With the rapid development of social networks, short texts make it easier for people to comment on hot events and express their emotions. The information published by users through short texts contains emotional featu...
With the rapid development of social networks, short texts make it easier for people to comment on hot events and express their emotions. The information published by users through short texts contains emotional features of different trends, and it is of great significance to dig deep into these features. However, the traditional RNN algorithm, SVM and linear LSTM can only discriminate emotional sentiment because of the short text grammar and the sparse data, which is far from the purpose of opinion mining. Therefore, this paper proposes to apply Graph LSTM to short text classification, mine deeper information, and achieve good results. Finally, the paper compares three different machine learning methods to achieve fine-grained sentiment analysis.
As a large number of renewable energy, electric vehicles and energy storage systems enter the regional integrated energy system and play an increasingly important role in the system, effective energy management for in...
详细信息
ISBN:
(数字)9781728101996
ISBN:
(纸本)9781728102009
As a large number of renewable energy, electric vehicles and energy storage systems enter the regional integrated energy system and play an increasingly important role in the system, effective energy management for integrated energy systems are necessary. However, there are many problems in the operation of integrated energy systems, including the uncertainty of renewable energy output, the operation mode of electric vehicles, the degraded cost of energy storage systems and the regulation of real-time electricity prices. To this end, this paper establishes a regional integrated energy management system model based on multi-agent method to control the balance between supply and demand and optimize operators' profit and users' cost. By setting up the operational agent and the user agent, combined with the Stackelberg game method, the energy storage devices' and the electric vehicles' work mode are determined and the electricity price is also decided. Simulations in the improved IEEE-14 bus test system show that the proposed multi-agent energy management system can control elastic loads and energy storage systems. What's more, it can reduce customer costs and increase operator revenue.
This paper is concerned on the design of H ∞ estimation for discrete-time T-S fuzzy system. In order to save limited bandwidth resources, the event-triggered scheme is introduced. By using Lyapunov functionals and i...
详细信息
ISBN:
(数字)9781728101996
ISBN:
(纸本)9781728102009
This paper is concerned on the design of H ∞ estimation for discrete-time T-S fuzzy system. In order to save limited bandwidth resources, the event-triggered scheme is introduced. By using Lyapunov functionals and integral inequalities, the stability of the error system is proved. In addition, the observer gain parameters are obtained by LMI technique in MATLAB. Finally, the effectiveness of the design method is verified by a simulation example.
Considering the photovoltaic volatility, intermittency and random, the accurate prediction of photovoltaic power output is very important for grid dispatching and energy management. In order to improve the accuracy of...
详细信息
ISBN:
(数字)9781728101996
ISBN:
(纸本)9781728102009
Considering the photovoltaic volatility, intermittency and random, the accurate prediction of photovoltaic power output is very important for grid dispatching and energy management. In order to improve the accuracy of photovoltaic system short-term power prediction, this paper analyzes the relationship between the power output and the environment factors. The principal component analysis (PCA) based particle group-ridge wave neural network model and support vector machine regression (SVR) for short-term prediction model are developed. In this paper, the PCA is used to reduce the number of input environment factors and extract the main components. The ridge wave neural network parameters are selected by particle swarm optimization (PSO). The SVR model is used to optimize the network structure for a better model performance. The correlation and reliability of the prediction results are discussed. The results show that, excluding the influence of weather interference factors, SVR has higher precision and accuracy in prediction model, smaller mean variance, and better prediction effect in the prediction mode.
For linear time-invariant (LTI) systems, we consider a switching control composed of a collection of static output feedback controllers and an output dependent switching law so that the closed-loop system is asymptoti...
详细信息
ISBN:
(数字)9781728190938
ISBN:
(纸本)9781728190945
For linear time-invariant (LTI) systems, we consider a switching control composed of a collection of static output feedback controllers and an output dependent switching law so that the closed-loop system is asymptotically stable when the controllers are switched under the switching law. Both certain and uncertain LTI systems are dealt with. Multiple Lyapunov functions and a piecewise observer are proposed to implement the switching law, and sufficient conditions are derived for the existence condition and the computation of multiple Lyapunov functions and static output feedback gains.
Nuclear reactors often operate at varying loads. In order to match the core thermal power with the load while ensuring the safe operation of the nuclear power plant, we estimate the core thermal power value of the nuc...
详细信息
Nuclear reactors often operate at varying loads. In order to match the core thermal power with the load while ensuring the safe operation of the nuclear power plant, we estimate the core thermal power value of the nuclear reactor for timely adjustment. The traditional physical models and experimental methods based on nuclear reaction mechanism cannot get the accurate value of thermal power by directly analyzing the relevant data. We construct a long short-term memory network (LSTM) by using the real monitoring data of a CANDU reactor nuclear power plant. Based on the self-learning characteristics, the LSTM can precisely predict the core thermal power of nuclear reactor. Simulation results show that the proportion of data with absolute error less than 50MW is 97.63%. The proportion of data with relative error less than 5% is 98.73%, and the average relative error is 2.65%. Furthermore, we compared the performance of LSTM with the back-propagation neural network (BPNN) and the convolution neural network (CNN), where the LSTM model outperforms the BPNN and CNN in terms of prediction precisions.
Environmental air quality affects people's life, obtaining real-time and accurate environmental air quality has a profound guiding significance for the development of social activities. At present, environmental a...
详细信息
State Grid Corporation of China has accumulated a large number of electric power fault textual data based on ICT customer services. Effectively classifying and analyzing these texts can provide important clues for res...
State Grid Corporation of China has accumulated a large number of electric power fault textual data based on ICT customer services. Effectively classifying and analyzing these texts can provide important clues for resolving new faults, and therefore helps customer service staffs provide more accurate fault diagnosis solutions. Because an occurred fault is possibly related to multiple classification labels, it is challenging to effectively classify the faults. In this paper, we present an ensemble learning based multi-label classification approach to analyzing electric power fault text data. Firstly, the power fault report data is pre-processed by word segmentation and stop word removal according to the structure of fault data. Each of fault text is represented as a TF-IDF vector. Then, we combine Binary Relevance with the Gradient Boosting ensemble learning algorithm for multi-label classification of fault texts. At last, the related experiments were made, and the experimental results show that our method is better than the traditional approaches such as Binary Relevance based on Logistic Regression and ML-KNN for fault text classification.
Over the past years, interest in classifying drivers’ behavior from data has surged. Such interest is particularly relevant for car insurance companies who, due to privacy constraints, often only have access to data ...
详细信息
We consider a community detection problem for gossip dynamics with stubborn agents in this paper. It is assumed that the communication probability matrix for agent pairs has a block structure. More specifically, we as...
详细信息
暂无评论