http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Xianglian Zhao (검색결과 3 건)
- 무료
- 기관 내 무료
- 유료
-
Prediction Simulation Study of Road Traffic Carbon Emission Based on Chaos Theory and Neural Network
Hao Wu,Xianglian Zhao 보안공학연구지원센터 2016 International Journal of Smart Home Vol.10 No.7
Study the road traffic carbon emission and accurately predict the problems, the road traffic carbon emission has the complex systems of chaos and nonlinearity, the traditional method ignores the chaos of the road traffic carbon emission change, and it is so difficult to precisely control the rules of the road traffic carbon emission change that the precision of the of traffic carbon emission prediction is lower. In this study, it proposes the road traffic carbon emission prediction model based on the chaos theory and neural network and improves the prediction precision of the road traffic carbon emission time sequence. First of all, it reconstructs the time sequence data of the road traffic carbon emission change through the space, and sorts out the chaos change rules hidden in the time sequence data and then uses the BP neural network to study and carry out the modeling of the time sequence data of the road traffic carbon emission, and optimize the neural network parameter in order to improve the prediction precision of the road traffic carbon emission time sequence. The simulation result shows that, Chao-BPNN has overcome the deficits of the traditional method and could precisely and comprehensively reflect the change rules of the road traffic carbon emission time sequence, and effectively improved the prediction precision of the road traffic carbon emission.
-
Carbon Emission Early Warning System Modeling and Simulation Study of Urban Regional Transportation
Hao Wu,Xianglian Zhao 보안공학연구지원센터 2016 International Journal of Smart Home Vol.10 No.8
Accurate assessment of carbon emission of urban regional transportation is the core of urban low-carbon traffic construction. Traditional carbon emission evaluation methods need a large number of samples and sample data of carbon emission of urban regional transportation is smaller, so the precision will be lower if traditional methods are adopted. This paper proposes particle swarm optimization to optimize support vector machine carbon emission early warning system of urban regional transportation (PSO-SVM) and takes the advantage of small sample data modeling of support vector machine to improve the carbon emission evaluation accuracy of urban regional transportation. Furthermore, this paper takes carbon emission evaluation accuracy of urban regional transportation as modeling target, selects reasonable evaluation index, confirms carbon emission evaluation model structure of urban regional transportation and then optimizes support vector machine (SVM) by adopting particle swarm optimization (PSO) to establish evaluation model and conduct system simulation. Results show that PSO-SVM actually increases the assessment accuracy, having practical application value in urban traffic carbon emission management.
-
Time-Series Forecasting Based on Multi-Layer Attention Architecture
Na Wang,Xianglian Zhao 한국인터넷정보학회 2024 KSII Transactions on Internet and Information Syst Vol.18 No.1
Time-series forecasting is extensively used in the actual world. Recent research has shown that Transformers with a self-attention mechanism at their core exhibit better performance when dealing with such problems. However, most of the existing Transformer models used for time series prediction use the traditional encoder-decoder architecture, which is complex and leads to low model processing efficiency, thus limiting the ability to mine deep time dependencies by increasing model depth. Secondly, the secondary computational complexity of the self-attention mechanism also increases computational overhead and reduces processing efficiency. To address these issues, the paper designs an efficient multi-layer attention-based time-series forecasting model. This model has the following characteristics: (i) It abandons the traditional encoder-decoder based Transformer architecture and constructs a time series prediction model based on multi-layer attention mechanism, improving the model's ability to mine deep time dependencies. (ii) A cross attention module based on cross attention mechanism was designed to enhance information exchange between historical and predictive sequences. (iii) Applying a recently proposed sparse attention mechanism to our model reduces computational overhead and improves processing efficiency. Experiments on multiple datasets have shown that our model can significantly increase the performance of current advanced Transformer methods in time series forecasting, including LogTrans, Reformer, and Informer.
ScienceON
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
