Accurate cellular network traffic prediction is a crucial task to access Internet services for various devices at any time.With the use of mobile devices,communication services generate numerous data for every moment....Accurate cellular network traffic prediction is a crucial task to access Internet services for various devices at any time.With the use of mobile devices,communication services generate numerous data for every moment.Given the increasing dense population of data,traffic learning and prediction are the main components to substantially enhance the effectiveness of demand-aware resource allocation.A novel deep learning technique called radial kernelized LSTM-based connectionist Tversky multilayer deep structure learning(RKLSTM-CTMDSL)model is introduced for traffic prediction with superior accuracy and minimal time consumption.The RKLSTM-CTMDSL model performs attribute selection and classification processes for cellular traffic prediction.In this model,the connectionist Tversky multilayer deep structure learning includes multiple layers for traffic prediction.A large volume of spatial-temporal data are considered as an input-to-input layer.Thereafter,input data are transmitted to hidden layer 1,where a radial kernelized long short-term memory architecture is designed for the relevant attribute selection using activation function results.After obtaining the relevant attributes,the selected attributes are given to the next layer.Tversky index function is used in this layer to compute similarities among the training and testing traffic patterns.Tversky similarity index outcomes are given to the output layer.Similarity value is used as basis to classify data as heavy network or normal traffic.Thus,cellular network traffic prediction is presented with minimal error rate using the RKLSTM-CTMDSL model.Comparative evaluation proved that the RKLSTM-CTMDSL model outperforms conventional methods.展开更多
This paper suggests an improved you only look once version 8n(YOLOv8n)algorithm for apple leaf disease detection,abbreviated as ALWB-YOLOv8n.The model is comprised of four essential components.Initially,arbitrary kern...This paper suggests an improved you only look once version 8n(YOLOv8n)algorithm for apple leaf disease detection,abbreviated as ALWB-YOLOv8n.The model is comprised of four essential components.Initially,arbitrary kernel convolution(AKConv)replaces the convolution module,which significantly decreases both the model’s parameter count and its overall size.Secondly,the large selective kernel network(LSKNet)attention mechanism is added in the Backbone,which can dynamically adjust the spatial sensory domain,and experiments have proved that this method is extremely advantageous for small target detection.Third,a weighted bi-directional feature pyramid network is introduced,which enables the model to achieve multi-scale feature fusion and is more concise and faster.Finally,wise intersection over union(WIoU)is used to replace complete intersection over union(CIoU)in YOLOv8,and the idea of focal loss is introduced,which effectively solves the detection problems in cases such as apple leaves occluding each other and blurred boundaries of diseased leaves.The improved algorithm exhibits superior performance compared to other common object detection algorithms.Compared with YOLOv8n,the improved algorithm achieves 2.3%improvement in precision,3.8%improvement in recall,and 2.5%and 2.7%improvement in mAP0.5 and mAP0.5:0.95,respectively.Compared with YOLOv8n,the improved model reduces the number of parameters and size of the model and realizes real-time monitoring with a frames per second(FPS)of 50.5.展开更多
In the realm of low-level vision tasks,such as image deraining and dehazing,restoring images distorted by adverse weather conditions remains a significant challenge.The emergence of abundant computational resources ha...In the realm of low-level vision tasks,such as image deraining and dehazing,restoring images distorted by adverse weather conditions remains a significant challenge.The emergence of abundant computational resources has driven the dominance of deep Convolutional Neural Networks(CNNs),supplanting traditional methods reliant on prior knowledge.However,the evolution of CNN architectures has tended towards increasing complexity,utilizing intricate structures to enhance performance,often at the expense of computational efficiency.In response,we propose the Selective Kernel Dense Residual M-shaped Network(SKDRMNet),a flexible solution adept at balancing computational efficiency with network accuracy.A key innovation is the incorporation of an M-shaped hierarchical structure,derived from the U-Net framework as M-Network(M-Net),within which the Selective Kernel Dense Residual Module(SDRM)is introduced to reinforce multi-scale semantic feature maps.Our methodology employs two sampling techniques-bilinear and pixel unshuffled and utilizes a multi-scale feature fusion approach to distil more robust spatial feature map information.During the reconstruction phase,feature maps of varying resolutions are seamlessly integrated,and the extracted features are effectively merged using the Selective Kernel Fusion Module(SKFM).Empirical results demonstrate the comprehensive superiority of SKDRMNet across both synthetic and real rain and haze datasets.展开更多
The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown adv...The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown advantage for the latter in different domains of application. However, some difficulties still deteriorate the performance of the support vector machines. The main one is related to the setting of the hyperparameters involved in their training. Techniques based on meta-heuristics have been employed to determine appropriate values for those hyperparameters. However, because of the high noneonvexity of this estimation problem, which makes the search for a good solution very hard, an approach based on Bayesian inference, called relevance vector machine, has been proposed more recently. The present paper aims at investigating the suitability of this new approach to the short-term load forecasting problem.展开更多
摘要Accurate cellular network traffic prediction is a crucial task to access Internet services for various devices at any time.With the use of mobile devices,communication services generate numerous data for every moment.Given the increasing dense population of data,traffic learning and prediction are the main components to substantially enhance the effectiveness of demand-aware resource allocation.A novel deep learning technique called radial kernelized LSTM-based connectionist Tversky multilayer deep structure learning(RKLSTM-CTMDSL)model is introduced for traffic prediction with superior accuracy and minimal time consumption.The RKLSTM-CTMDSL model performs attribute selection and classification processes for cellular traffic prediction.In this model,the connectionist Tversky multilayer deep structure learning includes multiple layers for traffic prediction.A large volume of spatial-temporal data are considered as an input-to-input layer.Thereafter,input data are transmitted to hidden layer 1,where a radial kernelized long short-term memory architecture is designed for the relevant attribute selection using activation function results.After obtaining the relevant attributes,the selected attributes are given to the next layer.Tversky index function is used in this layer to compute similarities among the training and testing traffic patterns.Tversky similarity index outcomes are given to the output layer.Similarity value is used as basis to classify data as heavy network or normal traffic.Thus,cellular network traffic prediction is presented with minimal error rate using the RKLSTM-CTMDSL model.Comparative evaluation proved that the RKLSTM-CTMDSL model outperforms conventional methods.
基金supported by the Intelligent Identification and Early Warning System for Pests and Diseases in Small-seeded Rapeseed(No.24ZYCGSN01360)the Intelligent Management Platform for Vegetable Greenhouses Project(No.YH003001)+1 种基金the Intelligent Agricultural Breeding System Project(No.YH003002)the Research and Application of AIoT Based Big Data System for Apple Tree Pest and Disease Detection(No.2024WA013)。
摘要This paper suggests an improved you only look once version 8n(YOLOv8n)algorithm for apple leaf disease detection,abbreviated as ALWB-YOLOv8n.The model is comprised of four essential components.Initially,arbitrary kernel convolution(AKConv)replaces the convolution module,which significantly decreases both the model’s parameter count and its overall size.Secondly,the large selective kernel network(LSKNet)attention mechanism is added in the Backbone,which can dynamically adjust the spatial sensory domain,and experiments have proved that this method is extremely advantageous for small target detection.Third,a weighted bi-directional feature pyramid network is introduced,which enables the model to achieve multi-scale feature fusion and is more concise and faster.Finally,wise intersection over union(WIoU)is used to replace complete intersection over union(CIoU)in YOLOv8,and the idea of focal loss is introduced,which effectively solves the detection problems in cases such as apple leaves occluding each other and blurred boundaries of diseased leaves.The improved algorithm exhibits superior performance compared to other common object detection algorithms.Compared with YOLOv8n,the improved algorithm achieves 2.3%improvement in precision,3.8%improvement in recall,and 2.5%and 2.7%improvement in mAP0.5 and mAP0.5:0.95,respectively.Compared with YOLOv8n,the improved model reduces the number of parameters and size of the model and realizes real-time monitoring with a frames per second(FPS)of 50.5.
摘要In the realm of low-level vision tasks,such as image deraining and dehazing,restoring images distorted by adverse weather conditions remains a significant challenge.The emergence of abundant computational resources has driven the dominance of deep Convolutional Neural Networks(CNNs),supplanting traditional methods reliant on prior knowledge.However,the evolution of CNN architectures has tended towards increasing complexity,utilizing intricate structures to enhance performance,often at the expense of computational efficiency.In response,we propose the Selective Kernel Dense Residual M-shaped Network(SKDRMNet),a flexible solution adept at balancing computational efficiency with network accuracy.A key innovation is the incorporation of an M-shaped hierarchical structure,derived from the U-Net framework as M-Network(M-Net),within which the Selective Kernel Dense Residual Module(SDRM)is introduced to reinforce multi-scale semantic feature maps.Our methodology employs two sampling techniques-bilinear and pixel unshuffled and utilizes a multi-scale feature fusion approach to distil more robust spatial feature map information.During the reconstruction phase,feature maps of varying resolutions are seamlessly integrated,and the extracted features are effectively merged using the Selective Kernel Fusion Module(SKFM).Empirical results demonstrate the comprehensive superiority of SKDRMNet across both synthetic and real rain and haze datasets.
摘要针对盾构姿态预测模型存在易过拟合、预测精度低的问题,提出一种基于融合注意力机制的盾构姿态组合预测模型。为强化有效特征的提取,抑制冗余特征信息的表达,引入基于选择性卷积核网络(selective kernel networks,SKNet)的特征注意力机制提取网络,消除固定尺寸卷积核带来的限制,并自适应形成带有注意力的特征映射。为更好地捕捉长期信息和特征模式,通过双向长短期记忆网络(bidirectional long short-term memory,BiLSTM)、门控循环单元(gated recurrent unit, GRU)得到2组隐含输出结果,再利用多头注意力机制,捕获组合模型输出的隐含特征与模型输出的盾构姿态之间的依赖关系,进一步提高预测模型对重要隐含特征的信息抓捕能力;同时,为解决地质勘察钻孔数据连续性差、精确性不足,难以应用于机器学习模型训练的问题,将基于人工先验知识的二级特征引入模型特征输入,提升模型对地层信息的感知能力。最后,基于广州地铁12号线官洲站—大学城北站盾构实例,对模型不同参数结构下的性能进行研究,并进行对比试验验证模型性能,采用可解释性试验评估特征对预测结果的影响。试验结果表明,相比其他预测模型,所提出的预测模型优越性更好,预测精度更高,解决了长时间序列高特征维度数据在传统模型下易过拟合且预测精度较低的问题。
摘要The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown advantage for the latter in different domains of application. However, some difficulties still deteriorate the performance of the support vector machines. The main one is related to the setting of the hyperparameters involved in their training. Techniques based on meta-heuristics have been employed to determine appropriate values for those hyperparameters. However, because of the high noneonvexity of this estimation problem, which makes the search for a good solution very hard, an approach based on Bayesian inference, called relevance vector machine, has been proposed more recently. The present paper aims at investigating the suitability of this new approach to the short-term load forecasting problem.