Showing items 1 - 20 of 32

A generalized 3-D four-wing chaotic system

- Wang, Zenghui

A hyperchaotic system without equilibrium

- Wang, Zenghui, Cang, Shijian, Ochola, Elisha Oketch, Sun, Yanxia

A machine-learning based nonintrusive smart home appliance status recognition

- Matindife, Liston, Sun, Yanxia, Wang, Zenghui

  • Authors: Matindife, Liston , Sun, Yanxia , Wang, Zenghui
  • Date: 2020
  • Language: English
  • Type: Article
  • Identifier: http://hdl.handle.net/10210/450398 , uj:39589 , Citation: Matindife, L., Sun, Y. & Wang, Z. 2020. A machine-learning based nonintrusive smart home appliance status recognition. , DOI: https://doi.org/10.1155/2020/9356165
  • Description: Abstract: In a smart home, the nonintrusive load monitoring recognition scheme normally achieves high appliance recognition performance in the case where the appliance signals have widely varying power levels and signature characteristics. However, it becomes more difficult to recognize appliances with equal or very close power specifications, often with almost identical signature characteristics. In literature, complex methods based on transient event detection and multiple classifiers that operate on different hand crafted features of the signal have been proposed to tackle this issue. In this paper, we propose a deep learning approach that dispenses with the complex transient event detection and hand crafting of signal features to provide high performance recognition of close tolerance appliances. ,e appliance classification is premised on the deep multilayer perceptron having three appliance signal parameters as input to increase the number of trainable samples and hence accuracy. In the case where we have limited data, we implement a transfer learning-based appliance classification strategy. With the view of obtaining an appropriate high performing disaggregation deep learning network for the said problem, we explore individually three deep learning disaggregation algorithms based on the multiple parallel structure convolutional neural networks, the recurrent neural network with parallel dense layers for a shared input, and the hybrid convolutional recurrent neural network. We disaggregate a total of three signal parameters per appliance in each case. To evaluate the performance of the proposed method, some simulations and comparisons have been carried out, and the results show that the proposed method can achieve promising performance.
  • Full Text:

A new golden ratio local search based particle swarm optimization

- Sun, Yanxia, Van Wyk, Barend Jacobus, Wang, Zenghui

A new multi-swarm multi-objective particle swarm optimization based on pareto front set

- Sun, Yanxia, Van Wyk, Barend Jacobus, Wang, Zenghui

A new multi-swarm multi-objective particle swarm optimization based power and supply voltage unbalance optimization of three-phase submerged arc furnace

- Sun, Yanxia, Wang, Zenghui

A novel algorithm for optimizing the Pareto set in dynamic problem spaces

- Essiet, Ima O., Sun, Yanxia, Wang, Zenghui

Adaptive optimal digital PID controller

- Sun, Yanxia, Wang, Zenghui

Adaptive sharing scheme based sub-swarm multi-objective PSO

- Sun, Yanxia, Wang, Zenghui

  • Authors: Sun, Yanxia , Wang, Zenghui
  • Date: 2017
  • Subjects: Multi-objective PSO , Adaptive sharing scheme , Sub-swarm
  • Language: English
  • Type: Conference proceedings
  • Identifier: http://hdl.handle.net/10210/247883 , uj:25750 , Citation: Sun, Y. & Wang, Z. 2017. Adaptive sharing scheme based sub-swarm multi-objective PSO.
  • Description: Abstract: To improve the optimization performance of multi-objective particle swarm optimization, a new sub-swarm method, where the particles are divided into several sub-swarms, is proposed. To enhance the quality of the Pareto front set, a new adaptive sharing scheme, which depends on the distances from nearest neighbouring individuals, is proposed and applied. In this method, the first sub-swarms particles dynamically search their corresponding areas which are around some points of the Pareto front set in the objective space, and the chosen points of the Pareto front set are determined based on the adaptive sharing scheme. The second sub-swarm particles search the rest objective space, and they are away from the Pareto front set, which can promote the global search ability of the method. Moreover, the core points of the first sub-swarms are dynamically determined by this new adaptive sharing scheme. Some Simulations are used to test the proposed method, and the results show that the proposed method can achieve better optimization performance comparing with some existing methods.
  • Full Text:

An improved ensemble learning approach for the prediction of heart disease risk

- Mienye, Ibomoiye Domor, Sun, Yanxia, Wang, Zenghui

  • Authors: Mienye, Ibomoiye Domor , Sun, Yanxia , Wang, Zenghui
  • Date: 2020
  • Subjects: Ensemble learning , Machine learning , CART
  • Language: English
  • Type: Article
  • Identifier: http://hdl.handle.net/10210/430433 , uj:37100 , Citation: Mienye, I.D., Sun, Y. & Wang, Z. 2020. An improved ensemble learning approach for the prediction of heart disease risk.
  • Description: Abstract: According to the world health organization (WHO), cardiovascular diseases are the leading cause of death worldwide, and identifying those at risk can help prevent sudden deaths. Some computational methods have been proposed to predict the patient’s heart disease risk. Meanwhile, the accurate prediction of diseases is a critical aspect of machine learning and to further enhance the classification of heart disease risk, this paper proposes an improved ensemble learning approach. The mean of the data columns is used to partition the dataset into smaller subsets, and then a classification and regression tree (CART) algorithm is applied to model each partition. Randomization is introduced during the data partitioning. The resulting ensemble produces a robust model for the prediction of heart disease risk. To evaluate the effectiveness of the proposed method, the Cleveland and Framingham heart disease datasets are used. When compared with other machine learning methods and some recent scholarly works, the proposed method showed significant improvement.
  • Full Text:

Analysis of a fractional order nonlinear system based on the frequency domain approximation

- Wang, Zenghui, Sun, Yanxia

Analysis of the effect of parameter variation on a dynamic cost function for distributed energy resources : a DER-CAM case study

- Essiet, Ima O., Sun, Yanxia, Wang, Zenghui

  • Authors: Essiet, Ima O. , Sun, Yanxia , Wang, Zenghui
  • Date: 2018
  • Subjects: Evolutionary algorithm , Pareto front , Distributed energy resource
  • Language: English
  • Type: Article
  • Identifier: http://hdl.handle.net/10210/274901 , uj:29350 , Citation: Essiet, I.O., Sun, Y. & Wang, Z. 2018. Analysis of the effect of parameter variation on a dynamic cost function for distributed energy resources : a DER-CAM case study.
  • Description: Abstract: This paper investigates the effect of selected strategies of distributed energy resources (DER) on an energy cost function, which optimizes the allocation of distributed energy resources for a mid-rise apartment building. This is achieved by comparison of parameter optimization results for both a high- and low-level optimizer respectively. The optimization process is carried out using the following approach: (1) a two-objective function is constructed with one objective function similar to that of the high-level optimizer (DER-CAM); (2) an evolutionary algorithm (EA) with modified selection capability is used to optimize the two-objective function problem in (1) for 4 selected cases of DER utilization previously optimized in DER-CAM. (3) the optimization results of the low-level optimizer are compared with the outcome of DER-CAM optimization for the 4 selected cases. This is done to establish the capability of DER-CAM as an effective tool for optimal distributed energy resource allocation. Results obtained demonstrate the effect of load shifting and solar photovoltaic (PV) panels with power exporting capability on the optimization of the cost function. The Pareto-based MOEA approach has also proved to be effective in observing the interactions between objective function parameters. Mean inverted generational distance (MIGD) values obtained over 10 runs for each of the 4 cases considered show that a DER combination of PV panel, battery storage, heat pump and load shifting outperforms the other strategies in 70% of the total simulation runs.
  • Full Text:

Asynchronous and stochastic dimension updating PSO and its application to parameter estimation for frequency modulated (FM) sound waves

- Sun, Yanxia, Wang, Zenghui

Big data analysis for gas sensor using convolutional neural network and ensemble of evolutionary algorithms

- Essieta, Ima, Sun, Yanxia, Wang, Zenghui

  • Authors: Essieta, Ima , Sun, Yanxia , Wang, Zenghui
  • Date: 2019
  • Subjects: Convolutional neural network (CNN), Deep learning, Classification accuracy
  • Language: English
  • Type: Conference proceedings
  • Identifier: http://hdl.handle.net/10210/397337 , uj:33021
  • Description: Abstract : Big data analysis has gained popularity over the years as a result of developments in computing and electronics. Several methods have been proposed in literature for efficiently mining data from dedicated databases and a wide range of electronic sensors. However, as the volume of data grows, diversity and velocity of the data also grows (sometimes exponentially). Neural networks have been proposed in literature for optimal big data mining; however, they suffer from problems of over-fitting and under-fitting. In this paper, an ensemble of evolutionary algorithms is proposed, namely: improved non-dominated sorting genetic algorithm (NSGA), differential evolution (DE) and multi-objective evolutionary algorithm based on dominance and decomposition (MOEAD/D). These algorithms are each combined with a convolutional neural network (CNN), and performance is evaluated using root mean square error (RMSE) and mean absolute percentage error (MAPE). The test data consists of gas sensor readings obtained from an array of 16 metal oxide semiconductor sensors. The gases being detected are Carbon Monoxide/Ethylene in air, and Methane/Ethylene in air. 4,178,504 data points were collected over an uninterrupted 12-hour period. Preliminary results show improved RMSE and MAPE values over 50 learning cycles compared to a case where the CNN learned on its own.
  • Full Text:

Cask theory based parameter optimization for particle swarm optimization

- Wang, Zenghui, Sun, Yanxia

Chaotic particle swarm optimization

- Sun, Yanxia, Qi, Guoyuan, Wang, Zenghui, Van Wyk, Barend Jacobus, Hamam, Yskandar

E-education in an open distance university

- Wang, Zenghui, Sun, Yanxia

Elitism set based particle swarm optimization and its application

- Sun, Yanxia, Wang, Zenghui

  • Authors: Sun, Yanxia , Wang, Zenghui
  • Date: 2017
  • Subjects: Particle swarm optimization , Statistical method , Topology structure
  • Language: English
  • Type: Article
  • Identifier: http://hdl.handle.net/10210/242178 , uj:24972 , Citation: Sun, Y. & Wang, Z. 2017. Elitism set based particle swarm optimization and its application.
  • Description: Abstract: Topology plays an important role for Particle Swarm Optimization (PSO) to achieve good optimization performance. It is difficult to find one topology structure for the particles to achieve better optimization performance than the others since the optimization performance not only depends on the searching abilities of the particles, also depends on the type of the optimization problems. Three elitist set based PSO algorithm without using explicit topology structure is proposed in this paper. An elitist set, which is based on the individual best experience, is used to communicate among the particles. Moreover, to avoid the premature of the particles, different statistical methods have been used in these three proposed methods. The performance of the proposed PSOs is compared with the results of the standard PSO 2011 and several PSO with different topologies, and the simulation results and comparisons demonstrate that the proposed PSO with adaptive probabilistic preference can achieve good optimization performance.
  • Full Text:

Enhanced NSGA based on adaptive crossover rate and reference points

- Essiet, Ima O., Sun, Yanxia, Wang, Zenghui

Fully connected multi-objective particle swarm optimizer based on neural network

- Wang, Zenghui, Sun, Yanxia

  • Disclaimer
  • Privacy
  • Copyright
  • Contact