than 20× on several datasets with respect to the best sequential algorithm solving the same problem. More importantly, we show that the adoption of new bitmap-based intermediate data structure we propose to avoid memory access contention entails a 10× speedup with respect to naive GPU based solutions. © 2014 IEEE.Source: PDP 2014 - 22nd Euromicro International Conference on Parallel, Distributed and Network-Based Processing, pp. 640–647, Torino, Italy, 12-14 February 2014
DOI: 10.1109/pdp.2014.27
Metrics:
See at:
doi.org | ieeexplore.ieee.org | PURE Aarhus University | VBN | CNR ExploRA
2007
Journal article
Open Access
Peer-to-peer systems for discovering resources in a dynamic grid
Marzolla M., Mordacchini M., Orlando S.
The convergence of the Grid and Peer-to-Peer (P2P) worlds has led to many solutions that try to efficiently solve the problem of resource discovery on Grids. Some of these solutions are extensions of P2P DHT-based networks. We believe that these systems are not flexible enough when the indexed data are very dynamic, i.e., the values of the resource attributes change very frequently over time. This is a common case for Grid metadata, like CPU loads, queue occupation, etc. Moreover, since common requests for Grid resources may be expressed as multi-attribute range queries, we think that the DHT-based P2P solutions are poorly flexible and efficient in handling them. In this paper we present two P2P systems. Both are based on Routing Indexes, which are used to efficiently route queries and update messages in the presence of highly variable data. The first system uses a tree-shaped overlay network. The second one is an evolution of the first, and is based on a two-level hierarchical network topology, where tree topologies must only be maintained at the lower level of the hierarchy, i.e., within the various node groups making up the network. The main goal of the second organization is to achieve a simpler maintenance of the overall P2P graph topology, by preserving the good properties of the tree-shaped topology. We discuss the results of extensive simulation studies aimed at assessing the performance and scalability of the proposed approaches. We also analyze how the network topologies affect the propagation of query and update messages.Source: Parallel computing 33 (2007): 339–358. doi:10.1016/j.parco.2007.02.006
DOI: 10.1016/j.parco.2007.02.006
Metrics:
Marzolla M., Mordacchini M., Orlando S.
The convergence of the Grid and Peer-to-Peer (P2P) worlds has led to many solutions that try to efficiently solve the problem of resource discovery on Grids. Some of these solutions are extensions of P2P DHT-based networks. We believe that these systems are not flexible enough when the indexed data are very dynamic, i.e., the values of the resource attributes change very frequently over time. This is a common case for Grid metadata, like CPU loads, queue occupation, etc. Moreover, since common requests for Grid resources may be expressed as multi-attribute range queries, we think that the DHT-based P2P solutions are poorly flexible and efficient in handling them. In this paper we present two P2P systems. Both are based on Routing Indexes, which are used to efficiently route queries and update messages in the presence of highly variable data. The first system uses a tree-shaped overlay network. The second one is an evolution of the first, and is based on a two-level hierarchical network topology, where tree topologies must only be maintained at the lower level of the hierarchy, i.e., within the various node groups making up the network. The main goal of the second organization is to achieve a simpler maintenance of the overall P2P graph topology, by preserving the good properties of the tree-shaped topology. We discuss the results of extensive simulation studies aimed at assessing the performance and scalability of the proposed approaches. We also analyze how the network topologies affect the propagation of query and update messages.Source: Parallel computing 33 (2007): 339–358. doi:10.1016/j.parco.2007.02.006
DOI: 10.1016/j.parco.2007.02.006
Metrics:
See at:
Parallel Computing | Parallel Computing | Archivio istituzionale della ricerca - Alma Mater Studiorum Università di Bologna | www.sciencedirect.com | CNR ExploRA
2003
Contribution to conference
Open Access
Recent Advances in Parallel Virtual Machine and Message Passing Interface
Dongarra J., Laforenza D., Orlando S.
This book constitutes the refereed proceedings of the 10th European PVM/MPI Users' Group Meeting held in Venice, Italy, in September/October 2003. The 64 revised full papers and 16 revised short papers presented together with abstracts of 8 invited contributions and 7 reviewed special track papers were carefully reviewed and selected from 115 submissions. The papers are organized in topical sections on evaluation and performance analysis; parallel algorithms using message passing; extensions, improvements, and implementations of PVM/MPI; parallel programming tools; applications in science and engineering; grid and heterogeneous computing; and numerical simulation of parallel engineering environments - ParSim 2003.DOI: 10.1007/b14070
Metrics:
Dongarra J., Laforenza D., Orlando S.
This book constitutes the refereed proceedings of the 10th European PVM/MPI Users' Group Meeting held in Venice, Italy, in September/October 2003. The 64 revised full papers and 16 revised short papers presented together with abstracts of 8 invited contributions and 7 reviewed special track papers were carefully reviewed and selected from 115 submissions. The papers are organized in topical sections on evaluation and performance analysis; parallel algorithms using message passing; extensions, improvements, and implementations of PVM/MPI; parallel programming tools; applications in science and engineering; grid and heterogeneous computing; and numerical simulation of parallel engineering environments - ParSim 2003.DOI: 10.1007/b14070
Metrics:
See at:
link.springer.com | CNR ExploRA
2005
Journal article
Unknown
Editorial activity - EUROPVM/MPI
Orlando S., Laforenza D.
Selected Papers from the EUROPVM/MPI 2003 Conference (Venice, Italy, 29 September-2 October 2003).Source: The international journal of high performance computing applications 19 (2005): 47–47.
Orlando S., Laforenza D.
Selected Papers from the EUROPVM/MPI 2003 Conference (Venice, Italy, 29 September-2 October 2003).Source: The international journal of high performance computing applications 19 (2005): 47–47.
See at: CNR ExploRA
2009
Conference article
Restricted
Mining query logs
Orlando S., Silvestri F.
Web Search Engines (WSEs) have stored in their query logs information about users since they started to operate. This information often serves many purposes. The primary focus of this tutorial is to introduce to the discipline of query log mining.We will show its foundations, by giving a unified view on the literature on query log analysis, and also present in detail the basic algorithms and techniques that could be used to extract useful knowledge from this (potentially) infinite source of information. Finally, we will discuss how the extracted knowledge can be exploited to improve different quality features of a WSE system, mainly its effectiveness and efficiency.Source: Advances in Information Retrieval. 31th European Conference on IR Research - ECIR 2009, pp. 814–817, Toulose, France, 6-9 Aprile 2009
DOI: 10.1007/978-3-642-00958-7_94
Metrics:
Orlando S., Silvestri F.
Web Search Engines (WSEs) have stored in their query logs information about users since they started to operate. This information often serves many purposes. The primary focus of this tutorial is to introduce to the discipline of query log mining.We will show its foundations, by giving a unified view on the literature on query log analysis, and also present in detail the basic algorithms and techniques that could be used to extract useful knowledge from this (potentially) infinite source of information. Finally, we will discuss how the extracted knowledge can be exploited to improve different quality features of a WSE system, mainly its effectiveness and efficiency.Source: Advances in Information Retrieval. 31th European Conference on IR Research - ECIR 2009, pp. 814–817, Toulose, France, 6-9 Aprile 2009
DOI: 10.1007/978-3-642-00958-7_94
Metrics:
See at:
link.springer.com | link.springer.com | CNR ExploRA
2005
Conference article
Unknown
Distributed approximate mining of frequent patterns
Silvestri C., Orlando S.
This paper discusses a novel communication effcient distributed algorithm for approximate mining of frequent patterns from transactional databases. The proposed algorithm consists in the distributed exact computation of locally frequent itemsets and an effective method for inferring the local support of locally unfrequent itemsets. The combination of the two strategies gives a good approximation of the set of the globally frequent patterns and their supports. Several tests on publicly available datasets were conducted, aimed at evaluating the similarity between the exact result set and the approximate ones returned by our distributed algorithm as well as the scalability of the proposed method.Source: Symposium on Applied Computing, pp. 529–536, Santa Fe, New Mexico, USA, 13 -17 Marzo 2005
Silvestri C., Orlando S.
This paper discusses a novel communication effcient distributed algorithm for approximate mining of frequent patterns from transactional databases. The proposed algorithm consists in the distributed exact computation of locally frequent itemsets and an effective method for inferring the local support of locally unfrequent itemsets. The combination of the two strategies gives a good approximation of the set of the globally frequent patterns and their supports. Several tests on publicly available datasets were conducted, aimed at evaluating the similarity between the exact result set and the approximate ones returned by our distributed algorithm as well as the scalability of the proposed method.Source: Symposium on Applied Computing, pp. 529–536, Santa Fe, New Mexico, USA, 13 -17 Marzo 2005
See at: CNR ExploRA
2006
Conference article
Restricted
Tree vector indexes: efficient range queries for dynamic content on Peer-to-Peer networks
Marzolla M., Mordacchini M., Salvatore O.
Locating data on peer-to-peer networks is a complex issue addressed by many P2P protocols. Most of the research in this area only considers static content, that is, it is often assumed that data in P2P systems do not vary over time. In this paper we describe a data location strategy for dynamic content on P2P networks. Data location exploits a distributed index based on bit vectors: this index is used to route queries towards areas of the system where matches can be found. The bit vectors can be efficiently updated when data is modified. Simulation results show that the proposed algorithms for queries and updates propagation have good performances, also on large networks, even if content exhibits a high degree of variability.Source: PDP 2006, Montbeliard-Sochaux, France, 05-17/02/2006
Marzolla M., Mordacchini M., Salvatore O.
Locating data on peer-to-peer networks is a complex issue addressed by many P2P protocols. Most of the research in this area only considers static content, that is, it is often assumed that data in P2P systems do not vary over time. In this paper we describe a data location strategy for dynamic content on P2P networks. Data location exploits a distributed index based on bit vectors: this index is used to route queries towards areas of the system where matches can be found. The bit vectors can be efficiently updated when data is modified. Simulation results show that the proposed algorithms for queries and updates propagation have good performances, also on large networks, even if content exhibits a high degree of variability.Source: PDP 2006, Montbeliard-Sochaux, France, 05-17/02/2006
See at:
ieeexplore.ieee.org | CNR ExploRA
2008
Conference article
Unknown
Trajectory data warehouses: storing and aggregating frequent ST patterns
Orlando S., Raffaetà A., Roncato A., Silvestri C.
In this paper we present an approach for storing and aggregating spatio-temporal patterns by using a Tra jectory Data Warehouse (TDW). In particular, our aim is to allow the analysts to quickly evaluate frequent patterns mined from tra jectories of moving ob jects occurring in a specific spatial zone and during a given temporal interval. We resort to a TDW, based on a data cube model, having spatial and tem- poral dimensions, discretized according to a hierarchy of regular grids, and whose facts are sets of tra jectories which intersect the ST cells of the cube. The idea is to enrich such a TDW with a new measure: frequent patterns obtained from a data-mining process on tra jectories. As a consequence these patterns can be analysed by the user at various levels of granularity with the use of OLAP queries. The research issues discussed in this paper are (1) the extraction/mining of the patterns to be stored in each cell, which requires an adequate pro jection phase of tra jectories before mining; (2) the ST aggregation of patterns to answer roll-up queries, which poses many problems due to the holistic nature of the aggregation function.Source: Sixteenth Italian Symposium on Advanced Database Systems, pp. 179–190, Mondello (PA), Italy, 22-25 Giugno 2008
Orlando S., Raffaetà A., Roncato A., Silvestri C.
In this paper we present an approach for storing and aggregating spatio-temporal patterns by using a Tra jectory Data Warehouse (TDW). In particular, our aim is to allow the analysts to quickly evaluate frequent patterns mined from tra jectories of moving ob jects occurring in a specific spatial zone and during a given temporal interval. We resort to a TDW, based on a data cube model, having spatial and tem- poral dimensions, discretized according to a hierarchy of regular grids, and whose facts are sets of tra jectories which intersect the ST cells of the cube. The idea is to enrich such a TDW with a new measure: frequent patterns obtained from a data-mining process on tra jectories. As a consequence these patterns can be analysed by the user at various levels of granularity with the use of OLAP queries. The research issues discussed in this paper are (1) the extraction/mining of the patterns to be stored in each cell, which requires an adequate pro jection phase of tra jectories before mining; (2) the ST aggregation of patterns to answer roll-up queries, which poses many problems due to the holistic nature of the aggregation function.Source: Sixteenth Italian Symposium on Advanced Database Systems, pp. 179–190, Mondello (PA), Italy, 22-25 Giugno 2008
See at: CNR ExploRA
2008
Contribution to book
Restricted
Mining@home: public resource computing for distributed data mining
Lucchese C., Orlando S., Talia D., Matroianni C., Barbalace D.
Several kinds of scientific and commercial applications require the execution of a large number of independent tasks. One highly successful and low cost mechanism for acquiring the necessary compute power for these applications is the "public-resource computing", or "desktop Grid" paradigm, which exploits the computational power of private computers. So far, this paradigmhas not been applied to data mining applications for two main reasons. First, it is not trivial to decompose a data mining algorithm into truly independent sub-tasks. Second, the large volume of data involved makes it difficult to handle the communication costs of a parallel paradigm. In this paper, we focus on one of the main data mining problem: the extraction of closed frequent itemsets from transactional databases. We show that is possible to decompose this problem into independent tasks, which however need to share a large volume of data. We thus introduce a data-intensive computing network, which adopts a P2P topology based on super peers with caching capabilities, aiming to support the dissemination of large amounts of information. Finally, we evaluate the execution of our data mining job on such network.Source: From Grids to Service and Pervasive Computing, edited by Thierry Priol, Marco Vanneschi, pp. 217–227, 2008
DOI: 10.1007/978-0-387-09455-7_16
Metrics:
Lucchese C., Orlando S., Talia D., Matroianni C., Barbalace D.
Several kinds of scientific and commercial applications require the execution of a large number of independent tasks. One highly successful and low cost mechanism for acquiring the necessary compute power for these applications is the "public-resource computing", or "desktop Grid" paradigm, which exploits the computational power of private computers. So far, this paradigmhas not been applied to data mining applications for two main reasons. First, it is not trivial to decompose a data mining algorithm into truly independent sub-tasks. Second, the large volume of data involved makes it difficult to handle the communication costs of a parallel paradigm. In this paper, we focus on one of the main data mining problem: the extraction of closed frequent itemsets from transactional databases. We show that is possible to decompose this problem into independent tasks, which however need to share a large volume of data. We thus introduce a data-intensive computing network, which adopts a P2P topology based on super peers with caching capabilities, aiming to support the dissemination of large amounts of information. Finally, we evaluate the execution of our data mining job on such network.Source: From Grids to Service and Pervasive Computing, edited by Thierry Priol, Marco Vanneschi, pp. 217–227, 2008
DOI: 10.1007/978-0-387-09455-7_16
Metrics:
See at:
doi.org | www.springerlink.com | CNR ExploRA
2012
Conference article
Open Access
Compiling CHR to parallel hardware
Triossi A., Orlando S., Raffaetà A., Fruhwirth T.
This paper investigates the compilation of a committed-choice rule- based language, Constraint Handling Rules (CHR), to specialized hardware circuits. The developed hardware is able to turn the intrin- sic concurrency of the language into parallelism. Rules are applied by a custom executor that handles constraints according to the best degree of parallelism the implemented CHR specification can of- fer. Our framework deploys the target digital circuits through the Field Programmable Gate Array (FPGA) technology, by first com- piling the CHR code fragment into a low level hardware description language. We also discuss the realization of a hybrid CHR inter- preter, consisting of a software component running on a general purpose processor, coupled with a hardware accelerator. The latter unburdens the processor by executing in parallel the most computa- tional intensive CHR rules directly compiled in hardware. Finally the performance of a prototype system is evaluated by time effi- ciency measures.Source: 14th Symposium on Principles and Practice of Declarative Programming, pp. 173–184, Leuven, Belgium, 19-21 September 2012
DOI: 10.1145/2370776.2370798
Metrics:
Triossi A., Orlando S., Raffaetà A., Fruhwirth T.
This paper investigates the compilation of a committed-choice rule- based language, Constraint Handling Rules (CHR), to specialized hardware circuits. The developed hardware is able to turn the intrin- sic concurrency of the language into parallelism. Rules are applied by a custom executor that handles constraints according to the best degree of parallelism the implemented CHR specification can of- fer. Our framework deploys the target digital circuits through the Field Programmable Gate Array (FPGA) technology, by first com- piling the CHR code fragment into a low level hardware description language. We also discuss the realization of a hybrid CHR inter- preter, consisting of a software component running on a general purpose processor, coupled with a hardware accelerator. The latter unburdens the processor by executing in parallel the most computa- tional intensive CHR rules directly compiled in hardware. Finally the performance of a prototype system is evaluated by time effi- ciency measures.Source: 14th Symposium on Principles and Practice of Declarative Programming, pp. 173–184, Leuven, Belgium, 19-21 September 2012
DOI: 10.1145/2370776.2370798
Metrics:
See at:
www.informatik.uni-ulm.de | dl.acm.org | doi.org | CNR ExploRA