Search

A concept hierarchy is an integral part of an ontology but it is expensive and time consuming to build. Motivated by this, many unsupervised learning methods have been proposed to (semi-) automatically develop a concept hierarchy. A significant work is the Guided Agglomerative Hierarchical Clustering (GAHC) which relies on linguistic patterns (i.e., hypernyms) to guide the clustering process. However, GAHC still relies on contextual features to build the concept hierarchy, thus data sparsity still remains an issue in GAHC. Artificial Immune Systems are known for robustness, noise tolerance and adaptability. Thus, an extension to the GAHC is proposed by hybridizing it with Artificial Immune Network (aiNet) which we call Guided Clustering and aiNet for Learning Concept Hierarchy (GCAINY). In this paper, we have tested GCAINY using two parameter settings. The first parameter setting is obtained from the literature as a baseline parameter setting and second is by automatic parameter tuning using Particle Swarm Optimization (PSO). The effectiveness of the GCAINY is evaluated on three data sets. For further validations, a comparison between GCAINY and GAHC has been conducted and with statistical tests showing that GCAINY increases the quality of the induced concept hierarchy. The results reveal that the parameters value found by using PSO significantly produce better concept hierarchy than the vanilla parameter. Thus it can be concluded that the proposed approach has greater ability to be used in the field of ontology learning.

Scheduling job shops in the real-world manufacturing environment is a multifarious task that involved various and multiple components, solutions and approach. Fuzzy Job-Shop Scheduling Problems (Fuzzy JSSPs) are most commonly addressed by the population-based Meta-heuristic algorithms. These algorithms usually derive near-optimum solutions within reasonable computational times, almost by two main steps; the initialisation and then improvement step. Numerous theoretical studies pointed out that a Meta-heuristic performance is mainly affected by the performance of its initialisation method. The main purpose of this paper is to understand the existing trend and concerns of issues in population initialisation for Fuzzy JSSPs research by examining the published articles and furthermore to provide comprehension insight and future direction on these methods. Therefore, this paper determined to review and classify the existing literature on Fuzzy JSSPs and analyse the performance of the initialisation methods used to identify their possible limitations. In consequence, previous works outlined three potential methods for initial solutions generation, which are Random-based, priority rules-based, and heuristic methods. However, the current analysis showed that Heuristic-based initialisation approach remains lacking in the Fuzzy JSSPs domain in spite of its successful performance in the crisp JSSP domain, especially, its capability to generate high-quality initial population that consists of optimal or near optimal solutions. Furthermore, this paper identifies probable gaps and reveals several performance limitations in the existing methods, which demands for an urgent solution to develop alternatives. Promising suggestions for future studies are also provided that may lead to new Heuristic Initialisation methods to be proposed in order to overcome the existing shortcomings .

Although wireless sensor networks (WSNs) have been the object of research focus for the past two decades, fault diagnosis in these networks has received little attention. This is an essential requirement for wireless networks, especially in WSNs, because of their ad-hoc nature, deployment requirements and resource limitations. Therefore, in this paper we survey fault diagnosis from the perspective of network operations. To the best of our knowledge, this is the first survey from such a perspective. We survey the proactive, active and passive fault diagnosis schemes that have appeared in the literature to date, accenting their advantages and limitations of each scheme. In addition to illuminating the details of past efforts, this survey also reveals new research challenges and strengthens our understanding of the field of fault diagnosis.

Neighbourhood search algorithms are often the most effective known approaches for solving partitioning problems. In this paper, we consider the capacitated examination timetabling problem as a partitioning problem and present an examination timetabling methodology that is based upon the large neighbourhood search algorithm that was originally developed by Ahuja and Orlin. It is based on searching a very large neighbourhood of solutions using graph theoretical algorithms implemented on a so-called improvement graph. In this paper, we present a tabu-based large neighbourhood search, in which the improvement moves are kept in a tabu list for a certain number of iterations. We have drawn upon Ahuja–Orlin's methodology incorporated with tabu lists and have developed an effective examination timetabling solution scheme which we evaluated on capacitated problem benchmark data sets from the literature. The capacitated problem includes the consideration of room capacities and, as such, represents an issue that is of particular importance in real-world situations. We compare our approach against other methodologies that have appeared in the literature over recent years. Our computational experiments indicate that the approach we describe produces the best known results on a number of these benchmark problems.

One of the global combinatorial optimization problems in machine learning is feature selection. It concerned with removing the irrelevant, noisy, and redundant data, along with keeping the original meaning of the original data. Attribute reduction in rough set theory is an important feature selection method. Since attribute reduction is an NP-hard problem, it is necessary to investigate fast and effective approximate algorithms. In this paper, we proposed two feature selection mechanisms based on memetic algorithms (MAs) which combine the genetic algorithm with a fuzzy record to record travel algorithm and a fuzzy controlled great deluge algorithm, to identify a good balance between local search and genetic search. In order to verify the proposed approaches, numerical experiments are carried out on thirteen datasets. The results show that the MAs approaches are efficient in solving attribute reduction problems when compared with other meta-heuristic approaches., {"references":["R. Jensen and Q. Shen, \"Fuzzy-rough sets for descriptive dimensionality\nreduction,\" presented at the Fuzzy Systems, 2002. FUZZ-IEEE'02.\nProceedings of the 2002 IEEE International Conference on, 2002.","L. Ke, Z. Feng, and Z. Ren, \"An efficient ant colony optimization\napproach to attribute reduction in rough set theory,\" Pattern Recognition\nLetters, vol. 29, 2008, pp. 1351-1357.","S. Theodoridis and K. Koutroumbas, Pattern Recognition, Third ed.\nOrlando, FL, USA Academic Press, Inc. , 2006.","Z. Pawalk, \"Rough sets: theoretical aspects of reasoning about data,\" ed:\nDordrecht: Kluwer Academic Publishers, 1991.","Z. Pawlak, \"Rough Sets,\" International Journal of Information and\nComputer Sciences, vol. 11, 1982, pp. 341-356.","Z. Pawlak, \"Rough sets and data analysis,\" presented at the Fuzzy\nSystems Symposium, 1996. 'Soft Computing in Intelligent Systems and\nInformation Processing', 1996.","Z. Pawlak and A. Skowron, \"Rudiments of rough sets,\" Information\nsciences, vol. 177, 2007, pp. 3-27.","R. W. Swiniarski and A. Skowron, \"Rough set methods in feature\nselection and recognition,\" Pattern Recognition Letters, vol. 24, 2003,\npp. 833-849.","A. Skowron and C. Rauszer, \"The discernibility matrices and functions\nin information systems,\" Intelligent decision support–Handbook of\napplications and advances of the rough set theory, 1992, pp. 311–362.\n[10] R. Jensen and Q. Shen, \"Semantics-Preserving Dimensionality\nReduction: Rough and Fuzzy-Rough-Based Approaches,\" IEEE Trans.\non Knowl. and Data Eng., vol. 16, 2004, pp. 1457-1471.\n[11] J. G. Bazan, A. Skowron, and P. Synak, \"Dynamic Reducts as a Tool for\nExtracting Laws from Decisions Tables,\" presented at the Proceedings\nof the 8th International Symposium on Methodologies for Intelligent\nSystems, 1994.\n[12] J. Wroblewski, \"Finding minimal reducts using genetic algorithms,\"\npresented at the 2nd Annual Joint Conf. on Information Sciences,\nWrightsville Beach, NC, 1995.\n[13] A.-R. Hedar, J. Wang, and M. Fukushima, \"Tabu search for attribute\nreduction in rough set theory,\" Soft Comput., vol. 12, 2006, pp. 909-918.\n[14] J. Wang, A.-R. Hedar, G. Zheng, and S. Wang, \"Scatter Search for\nRough Set Attribute Reduction,\" presented at the Bio-Inspired\nComputing: Theories and Applications, 2007. BIC-TA 2007. Second\nInternational Conference on, 2007.\n[15] S. Abdullah and N. S. Jaddi, \"Great Deluge Algorithm for Rough Set\nAttribute Reduction,\" in Database Theory and Application, Bio-Science\nand Bio-Technology. vol. 118, Y. Zhang, A. Cuzzocrea, J. Ma, K.-i.\nChung, T. Arslan, and X. Song, Eds., ed: Springer Berlin Heidelberg,\n2010, pp. 189-197.\n[16] S. K. Jihad and S. Abdullah, \"Investigating composite neighbourhood\nstructure for attribute reduction in rough set theory,\" presented at the\nIntelligent Systems Design and Applications (ISDA), 10th International\nConference, 2010.\n[17] Y. Z. Arajy and S. Abdullah, \"Hybrid variable neighbourhood search\nalgorithm for attribute reduction in Rough Set Theory,\" presented at the\nIntelligent Systems Design and Applications (ISDA), 2010.\n[18] S. Abdullah, N. R. Sabar, M. Z. A. Nazri, H. Turabieh, and B.\nMcCollum, \"A constructive hyper-heuristics for rough set attribute\nreduction,\" presented at the Intelligent Systems Design and Applications\n(ISDA), 2010.\n[19] M. Mafarja and S. Abdullah, \"Modified great deluge for attribute\nreduction in rough set theory,\" presented at the Fuzzy Systems and\nKnowledge Discovery (FSKD), 2011.\n[20] D. Koller and M. Sahami, \"Toward Optimal Feature Selection,\"\npresented at the International Conference on Machine Learning 1996.\n[21] R. Kohavi and G. H. John, \"Wrappers for feature subset selection,\"\nArtificial Intelligence vol. 97, 1997, pp. 273-324.\n[22] G. H. John, R. Kohavi, and K. Pfleger, \"Irrelevant Features and the\nSubset Selection Problem\", 1994.\n[23] R. Jensen and Q. Shen, Computational Intelligence and Feature\nSelection: Rough and Fuzzy Approaches: Wiley-IEEE Press, 2008.\n[24] J. Dong, N. Zhong, and S. Ohsuga, \"Using Rough Sets with Heuristics\nfor Feature Selection,\" presented at the Proceedings of the 7th\nInternational Workshop on New Directions in Rough Sets, Data Mining,\nand Granular-Soft Computing, 1999.\n[25] J. Bazan, H. S. Nguyen, S. H. Nguyen, P. Synak, and J. Wróblewski,\n\"Rough set algorithms in classification problem,\" Rough Set Methods\nand Applications. Physica Verlag, 2000, pp. 49–88.\n[26] P. Moscato, \"On Evolution, Search, Optimization, Genetic Algorithms\nand Martial Arts - Towards Memetic Algorithms,\" California Instiyute\nof Technology, Pasadena, CA1989.\n[27] C. Guerra-Salcedo, S. Chen, D. Whitley, and S. Smith, \"Fast and\naccurate feature selection using hybrid genetic strategies,\" presented at\nthe Genetic and Evolutionary Computation Conf, 1999.\n[28] I. S. Oh, J. S. Lee, and B. R. Moon, \"Hybrid genetic algorithms for\nfeature selection,\" Pattern Analysis and Machine Intelligence, IEEE\nTransactions on, vol. 26, 2004, pp. 1424-1437.\n[29] N. Krasnogor, \"Studies on the Theory and Design Space of Memetic\nAlgorithms\" PhD, University of the West of England, 2002, 2002. [30] W. E. Hart, N. Krasnogor, and J. E. Smith, \"Recent Advances in\nMemetic Algorithms,\" vol. 166, 2005.\n[31] J. H. Holland, Adaptation in natural and artificial systems: MIT Press,\n1992.\n[32] J. Yang and V. G. Honavar, \"Feature Subset Selection Using a Genetic\nAlgorithm,\" IEEE Intelligent Systems, vol. 13, pp. 44-49, 1998.\n[33] Z. Michalewicz, Genetic algorithms+ data structures: Springer, 1996.\n[34] L. A. Zadeh, \"Fuzzy sets,\" Information and Control, vol. 8, 1965, pp.\n338-353.\n[35] R. Jensen and Q. Shen, \"New approaches to fuzzy-rough feature\nselection,\" Fuzzy Systems, IEEE Transactions on, vol. 17, 2009, pp. 824-\n838.\n[36] E. Cox, The fuzzy systems handbook: a practitioner's guide to building,\nusing, and maintaining fuzzy systems: Academic Press Professional, Inc.,\n1994.\n[37] H. Zimmermann, Fuzzy Set Theory and its Applications: Kluwer\nAcademic Publishers, Boston, 1996.\n[38] G. Dueck, \"New Optimization Heuristics The Great Deluge Algorithm\nand the Record-to-Record Travel,\" Journal of Computational Physics,,\nvol. 104, 1993, pp. 86-92.\n[39] R. Jensen and Q. Shen, \"Finding Rough Set Reducts with Ant Colony\nOptimization,\" in Proceedings of the 2003 UK Workshop on\nComputational Intelligence, ed, 2003, pp. 15–22\n[40] A. Øhrn, \"Discernibility and rough sets in medicine: tools and\napplications,\" Department of Computer and Information Science,\nNorwegian University of Science and Technology, Trondheim, Norway,\n1999.\n[41] S. Abdullah, N.R. Sabar, M.Z. Ahmad Nazri, M. Ayob. \"An Exponential\nMonte-Carlo algorithm for feature selection problems\", Computers &\nIndustrial Engineering. vol 67 (2014), pp 160-167."]}

MARA Junior Science College (MRSM) Lenggong is one of the educational institutes under Majlis Amanah Rakyat (MARA). Based on the current academic performance and selected criteria of 6A's in the Penilaian Menengah Rendah (PMR, now it is known as PT3), rationally there should be no reason for the failure to achieve excellent results in the Sijil Pelajaran Malaysia (SPM). However, every time the results are announced, the average school achievement grade (GPS) does not meet the performance goals of an average grade of 1.00 for PMR and below 2.00 for SPM, even though it has been in operation for 10 years. Therefore, this research aimed at identifying the influencing factors that affected the students' academic performance. Early prediction is one of the strategies performed in order to improve the students' performance. Neural network and fuzzy logic models are used to realize the accurate prediction based on three factors namely demography, academic and co-curricular activities, including a combination of all three factors. Demography, academic and co-curricular information for the year 2008 to 2010 SPM candidates of MRSM Lenggong are the data sample used. It can be concluded that the prediction outcome using the neural network model shows that the academic factor influences the students' academic performance with the prediction accuracy around 93.65%. Meanwhile, the fuzzy logic model gives an opposite result, where the students' academic performance has also been influenced by the demography factor with an accuracy of 87.00%. Although different techniques yield different results, it is undeniable that the combination of demography and academic factors establishes a solid outcome in identifying the students' present and future academic performances.

In this paper, a class of discrete Radon transforms namely Finite Radon Transform (FRAT) was proposed as a modulation technique in the realization of Orthogonal Frequency Division Multiplexing (OFDM). The proposed FRAT operates as a data mapper in the OFDM transceiver instead of the conventional phase shift mapping and quadrature amplitude mapping that are usually used with the standard OFDM based on Fast Fourier Transform (FFT), by the way that ensure increasing the orthogonality of the system. The Fourier domain approach was found here to be the more suitable way for obtaining the forward and inverse FRAT. This structure resulted in a more suitable realization of conventional FFT- OFDM. It was shown that this application increases the orthogonality significantly in this case due to the use of Inverse Fast Fourier Transform (IFFT) twice, namely, in the data mapping and in the sub-carrier modulation also due to the use of an efficient algorithm in determining the FRAT coefficients called the optimal ordering method. The proposed approach was tested and compared with conventional OFDM, for additive white Gaussian noise (AWGN) channel, flat fading channel, and multi-path frequency selective fading channel. The obtained results showed that the proposed system has improved the bit error rate (BER) performance by reducing inter-symbol interference (ISI) and inter-carrier interference (ICI), comparing with conventional OFDM system.

Attribute reduction is a combinatorial optimization problem in data mining that aims to find minimal reducts from large set of attributes. The problem is exacerbated if the number of instances is large. Therefore, this paper concentrates on a double treatment iterative improvement algorithm with intelligent selection on composite neighbourhood structure to solve the attribute reduction problems and to obtain near optimal reducts. The algorithm works iteratively with only accepting an improved solution. The proposed approach has been tested on a set of 13 benchmark datasets taken from the University of California, Irvine (UCI) machine learning repository in line with the state-of-the-art methods. The 13 datasets have been chosen due to the differences in size and complexity in order to test the stability of the proposed algorithm. The experimental results show that the proposed approach is able to produce competitive results for the tested datasets.

This paper presents a novel study of evaluating non-ionizing effect of 2.45 GHz Wireless Body Area Networks (WBAN) radiofrequency (RF) electromagnetic fields (EMF) exposure on human physiological parameters and cognitive performance. The study aims to test the hypothesis whether exposure of 2.45 GHz WBAN radio electromagnetic fields may affect physiological parameters and cognitive performance of human. Twenty healthy volunteers are involved in the test and exposed to 2.45 GHz WBAN RF radiation, emitted by a planar textile monopole antenna. Physiological measures of body temperature, systolic blood pressure, diastolic blood pressure and heart rate are obtained, along with cognitive performance outcomes. Results indicated that no significant difference is observed in any of the three sessions (pre, exposure and post) for all physiological parameters, p > 0.05. Insufficient evident is found to indicate a difference in mean of all cognitive tests between WBAN RF and Sham exposure sessions, p’s > 0.05.

The optimisation of the nurse rostering problem is chosen in this work seeking to improve the organization of hospital duties and to elevate health care by enhancing the quality of the decision-making process. Nurse rostering is a difficult and complex problem with a large number of demands and requirements that conflict with hospital workload constraints in terms of employee work regulations and personal preferences. We propose a variable population-based metaheuristic algorithm, the chemical reaction optimisation (CRO), to solve the NRP at the First International Nurse Rostering Competition (2010). The CRO algorithm features an adaptive search procedure that systematically controls the selection between an intensive search strategy and diversification search based on specific criteria to reach the best solution. Computational results were measured with three complexity levels as a total of 30 variant instances based on real-world constraints.

In this paper, three levels of analysis and synthesis filter banks were used to create coefficients for a continuous wavelet transform (CWT) and discrete wavelet transform (DWT). The main property of these wavelet transform schemes is their ability to construct the transmitted signal across a log-normal fading channel over additive white Gaussian noise (AWGN). Wireless rake-receiver structure was chosen as a major application to reduce the inter-symbol interference (ISI) and to minimize the noise. In this work, a new scheme of rake receiver is proposed to receive indoor, multi-path components (MPCs) for ultra-wideband (UWB) wireless communication systems. Rake receivers consist of a continuous wavelet rake (CW-rake) and a discrete wavelet rake (DW-rake), and they use huge bandwidth (7.5 GHz), as reported by the Federal Communications Commission (FCC). The indoor channel models chose for analysis in this research were the non line-of-sight (LOS) channel model (CM4 from 4 to 10 meters) to show the behavior ...

This paper is to study the dielectric properties and microwave absorption of rice husk ash/polyester (RHAP) composites. The RHAP composites prepared with different weight ratio (40–80 wt. %) of rice husk ash (RHA) loading into polyester was fabricated. A rectangular waveguide transmission line method was used to measure the dielectric properties of the RHAP composites. The RHAP samples were designed and simulated with different thickness and percentage of RHA loading by using Computer Simulation Technology Microwave Studio (CST-MWS) software. The materials, their dielectrics properties measurement and microwave absorption result over 12.4–18 GHz (Ku-Band) frequency range are discussed. The dielectric properties of composites increase with increasing loading the RA wt%. The RHAP sample with different thickness was investigated in Ku-Band. The microwave absorption was up to 99.84 %, using 80 % loading of RHA with thickness 15 mm at 13.81 GHz, and showing the RHAP composites is applicable as microwave absorber.

For high data rate propagation in wireless ultra-wideband (UWB) communication systems, the inter-symbol interference (ISI), multiple-access interference (MAI), and multiple-users interference (MUI) are influencing the performance of the wireless systems. In this paper, the rake-receiver was presented with the spread signal by direct sequence spread spectrum (DS-SS) technique. The adaptive rake-receiver structure was shown with adjusting the receiver tap weights using least mean squares (LMS), normalized least mean squares (NLMS), and affine projection algorithms (APA) to support the weak signals by noise cancellation and mitigate the interferences. To minimize the data convergence speed and to reduce the computational complexity by the previous algorithms, a well-known approach of partial-updates (PU) adaptive filters were employed with algorithms, such as sequential-partial, periodic-partial, M-max-partial, and selective-partial updates (SPU) in the proposed system. The simulation results of bit error ra...

This study aims to investigate the relationship between government ownership and dividend policy of Malaysian listed companies. Specifically, the objective of the study is to examine whether government and state ownerships influence dividend payout and dividend per share. The study used a sample of 400 companies, w h i c h were randomly chosen. Two dependent variables were used as a proxy for dividend namely the dividend per share (DPS) and dividend payout ratio (DPR), while 8 government agencies (EPF, LTH, KWAP, LTAT, MKD, KNB, PNB and STATE) represented government ownership. Since dividends are truncated, the Tobit model was utilized to examine the effect of government ownership. The findings showed that there is no relationship between government ownership and dividends when using the DPS as the dependent variable. However, when DPR is used, the result showed that government ownership could affect the dividend policy. Furthermore, it is found that privately funded government agencies were more likely to affect dividends. This result indicates that these government agencies influence the proportion of earnings distribution or the payable amount rather than the amount of dividend per unit of shares.

Attribute reduction is one of the main contributions in rough set theory (RST) that tries to discover all possible reducts by eliminating redundant attributes while maintaining the information of the problem in hand. In this paper, we propose a meta-heuristic methodology called a double treatment iterative improvement algorithm with intelligent selection of composite neighbourhood structure, to solve the attribute reduction problems and to obtain near optimal reducts. The algorithm works iteratively by only accepting an improved solution. The proposed approach has been tried on a set of 13 benchmark datasets taken from the University of California Irvine (UCI) machine learning repository in line with the state-of-the-art methods. Thirteen datasets have been chosen due to the differences in size and complexity in order to test the stability of the proposed algorithm. The experimental results demonstrate that the proposed approach is able to produce competitive results for the tested datasets.

This paper proposes a robust intelligent technique to produce the initial population close to the optimal solution for the job-shop scheduling problem (JSSP). The proposed technique is designed by a new heuristic based on an intelligent skip from the primal point of the solution space to a better one that considers a new classification of jobs on machines. This new classification is named mPlates-Jobs. The main advantages of the proposed technique are its capability to produce any size of the initial population, its proximity to the optimal solution, and its capability to observe the best-known solution in the generated initial population for benchmark datasets. The comparison of the experimental results with those of Kuczapski’s, Yahyaoui’s, Moghaddam and Giffler’s, and Thompson’s initialization techniques, which are considered the four state-of-the-art initialization techniques, proves the abovementioned advantages. In this study, the proposed intelligent initialization technique can be considered a fast and intelligent heuristic algorithm to solve the JSSP based on the quality of its results. DOI: http://dx.doi.org/10.5755/j01.itc.43.3.3536

Orthogonal frequency division multiplexing (OFDM) is a very interesting approach for high data rate transmission in a multipath fading environment that leads to intersymbol interference (ISI). In this paper, two steps are used to improve the error rate performance of OFDM system. First, the discrete multiwavelet transform (DMWT) is proposed instead of fast Fourier transform (FFT) to obtain high orthogonality between subcarriers and hence reduce (ISI). Second, the performance of OFDM based on DMWT is examined for different modulation schemes such as M-PSK (M-ary phase shift keying) and M-QAM (M-ary quadrature amplitude modulation) to achieve high data rate. The simulation results demonstrated that, for high capacity data rate transmission, the M-QAM modulation is better than the M-PSK modulation.

For high data rate propagation and indoor obstacles in wireless ultra-wideband (UWB) communication systems, the signal fading and noises are influencing the performance of the wireless systems. In this paper, the rake-receiver was presented with the spread signal by time-hopping spread spectrum (TH-SS) technique. The adaptive filter used in rake-receiver structure was shown with adjusting the receiver tap weights using Euclidean Direction Search (EDS) algorithm to support the weak signals by noise cancellation. To minimize the data convergence speed and to reduce the computational complexity by the previous algorithms, a well-known approach of selective-updates (SU) adaptive filter was employed with algorithms, such as sequential-selective, periodic-selective, and M-max-selective in the proposed system. The simulation results of bit error rate (BER) versus signal-to-noise ratio (SNR) are illustrated to show the performance of selective-update algorithm that has nearly comparable performance with the full update adaptive filters.

In this paper, an over-sampling inverse discrete multiwavelet transform (IDMWT) is suggested as a modulator strategy instead of inverse fast Fourier transform (IFFT) in the realization of the multicarrier code division multiple access (MC-CDMA) system. The suggested strategy was applied on the MC-CDMA with additive white Gaussian noise (AWGN) channel, flat fading channel and frequency selective fading channel. Simulation results showed that, the proposed method gives a better bit error rate (BER) efficiency than the traditional MC-CDMA model based on fast Fourier transform (FFT) and MC-CDMA based on discrete wavelet transform (DWT).

Electromagnetic algorithm is a population based meta-heuristic which imitates the attraction and repulsion of sample points. In this paper, we propose an electromagnetic algorithm to simultaneously tune the structure and parameter of the feed forward neural network. Each solution in the electromagnetic algorithm contains both the design structure and the parameters values of the neural network. This solution later will be used by the neural network to represents its configuration. The classification accuracy returned by the neural network represents the quality of the solution. The performance of the proposed method is verified by using the well-known classification benchmarks and compared against the latest methodologies in the literature. Empirical results demonstrate that the proposed algorithm is able to obtain competitive results, when compared to the best-known results in the literature.

Attribute reduction is one of the main contributions in Rough Set Theory RST that tries to find all possible reducts by eliminating redundant attributes while maintaining the information of the problem in hand. In this paper, we propose a meta-heuristic approach called a Variable Neighbourhood Iterated Improvement Search VNS-IIS algorithm for attribute reduction. It is a combination of the variable neighbourhood search with the iterated search algorithm where two local search algorithms i.e. a random iterated local search and a sequential iterated local search algorithm are employed in a parallel strategy. In VNS-IIS, an improved solution will always be accepted. The proposed method has been tested on the 13 well-known datasets that are available in the UCI machine learning repository. Experimental results show that the VNS-IIS is able to obtain competitive results when compared with other approaches mentioned in the literature in terms of minimal reducts.

This paper presents the different layers of microwave absorbing materials (MAM) effects microwave absorption performance. The different layers microwave absorbers were simulated using Computer Simulation Technology (CST) Microwave Studio simulation software. The absorption of different layer MAM will be investigated. The absorption in microwave frequency between different arrangement layers of MAM was compared.

Electromagnetic Interference (EMI) is a serious threat to the modern unprotected microelectronics-based integrated systems. Various techniques are implemented, to protect the mission critical and sensitive systems, against the EMI threats. One of the most important techniques is the use of absorbing material to suppress the EMI at the sources and/or receptors to ensure their Electromagnetic compatibility (EMC). Rice husk is an agro-waste and had been identified, as a naturally available cheaper anechoic material, in recent years. Some of the investigations, based on the transmission line theory, in the C band frequency range from 4 to 8 GHz, are presented in this paper. The main goal of this paper was to investigate the potential use of a single layer of the agro-waste for no reflection (perfectly matched) condition. We fabricated samples by mixing the Rice Husk Powder (RHP) with a commercially available, an easy to apply and non-toxic, glue and complex permittivity was measured. These measured values were then used to determine the perfect impedance matched condition and finally we simulate the material using CST MWS software.

A number of properties of Artificial Neural Networks (ANNs) make them suitable for many applications such as time series prediction problem. However, lack of training model which finds a global optimal set of weights has been disadvantaged in some real-world problems. Genetic algorithm is an optimization procedure which is superior at exploring a search space in an intelligent method. In this paper we present a genetic-based algorithm to optimize the weights and biases of the ANN. In this work we tune the parameters of the genetic algorithm using Taguchi method. To test the method two standard time series prediction problems are employed. The results are compared to the methods in the literature. The comparison showed the superiority of the proposed method.

In this paper, two single-solution-based meta-heuristic methods for attribute reduction are presented. The first one is based on a record-to-record travel algorithm, while the second is based on a Great Deluge algorithm. These two methods are coded as RRT and m-GD, respectively. Both algorithms are deterministic optimisation algorithms, where their structures are inspired by and resemble the Simulated Annealing algorithm, while they differ in the acceptance of worse solutions. Moreover, they belong to the same family of meta-heuristic algorithms that try to avoid stacking in the local optima by accepting non-improving neighbours. The obtained reducts from both algorithms were passed to ROSETTA and the classification accuracy and the number of generated rules are reported. Computational experiments confirm that RRT m-GD is able to select the most informative attributes which leads to a higher classification accuracy.

In this paper we have presented a combination of two meta-heuristics, namely great deluge and tabu search, for solving the university course timetabling problem. This problem occurs during the assignment of a set of courses to specific timeslots and rooms within a working week and subject to a variety of hard and soft constraints. Essentially a set of hard constraints must be satisfied in order to obtain a feasible solution and satisfying as many as of the soft constraints as possible. The algorithm is tested over two databases: eleven enrolment-based benchmark datasets representing one large, five medium and five small problems and curriculum-based datasets used and developed from the International Timetabling Competition, ITC2007 UD2 problems. A new strategy has been introduced to control the application of a set of neighbourhood structures using the tabu search and great deluge. The results demonstrate that our approach is able to produce solutions that have lower penalties on all the small and medium problems in eleven enrolment-based datasets and can produce solutions with comparable results on the curriculum-based datasets with lower penalties on several data instances when compared against other techniques from the literature.

Data clustering is the first step in data mining. It aims at finding homogeneous groups of objects based on the degree of similarity and dissimilarity of their attributes. Most of the existing clustering methods are based on a single criterion to measure the goodness of clusters. In most cases, these methods are not suitable for different types of datasets with different characteristics. In this study, biogeography-based optimisation BBO and great deluge GD algorithms are combined to address the data clustering as single objective optimisation problem; two versions of the proposed approach that employed two different clustering criteria as the objective function have been investigated using fourteen 2D synthetic benchmark datasets. The quality of the obtained clusters of both versions of the proposed approach is insufficient with respect to the external evaluation function i.e. F-measure. Thus, the data-clustering problem preferred to be tackled as multi-objective clustering algorithms.

The University course timetabling problem is known as a NP-hard problem. It is a complex problem wherein the problem size can become huge due to limited resources (e.g. amount of rooms, their capacities and number availability of lecturers) and the requirements for these resources. The university course timetabling problem involves assigning a given number of events to a limited number of timeslots and rooms under a given set of constraints; the objective is to satisfy the hard constraints and minimize the violation of soft constraints. In this paper, a Differential Evolution (DE) algorithm is proposed. DE algorithm relies on the mutation operation to reduce the convergence time while reducing the penalty cost of solution. The proposed algorithm is tested over eleven benchmark datasets (representing one large, five medium and five small problems). Experimental results show that our approach is able to generate competitive results when compared with previous available approaches. Possible extensions upon this simple approach are also discussed.

Attribute reduction can be defined as a process of selecting a minimal subset of attributes (based on a rough set theory as a mathematical tool) from an original set with least lose of information. In this work, a modified great deluge algorithm has been employed on attribute reduction problems, where the search space is divided into three regions. In each region, the water level is updated using a different scheme based on the quality of the current solution, instead of using a linear mechanism which is used in the original great deluge algorithm. The proposed approach is tested on 13 standard benchmark datasets and able to obtain promising results when compared to state-of-the-art approaches.

In this paper, we present an efficient algorithm for cluster analysis, which is based on gravitational search and a heuristic search algorithm. In the proposed algorithm, called GSA-HS, the gravitational search algorithm is used to find a near optimal solution for clustering problem, and then at the next step a heuristic search algorithm is applied to improve the initial solution by searching around it. Four benchmark datasets are used to evaluate and to compare the performance of the presented algorithm with two other famous clustering algorithms, i.e. K-means and particle swarm optimization algorithm. The results show that the proposed algorithm can find high quality clusters in all the tested datasets.

Microarray technology provides a platform to study expression level of thousands of genes simultaneously, but its high dimensionality and noisy nature forces the usage of dimensionality reduction techniques. Among these techniques feature selection seems to be more favorable due to its goal to preserve feature semantic. Feature selection is also called gene selection while applied to genetic data. Inherently, gene selection objectives are manifold which makes it a proper candidate for multi-objective optimization. There are three different ways to deal with fitness evaluation in multi-objective literature. Between these three the Pareto base approach seems to deliver more promising advantages to the biologist, but it did not grab that much attention till now, probably due to its computational complexity. The intention of this paper is to provide an insight to gene selection problem from multi-objective perspective. Although, covering all the proposed methods are impossible, but hopefully those algorithms discussed here are enough to show the common trend in multi-objective gene selection in microarray data.

Most of the methods to solve job-shop scheduling problem (JSSP) are population-based and one of the strategies to reduce the time to reach the optimal solution is to produce an initial population that firstly has suitable distribution on space solution, secondly some of its points settle nearby to the optimal solution and lastly generate it in the shortest possible time. But since JSSP is one of the most difficult NP-complete problems and its space solution is complex, most of the previous researchers have preferred to utilize random methods or priority rules for producing initial population. In this paper, by mapping each schedule to a unique sequence of jobs on machines matrix (SJM), we have proposed the novel concept of plates, and have redefined and adapted concepts of tail and head path and have designed evaluator functions between SJM matrix and its corresponding schedule aiming at identifying gaps in the obtained schedule, we have proposed three novel initialization procedures. The proposed procedures have been run on 73 benchmark datasets and their results have been compared with some existing initialization procedures and even some approximation algorithms for solving JSSP. Based on this comparison, we have seen the proposed procedures have the significant advantage both in the quality-generated points and in the time producing them. The more interesting point in the implementation of proposed procedures on some datasets is that we see the best known solution in the produced initial population.

Timber Harvest Planning (THP) model is used to determine which forest areas to be harvested in different time periods with objective to maximize profit subject to harvesting regulations. Various THP models have been developed in the Western countries based on optimisation approach to generate an optimal or feasible harvest plan. However similar studies have gained less attention in Tropical countries. Thus, this study proposes an optimisation model of THP that reflects selective cutting in Peninsular Malaysia. The model was tested on seven blocks that consists a total of 636 trees with different size and species. We found that, optimisation approach generates selectively timber harvest plan with higher volume and less damage.

2011 3rd Conference on Data Mining and Optimization, DMO 2011, 28 June 2011 through 29 June 2011, Putrajaya

Data clustering, the process of grouping similar objects in a set of observations is one of the attractive and main tasks in data mining that is used in many areas and applications such as text clustering and information retrieval, data compaction, fraud detection, biology, computer vision, data summarization, marketing and customer analysis, etc. The well-known k-means algorithm, which widely applied to the clustering problem, has the drawbacks of depending on the initial state of centroids and may converge to the local optima rather than global optima. A data clustering algorithm based on the gravitational search algorithm (GSA) is proposed in this research. In this algorithm, some candidate solutions for clustering problem are created randomly and then interact with one another via Newton's gravity law to search the problem space. The performance of the presented algorithm is compared with three other well-known clustering algorithms, including k-means, genetic algorithm (GA), and particle swarm optimization algorithm (PSO) on four real and standard datasets. Experimental results confirm that the GSA is a robust and viable method for data clustering.

The Big Bang–Big Crunch (BB–BC) algorithm is a new optimization method that is based on one of the theories of the evolution of the universe namely the Big Bang and Big Crunch theory. According to this method, in the Big Bang phase some candidate solutions to the optimization problem are randomly generated and spread all over the search space. In the Big Crunch phase, randomly distributed candidate solutions are drawn into a single representative point via a center of population or minimal cost approach. This paper presents BB-BC based novel approach for data clustering. The simulation results indicate the applicability and potential of this algorithm on data clustering.

Artificial Bee Colony (ABC) is a population-based algorithm that employed the natural metaphors, based on foraging behavior of honey bee swarm. In ABC algorithm, there are three categories of bees. Employed bees select a random solution and apply a random neighborhood structure (exploration process), onlooker bees choose a food source depending on a selection strategy (exploitation process), and scout bees involves to search for new food sources (scouting process). In this paper, firstly we introduce a disruptive selection strategy for onlooker bees, to improve the diversity of the population and the premature convergence, and also a local search (i.e. simulated annealing) is introduced, in order to attain a balance between exploration and exploitation processes. Furthermore, a self adaptive strategy for selecting neighborhood structures is added to further enhance the local intensification capability. Experimental results show that the hybrid ABC with disruptive selection strategy outperforms the ABC algorithm alone when tested on examination timetabling problems.

Hyper-heuristics can be defined as search method for selecting or generating heuristics to solve difficult problem. A high level heuristic therefore operate on a set of low level heuristics with the overall aim of selecting the most suitable set of low level heuristics at a particular point in generating an overall solution. In this work, we propose a set of constructive hyper-heuristics for solving attribute reduction problems. At the high level, the hyper-heuristics (at each iteration) adaptively select the most suitable low level heuristics using roulette wheel selection mechanism. Whilst, at the underlying low level, four low level heuristics are used to gradually, and indirectly construct the solution. The proposed hyper-heuristics has been evaluated on a widely used UCI datasets. Results show that our hyper-heuristic produces good quality solutions when compared against other metaheuristic and outperforms other approaches on some benchmark instances.

This paper presents a multi-objective post enrolment course timetabling problem as a new case study. We added a new soft constraint to the original single objective problem to both increase the complexity and represent a real world course timetabling problem. The new soft constraint introduced here attempts to minimize the total number of waiting timeslots in between courses for every student in a day. We proposed a Non-dominated Sorting Genetic Algorithm-II with a variable population size, called NSGA-II VPS, based on a given lifetime for each individual that is evaluated at the time of its birth. The algorithm was tested on the standard benchmark problems and experimental results show that the proposed method demonstrably improved upon the original approach (NSGA-II).

In general, course timetabling refers to assignment processes that assign events (courses) to a given rooms and timeslots subject to a list of hard and soft constraints. It is a challenging task for the educational institutions. In this study we employed a great deluge algorithm with kempe chain neighbourhood structure as an improvement algorithm. The Round Robin (RR) algorithm is used to control the selection of neighbourhood structures within the great deluge algorithm. The performance of our approach is tested over eleven benchmark datasets (representing one large, five medium and five small problems). Experimental results show that our approach is able to generate competitive results when compared with previous available approaches. Possible extensions upon this simple approach are also discussed.

Attribute reduction is the process of selecting a subset of features from the original set of features that forms patterns in a given dataset. It can be defined as a process to eliminate redundant attributes and at the same time is able to avoid any information loss, so that the selected subset is sufficient to describe the original features. In this paper, we present a great deluge algorithm for attribute reduction in rough set theory (GD-RSAR). Great deluge is a meta-heuristic approach that is less parameter dependent. There are only two parameters needed; the time to “spend” and the expected final solution. The algorithm always accepts improved solutions. The worse solution will be accepted if it is better than the upper boundary value or “level”. GD-RSAR has been tested on the public domain datasets available in UCI. Experimental results on benchmark datasets demonstrate that this approach is effective and able to obtain competitive results compared to previous available methods. Possible extensions upon this simple approach are also discussed.

The university course timetabling problem involves assigning a given number of events into a limited number of timeslots and rooms under a given set of constraints; the objective is to satisfy the hard constraints (essential requirements) and minimize the violation of soft constraints (desirable requirements). In this study we employed a Dual-sequence Simulated Annealing (DSA) algorithm as an improvement algorithm. The Round Robin (RR) algorithm is used to control the selection of neighbourhood structures within DSA. The performance of our approach is tested over eleven benchmark datasets. Experimental results show that our approach is able to generate competitive results when compared with other state-of-the-art techniques.

The university course timetabling problem (CTTP) involves assigning a given number of events into a limited number of timeslots and rooms under a given set of constraint. The objective is to satisfy the hard constraints (essential requirements) and minimise the violation of soft constraints (desirable requirements). In this study, we apply three algorithms to the CTTP problem: Great Deluge, Simulated Annealing and Hill Climbing. We use a Round Robin Scheduling Algorithm (RR) as a strategy to control the application of these three algorithms. The performance of our approach is tested over eleven benchmark datasets: one large, five medium and five small problems. Competitive results have been obtained when compared with other state-of-the-art techniques.

The objective of this research is to develop a diagnosis system to recognize the paddy diseases, which are Blast Disease (BD), Brown-Spot Disease (BSD), and Narrow Brown-Spot Disease (NBSD). This paper concentrates on extracting paddy features through off-line image. The methodology involves converting the RGB images into a binary image using variable, global and automatic threshold based on Otsu method. A morphological algorithm is used to remove noises by using region filling technique. Then image characteristics consisting of lesion percentage, lesion type, boundary color, spot color, and broken paddy leaf color are extracted from paddy leaf images. Consequently, by employing production rule technique, the paddy diseases are recognized about 87.5 percent of accuracy rates. This prototype has a very great potential to be further improved in the future.

In this paper, we present a hybridization of an electromagnetic-like mechanism (EM) and the great deluge (GD) algorithm. This technique can be seen as a dynamic approach as an estimated quality of a new solution and a decay rate are calculated each iteration during the search process. These values are depending on a force value calculated using the EM approach. It is observed that applying these dynamic values help generate high quality solutions. Experimental results on benchmark examination timetabling problems demonstrate the effectiveness of this hybrid EM-GD approach compared with previous available methods. Possible extensions upon this simple approach are also discussed.

The main objective of this research is to develop a prototype system for diagnosing paddy diseases, which are Blast Disease (BD), Brown-Spot Disease (BSD), and Narrow Brown-Spot Disease (NBSD). This paper concentrates on extracting paddy features through off-line image. The methodology involves image acquisition, converting the RGB images into a binary image using automatic thresholding based on local entropy threshold and Otsu method. A morphological algorithm is used to remove noises by using region filling technique. Then, the image characteristics consisting of lesion type, boundary colour, spot colour, and broken paddy leaf colour are extracted from paddy leaf images. Consequently, by employing production rule technique, the paddy diseases are recognized about 94.7 percent of accuracy rates. This prototype has a very great potential to be further improved in the future.