Nanchang Institute of Technology
Nanchang, China

Nanchang Institute of Technology is a university in Nanchang, Jiangxi, China.Nanchang Institute of Technology is located in the capital city of Jiangxi province - Nanchang, is approved by the Ministry of Education set up a second level of regular undergraduate institutions, a bachelor's degree-granting units. According to April 2014 the school's official website revealed that the campus covers an area of 757.79 acres. 1.19 million square meters have been built school, library books 2,650,000, a variety of educational assets totaled 1.8 billion rmb, teaching equipment worth 176 million rmb. The school has 16 sub-colleges, 42 undergraduate majors, 62 specialties, Jiangxi university "five" key disciplines 2 , there are students in nearly 30,000 people . Wikipedia.

Time filter
Source Type

Bao X.,Nanchang Institute of Technology
Communications in Computer and Information Science | Year: 2017

In energy harvesting wireless sensor network (EH-WSN), many energy harvesting technologies are developed to sustain the long-term operation of wireless sensor network. However, the prediction of harvested energy plays an important role for energy management. In this paper, we focus on energy prediction for EH-WSN. We first analyze the factors of affecting energy harvesting and the characteristic of the solar array. Then, the kernel partial least squares (KPLS) is proposed as the energy prediction model. According to the difference of energy intake for the days, months, season and year, the four energy prediction models are established. By extensive experimental analysis for real solar data in different areas, the proposed prediction model improves prediction accuracy than existing energy prediction algorithms in EH-WSN. © Springer Nature Singapore Pte Ltd. 2017.

Niu X.,Nanchang Institute of Technology
Civil Engineering and Urban Planning IV - Proceedings of the 4th International Conference on Civil Engineering and Urban Planning, CEUP 2015 | Year: 2016

Industrial park has played a major role in economic development these years. But there are also some issues restricting the further development of industrial park. The purpose of this research is to identify whether ecological industry significantly impacts the sustainable development of industrial park. Based on the relevant literature and theories, the paper confirmed the evaluation index system and built comprehensive evaluation model of industrial park and ecological industry. Data sources were got from Jiangxi Statistical Yearbook and China Industry Economy Statistical Yearbook. The paper used SPSS 20.0 to do correlation and regression analysis. The results confirm that ecological industry has a positive and significant impact on the sustainable development of industrial park. According to the results, industrial park should focus on the ecological industry in the future development. © 2016 Taylor & Francis Group, London.

Lan Y.,Nanchang Institute of Technology
IOP Conference Series: Earth and Environmental Science | Year: 2017

Nanchang city subway excavation depth and the Quaternary aquifer layers are located at approximately the same depth. After the completion of the subway, that is equivalent to adding a retaining wall in the phreatic aquifer. The metro line 4 influence on groundwater flow field was analyzed based on the groundwater flow field and the dynamic relationship between groundwater and surface water. The result was that the groundwater level would rise in the area of facing groundwater movement, while others decrease. The influence of metro was apparent at the place where hydraulic contact of Gan River with groundwater was good, and vice versa. © Published under licence by IOP Publishing Ltd.

Li L.,Nanchang Institute of Technology
International Journal of Advancements in Computing Technology | Year: 2012

This paper proposes a vector learning particle swarm optimization based on the traditional particle swarm optimization (PSO) algorithm. Unlike the traditional PSO algorithm, the algorithm does not update the entire speed or position vector at the same time, but divides the entire speed or position vector into sub-vectors and cyclically updates each speed or position sub-vector in order. By introducing a new speed update learning strategy in speed sub-vector update, the algorithm makes the particles examine ahead the effects of particle evolution and feed the information back during the update process, to finally determine the next generation value of the particle speed sub-vector, which can effectively avoid the blindness of speed evolution. On the other hand, the speed update learning strategy contains a diversity factor that can effectively expand the diversity of particle evolution. The experimental results show that: This algorithm has strong global search ability for most standard composite test functions and stronger optimization ability than popular PSO based improved algorithms and intelligent single particle optimizer.

Che J.,Nanchang Institute of Technology
Neurocomputing | Year: 2015

It has been widely demonstrated in forecasting that combining forecasts can improve the forecast performance compared to individual forecasts. However, how to select the optimal sub-models from all the available models is a difficult problem in combination forecasting model. Consider that the redundancy information among the selected sub-models will reduce the performance of the combination forecasting model, it is advocated to select a sub-model only if it contributes to the redundancy removing mutual information between the outputs of the selected sub-models and the actual outputs. As linear combination method is promising and popular in the field of combination forecast, a novel Max-Linear-Relevance and Min-Linear-Redundancy based selection algorithm is proposed in this paper. The proposed selection algorithm provides a theoretical approach for the optimal sub-models selection, and tries to compute the redundancy removing linear mutual information between the outputs of the selected sub-models and the actual outputs. Three monthly time series from DataMarket are used as illustrative examples to evaluate the forecasting. As a result of the implementation, it is seen that the proposed combination forecasting model produces better forecasts than those produced by other models. © 2014 Elsevier B.V.

Wang H.,Nanchang Institute of Technology
Mathematical Problems in Engineering | Year: 2012

This paper presents a modified barebones particle swarm optimization (OBPSO) to solve constrained nonlinear optimization problems. The proposed approach OBPSO combines barebones particle swarm optimization (BPSO) and opposition-based learning (OBL) to improve the quality of solutions. A novel boundary search strategy is used to approach the boundary between the feasible and infeasible search region. Moreover, an adaptive penalty method is employed to handle constraints. To verify the performance of OBPSO, a set of well-known constrained benchmark functions is used in the experiments. Simulation results show that our approach achieves a promising performance. © 2012 Hui Wang.

Che J.X.,Nanchang Institute of Technology
Applied Soft Computing Journal | Year: 2013

Support vector regression (SVR) has become very promising and popular in the field of machine learning due to its attractive features and profound empirical performance for small sample, nonlinearity and high dimensional data application. However, most existing support vector regression learning algorithms are limited to the parameters selection and slow learning for large sample. This paper considers an adaptive particle swarm optimization (APSO) algorithm for the parameters selection of support vector regression model. In order to accelerate its training process while keeping high accurate forecasting in each parameters selection step of APSO iteration, an optimal training subset (OTS) method is carried out to choose the representation data points of the full training data set. Furthermore, the optimal parameters setting of SVR and the optimal size of OTS are studied preliminary. Experimental results of an UCI data set and electric load forecasting in New South Wales show that the proposed model is effective and produces better generalization performance. © 2013 Elsevier B.V. All rights reserved.

Wang C.,Nanchang Institute of Technology
Diangong Jishu Xuebao/Transactions of China Electrotechnical Society | Year: 2013

Zero order voltage of the multilevel inverter is a serious threat to the performance and the aging of the motor, so restraining zero order voltage to optimize the motor running state and its maintenance has practical value. In order to restrain zero order voltage, this paper analyzes the distribution rule of zero order voltage for n-cell inverters and proposes a optimal modulation algorithm. The proposed algorithm, without adding any hardware, makes zero order voltage change within the minimum range, while it can ensure the quality of output waveform. Finally, the simulation and experimental results prove that the theoretical analysis of the proposed algorithm on restraining zero order voltage is correct and feasible.

Liu Y.,Nanchang Institute of Technology
Procedia Engineering | Year: 2012

Based on Karhunen-Loève expansion of random field, the paper utilizes Hermite polynomial chaos expansion to build the stochastic response surface function, and the unknown coefficients of the function can be calculated by probabilistic collocation approach. Then, the geometric method can be used to calculate the structural reliability. A comparison with Monte Carlo simulation shows that the proposed method can achieve high accuracy and efficiency while analyzing the property of the second-order and the third-order stochastic response surface. © 2012 Published by Elsevier Ltd.

Che J.,Nanchang Institute of Technology
International Journal of Electrical Power and Energy Systems | Year: 2014

Context: Current decision development in electricity market needs a variety of forecasting techniques to analysis the nature of electric load series. And the interpretability and forecasting accuracy of the electric load series are two main objectives when establishing the load forecasting model. Objective: Considering that electric load series exhibit repeating seasonal cycles at different level (daily, weekly and annual seasonality), this paper concerns the interpretability of these seasonal cycles and the forecasting accuracy. Method: For the above proposes, the author firstly introduces a multiple linear regression model that involves treating all the seasonal cycles as the input attributes. The result helps the managers to interpret the series structure with multiple seasonal cycles. To improve the forecasting accuracy, a support vector regression model based on optimal training subset (OTS) and adaptive particle swarm optimization (APSO) algorithm is established to forecast the residual series. Thus, a novel hybrid model combining the proposed linear regression model and support vector regression model is built to achieve the above bi-objective short-term load forecasting. Results: The effectiveness of the hybrid model is evaluated by an electrical load forecasting in California electricity market. The proposed modeling algorithm generates not only the seasonal cycle's decomposition for the time series, but also better accuracy predictions. Conclusion: It is concluded that the hybrid model provides a very powerful tool of easy implementation for bi-objective short-term electric load forecasting. © 2014 Elsevier Ltd. All rights reserved.

Loading Nanchang Institute of Technology collaborators
Loading Nanchang Institute of Technology collaborators