Find Research Output

Research Output
  • All
  • Scholar Profiles
  • Research Units
  • Research Output
Filter
Department Publication Year Content Type Data Sources

SELECTED FILTERS

Department of Computing
BOOK
Clear all

1.Recursive learning of genetic algorithms with task decomposition and varied rule set

Author:Fang, Lei ; Guan, Sheng-Uei ; Zhang, Haofan

Source:Modeling Applications and Theoretical Innovations in Interdisciplinary Evolutionary Computation,2013,Vol.

Abstract:Rule-based Genetic Algorithms (GAs) have been used in the application of pattern classification (Corcoran & Sen, 1994), but conventional GAs have weaknesses. First, the time spent on learning is long. Moreover, the classification accuracy achieved by a GA is not satisfactory. These drawbacks are due to existing undesirable features embedded in conventional GAs. The number of rules within the chromosome of a GA classifier is usually set and fixed before training and is not problem-dependent. Secondly, conventional approaches train the data in batch without considering whether decomposition solves the problem. Thirdly, when facing large-scale real-world problems, GAs cannot utilise resources efficiently, leading to premature convergence. Based on these observations, this paper develops a novel algorithmic framework that features automatic domain and task decomposition and problem-dependent chromosome length (rule number) selection to resolve these undesirable features. The proposed Recursive Learning of Genetic Algorithm with Task Decomposition and Varied Rule Set (RLGA) method is recursive and trains and evolves a team of learners using the concept of local fitness to decompose the original problem into sub-problems. RLGA performs better than GAs and other related solutions regarding training duration and generalization accuracy according to the experimental results. © 2013 by IGI Global. All rights reserved.

2.Statistical discriminability estimation for pattern classification based on neural incremental attribute learning

Author:Wang,Ting;Puthusserypady,Sadasivan;Guan,Sheng Uei;Wong,Prudence W.H.

Source:Artificial Intelligence: Concepts, Methodologies, Tools, and Applications,2016,Vol.3

Abstract:Feature ordering is a significant data preprocessing method in Incremental Attribute Learning (IAL), a novel machine learning approach which gradually trains features according to a given order. Previous research has shown that, similar to feature selection, feature ordering is also important based on each feature's discrimination ability, and should be sorted in a descending order of their discrimination ability. However, such an ordering is crucial for the performance of IAL. As the number of feature dimensions in IAL is increasing, feature discrimination ability also should be calculated in the corresponding incremental way. Based on Single Discriminability (SD), where only the feature discrimination ability is computed, a new filter statistical feature discrimination ability predictive metric, called the Accumulative Discriminability (AD), is designed for the dynamical feature discrimination ability estimation. Moreover, a criterion that summarizes all the produced values of AD is employed with a GA (Genetic Algorithm)- based approach to obtain the optimum feature ordering for classification problems based on neural networks by means of IAL. Compared with the feature ordering obtained by other approaches, the method proposed in this paper exhibits better performance in the final classification results. Such a phenomenon indicates that, (i) the feature discrimination ability should be incrementally estimated in IAL, and (ii) the feature ordering derived by AD and its corresponding approaches are applicable with IAL.

3.Big Data A Classification of Acquisition and Generation Methods

Author:Nanjappan, Vijayakumar ; Liang, Hai-Ning ; Wang, Wei ; Man, Ka L.

Source:Big Data Analytics for Sensor-Network Collected Intelligence,2017,Vol.

Abstract:Traditionally, data have been stored in securely protected databases for special purposes, such as satellite imagery data for earth science research or customer transaction data for business analytics. The usefulness of data lies in the fact that they can be examined and analyzed to unearth correlations among data items and to discover knowledge to gain deeper insightful trends. Data analytics has been the key research topic in data mining, knowledge discovery and machine learning for decades. In recent years, the term "data" has experienced a major rejuvenation in many aspects of our lives. The rapid development of the Internet and web technologies allows ordinary users to generate vast amounts of data about their daily lives. On the Internet of Things, the number of connected devices has grown exponentially; each of these produces real-time or near real-time streaming data about our physical world. The resulting data, which is extremely difficult, if not impossible, to be stored, processed, and analyzed with conventional computing methodologies and resources, is referred to as the "Big Data." In this chapter, we focus on a subset of big data digital data and analog data. These two major subsets are further divided as the environmental and personal source of data. We have also highlighted the data types and formats as well as different input mechanisms. These classifications are helpful to understand the active and passive way of data collection and production with explicit and without (i.e., implicit) human involvement. This chapter intends to provide enough information to support the reader to understand the role of digital and analog sources, and how data is acquired, transmitted, and preprocessed using today's growing variety of computing devices and sensors. © 2017 All rights reserved.

4.Cyber-physical technologies: Hype cycle 2017

Author:Hahanov,Vladimir;Gharibi,Wajeb;Man,Ka Lok;Iemelianov,Igor;Liubarskyi,Mykhailo;Abdullayev,Vugar;Litvinova,Eugenia;Chumachenko,Svetlana

Source:Cyber Physical Computing for IoT-driven Services,2018,Vol.

Total 4 results found
Copyright 2006-2020 © Xi'an Jiaotong-Liverpool University 苏ICP备07016150号-1 京公网安备 11010102002019号