A robust ensemble regression model for reconstructing genetic networks
- Authors: Gamage, Hasini , Chetty, Madhu , Lim, Suryani , Hallinan, Jennifer , Nguyen, Huy
- Date: 2023
- Type: Text , Conference paper
- Relation: 2023 International Joint Conference on Neural Networks, IJCNN 2023 Vol. 2023-June
- Full Text: false
- Reviewed:
- Description: Genetic networks contain important information about biological processes, including regulatory relationships and gene-gene interactions. Numerous methods, using high-dimensional gene expression data have been developed to capture these interactions. These gene expression data, generated using high-throughput technologies, are prone to noise. However, most existing network inference methods are unable to cope with noisy data, making genetic network reconstruction challenging. In this paper, we propose a novel ensemble regression model combining quantile regression and cross-validated Ridge regression, RidgeCV, to infer interactions from noisy gene expression data. The application of quantile regression to GRN inference is novel, and its design makes it appropriate for noisy data. RidgeCV also addresses other important issues, such as data overfitting and multicollinearity. First, each regression method is independently applied to gene expression data and the output of these methods, in the form of ranked gene lists, is aggregated using a novel gene score-based method by considering the gene rank and model importance. The model importance score is evaluated based on an adjusted coefficient of determination. This method implicitly includes majority voting by averaging each gene score value across all models. The proposed model was tested on the DREAM4 datasets and publicly available small-scale real-world network datasets. Experiments with noisy datasets showed that the proposed ensemble model is more accurate and efficient than other state-of-the-art methods. © 2023 IEEE.
Blockchain based smart auction mechanism for distributed peer-to-peer energy trading
- Authors: Islam, Md Ezazul , Chetty, Madhu , Lim, Suryani , Chadhar, Mehmood , Islam, Syed
- Date: 2022
- Type: Text , Conference paper
- Relation: 55th Annual Hawaii International Conference on System Sciences, HICSS 2022, Virtual, online, 3-7 January 2022, Proceedings of the Annual Hawaii International Conference on System Sciences Vol. 2022-January, p. 6013-6022
- Full Text:
- Reviewed:
- Description: Blockchain based framework provides data immutability in a distributed network. In this paper, we investigate the application of blockchain for peer-to-peer (P2P) energy trading. Traditional energy trading systems use simple passing mechanisms and basic pricing methods, thus adversely affect the efficiency and buyers' social welfare. We propose a blockchain based energy trading mechanism that uses smart passing of unspent auction reservations to (a) minimise the time taken to settle an auction (convergence time), (b) maximise the number of auction settlement; and (c) incorporate second-price auction pricing to maximise buyers' social welfare in a distributed double auction environment. The entire mechanism is implemented within Hyperledger Fabric, an open-source blockchain framework, to manage the data and provide smart contracts. Experiments show that our approach minimises the convergence time, maximises the number of auction settlement, and increases the social welfare of buyers compared to existing methods. © 2022 IEEE Computer Society. All rights reserved.
Ensemble regression modelling for genetic network inference
- Authors: Gamage, Hasini , Chetty, Madhu , Shatte, Adrian , Hallinan, Jennifer
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022, Ottawa Canada, 15-17 August 2022, 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022
- Full Text: false
- Reviewed:
- Description: An accurate reconstruction of Gene Regulatory Networks (GRNs) from time series gene expression data is crucial for discovering complex biological interactions. Among many different approaches for inferring GRNs, there are several methods which produce high false positive interactions, and are unstable, requiring fine tuning for many of their parameters. In this paper, we consider the GRN inference problem as a regression problem, and propose a simple ensemble regression-based feature selection model which is a combination of cross-validated Lasso and cross-validated Ridge algorithms for reconstructing GRNs. Due to the novelty of the proposed ensemble model, it is able to eliminate overfitting, multi co-linearity issues, and irrelevant genes within one computational approach. While observing the type of gene-gene regulatory interactions the regression model also identifies the direction of these interactions. A new coefficient of determination (R2)-based approach identifies the best model to fit the data among LassoCV and RidgeCV, and evaluates the model importance in term of gene-wise maximum in-degree which decides the maximum number of regulatory genes including self-regulations that can be selected from a given method. Then, an evaluated gene score-based majority voting technique aggregates the selected gene lists from each method. In our experiments, the performance of the proposed ensemble approach was evaluated using gene expression datasets from three small-scale real gene networks. Our proposed model outperformed other state-of-the-art methods, producing high true positives, reducing false positives, and obtaining high Structural Accuracy, while maintaining model stability and efficiency. © 2022 IEEE.
Integrating steady-state and dynamic gene expression data for improving genetic network modelling
- Authors: Gill, Jaskaran , Chetty, Madhu , Shatte, Adrian , Hallinan, Jennifer
- Date: 2022
- Type: Text , Conference paper
- Relation: 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022, Ottawa Canada, 15-17 August 2022, 2022 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2022
- Full Text: false
- Reviewed:
- Description: Reverse engineering of Gene Regulatory Networks (GRNs) from experimentally obtained high-throughput data is an active and promising area of research. Among several modelling techniques, the S-System model, a set of tightly coupled differential equations, mimics the complexities and dynamics of biochemical systems, and thus provides realistic GRN representation. While it offers mathematical flexibility and biological relevance, the high number of learning parameters can lead to a computational burden. In our earlier work, we addressed this issue by judicious use of prior knowledge. However, another major cause of computational load is the need for numerical integration of the differential equations for the estimation of S-system model parameters. In this paper, we propose a method to obtain initial model parameter values from the steady state of the system, thereby computing simpler and less complex algebraic equations compared to the regular differential equations of S-systems. These network parameters are input as prior knowledge for the optimization of the dynamic S-System using differential equations. The proposed framework includes a novel fitness evaluation for steady-state S-System models, a novel evolutionary parameter learning framework, and a technique to incorporate the candidate solutions in dynamic S-System modelling. Our proposed methodology reached optimal model parameter values quickly, requiring only one-third of the fitness function evaluations, compared to our previously reported DRNI (Dynamically regulated network initialization) method for S-System modelling. © 2022 IEEE.
Resilience of stablecoin reserve for distributed energy trading
- Authors: Islam, Md Ezazul , Chetty, Madhu , Lim, Suryani , Chadhar, Mehmood , Islam, Syed
- Date: 2022
- Type: Text , Conference paper
- Relation: 14th IEEE PES Asia-Pacific Power and Energy Engineering Conference, APPEEC 2022, Melbourne, Australia, 20-23 November 2022, Asia-Pacific Power and Energy Engineering Conference, APPEEC Vol. 2022-November
- Full Text: false
- Reviewed:
- Description: For payment settlement, a blockchain-based Peer-To-Peer (P2P) energy trading requires a stable medium of exchange with little price volatility. Stablecoins, the most suitable medium of exchange, gaining concentration even from central banks. A consortium of central banks recommends complying with capital and liquidity standards for the high-quality liquid asset (HQLA) for the solvency of banks or financial institutions. Stablecoin as HQLA requires the adaption of such standards in P2P energy trading for reserve resilience. We propose a mechanism (NF90) that controls the inflow of stablecoins responding to Liquidity Coverage Ratio (LCR) for reserve resilience. Basel III accord recommends 100% of LCR. We measure the efficiency of NF90 concerning LCR as a metric. We simulate the proposed mechanism in Hyperledger Fabric as a permissioned blockchain platform for decentralisation, data storage, and smart contract. Experiments show that NF90 is the most efficient inflow control mechanism compared to other simulated mechanisms. © 2022 IEEE.
An efficient boolean modelling approach for genetic network inference
- Authors: Gamage, Hasini , Chetty, Madhu , Shatte, Arian , Hallinan, Jennifer
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2021, Virtual, Online, 13-15 October 2021, 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2021
- Full Text:
- Reviewed:
- Description: The inference of Gene Regulatory Networks (GRNs) from time series gene expression data is an effective approach for unveiling important underlying gene-gene relationships and dynamics. While various computational models exist for accurate inference of GRNs, many are computationally inefficient, and do not focus on simultaneous inference of both network topology and dynamics. In this paper, we introduce a simple, Boolean network model-based solution for efficient inference of GRNs. First, the microarray expression data are discretized using the average gene expression value as a threshold. This step permits an experimental approach of defining the maximum indegree of a network. Next, regulatory genes, including the self-regulations for each target gene, are inferred using estimated multivariate mutual information-based Min-Redundancy Max-Relevance Criterion, and further accurate inference is performed by a swapping operation. Subsequently, we introduce a new method, combining Boolean network regulation modelling and Pearson correlation coefficient to identify the interaction types (inhibition or activation) of the regulatory genes. This method is utilized for the efficient determination of the optimal regulatory rule, consisting AND, OR, and NOT operators, by defining the accurate application of the NOT operation in conjunction and disjunction Boolean functions. The proposed approach is evaluated using two real gene expression datasets for an Escherichia coli gene regulatory network and a fission yeast cell cycle network. Although the Structural Accuracy is approximately the same as existing methods (MIBNI, REVEAL, Best-Fit, BIBN, and CST), the proposed method outperforms all these methods with respect to efficiency and Dynamic Accuracy. © 2021 IEEE.
Cost effective annotation framework using zero-shot text classification
- Authors: Kasthuriarachchy, Buddhika , Chetty, Madhu , Shatte, Adrian , Walls, Darren
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 International Joint Conference on Neural Networks, IJCNN 2021 Vol. 2021-July
- Full Text: false
- Reviewed:
- Description: Manual and high-quality annotation of social media data has enabled companies and researchers to develop improved implementations using natural language processing. However, human text-annotation is expensive and time-consuming. Crowd-sourcing platforms such as Amazon's Mechanical Turk (MTurk) can be leveraged for the creation of large training corpora for text classification tasks using social media data. Nevertheless, the quality of annotations can vary significantly, based on the interpretations and motivations of annotators completing the tasks. Further, the labelling cost of data through MTurk will increase if target messages are small and having a significant amount of noise (e.g. promotional messages on Twitter). In this work, we propose a new annotation framework to create high-quality human-annotated datasets for text classification from social media data. We present a zero-shot text classification based pre-annotation technique reducing the adverse effects arising due to the highly skewed distribution of data across target classes. The proposed framework significantly reduces the cost and time while maintaining the quality of the annotations. Being generic, it can be applied to annotating text data from any discipline. Our experiment with a Twitter data annotation using the proposed annotation framework shows a cost reduction of 80% with no compromise to quality. © 2021 IEEE.
Dynamically regulated initialization for S-system modelling of genetic networks
- Authors: Gill, Jaskaran , Chetty, Madhu , Shatte, Adrian , Hallinan, Jennifer
- Date: 2021
- Type: Text , Conference paper
- Relation: 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2021, Virtual, Online, 13-15 October 2021, 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology, CIBCB 2021
- Full Text: false
- Reviewed:
- Description: Reverse engineering of gene regulatory networks through temporal gene expression data is an active area of research. Among the plethora of modelling techniques under investigation is the decoupled S-system model, which attempts to capture the non-linearity of biological systems in detail. For the model, number of parameters to be estimated are significantly high even when the network is of small or medium scale. Thus, the inference process poses a significant computational burden. In this paper, we propose: (1) a novel population initialization technique, Dynamically Regulated Prediction Initialization (DRPI), which utilises prior knowledge of biological gene expression data to create a feedback loop to produce dynamically regulated high-quality individuals for initial population; (2) an adaptive fitness function; and (3) a method for the maintenance of population diversity. The aim of this work is to reduce the computational complexity of the inference algorithm, to speed up the entire process of reverse engineering. The performance of the proposed algorithm was evaluated against a benchmark dataset and compared with other methods from earlier work. The experimental results show that we succeeded in achieving higher accuracy results in lesser fitness evaluations, considerably reducing the computational burden of the inference process. © 2021 IEEE.
Factors affecting the organizational adoption of blockchain technology : an Australian perspective
- Authors: Malik, Saleem , Chadhar, Mehmood , Chetty, Madhu
- Date: 2021
- Type: Text , Conference paper
- Relation: 54th Annual Hawaii International Conference on System Sciences, HICSS 2021 Vol. 2020-January, p. 5597-5606
- Full Text:
- Reviewed:
- Description: Blockchain Technology (BCT) is a novel innovation that has the potential to transform industries, for instance, supply chain, energy, finance, and healthcare. However, despite the potential and the wide range of benefits reported, organizational adoption of BCT is low in several countries including Australia. Some studies investigated the adoption of BCT in different countries, however, there is a lack of research that examines the organizational adoption of BCT in Australia. This study fills this gap by exploring the factors, which influence BCT adoption among Australian organizations. To achieve this, we used an interpretative qualitative research approach based on the Technology, Organization, and Environment (TOE) framework and the Institutional Theory. The findings show that organizational adoption of BCT in Australia is influenced by perceived novelty, complexity, cost, and disintermediation feature of BCT; top management knowledge and support; government support, customer pressure, trading partner readiness, and consensus among trading partners. © 2021 IEEE Computer Society. All rights reserved.
An exploratory study of the adoption of blockchain technology among Australian organizations : a theoretical model
- Authors: Malik, Saleem , Chadhar, Mehmood , Chetty, Madhu , Vatanasakdakul, Savanid
- Date: 2020
- Type: Text , Conference paper
- Relation: 17th European, Mediterranean, and Middle Eastern Conference on Information Systems, EMCIS 2020; Dubai; 25-26 November 2020 Vol. 402, p. 205-220
- Full Text:
- Reviewed:
- Description: Scholarly and commercial literature indicates several applications of Blockchain Technology (BCT) in different industries e.g. health, finance, supply chain, government, and energy. Despite abundant benefits reported and growing prominence, BCT has been facing various challenges across the globe, including low adoption by organizations. There is a dearth of studies that examined the organizational adoption of blockchain technology, particularly in Australia. This lack of uptake provides the rationale to initiate this research to identify the factors influencing the Australian organizations to adopt BCT. To achieve this, we conducted a qualitative study based on the Technology, Organization, Environment (TOE) framework. The study proposes a theoretical model grounded on the findings of semi-structured interviews of blockchain experts in Australia. The proposed model shows that the organizational adoption of blockchain is influenced by perceived benefits, compatibility, and complexity, organization innovativeness, organizational learning capability, competitive intensity, government support, trading partner readiness, and standards uncertainty. © 2020, Springer Nature Switzerland AG.
Pre-trained language models with limited data for intent classification
- Authors: Kasthuriarachchy, Buddhika , Chetty, Madhu , Karmakar, Gour , Walls, Darren
- Date: 2020
- Type: Text , Conference proceedings , Conference paper
- Relation: 2020 International Joint Conference on Neural Networks, IJCNN 2020
- Full Text: false
- Reviewed:
- Description: Intent analysis is capturing the attention of both the industry and academia due to its commercial and noncommercial significance. The rapid growth of unstructured data of micro-blogging platforms, such as Twitter and Facebook, are amongst the important sources for intent analysis. However, the social media data are often noisy and diverse, thus making the task very challenging. Further, the intent analysis frequently suffers from lack of sufficient data because the labeled datasets are often manually annotated. Recently, BERT (Bidirectional Encoder Representation from Transformers), a state-of-the-art language representation model, has attracted attention for accurate language modelling. In this paper, we investigate the application of BERT for its suitability for intent analysis. We study the fine-tuning of the BERT model through inductive transfer learning and investigate methods to overcome the challenges due to limited data availability by proposing a novel semantic data augmentation approach. This technique generates synthetic sentences while preserving the label-compatibility using the semantic meaning of the sentences, to improve the intent classification accuracy. Thus, based on the considerations for finetuning and data augmentation, a systematic and novel step-bystep methodology is presented for applying the linguistic model BERT for intent classification with limited data available. Our results show that the pre-trained language can be effectively used with noisy social media data to achieve state-of-the-art accuracy in intent analysis under low labeled-data regime. Moreover, our results also confirm that the proposed text augmentation technique is effective in eliminating noisy synthetic sentences, thereby achieving further performance improvements. © 2020 IEEE.
Assessing transformer oil quality using deep convolutional networks
- Authors: Alam, Mohammad , Karmakar, Gour , Islam, Syed , Kamruzzaman, Joarder , Chetty, Madhu , Lim, Suryani , Appuhamillage, Gayan , Chattopadhyay, Gopi , Wilcox, Steve , Verheyen, Vincent
- Date: 2019
- Type: Text , Conference proceedings , Conference paper
- Relation: 29th Australasian Universities Power Engineering Conference, AUPEC 2019
- Full Text:
- Reviewed:
- Description: Electrical power grids comprise a significantly large number of transformers that interconnect power generation, transmission and distribution. These transformers having different MVA ratings are critical assets that require proper maintenance to provide long and uninterrupted electrical service. The mineral oil, an essential component of any transformer, not only provides cooling but also acts as an insulating medium within the transformer. The quality and the key dissolved properties of insulating mineral oil for the transformer are critical with its proper and reliable operation. However, traditional chemical diagnostic methods are expensive and time-consuming. A transformer oil image analysis approach, based on the entropy value of oil, which is inexpensive, effective and quick. However, the inability of entropy to estimate the vital transformer oil properties such as equivalent age, Neutralization Number (NN), dissipation factor (tanδ) and power factor (PF); and many intuitively derived constants usage limit its estimation accuracy. To address this issue, in this paper, we introduce an innovative transformer oil analysis using two deep convolutional learning techniques such as Convolutional Neural Network (ConvNet) and Residual Neural Network (ResNet). These two deep neural networks are chosen for this project as they have superior performance in computer vision. After estimating the equivalent aging year of transformer oil from its image by our proposed method, NN, tanδ and PF are computed using that estimated age. Our deep learning based techniques can accurately predict the transformer oil equivalent age, leading to calculate NN, tanδ and PF more accurately. The root means square error of estimated equivalent age produced by entropy, ConvNet and ResNet based methods are 0.718, 0.122 and 0.065, respectively. ConvNet and ResNet based methods have reduced the error of the oil age estimation by 83% and 91%, respectively compared to that of the entropy method. Our proposed oil image analysis can calculate the equivalent age that is very close to the actual age for all images used in the experiment. © 2019 IEEE.
- Description: E1
Challenges and opportunities for blockchain technology adoption : a systematic review
- Authors: Chhina, Shipra , Chadhar, Mehmood , Vatanasakdakul, Savanid , Chetty, Madhu
- Date: 2019
- Type: Text , Conference paper
- Relation: 30th Australasian Conference on Information Systems (ACIS), 9-11 December, Perth (Australia)
- Full Text:
- Reviewed:
- Description: Blockchain technology promises to significantly impact current business processes in industries from various sectors and reduce transactional cost. Firms, suppliers, government, financial institutions etc. are anticipating a business model transformation through blockchain by accomplishing a decentralized architecture of interorganizational dealings without intermediaries. In spite of its immense potential, however, there are key challenges of blockchain implementation which need to be studied for identifying the opportunities arising and for its successful implementations in future. In this paper, we aim to identify these challenges for blockchain adoption and classify them for clearer understanding. To pursue this effectively, this paper follows a hybrid model of systematic literature review. This paper also explicitly enumerates future research opportunities to lead industry and researchers in correct directions
Frequency decomposition based gene clustering
- Authors: Rahman, Md Abdur , Chetty, Madhu , Bulach, Dieter , Wangikar, Pramod
- Date: 2015
- Type: Text , Conference paper
- Relation: 22nd International Conference on Neural Information Processing, ICONIP 2015; Istanbul, Turkey; 9th-12th November 2015 Vol. 9490, p. 170-181
- Full Text: false
- Reviewed:
- Description: Gene expressions have been commonly applied to understand the inherent underlying mechanism of known biological processes. Although the microarray gene expressions usually appear aperiodic, with proper signal processing techniques, its periodic components can be easily obtained. Thus, if expressions of interconnected (regulatory and regulated) genes are decomposed, at least one common frequency component will appear in these genes. Exploiting this novel concept, we propose a frequency decomposition approach for gene clustering to better understand the gene interconnection topology. This method, based on Hilbert Huang Transform (HHT) enables us to segregate every periodic component of the gene expressions. Next, a multilevel clustering is performed based on these frequency components. Unlike existing clustering algorithms, the proposed method assimilates a meaningful knowledge of the gene interactions topology. The information related to underlying gene interactions is vital and can prove useful in many existing evolutionary optimisation algorithms for genetic network reconstruction. We validate the entire approach by its application to a 15-gene synthetic network. © Springer International Publishing Switzerland 2015.
Sib-based survival selection technique for protein structure prediction in 3D-FCC Lattice Model
- Authors: Rumana, Nazmul , Chetty, Madhu
- Date: 2014
- Type: Text , Conference paper
- Relation: 21st International Conference on Neural Information Processing, ICONIP 2014; Kuching; Malaysia; 3rd - 6th November 2014; In Neural Information Processing (Lecture Notes in Computer Science ) Vol.8835 p.470-478 p. 470-478
- Full Text: false
- Reviewed:
- Description: Protein Structure Prediction (PSP) is a challenging optimization problem in computational biology. A large number of non-deterministic approaches such as Evolutionary Algorithms (EAs) have been have been effectively applied to a variety of fields though, in the rugged landscape of multimodal problem like PSP, it can perform unsatisfactorily, due to premature convergence. In EAs, selection plays a significant role to avoid getting trapped in local optima and also to guide the evolution towards an optimal solution. In this paper, we propose a new Sib-based survival selection strategy suitable for application in a genetic algorithm (GA) to deal with multimodal problems. The proposed strategy, inspired by the concept of crowding method, controls the flow of genetic material by pairing off the fittest offspring amongst all the sibs (offspring inheriting most of the genetic material from an ancestor) with its ancestor for survival. Furthermore, by selecting the survivors in a hybridized manner of deterministic and probabilistic selection, the method allows the exploitation of less fit solutions along with the fitter ones and thus facilitates escaping from local optima (minima in case of PSP). Experiments conducted on a set of widely used benchmark sequences for 3D-FCC HP lattice model, demonstrate the potential of the proposed method, both in terms of diversity and optimal energy in regard to various state-of-the-art selection methods.
Significance of non-edge priors in gene regulatory network reconstruction
- Authors: Nair, Ajay , Chetty, Madhu , Wangikar, Pramod
- Date: 2014
- Type: Text , Conference paper
- Relation: 21st International Conference, ICONIP 2014 Kuching, Malaysia, November 3–6, 2014; published in Neural Information Processing, (Lecture Notes in Computer Science) Vol. 8834 p446-453
- Full Text: false
- Reviewed:
- Description: It is well known that incorporating prior knowledge improves gene regulatory network reconstruction from data. Two types of prior knowledge can be given for the gene regulatory network inference - known interactions (edge priors) and known absence of interactions (non-edge priors). However, previous studies have focused mainly on edge priors. This paper shows that the edge priors give only limited improvement. Moreover, non-edge priors are crucial for better overall performance and their effect dominates edge priors at larger data samples. The studies are carried out on two real networks and a computationally tractable synthetic network, using Bayesian network framework. Further, a method to obtain large numbers of non-edge priors for real gene regulatory networks is presented. © Springer International Publishing Switzerland 2014.
A knowledge-based initial population generation in memetic algorithm for protein structure prediction
- Authors: Nazmul, Rumana , Chetty, Madhu
- Date: 2013
- Type: Text , Conference paper
- Relation: 20th International Conference, ICONIP 2013 p. 546-553
- Full Text: false
- Reviewed:
- Description: Predicting the minimum energy protein structure from its amino acid sequence, even under the rather simplified HP lattice model, continues to be an important and challenging problem in computational biology. In this paper, we propose a novel initial population generation strategy for evolutionary algorithm incorporating domain knowledge based on the concept of maximum hydrophobic core formation for Protein structure prediction (PSP) problem. The proposed technique helps the optimization process to commence with diverse seeds and thereby aids in converging to the global solution quickly. The experimental results, conducted on PSP problem using HP benchmark sequences for 2D square and 3D cubic lattice model, demonstrate that the proposed evolutionary algorithm with new core-based population initialization technique is very effective in improving the optimization process in terms of convergence as well as in achieving the optimal energy.
A priority based parental selection method for genetic algorithm
- Authors: Nazmul, Rumana , Chetty, Madhu
- Date: 2013
- Type: Text , Conference paper
- Relation: GECCO '13 , Amsterdam, July 6th-10th, 2013 ; published in Proceedings of the 15th annual conference companion on Genetic and evolutionary computation pg.125-126
- Full Text: false
- Reviewed:
- Description: Selection is an important and critical aspect in evolutionary computation. This paper presents a novel parental selection technique that includes the advantages of both the deterministic and the stochastic selection techniques and helps to reduce the loss of diversity by distributing the reproduction opportunity among all the members of the population. Moreover, the proposed selection strategy promotes the concept of non-random mating by clustering the population into groups according to the fitness values and then by persuading the mating between individuals from different groups based on performance determined dynamically over the evolution. Computational results using widely used benchmark functions show significant improvements in the convergence characteristics of the proposed selection method over two well-known selection techniques.
An adaptive strategy for assortative mating in genetic algorithm
- Authors: Nazmul, Rumana , Chetty, Madhu
- Date: 2013
- Type: Text , Conference paper
- Relation: 2013 IEEE Congress on Evolutionary Computation p. 2237-2244
- Full Text: false
- Reviewed:
- Description: In any traditional Genetic Algorithm (GA), recombination is a dominant search operator and capable of exploring the search space by sharing genetic information among the individuals in the population. However, a simple application of recombination alone is insufficient to guide convergence to an optimal solution. The selection of parents for recombination operation has a significant role in guiding the evolution towards the optimal solution and also for maintaining genetic diversity to avoid getting trapped in local minima. A non-random mating mimics the mechanism of reproduction in nature and is effective in maintaining diversity in population. This paper proposes a new strategy for selection of mating pairs based on a type of non-random mating called as assortative mating. The proposed mate selection scheme conserves the merits of both positive and negative assortative mating in a controlled manner by allowing mating between individuals having both similar and dissimilar phenotypes. For effective cross-over, it maintains genetic diversity in population by distributing the recombination among dissimilar individuals. Furthermore, it ensures the preservation and propagation of useful genetic information to the later stages of search by the selection of mates having similar phenotypes. Experimental results, using not only the five widely used benchmark functions but also twenty newly developed modified functions, are reported. The results show significant improvements in the convergence characteristics of the proposed mating strategy over existing nonrandom mating techniques.
Inferring large scale genetic networks with S-System model
- Authors: Chowdhury, Ahsan , Chetty, Madhu , Nguyen, Vinh
- Date: 2013
- Type: Text , Conference paper
- Relation: Genetic and Evolutionary Computation Conference p. 271-278
- Full Text: false
- Reviewed:
- Description: Gene regulatory network (GRN) reconstruction from high-throughput microarray data is an important problem in systems biology. The S-System model, a differential equation based approach, is among the mainstream approaches for modeling GRNs