|
Paper Title |
Authors |
Conference |
Abstract |
|
|
A Fault-Tolerance Pattern Recommender for Transactional Service Compositions |
Omid Bushehrian
Mohammad Mohsen Mavaddat
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
Combining services to build compositions is a key concept in Service Oriented Architecture. In a service composition with transactional property, each service failure may impose a rollback cost on the ... more
Combining services to build compositions is a key concept in Service Oriented Architecture. In a service composition with transactional property, each service failure may impose a rollback cost on the composition due to the rollback of its dependent successfully ended services. Reducing the mean rollback cost of a composition is possible by applying Fault Tolerance (FT) patterns to each task in order to decrease the failure probability of the composition. Different FT patterns with different imposed cost and execution time overheads can be applied to each task within the composition workflow. In this paper we have formulated the problem of choosing FT patterns for a given transactional composition as an optimization problem and a NSGA-II genetic algorithm has been proposed to find a mapping of patterns totasks which satisfies conflicting objectives. The effectiveness of the proposed approach has been evaluated by applying the optimization process to different compositions less
Combining services to build compositions is a key concept in Service Oriented Architecture. In a service composition with transactional property, each service failure may impose a rollback cost on the ... more |
خرید مقاله
|
|
SiftCU: An AcceleratedCuda Based Implementation of SIFT |
Mahdi S. Mohammadi
Mehdi Rezaeian
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
Scale Invariant Feature Transform (SIFT) is a popular image feature extraction algorithm. SIFT’s features are invariant to many image related variables including scale and change in viewpoint. Despite its broad ... more
Scale Invariant Feature Transform (SIFT) is a popular image feature extraction algorithm. SIFT’s features are invariant to many image related variables including scale and change in viewpoint. Despite its broad capabilities, it is computationally expensive. This characteristic makes it hard for researchers to use SIFT in their works especially in real time application. This is a common problem with many image-processing related algorithm. Utilizing graphical processing unit (GPU) through parallel programming is an affordable solution for this issue. In this paper we present a GPU-based implementation of SIFT using Compute Unified Device Architecture (CUDA) programming framework. We compare our CUDA-based implementation, namely siftCU, with CPU-based serial implementations of SIFT both in feature matching accuracy and time consumption. Results show our implementation can gain 4x speed up over serial CPU implementation even though we have used a low end graphic card while using a powerful CPU for test platform less
Scale Invariant Feature Transform (SIFT) is a popular image feature extraction algorithm. SIFT’s features are invariant to many image related variables including scale and change in viewpoint. Despite its broad ... more |
خرید مقاله
|
|
A Computational Model of Trust Based on a Multi-Criteria Decision Making Approach |
Mehrdad Ashtiani
Mohammad Abdollahi Azgomi
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
In this paper, we formulate trust as a multi-criteria decision making process. Making trust decisions needs a structural way in computational environments. Based on this need, we use a combination ... more
In this paper, we formulate trust as a multi-criteria decision making process. Making trust decisions needs a structural way in computational environments. Based on this need, we use a combination of fuzzy AHP and fuzzy VIKOR approaches from the domain of multi-criteria decision making to formulate trust. The VIKOR method was originally developed to solve decision problems with conflicting and non-commensurable criteria.By using the VIKOR approach, we can rank the trustee alternatives and determine the compromise solution that is closest to the ideal. Combining fuzzy logic with this approach lets us model the vague, uncertain and subjective nature of trust less
In this paper, we formulate trust as a multi-criteria decision making process. Making trust decisions needs a structural way in computational environments. Based on this need, we use a combination ... more |
خرید مقاله
|
|
A semi-automatic approach for WSC |
Parinaz Mobedi
Asadollah Shahbahrami
Reza Ebrahimi Atani
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
Web Services Composition (WSC) is a seamless approach to develop the software development projects on the basis of reusability potentials. Most web services composition approaches tend to benefit from either ... more
Web Services Composition (WSC) is a seamless approach to develop the software development projects on the basis of reusability potentials. Most web services composition approaches tend to benefit from either of practical or formal models; this paper proposes an approach for semi-automatic web services composition to close the gap between formal models and database practice. In this approach, the web services are stored in a database after being modeled in G-net. The G-net services employed in the composition process can be subsequently obtained using a proposed WSC search algorithm with SQL queries. Finally, based on the relational algebra operators the WSC is performed and a Java-based tool is developed for WSC. The proposed approach is demonstrated using a digital class assistant as a case study less
Web Services Composition (WSC) is a seamless approach to develop the software development projects on the basis of reusability potentials. Most web services composition approaches tend to benefit from either ... more |
خرید مقاله
|
|
Acceleration of IPTABLES Linux Packet Filtering using GPGPU |
Keyvan Karimi
Arash Ahmadi
Mahmood Ahmadi
Bahram Bahrambeigy
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
Firewalls are a piece of software or hardware that control access to organization networks. Packet filtering is placed in the heart of firewalls. It is performed by comparing each data ... more
Firewalls are a piece of software or hardware that control access to organization networks. Packet filtering is placed in the heart of firewalls. It is performed by comparing each data packet against a rule set. In the high bandwidth networks, filtering becomes a time consuming task. In this situation, the packet filtering firewall can reduce the overall throughput and become a bottleneck. To solve this problem a wide range ofresearcheshave been done to improve overall throughput of the packet filtering firewalls. In this paper, the first matching rule mechanism of Iptablesis implemented in user-space by employing parallel processing capability of Graphics Processing Unit (GPU). The results show that CPU-GPU accelerated code brings significantly higher throughput over the CPU version ofIptablescode. The overall throughput of packet filtering on GPU for 10,000 rules is about 400,000 Packets PerSecond (PPS) which is 43 times faster than inefficient first matching rule algorithm of Iptableson CPU less
Firewalls are a piece of software or hardware that control access to organization networks. Packet filtering is placed in the heart of firewalls. It is performed by comparing each data ... more |
خرید مقاله
|
|
An Improved Architectural Pattern for Organic Resource-Flow Systems |
Ali Tarihi
Hassan Haghighi
Fereidoon Shams
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
Organic Computing or OC for short is rather a new bio-inspired paradigm that applies the OC principles extracted from the nature to technical application. To control the emergence caused by ... more
Organic Computing or OC for short is rather a new bio-inspired paradigm that applies the OC principles extracted from the nature to technical application. To control the emergence caused by the self-organizing property of OC systems, an architectural pattern called observer/controller has been proposed. In this paper, the observer/controller architecture is improved for a subset of OC systems known as Resource-Flow Organic systems by using some known architectural/design patterns in order to achieve a new architectural pattern. The proposed architectural pattern splits the observer/controller into a set of cooperative capabilities among the agents that both covers the whole-system architecture and enables straightforward distribution of observer and controller. The result of the study is presented as a case study to show the applicationof the proposed pattern and its advantages less
Organic Computing or OC for short is rather a new bio-inspired paradigm that applies the OC principles extracted from the nature to technical application. To control the emergence caused by ... more |
خرید مقاله
|
|
Modified Bitwise Hill Crypto System |
Jaber Karimpour
Masoud Aghdasifam
Ali Asghar Noroozi
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
Hill Cipher (HC) is a polygraph symmetric data encryption method which is based on matrices. In 2011, Desoky et al.proposed the Bitwise Hill Crypto System (BHC) which is based on ... more
Hill Cipher (HC) is a polygraph symmetric data encryption method which is based on matrices. In 2011, Desoky et al.proposed the Bitwise Hill Crypto System (BHC) which is based on bit arithmetic. In this paper,weanalyze BHC and show that it is insecure. Then, we propose a new modification using chaotic map which provides better security less
Hill Cipher (HC) is a polygraph symmetric data encryption method which is based on matrices. In 2011, Desoky et al.proposed the Bitwise Hill Crypto System (BHC) which is based on ... more |
خرید مقاله
|
|
Applying Link Prediction Techniques for Item Recommendation in C2C Commercial Networks |
Mohammad Dehghan Bahabadi
Alireza Hashemi Golpayegani
Leila Esmaeili
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
There has been a big revolution in electronic commerce since the advent of recommender systems. Most of the current recommender systems are designed for B2C e-commerce sites. But this paper ... more
There has been a big revolution in electronic commerce since the advent of recommender systems. Most of the current recommender systems are designed for B2C e-commerce sites. But this paper focuses on building a recommendation algorithm that increases volume and speed of forming trades between users by considering special features of C2C e-commerce sites. In this paper, we consider users and transactions between them as a network in which nodes represent users and edges represent transactions between them. By this mapping, link prediction approaches could be used to build the recommender system. The proposed model, rather than topology of the network, uses nodes’ features like: category of items, ratings of users, and reputation of sellers. The results show that the proposed model can be used to predict future trades between users in a C2C commercial network less
There has been a big revolution in electronic commerce since the advent of recommender systems. Most of the current recommender systems are designed for B2C e-commerce sites. But this paper ... more |
خرید مقاله
|
|
A Self Organizing Architecture for Adjusting Level of Difficulty in Games |
Adeleh Ebrahimi
Mohammad-R Akbarzadeh-T
|
سمپوزیوم علوم کامپیوتر و مهندسی نرمافزار 2013 |
Games are played by players with different strategies; a game could be frustrating or disappointing, if the level of difficulty does not match the player’s skills. In this paper we ... more
Games are played by players with different strategies; a game could be frustrating or disappointing, if the level of difficulty does not match the player’s skills. In this paper we use Non-Player Characters (NPCs) to build a Self-Organizing System (SOS) for adjusting the level of difficulty in games. To this end, we apply Artificial Neural Network and Interactive Evolutionary Algorithms, and focus on player’s hidden responses. Our results demonstrate that the proposed SOS can adapt itself with different level of skills less
Games are played by players with different strategies; a game could be frustrating or disappointing, if the level of difficulty does not match the player’s skills. In this paper we ... more |
خرید مقاله
|
|
Weighted Consensus-Based Cooperative Spectrum Sensing with Learning Automata (LA) in Cognitive Radio Networks |
Milad Soltani
Abdorasoul Ghasemi
|
سمپوزیوم شبکههای کامپیوتری و سیستمهای توزیع شده 2013 |
In traditional cooperative spectrum sensing such as OR-rule
or AND-rule, secondary user (SU) must maintain coordination based on
a fusion center. In this paper, we propose the weighted average consen-
sus, based on ... more
In traditional cooperative spectrum sensing such as OR-rule
or AND-rule, secondary user (SU) must maintain coordination based on
a fusion center. In this paper, we propose the weighted average consen-
sus, based on Learning Automata(LA), for fully distributed cooperative
spectrum sensing without fusion center. At the first stage of the pro-
posed scheme, each SU makes measurement about presence of primary
user (PU) at the beginning of each time slot, then communicates with
local neighbors to exchange information to make the final decision and
update its weight using a LA based algorithm. Simulation results show
that the proposed scheme has better performance than the non weighted
consensus and existing weighted consensus scheme. Also, the convergence
time of the proposed scheme is less than the existing weighted consensus
and almost equal to non weighted consensus scheme less
In traditional cooperative spectrum sensing such as OR-rule
or AND-rule, secondary user (SU) must maintain coordination based on
a fusion center. In this paper, we propose the weighted average consen-
sus, based on ... more |
خرید مقاله
|
.gif){kind=icon}
