A review of wind speed and wind power forecasting with deep neural networks

Skin cancer is a type of disease in which malignant cells are formed in skin tissues. However, skin cancer is a dangerous disease, and an early detection of this disease helps the therapists to cure this disease. In the present research, an automatic computer-aided method is presented for the early diagnosis of skin cancer. After image noise reduction based on median filter in the first stage, a new image segmentation based on the convolutional neural network optimized by satin bowerbird optimization (SBO) has been adopted and its efficiency has been indicated by the confusion matrix. Then, feature extraction is performed to extract the useful information from the segmented image. An optimized feature selection based on the SBO algorithm is also applied to prune excessive information. Finally, a support vector machine classifier is used to categorize the processed image into the following two groups: cancerous and healthy cases. Simulations have been performed of the American Cancer Society database, and the results have been compared with ten different methods from the literature to investigate the performance of the system in terms of accuracy, sensitivity, negative predictive value, specificity, and positive predictive value.

https://www.degruyter.com/document/doi/10.1515/med-2020-0131/pdf

Computer-aided diagnosis of skin cancer based on soft computing techniques

Skin cancer diagnosis based on optimized convolutional neural network

This paper presents a new prediction model based on empirical mode decomposition, feature selection and hybrid forecast engine. The whole structure of proposed model is based on nonstationarity and non-convex nature of wind power signal. The hybrid forecast engine consists of three main stages as; empirical mode decomposition, an intelligent algorithm and back propagation neural network. All parameters of proposed neural network will be optimized by intelligent algorithm. Effectiveness of the proposed model is tested with real-world hourly data of wind farms in Spain and Texas. In order to demonstrate the validity of the proposed model, it is compared with several other wind speed and power forecast techniques. Obtained results confirm the validity of the developed approach.

Application of hybrid forecast engine based intelligent algorithm and feature selection for wind signal prediction

A data-driven strategy for short-term electric load forecasting using dynamic mode decomposition model

A new wind power prediction method based on ridgelet transforms, hybrid feature selection and closed-loop forecasting

Disclosed in the invention is a running state evaluation method of an urban distribution network. According to the method, with combination of actual investigation and expertise, single indexes capable of reflecting a running state of a distribution network comprehensively are selected by following the principles of objectivity, high accuracy, mutual independence, and high operability in a perspective of system engineering; superior indexes which the single indexes belong to are defined based on an analytic hierarchy process method, and an overall and complete index system is established and so on; a scoring formula of the single indexes is determined based on combination with the correlated industrial standard and the expertise by using a fuzzy membership function, and weight factors of all indexes are determined by using a pairwise comparison matrix method; and with running data collected by other systems of the distribution network automatically, scores of all indexes are calculated and then a running state evaluation score of the whole distribution network is provided.

Running state evaluation method of urban distribution network

The invention discloses a distribution network reconstruction optimization method based on multi-objective optimization The method includes the following implementation steps that the current system losses, the load balance index and the minimum node voltage of a distribution network are respectively calculated, whether reconstruction optimization is needed or not is judged, if reconstruction optimization is needed, the distribution network is reconstructed, and then an optimal topological structure is acquired; when the load balance index or the minimum node voltage exceeds threshold values, network reconstruction operation is directly executed, when only the system losses exceed threshold values, an economic benefit evaluation index needed for switching the distribution network from the current topological structure to the optical topological structure is calculated, and if the index is larger than a designated threshold value, it is judged that economic benefit evaluation passes and the network reconstruction operation is executed; or else evaluation does not pass and the network reconstruction operation is not executed The reconstruction optimization effect of the distribution network is good, economic benefit evaluation can be conducted before execution of the network reconstruction operation, waste is avoided, use is convenient, resources are saved, and economical efficiency and safety are good

Distribution network reconstruction optimization method based on multi-objective optimization

The invention discloses a power distribution network reconstruction design method, and belongs to the technical field of power distribution network optimization The power distribution network reconstruction design method comprises the following steps that a, target normalization is performed on the three commonly used optimization indexes of a power distribution network, including a network loss target, a load balancing target and a voltage quality target; b, all target weights are set by utilizing an analytic hierarchy method; c, and a target function is constructed according to the steps a and b The power distribution network operation mode of the power distribution network under the condition that multiple indexes of the power distribution network are optimal can be acquired via normalization of multiple targets and target weight setting under the premise that the voltage quality requirements, the line current requirements and the transformer capacity requirements of the power distribution network are met and radiation operation is realized so that the power distribution network is enabled to achieve the optimal operation efficiency

Power distribution network reconstruction design method

The invention discloses a load characteristic classification and synthesis method based on frequency domain indexes. Firstly, electrical transformer districts to be classified are obtained form a monitoring control and data acquisition system, data are preprocessed, normalization processing is conducted the data, the data are represented through per unit values, an average is obtained according to the data in one or more weeks, and a typical daily load curve is obtained; then, based on a defined frequency domain index description system, an appointed clustering method is adopted for obtaining electrical transformer district types similar to frequency domain characteristic parameters, and finally typical load curves of classified users and frequency domain index description sets of the typical load curves are obtained. Compared with traditional load classification and synthesis methods, the load characteristic classification and synthesis method has the advantages that the number of data dimensions can be reduced effectively, computation overheads and memory capacity are reduced, and the load classification effect is similar to that of the traditional methods.

Li Xinran

Papers

A new wind power prediction method based on ridgelet transforms, hybrid feature selection and closed-loop forecasting

Running state evaluation method of urban distribution network

Distribution network reconstruction optimization method based on multi-objective optimization

Power distribution network reconstruction design method

Load characteristic classification and synthesis method based on frequency domain indexes