Dr. Vahid Behbood is Lecturer at the School of Software in the Faculty of Engineering and Information Technology. Additionally he is a member of the Decision Systems and e-Service Intelligence Research Laboratory in the Centre for Quantum Computation & Intelligent Systems at the University of Technology, Sydney (UTS). He received the Ph.D. degree in software engineering from the University of Technology Sydney, Sydney, Australia. His research interests include machine learning, big data analytics and computational intelligence. He has published over 20 papers in journals and conferences.
Zuo, H, Zhang, G, Pedrycz, W, Behbood, V & Lu, J 2018, 'Granular Fuzzy Regression Domain Adaptation in Takagi-Sugeno Fuzzy Models', IEEE Transactions on Fuzzy Systems, vol. 26, no. 2, pp. 847-858.View/Download from: Publisher's site
© 1993-2012 IEEE. In classical data-driven machine learning methods, massive amounts of labeled data are required to build a high-performance prediction model. However, the amount of labeled data in many real-world applications is insufficient, so establishing a prediction model is impossible. Transfer learning has recently emerged as a solution to this problem. It exploits the knowledge accumulated in auxiliary domains to help construct prediction models in a target domain with inadequate training data. Most existing transfer learning methods solve classification tasks; only a few are devoted to regression problems. In addition, the current methods ignore the inherent phenomenon of information granularity in transfer learning. In this study, granular computing techniques are applied to transfer learning. Three granular fuzzy regression domain adaptation methods to determine the estimated values for a regression target are proposed to address three challenging cases in domain adaptation. The proposed granular fuzzy regression domain adaptation methods change the input and/or output space of the source domain's model using space transformation, so that the fuzzy rules are more compatible with the target data. Experiments on synthetic and real-world datasets validate the effectiveness of the proposed methods.
Zuo, H, Zhang, G, Pedrycz, W, Behbood, V & Lu, J 2017, 'Fuzzy Regression Transfer Learning in Takagi-Sugeno Fuzzy Models', IEEE Transactions on Fuzzy Systems, vol. 25, no. 6, pp. 1795-1807.View/Download from: Publisher's site
Data Science is a research field concerned with
processes and systems that extract knowledge from massive
amounts of data. In some situations, however, data shortage
renders existing data-driven methods difficult or even impossible
to apply. Transfer learning has recently emerged as a way of
exploiting previously acquired knowledge to solve new yet similar
problems much more quickly and effectively. In contrast to
classical data-driven machine learning methods, transfer learning
methods exploit the knowledge accumulated from data in
auxiliary domains to facilitate predictive modeling in the current
domain. A significant number of transfer learning methods that
address classification tasks have been proposed, but studies on
transfer learning in the case of regression problems are still
scarce. This study focuses on using transfer learning techniques to
handle regression problems in a domain that has insufficient
training data. We propose an original fuzzy regression transfer
learning method, based on fuzzy rules, to address the problem of
estimating the value of the target for regression. A Takagi-Sugeno
fuzzy regression model is developed to transfer knowledge from a
source domain to a target domain. Experimental results using
synthetic data and real world datasets demonstrate that the
proposed fuzzy regression transfer learning method significantly
improves the performance of existing models when tackling
regression problems in the target domain.
Behbood, V, Lu, J, Zhang, G & Pedrycz, W 2015, 'Multi-Step Fuzzy Bridged Refinement Domain Adaptation Algorithm and Its Application to Bank Failure Prediction', IEEE Transactions on Fuzzy Systems, vol. 23, no. 6, pp. 1917-1935.View/Download from: Publisher's site
Machine learning plays an important role in data classification and data-based prediction. In some real world applications, however, the training data (coming from the source domain) and test data (from the target domain) come from different domains or time periods, and this may result in the different distributions of some features. Moreover, the values of the features and/or labels of the data sets might be non-numeric and involve vague values. Traditional learning-based prediction and classification methods cannot handle these two issues. In this study, we propose a multi-step fuzzy bridged refinement domain adaptation algorithm, which offers an effective way to deal with both issues. It utilizes a concept of similarity to modify the labels of the target instances that were initially predicted by a shift-unaware model. It then refines the labels using instances that are most similar to a given target instance. These instances are extracted from mixture domains composed of source and target domains. The proposed algorithm is built on a basis of some data and refines the labels, thus performing completely independently of the shift-unaware prediction model. The algorithm uses a fuzzy set-based approach to deal with the vague values of the features and labels. Four different data sets are used in the experiments to validate the proposed algorithm. The results, which are compared with those generated by the existing domain adaptation methods, demonstrate a significant improvement in prediction accuracy in both the above-mentioned data sets.
Lu, J, Behbood, V, Hao, P, Zuo, H, Xue, S & Zhang, G 2015, 'Transfer Learning using Computational Intelligence: A Survey', Knowledge-Based Systems, vol. 80, pp. 14-23.View/Download from: Publisher's site
Abstract Transfer learning aims to provide a framework to utilize previously-acquired
knowledge to solve new but similar problems much more quickly and effectively. In contrast
to classical machine learning methods, transfer learning methods exploit the knowledge
accumulated from data in auxiliary domains to facilitate predictive modeling consisting of
different data patterns in the current domain. To improve the performance of existing transfer
learning methods and handle the knowledge transfer process in real-world systems, ...
Behbood, V, Lu, J & Zhang, G 2014, 'Fuzzy Refinement Domain Adaptation for Long Term Prediction in Banking Ecosystem', IEEE Transaction on Industrial Informatics, vol. 10, no. 2, pp. 1637-1646.View/Download from: Publisher's site
Long-term bank failure prediction is a challenging real world problem in banking ecosystem and machine learning methods have been recently applied to improve the prediction accuracy. However, traditional machine learning methods assume that the training data and the test data are drawn from the same distribution, which is hard to be met in real world banking applications. This paper proposes a novel algorithm known as fuzzy refinement domain adaptation to solve this problem based on the ecosystem-oriented architecture. The algorithm utilizes the fuzzy system and similarity/dissimilarity concepts to modify the target instances' labels which were initially predicted by a shift-unaware prediction model. It employs a classifier to modify the label values of target instances based on their similarity/dissimilarity to the candidate positive and negative instances in mixture domains. Thirty six experiments are performed using three different shift-unaware prediction models. In these experiments bank failure financial data is used to evaluate the algorithm. The results demonstrate that the proposed algorithm significantly improves predictive accuracy and outperforms other refinement algorithms.
Behbood, V, Lu, J & Zhang, G 2013, 'Fuzzy bridged refinement domain adaptation: Long-term bank failure prediction', International Journal of Computational Intelligence and Applications, vol. 12, no. 1, pp. 1-17.View/Download from: Publisher's site
Machine learning methods, such as neural network (NN) and support vector machine, assume that the training data and the test data are drawn from the same distribution. This assumption may not be satisfied in many real world applications, like long-term financial failure prediction, because the training and test data may each come from different time periods or domains. This paper proposes a novel algorithm known as fuzzy bridged refinement-based domain adaptation to solve the problem of long-term prediction. The algorithm utilizes the fuzzy system and similarity concepts to modify the target instances' labels which were initially predicted by a shift-unaware prediction model. The experiments are performed using three shift-unaware prediction models based on nine different settings including two main situations: (1) there is no labeled instance in the target domain; (2) there are a few labeled instances in the target domain. In these experiments bank failure financial data is used to validate the algorithm. The results demonstrate a significant improvement in the predictive accuracy, particularly in the second situation identified above
Nejad, MZ, Lu, J & Behbood, V 2017, 'Applying dynamic Bayesian tree in property sales price estimation', Proceedings of the 2017 12th International Conference on Intelligent Systems and Knowledge Engineering, ISKE 2017, International Conference on Intelligent Systems and Knowledge Engineering, IEEE, NanJing, JiangSu, China, pp. 1-6.View/Download from: Publisher's site
© 2017 IEEE. Accurate prediction of Residential Property Sale Price is very important and significant in the operation of the real estate market. Property sellers and buyers/Investors wish to know a fair value for their properties in particular at the time of the sales transaction. The main reason to build an Automated Valuation Model is to be accurate enough to replace human. To select a most suitable model for the property sale price prediction, this paper examined seven Tree-based machine learning models including Dynamic Bayesian Tree (online learning method), Random Forest, Stochastic Gradient Boosting, CART, Bagged CART, Tree Bagged Ensembles and Boosted Tree (batch learning methods) by comparing their RMSE and MAE performances. The performance of these models are tested on 1967 records of unit sales from 19 suburbs of Sydney, Australia. The main purpose of this study is to compare the performance of batch models with the online model. The results demonstrated that Dynamic Bayesian Tree as an online model stands in the middle of batch models based on the root mean square error (RMSE) and mean absolute error (MAE). It shows using online model for estimating the property sale price is reasonable for real world application.
Gill, AQ, Behbood, V, Ramadan-Jradi, R & Beydoun, G 2017, 'IoT architectural concerns: a systematic review', Proceedings of the Second International Conference on Internet of things, Data and Cloud Computing, International Conference on Internet of things and Cloud Computing, ACM, Cambridge, United Kingdom, pp. 1-9.View/Download from: Publisher's site
There is increasing interest in studying and applying Internet of Things (IoT) within the overall context of digital-physical ecosystems. Most recently, much has been published on the benefits and applications of IoT. The main question is: what are the key IoT architectural concerns, which must be addressed to effectively develop and implement an IoT architecture? There is a need to systematically review and synthesize the literature on IoT architectural challenges or concerns. Using the SLR approach and applying customised search criteria derived from the research question, 22 relevant studies were identified and reviewed in this paper. The data from these papers were extracted to identify the IoT architectural challenges and relevant solutions. These results were organised into to 9 major challenge and 7 solution categories. The results of this research will serve as a resource for practitioners and researchers for the effective adoption, and setting future research priorities and directions in this emerging area of IoT architecture.
Ziaee Nejad, M, Lu, Pooyan Asgari, DPAIDGFM & Behbood 2016, 'THE EFFECT OF GOOGLE DRIVE DISTANCE AND DURATION IN RESIDENTIAL PROPERTY IN SYDNEY,AUSTRALIA', International Fuzzy Logic and Intelligent technologies in Nuclear Science Conference, FRANCE.
Zuo, H, Zhang, G, Behbood, V, Lu, J, Pedrycz, W & Zhang, T 2016, 'FUZZY TRANSFER LEARNING IN DATA-SHORTAGE AND RAPIDLY CHANGING ENVIRONMENTS', UNCERTAINTY MODELLING IN KNOWLEDGE ENGINEERING AND DECISION MAKING, 12th International Conference on Fuzzy Logic and Intelligent Technologies in Nuclear Science (FLINS), WORLD SCIENTIFIC PUBL CO PTE LTD, Roubaix, FRANCE, pp. 175-180.
Ahadi, A, Behbood, V, Lister, R, Prior, J & Vihavainen, A 2016, 'Students' Syntactic Mistakes in Writing Seven Different Types of SQL Queries and its Application to Predicting Students' Success', Proceedings of the 47th ACM Technical Symposium on Computing Science Education, Special Interest Group in COmputer Science Education, ACM, Memphis, Tennessee, pp. 401-406.View/Download from: Publisher's site
The computing education community has studied extensively the errors of novice programmers. In contrast, little attention has been given to student's mistake in writing SQL statements. This paper represents the first large scale quantitative analysis of the student's syntactic mistakes in writing different types of SQL queries. Over 160 thousand snapshots of SQL queries were collected from over 2000 students across eight years. We describe the most common types of syntactic errors that students make. We also describe our development of an automatic classifier with an overall accuracy of 0.78 for predicting student performance in writing SQL queries.
Ahadi, A, behbood, V, prior, J & Lister, R 2016, 'Students' Semantic Mistakes in Writing Seven Different Types of SQL Queries', ITiCSE'16: Proceedings of the 2016 ACM Conference on Innovation and Technology in Computer Science Education, Annual Conference on Innovation and Technology in Computer Science Education, ACM, Peru.View/Download from: Publisher's site
Ali, M & Behbood, V 2015, 'Operation Properties and delta-Equalities of Complex Fuzzy Classes', Proceedings of the 10th International Conference on Intelligent Systems and Knowledge Engineering, International Conference on Intelligent Systems and Knowledge Engineering, IEEE, Taipei, pp. 586-593.View/Download from: Publisher's site
A complex fuzzy class is a set of fuzzy sets which is characterized by a pure complex fuzzy grade of membership where both the real and imaginary parts are fuzzy functions. The values that a pure complex fuzzy grade of membership may receive all lie within the unite square or unit circle in the complex plane. In this paper, we investigate different operation properties and propose a distance measure for complex fuzzy classes. The distance of two complex fuzzy classes measures the difference between the memberships of the fuzzy sets in the two complex fuzzy classes as well as the difference between the memberships in the related fuzzy sets in the two complex fuzzy classes. d-equalities of two complex fuzzy classes are then defined which mainly base on this distance measure. If the distance between two complex fuzzy classes is less than or equal to d, then they are said to be d-equal. This paper reveals that different operations between complex fuzzy classes can affect given delta-equalities of complex fuzzy classes. Further, an application of utilizing the concept of d-equalities of complex fuzzy classes in stocks and mutual funds in the stock market is presented.
Zuo, H, Zhang, G, Behbood, V & Lu, J 2015, 'Feature Spaces-based Transfer Learning', PROCEEDINGS OF THE 2015 CONFERENCE OF THE INTERNATIONAL FUZZY SYSTEMS ASSOCIATION AND THE EUROPEAN SOCIETY FOR FUZZY LOGIC AND TECHNOLOGY, World Congress of the International-Fuzzy-Systems-Association (IFSA) / Conference of the European-Society-for-Fuzzy-Logic-and-Technology (EUSFLAT), Atlantis Press, Gijon, Spain, pp. 1000-1005.View/Download from: Publisher's site
Transfer learning provides an approach to solve target tasks more quickly and effectively by using previously-acquired knowledge learned from source tasks. Most of transfer learning approaches extract knowledge of source domain in the given feature space. The issue is that single perspective can t mine the relationship of source domain and target domain fully. To deal with this issue, this paper develops a method using Stacked Denoising Autoencoder (SDA) to extract new feature spaces for source domain and target domain, and define two fuzzy sets to analyse the variation of prediction ac-curacy of target task in new feature spaces
Zuo, H, Zhang, G, Behbood, V, Lu, J & Meng, X 2015, 'Transfer Learning in Hierarchical Feature Spaces', Procedings of the 10th International Conference on Intelligent Systems and Knowledge Engineering, International Conference on Intelligent Systems and Knowledge Engineering, IEEE, Taipei, Taiwan, pp. 183-188.View/Download from: Publisher's site
Transfer learning provides an approach to solve target tasks more quickly and effectively by using previously acquired knowledge learned from source tasks. As one category of transfer learning approaches, feature-based transfer learning approaches aim to find a latent feature space shared between source and target domains. The issue is that the sole feature space can't exploit the relationship of source domain and target domain fully. To deal with this issue, this paper proposes a transfer learning method that uses deep learning to extract hierarchical feature spaces, so knowledge of source domain can be exploited and transferred in multiple feature spaces with different levels of abstraction. In the experiment, the effectiveness of transfer learning in multiple feature spaces is compared and this can help us find the optimal feature space for transfer learning
Ahadi, A, Prior, J, Behbood, V & Lister, R 2015, 'A Quantitative Study of the Relative Difficulty for Novices of Writing Seven Different Types of SQL Queries', Proceedings of the 2015 ACM Conference on Innovation and Technology in Computer Science Education, Annual Conference on Innovation and Technology in Computer Science Education, ACM, Lithuania, pp. 201-206.View/Download from: Publisher's site
This paper presents a quantitative analysis of data collected by an online testing system for SQL "select" queries. The data was collected from almost one thousand students, over eight years. We examine which types of queries our students found harder to write. The seven types of SQL queries studied are: simple queries on one table; grouping, both with and without "having"; natural joins; simple and correlated sub-queries; and self-joins. The order of queries in the preceding sentence reflects the order of student difficulty we see in our data.
Hao, P, Zhang, GQ, Behbood, V & Zheng, Z 2014, 'A Fuzzy Domain Adaptation Method Based On Self-Constructing Fuzzy Neural Network', Proceedings of the 11th International FLINS Conference, International Fuzzy Logic and Intelligent technologies in Nuclear Science Conference, World Scientific Publishing Co. Pte. Ltd., Brazil, pp. 676-681.View/Download from: Publisher's site
Domain adaptation addresses the problem of how to utilize a model trained in the source domain to make predictions for target domain when the distribution between two domains differs substantially and labeled data in target domain is costly to collect for retraining. Existed studies are incapable to handle the issue of information granularity, in this paper, we propose a new fuzzy domain adaptation method based on self-constructing fuzzy neural network. This approach models the transferred knowledge supporting the development of the current models granularity in the form of fuzzy sets and adapts the knowledge using fuzzy similarity measure to reduce prediction error in the target domain.
Behbood, V, Lu, J & Zhang, G 2013, 'Text categorization by fuzzy domain adaptation', 2013 IEEE International Conference on Fuzzy Systems, IEEE International Conference on Fuzzy Systems, IEEE, Hyderabad, India, pp. 1841-1848.View/Download from: Publisher's site
Machine learning methods have attracted attention of researches in computational fields such as classification/categorization. However, these learning methods work under the assumption that the training and test data distributions are identical. In some real world applications, the training data (from the source domain) and test data (from the target domain) come from different domains and this may result in different data distributions. Moreover, the values of the features and/or labels of the data sets could be non-numeric and contain vague values. In this study, we propose a fuzzy domain adaptation method, which offers an effective way to deal with both issues. It utilizes the similarity concept to modify the target instances' labels, which were initially classified by a shift-unaware classifier. The proposed method is built on the given data and refines the labels. In this way it performs completely independently of the shift-unaware classifier. As an example of text categorization, 20Newsgroup data set is used in the experiments to validate the proposed method. The results, which are compared with those generated when using different baselines, demonstrate a significant improvement in the accuracy
Behbood, V & Lu, J 2011, 'Efficiency Prediction in Decision Making Units Merger using Data Envelopment Analysis and Neural Network', 19th Triennial Conference of the International Federation of Operational Research Societies, IFORS, Australia.
Behbood, V & Lu, J 2011, 'Financial Early Warning System: Adaptive Inference-based Fuzzy Neural Network', 19th Triennial Conference of the International Federation of Operational Research Societies, IFORS, Australia.
Behbood, V & Lu, J 2011, 'Intelligent Financial Warning Model Using Fuzzy Neural Network and Case-Based Reasoning', Proceedings for the IEEE Symposium on Computational Intelligence for Financial Engineering & Economics, IEEE Symposium on Computational Intelligence for Financial Engineering, IEEE, Paris, France, pp. 9-15.View/Download from: Publisher's site
Creating an applicable and precise financial early warning model is highly desirable for decision makers and regulators in the financial industry. Although Business Failure Prediction (BFP) especially banks has been extensively a researched area since late 1960s, the next critical step which is the decision making support scheme has been ignored. This paper presents a novel model for financial warning which combines a fuzzy inference system with the learning ability of neural network as a Fuzzy Neural Network (FNN) to predict organizational financial status and also applies reasoning capability of Fuzzy Case-Based Reasoning (FCBR) to support decision makers measuring appropriate solutions. The proposed financial warning model generates an adaptive fuzzy rule base to predict financial status of target case and then if it is predicted to fail, the FCBR is used to find similar survived cases. Finally according similar cases and a fuzzy rule base, the model provides financial decisions to change particular features as company goals in upcoming year to avoid future financial distress.
Behbood, V, Lu, J & Zhang, G 2011, 'Long Term Bank Failure Prediction using Fuzzy Refinement-based Transductive Transfer Learning', 2011 IEEE International Conference on Fuzzy Systems (FUZZ), IEEE International Conference on Fuzzy Systems, IEEE, Taipei, Taiwan, pp. 2676-2683.View/Download from: Publisher's site
Machine learning algorithms, which have been considered as robust methods in different computational fields, assume that the training and test data are drawn from the same distribution. This assumption may be violated in many real world applications like bank failure prediction because training and test data may come from different time periods or domains. An efficient novel algorithm known as Fuzzy Refinement (FR) is proposed in this paper to solve this problem and improve the performance. The algorithm utilizes the fuzzy system and similarity concept to modify the instances' labels in target domain which was initially predicted by shift-unaware Fuzzy Neural Network (FNN) proposed by . The experiments are performed using bank failure financial data of United States to evaluate the algorithm performance. The results address a significant improvement in the predictive accuracy of FNN due to applying the proposed algorithm.
Behbood, V, Lu, J & Zhang, G 2010, 'Adaptive Inference-based Learning and Rule Generation Algorithms in Fuzzy Neural Network for Failure Prediction', The Proceedings of 2010 IEEE International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2010), IEEE International Conference on Intelligent Systems and Knowledge Engineering, IEEE, China, pp. 33-38.View/Download from: Publisher's site
highly desirable for decision makers and regulators in the finance industry. This study develops a new Failure Prediction (FP) approach which effectively integrates a fuzzy logic-based adaptive inference system with the learning ability of a neural network to generate knowledge in the form of a fuzzy rule base. This FP approach uses a preprocessing phase to deal with the imbalanced data-sets problem and develops a new Fuzzy Neural Network (FNN) including an adaptive inference system in the learning algorithm along with its network structure and rule generation algorithm as a means to reduce prediction error in the FP approach.
Behbood, V, Lu, J & Zhang, G 2010, 'Intelligent financial warning support system', International Conference on Applied Statistics and Financial Mathematics, International Conference on Applied Statistics and Financial Mathematics, IOS Press, Hong Kong.