Driven by the development and application of smart grid and renewable energy sources (RES) generation technologies, microgrid (MG) plays an important role in environmental protection and optimization of the grid struc...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
Driven by the development and application of smart grid and renewable energy sources (RES) generation technologies, microgrid (MG) plays an important role in environmental protection and optimization of the grid structure by integrating local loads and distributed energy. However, the stochastic and intermittent nature of RES have caused difficulties in the economic energy dispatching of MG. Inspired by reinforcement learning (RL) algorithms, this paper proposes a novel learning-based control MG scheduling strategy. Unlike traditional model-based methods that require predictors to estimate stochastic variables with uncertainties, the proposed solution does not require an explicit model. The proposed method is simulated in the environment composed of realistic data, and the effectiveness of the method is explained and verified.
Based on the agglomerative hierarchical clustering algorithm, this paper proposes a new information entropy evaluation indicator-Average Discriminant Entropy(ADE), to measure the stability of cluster structure. After ...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
Based on the agglomerative hierarchical clustering algorithm, this paper proposes a new information entropy evaluation indicator-Average Discriminant Entropy(ADE), to measure the stability of cluster structure. After that, We designed the corresponding algorithm. In order to verify the validity of the indicator, six heterogeneous artificial data sets were used to simulate. By comparing ADE with other classic evaluation indicators, we found that ADE can obtain the best results under various data sets. Finally, a Monte Carlo experiment on the data with different noise levels proved the robust of ADE.
Imbalanced data classification has always been a hot topic in traditional machine learning. The usual method is oversampling. Its main idea is to randomly synthesize the new minority samples between the minority sampl...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
Imbalanced data classification has always been a hot topic in traditional machine learning. The usual method is oversampling. Its main idea is to randomly synthesize the new minority samples between the minority samples and their neighboring samples, to put the data in a particular state of equilibrium. The existing improved methods have improved the classifier's performance to some extent, but most of the focus is on the minority sample. In this paper, a denoise-based oversampling method (DNOS) is proposed, which performs different denoise processes for the majority and minority samples. Then, it is combined with ADASYN to oversampling the data. Experimental results show that DNOS has a better classification effect than ADASYN.
The purpose of this paper is to realize system analysis and algorithm design for biological data. In this paper, primary bladder cancer is taken as a typical example, the structure of the system is extracted by hierar...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
The purpose of this paper is to realize system analysis and algorithm design for biological data. In this paper, primary bladder cancer is taken as a typical example, the structure of the system is extracted by hierarchical clustering method, and the function of the system is mined by convolutional neural network technology. Based on these methods, a complex system structure analysis model and an algorithm are constructed to study the big data system. Furthermore, the feasibility study of relevant theories and methods are carried out while the application and expand of technology are mentioned, combined with the actual data. The effectiveness and practicability of the algorithm and system are also verified by simulation.
In order to improve the real-time performance and accuracy of localization for mobile robot in indoor environment, a neural network data fusion approach is proposed to eliminate the affection caused by errors from env...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
In order to improve the real-time performance and accuracy of localization for mobile robot in indoor environment, a neural network data fusion approach is proposed to eliminate the affection caused by errors from environment or measurements. In the approach, the odometry data are firstly obtained by calculating the collected encoder data through the Dead Reckoning (DR), then we fuse the odometry data and the lidar data by inputting them into a three-layer neural network. Experimental results show that the trained network improved the robot localization performance and its position accurate is within 6cm with good real time response.
For medical image processing, as the target area of the tumor lesions is small, and the boundaries of the organs are blurred, so the segmentation of the medical images is difficult. In the original 3D U-net model, fea...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
For medical image processing, as the target area of the tumor lesions is small, and the boundaries of the organs are blurred, so the segmentation of the medical images is difficult. In the original 3D U-net model, feature extraction is performed on the interest image region by increasing the channel attention mechanism, so that the model keep a watchful eye on key region before segmentation. Test results indicate that the improved model has significantly improved segmentation accuracy relative to the original 3D U-net model and is a valid image segmentation model.
In this paper, the information provided by the annex is data support, based on matlab and Excel software, based on the simulated annealing algorithm, the mathematical model of the power planning investment plan is est...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
In this paper, the information provided by the annex is data support, based on matlab and Excel software, based on the simulated annealing algorithm, the mathematical model of the power planning investment plan is established. Taking the mathematical model of power planning investment plan as the leading analysis, starting from the engineering economic analysis, we can find out the influence of “time” value, and then study the single-stage power expansion planning from different angles, then extend the power expansion planning to multiple stages, and finally according to the analysis. The calculation analyzes the impact of renewable energy access to the power system and provides a new solution to the enormous challenges brought about by the numerous components of the actual power system.
A new bionic algorithm named as Flower Pollination algorithm (FPA) was proposed by Yang. FPA has some shortcomings, such as premature convergence, low precision, et al. So an improved flower pollination algorithm (IFP...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
A new bionic algorithm named as Flower Pollination algorithm (FPA) was proposed by Yang. FPA has some shortcomings, such as premature convergence, low precision, et al. So an improved flower pollination algorithm (IFPA) is proposed in this paper. IFPA combines three aspects: global pollination with quantum search mechanics, local pollination with DE/rand/1 mutation, and switch on dimensions. The experimental results show that IFPA can speed up convergence and improve accuracy.
The prevention, control and prediction of emerging infectious diseases are vital in order to effectively manage their spread and impact. Over the years many modelling techniques have been developed for the management ...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
The prevention, control and prediction of emerging infectious diseases are vital in order to effectively manage their spread and impact. Over the years many modelling techniques have been developed for the management of infectious diseases. However, emerging diseases are linked to selective pressures caused by humans, for example environmental pressure such as urbanisation and habitat fragmentation. In this paper we present a new approach, which combines human behavioural factors together with advanced mathematical modelling and machine learning, for preventing, monitoring and predicting future epidemics. This will help medical professionals and policy makers to optimize, in real-time, response efforts to major outbreaks.
Visible and infrared image fusion is widely adopted in navigation, object recognition and smart city. In this paper, we use the saliency object detection method to fusion the visible and infrared images. In considerat...
详细信息
ISBN:
(数字)9781728197241
ISBN:
(纸本)9781728197258
Visible and infrared image fusion is widely adopted in navigation, object recognition and smart city. In this paper, we use the saliency object detection method to fusion the visible and infrared images. In consideration of the properties of the different type of image, we design two different visual saliency object detection methods to fuse the coefficients of detail image layers and coarse image layers. Then we can reconstruct the fused image from those coefficients. The experimental results indicate that the proposed fusion algorithm conforms to the human vision characteristics and has a strong comparability and effectiveness in both objective and subjective evaluation.
暂无评论