BLOCK SUBSPACE PURSUIT FOR BLOCK-SPARSE SIGNAL RECONSTRUCTION
text
article
2013
eng
Subspace Pursuit (SP) is an efficient algorithm for sparse signal reconstruction. Whenthe interested signal is block sparse, i.e., the nonzero elements occur in clusters, block sparserecovery algorithms are developed. In this paper, a blocked algorithm based on SP, namely BlockSP (BSP) is presented. Contrary to the previous algorithms such as Block Orthogonal MatchingPursuit (BOMP) and mixed 2 1 l /l -norm, our approach presents better recovery performance andrequires less time when non-zero elements appear in fixed blocks in a particular hardware in mostof the cases. It is demonstrated that our proposed algorithm can precisely reconstruct the blocksparsesignals, provided that the sampling matrix satisfies the block restricted isometry property -which is a generalization of the standard RIP widely used in the context of compressed sensingwitha constant parameter. Furthermore, it is experimentally illustrated that the BSP algorithmoutperforms other methods such as SP, mixed 2 1 l /l -norm and BOMP. This is more pronouncedwhen the block length is small.
Iranian Journal of Science and Technology Transactions of Electrical Engineering
Shiraz University
2228-6179
37
v.
1
no.
2013
1
16
https://ijste.shirazu.ac.ir/article_1757_380655d0552ae69c534ff438901488b8.pdf
dx.doi.org/10.22099/ijste.2013.1757
A NOVEL APPROACH TO MEASURING NODE AND ENERGY UNIFORMITY
FOR THE OPTIMAL ASSIGNMENT OF DIRECTIONAL SENSORS
text
article
2013
eng
One of the prevalent methods to increase the network lifetime is to develop theuniformity in the sensor node distribution and load balancing. The existing criteria to calculate theuniformity are only able to locally or globally measure the uniformity of sensor distribution in thenetwork. In this paper, a new criterion is proposed for the uniformity measurement of sensordistribution. The criterion can calculate the both global and local uniformity in various levels ofnode distribution. In addition, using the model of sensing area of each sensor, this criterion hasbeen generalized for the uniformity of sensors energy distribution in the network via calculatingthe uniformity of sensor node distribution. In order to assess the performance of the proposedcriterion, a set of sensor distribution patterns has been utilized; also, the uniformity calculationresults of these patterns have been studied. Then, a method for the sensor assignment has beenproposed in a network, in which sensor nodes have the possibility of rotation and a coverage areais selected. This method enhances the energy distribution uniformity in the network. Thecomparison is finally provided among the perceived results to show an acceptable performance ofthe proposed method.
Iranian Journal of Science and Technology Transactions of Electrical Engineering
Shiraz University
2228-6179
37
v.
1
no.
2013
17
33
https://ijste.shirazu.ac.ir/article_1758_4fc1d609db35add2f94bd9bf5f4a5cea.pdf
dx.doi.org/10.22099/ijste.2013.1758
SMART FLEXIBLE DISPATCHABLE TRANSMISSION SERVICES AND FLOWGATE
BIDDING IN SECURITY CONSTRAINT UNIT COMMITMENT
text
article
2013
eng
To attract more investments for developing smart transmission networks and increasingtheir flexibility and efficiency, recently policies have been suggested which provide financialincentives in transmission network investment. One of these policies is price biding forincremental transmission capacity and transmission elements in power markets. According toFederal Electricity Regulatory Committee, flowgate bidding is defined as allowing a line’s flow toexceed its rated capacity for a short period of time for a set penalty, i.e., price. This paperconcentrates on the development of a comprehensive model for flowgate bidding and DispatchableTransmission Services (DTS) in security constraint unit commitment.DTS and flowgate biddings are used during contingencies and steady state to determineoptimal required energy and reserve values. As the scale of the problem is large, the bendersdecomposition algorithm is used to solve the problem. To investigate the efficiency of theproposed strategy, IEEE 6 and 24 bus case tests are studied. According to the obtained results, thisstrategy decreases energy and reserve marginal prices, as well as reliability cost. Furthermore, thesuggested plan is an incentive to the owners of transmission companies.
Iranian Journal of Science and Technology Transactions of Electrical Engineering
Shiraz University
2228-6179
37
v.
1
no.
2013
35
49
https://ijste.shirazu.ac.ir/article_1759_ede209ec754b49dfc12931e49bc4cb28.pdf
dx.doi.org/10.22099/ijste.2013.1759
SOCIAL NETWORKS COMMUNITY DETECTION
USING THE SHAPLEY VALUE
text
article
2013
eng
As a result of the increasing popularity of social networking websites like Facebookand Twitter, analysis of the structure of these networks has received significant attention. The mostimportant part of these analyses is towards detecting communities. The aforementioned structuresare usually known with extremely high inter-connections versus few intra-connections in thegraphs. In this paper, in spite of most approaches being optimization based, we have addressed thecommunity detection problem (CDP) by a novel framework based on Information DiffusionModel and Shapley Value Concept. Here, each node of the underlying graph is attributed to arational agent trying to maximize its Shapley Value in the form of information it receives. Nashequilibrium of the game corresponds to the community structure of the graph. Compared with theother methods, our approach demonstrates promising results on the well-known real world andsynthetic graphs.
Iranian Journal of Science and Technology Transactions of Electrical Engineering
Shiraz University
2228-6179
37
v.
1
no.
2013
51
65
https://ijste.shirazu.ac.ir/article_1760_73d521b4dc4c90233506dba243b747f4.pdf
dx.doi.org/10.22099/ijste.2013.1760
A NEW CLUSTERING-BASED APPROACH FOR MODELING FUZZY
RULE-BASED CLASSIFICATION SYSTEMS
text
article
2013
eng
In the present study, we propose a novel clustering-based method for modeling accuratefuzzy rule-based classification systems. The new method is a combination of a data mappingmethod, subtractive clustering method and an efficient gradient descent algorithm. A data mappingmethod considers the intricate geometric relationships that may exist among the data and computesa new representation of data that optimally preserves local neighbourhood information in a certainsense. The approach uses subtractive clustering method to extract the fuzzy classification rulesfrom data; the rule parameters are then optimized by using an efficient gradient descent algorithm.Twenty datasets taken from UCI repository are employed to compare the performance of theproposed approach with the other similar existing classifiers. Some non-parametric statistical testsare utilized to compare the results obtained in experiments. The statistical comparisons confirm thesuperiority of the proposed method compared to other similar classifiers, both in terms ofclassification accuracy and computational effort.
Iranian Journal of Science and Technology Transactions of Electrical Engineering
Shiraz University
2228-6179
37
v.
1
no.
2013
67
77
https://ijste.shirazu.ac.ir/article_1761_2b52dfeaf261ad8b55cc0a7aca42ea08.pdf
dx.doi.org/10.22099/ijste.2013.1761
AN ADAPTIVE MULTI-OBJECTIVE ARTIFICIAL BEE COLONY
WITH CROWDING DISTANCE MECHANISM
text
article
2013
eng
Artificial Bee Colony (ABC) is one of the recently introduced optimization methodsbased on intelligent behavior of honey bees. In this work, we propose an Adaptive Multi-ObjectiveArtificial Bee Colony (A-MOABC) Optimizer which uses Pareto dominance notion and takesadvantage of crowding distance and windowing mechanisms. The employed bees use an adaptivewindowing mechanism to select their own leaders and alter their positions. Besides, onlookersupdate their positions using food sources presented by employed bees. Pareto dominance notion isused to show the quality of the food sources. Those employed or onlooker bees which find foodsources with poor quality turn into scout bees in order to search other areas. The suggested methoduses crowding distance technique in conjunction with the windowing mechanism in order to keepdiversity in the external archive. The experimental results indicate that the proposed approach isnot only thoroughly competitive compared to other algorithms considered in this work, but alsofinds the result with satisfactory precision.
Iranian Journal of Science and Technology Transactions of Electrical Engineering
Shiraz University
2228-6179
37
v.
1
no.
2013
79
92
https://ijste.shirazu.ac.ir/article_1762_29d6ea87a0aa7a7bebbe1e4a309b8fce.pdf
dx.doi.org/10.22099/ijste.2013.1762
A NOVEL COLLABORATIVE FILTERING MODEL BASED ON COMBINATION OF
CORRELATION METHOD WITH MATRIX COMPLETION TECHNIQUE
text
article
2013
eng
One of the fundamental methods used in collaborative filtering systems is Correlationbased on K-nearest neighborhood. These systems rely on historical rating data and preferences ofusers and items in order to propose appropriate recommendations for active users. These systemsdo not often have a complete matrix of input data. This challenge leads to a decrease in theaccuracy level of recommendations for new users. The exact matrix completion technique tries topredict unknown values in data matrices. This study is to show how the exact matrix completioncan be used as a preprocessing step to tackle the sparseness problem. Compared to application ofthe sparse data matrix, selection of neighborhood set for active user based on the completed datamatrix leads to achieving more similar users. The main advantages of the proposed method arehigher prediction accuracy and an explicit model representation. The experiments show significantimprovement in prediction accuracy in comparison with other substantial methods.
Iranian Journal of Science and Technology Transactions of Electrical Engineering
Shiraz University
2228-6179
37
v.
1
no.
2013
93
100
https://ijste.shirazu.ac.ir/article_1763_c6dd0c4a249468fa5dddaf137a8a1829.pdf
dx.doi.org/10.22099/ijste.2013.1763