In the process of urbanisation in China, many cities expect to promote the development of new towns through the construction of sports centres. However, due to the unreasonable design of the scale, accessibility and v...
详细信息
In the process of urbanisation in China, many cities expect to promote the development of new towns through the construction of sports centres. However, due to the unreasonable design of the scale, accessibility and vitality of the sports centre, the catalyst effect of the sports centre is difficult to play an effective role. Using cluster analysis algorithm and spatial syntax, this study analyses the algorithm of sports centres with sustainable development characteristics, and puts forward the conclusions of sustainable development planning strategies such as venue merger design under the principle of intensive, maintaining high accessibility of sports centres, ensuring the compound function of surrounding plots and grid space to improve regional vitality, in order to provide some inspiration for the planning and construction of Sports Centre in the future.
The smart meter is an important part of the smart grid, and in order to take full advantage of smart meter data, this paper mines the electricity behaviors of smart meter users to improve the accuracy of load forecast...
详细信息
The smart meter is an important part of the smart grid, and in order to take full advantage of smart meter data, this paper mines the electricity behaviors of smart meter users to improve the accuracy of load forecasting. First, the typical day loads of users are calculated separately according to different date types (ordinary workdays, day before holidays, holidays). Second, the similarity between user electricity behaviors is mined and the user electricity loads are clustered to classify the users with similar behaviors into the same cluster. Finally, the load forecasting model based on the Online Sequential Extreme Learning Machine (OS-ELM) is applied to different clusters to conduct load forecasting and the load forecast is summed to obtain the system load. In order to prove the validity of the proposed method, we performed simulation experiments on the MATLAB platform using smart meter data from the Ireland electric power cooperation. The experimental results show that the proposed method is able to mine the user electricity behaviors deeply, improve the accuracy of load forecasting by the reasonable clustering of users, and reveal the relationship between forecasting accuracy and cluster numbers.
Understanding the spatiotemporal evolution of droughts is critical for food security and water allocation. In this study, we propose an approach to construct the linkage of the propagation from meteorological drought ...
详细信息
Understanding the spatiotemporal evolution of droughts is critical for food security and water allocation. In this study, we propose an approach to construct the linkage of the propagation from meteorological drought to agricultural drought to explore the simultaneous spatiotemporal evolution of droughts based on a 3-dimensional clustering algorithm. We first evaluate the improvement of the downscaled high-resolution outputs from the Weather Research and Forecasting (WRF) model to reanalysis data in detecting wet-dry variations in the agro-pastoral ecotone of northern China (APENC). The WRF simulation results well characterize the evolution of droughts with a high correlation coefficient of 0.82 (p<0.05), which implies that the WRF downscaling model provides reliable hydrometeorological results for assessing and analyzing long-term wet-dry variations. Subse-quently, we identify and track the spatiotemporal evolution of each individual drought event in the APENC for the first time. Based on the standardized precipitation index calculated from the WRF outputs, a total of 185 drought clusters were identified during 2000-2017, with 28 drought events lasting at least 3 months duration occurring in the APENC. The characteristics of the different drought events vary considerably. Droughts in the APENC have a larger percentage of propagation to the northeast and northwest and migrated hundreds of ki-lometers from the source sites. The results of the propagation of meteorological droughts to agricultural droughts indicate that 53.75% of the meteorological drought events progressed further to agricultural droughts. Agri-cultural droughts exhibit spatial variations consistent with meteorological droughts. Agricultural droughts have 1.69 months onset lag time, 2.12 months termination lag time, and overall longer duration than meteorological droughts in the APENC. Our findings provide valuable information for the mechanism and prediction of drought propagation.
The traditional lane line detection algorithm relies on artificial design features, which has poor robustness and cannot cope with the complex urban street background. With the rise of deep learning technology, the al...
详细信息
The traditional lane line detection algorithm relies on artificial design features, which has poor robustness and cannot cope with the complex urban street background. With the rise of deep learning technology, the algorithm model with convolutional neural network as the mainstream is widely used in the field of computer vision, which provides a new idea for lane line detection. In order to improve the disadvantages of traditional lane line detection methods that are vulnerable to environmental impact and poor robustness, a nonlinear convolution neural network algorithm for driverless lane line detection is proposed. Firstly, the pretreatment method of extracting the region of interest and enhancing the contrast of lane lines is used to reduce the unnecessary image background and enhance the feature details of the image. Existing deep learning-based lane line detection algorithms still have difficulties. First, accumulated wear and tear will cause lane line to fade and fade;roadside trees and buildings can interfere with the performance of lane line detection algorithm. In addition, compared with the pixels of the whole picture, the lane line pixels are too few, and the deep convolution neural network of layer convolution is easy to lead to the loss of details. In addition, when the traffic flow is large, the lane line is easily blocked, which makes it more difficult to detect the lane line. Then the model is built based on the lane line image features extracted by CNN, and the DBSCAN clustering algorithm is used to post-process the lane line segmentation model;Finally, the least square method is used to fit the quadratic curve of the pixel peak points of the lane line, and the fitting results are regressed to the original image. The experimental results show that the accuracy and recall of the lane line detection model verification set are 91.3% and 90.6%, respectively, indicating that the model has a good segmentation effect. It is proved that the lane line detect
The accurate measurement of slope displacement profiles using a fiber Bragg grating flexible sensor is limited due to the influence of accumulative measurement errors. The measurement errors vary with the deformation ...
详细信息
The accurate measurement of slope displacement profiles using a fiber Bragg grating flexible sensor is limited due to the influence of accumulative measurement errors. The measurement errors vary with the deformation forms of the sensor, which dramatically affects the measurement accuracy of the slope displacement profiles. To tackle the limitations and improve the measurement precision of displacement profiles, a segmental correction method based on strain increments clustering was proposed. A K-means clustering algorithm was used to automatically identify the deformation segments of a flexible sensor with different bending shapes. Then, the particle swarm optimization method was adopted to determine the correction coefficients corresponding to different deformation segments. Both finite element simulations and experiments were performed to validate the superiority of the proposed method. The experimental results indicated that the mean absolute errors (MAEs) percentages of the reconstructed displacements using the proposed method for six different bending shapes were 1.87%, 5.28%, 6.98%, 7.62%, 4.16% and 8.31%, respectively, which had improved the accuracy by 26.83%, 18.94%, 29.49%, 26.35%, 7.39%, and 19.65%, respectively. Therefore, it was confirmed that the proposed correction method was competent for effectively mitigating the measurement errors and improving the measurement accuracy of slope displacement profiles, and it presented a vital significance and application promotion value.
One common problem in viral marketing, counter-terrorism and epidemic modeling is the efficient detection of a community that is centered at an individual of interest. Most community detection algorithms are designed ...
详细信息
ISBN:
(纸本)9781921770296
One common problem in viral marketing, counter-terrorism and epidemic modeling is the efficient detection of a community that is centered at an individual of interest. Most community detection algorithms are designed to detect all communities in the entire network. As such, it would be computationally intensive to first detect all communities followed by identifying communities where the individual of interest belongs to, especially for large scale networks. We propose a community detection algorithm that directly detects the community centered at an individual of interest, without the need to first detect all communities. Our proposed algorithm utilizes an expanding ring search starting from the individual of interest as the seed user. Following which, we iteratively include users at increasing number of hops from the seed user, based on our definition of a community. This iterative step continues until no further users can be added, thus resulting in the detected community comprising the list of added users. We evaluate our algorithm on four social network datasets and show that our algorithm is able to detect communities that strongly resemble the corresponding real-life communities.
Topology construction, the initial step of the topology control, is an important technique for a wireless ad hoc network to be energy-efficient. In [4], we have proposed to use the relative neighborhood graph (RNG) to...
详细信息
ISBN:
(纸本)9781457720536
Topology construction, the initial step of the topology control, is an important technique for a wireless ad hoc network to be energy-efficient. In [4], we have proposed to use the relative neighborhood graph (RNG) to obtain an RNG-based topology in which the transmission ranges between wireless nodes are reduced. Then, among the RNG-based topology, we proposed a green clustering algorithm (GCA) to organize the wireless nodes into a clustered network topology. In this paper, we further analyze the energy consumption in exchanging data packets and cluster maintenance messages. Simulation results confirm that the proposed RGCA (i.e., combining the RNG and GCA) provides a way to construct an energy-efficient cluster topology for wireless ad hoc networks.
It is challenging to detect small targets in aerial images captured by drones due to variations in target sizes and occlusions arising from the surrounding environment. This study proposes an optimized object detectio...
详细信息
It is challenging to detect small targets in aerial images captured by drones due to variations in target sizes and occlusions arising from the surrounding environment. This study proposes an optimized object detection algorithm based on YOLOv7 to address the above-mentioned challenges. The proposed method comprises the design of a Genetic Kmeans (1IoU) clustering algorithm to obtain customized anchor boxes that more significantly apply to the dataset. Moreover, the SPPFCSPC_group structure is optimized using group convolutions to reduce model parameters. The fusion of Spatial Pyramid Pooling-Fast (SPPF) and Cross Stage Partial (CSP) structures leads to increased detection accuracy and enhanced multi-scale feature fusion network. Furthermore, a Detect Head is incorporated into the classification phase for more accurate position and class predictions. According to experimental findings, the optimized YOLOv7 algorithm performs quite well on the VisDrone2019 dataset in terms of detection accuracy. Compared with the original YOLOv7 algorithm, the optimized version shows a 0.18% increase in the Average Precision (AP), a reduction of 5.7 M model parameters, and a 1.12 Frames Per Second (FPS) improvement in the frame rate. With the above described enhancements in AP and parameter reduction, the precision of small target detection and the real-time detection speed are increased notably. In general, the optimized YOLOv7 algorithm offers superior accuracy and real-time capability, thus making it well-suited for small target detection tasks in real-time drone aerial photography.
In order to overcome the problems of large calculation error and low evaluation accuracy of traditional online education reform effect evaluation methods, this paper proposes a new online education reform effect evalu...
详细信息
In order to overcome the problems of large calculation error and low evaluation accuracy of traditional online education reform effect evaluation methods, this paper proposes a new online education reform effect evaluation method based on fuzzy weight. First, the key influencing factors of online teaching reform effect evaluation are determined for different subjects. Then, the cluster algorithm is used to determine the cluster centre of the evaluation index data, and the construction and quantification of the online teaching reform effect evaluation index system are completed. Finally, the fuzzy weight is determined, and the online education reform effect evaluation algorithm is constructed by using the judgment matrix and the training evaluation index data set. The experimental results show that this method can reduce the calculation error of evaluation weight and improve the evaluation accuracy, and the evaluation accuracy is always kept above 90%.
Ultra-high frequency (UHF) monitoring technique for partial discharge (PD) is an important technical means to evaluate the insulation deterioration state of GIS equipment. However, huge interference and aliasing of a ...
详细信息
ISBN:
(纸本)9781538664612
Ultra-high frequency (UHF) monitoring technique for partial discharge (PD) is an important technical means to evaluate the insulation deterioration state of GIS equipment. However, huge interference and aliasing of a multiple PD signals in field test effect the sensitivity and reliability of UHF detection. To identify the interference and aliasing of a multiple PD signals more accurately, meanwhile to cover the shortage of amplitude ratio clustering technique which can not identify signals' characteristics in frequency domain, the accuracy and adaptability of clustering algorithm should be further improved. To solve these problems, the separation and measurement technique based on dynamic frequency-selection and frequency division applied to multi discharge sources are proposed. UHF conditioner with high sensitivity and wide dynamic range are designed, whose work modes include wide-band amplification detection and narrowband frequency selection. Accordingly, the interactive dynamic clustering algorithm is proposed. The PD tests in real GIS with five kinds of PD defect and interference models are designed, the real PD tests indicate that the interactive dynamic clustering algorithm is more adaptable in the complex environment of the multiple PD and interference signals.
暂无评论