The conductive polymer poly(3,4-thylenedioxythiophene):poly(styrenesulfonate)(PEDOT:PSS)exhibits po-tential in the development of flexible devices due to its unique conjugated structure and water-solubility characteri...The conductive polymer poly(3,4-thylenedioxythiophene):poly(styrenesulfonate)(PEDOT:PSS)exhibits po-tential in the development of flexible devices due to its unique conjugated structure and water-solubility characteristics.To address the incompressibility of the original PEDOT:PSS aerogel without compromis-ing its high conductivity,a stable interpenetrating polymer network(IPN)was self-assembled by guiding the molecular motion within PEDOT:PSS and introducing multi-walled carbon nanotubes(MWCNTs).By combining critical surface removal,directional freeze-drying,and polydimethylsiloxane(PDMS)reinforce-ment processes,a hydrophobic PDMS@MWCNTs/PP aerogel with a highly oriented porous structure and high strength was prepared.Under the synergistic effect of MWCNTs/PEDOT:PSS electroactive scaffold,the composite aerogel exhibited a high sensitivity of up to 16.603 kPa^(-1) at 0-2 kPa,a fast response time of 74 ms,and excellent repeatability.Moreover,the sensor possessed hydrophobicity with a good water contact angle of 137°The sensor could serve as a wearable electronic monitoring device to achieve ac-curate and sensitive detection of human motion including large-scale human activities and tiny muscle movements.Therefore,our findings provide a new direction to fabricate high-performance piezoresistive sensors based on three-dimensional(3D)conductive polymer active scaffolds,demonstrating their great potential for flexible electronics,human-computer interaction,and a wide range of applications under special working conditions.展开更多
[目的/意义]针对当前玫瑰鲜切花分级仍依赖人工进行简单分级,造成效率低、准确率低等问题,提出一种新的模型Flower-YOLOv8s来实现玫瑰鲜切花的分级检测。[方法]以单一背景下单支玫瑰花的花头作为检测目标,将鲜切花分为A、B、C、D四个等...[目的/意义]针对当前玫瑰鲜切花分级仍依赖人工进行简单分级,造成效率低、准确率低等问题,提出一种新的模型Flower-YOLOv8s来实现玫瑰鲜切花的分级检测。[方法]以单一背景下单支玫瑰花的花头作为检测目标,将鲜切花分为A、B、C、D四个等级,对YOLOv8s(You Only Look Once version 8 small)模型进行了优化改进。首先,构建了一个全新的玫瑰鲜切花分级检测数据集。其次,在YOLOv8s的骨干网络分别添加CBAM(Con⁃volutional Block Attention Module)和SAM(Spatial Attion Module)两个注意力机制模块进行对比实验;选择SAM模块并对其进一步优化,针对模型轻量化需求,再结合深度可分离卷积模块一起添加到C2f结构中,形成Flower-YOLOv8s模型。[结果和讨论]从实验结果来看YOLOv8s添加SAM的模型具有更高的检测精度,mAP@0.5达到86.4%。Flower-YOLOv8s相较于基线模型精确率提高了2.1%,达到97.4%,平均精度均值(mAP)提高了0.7%,同时降低了模型参数和计算量,分别降低2.26 M和4.45 MB;最后使用相同的数据集和预处理方法与Fast-RCNN、Faster-RCNN、SSD、YOLOv3、YOLOv5s和YOLOv8s进行对比实验,证明所提出的实验方法综合强于其他经典YOLO模型。[结论]提出的基于改进YOLOv8s的玫瑰鲜切花分级方法研究能有效提升玫瑰鲜切花分级检测的精准度,为玫瑰鲜切花分级检测技术提供一定的参考价值。展开更多
Considering that growing hierarchical self-organizing map(GHSOM) ignores the influence of individual component in sample vector analysis, and its accurate rate in detecting unknown network attacks is relatively lower,...Considering that growing hierarchical self-organizing map(GHSOM) ignores the influence of individual component in sample vector analysis, and its accurate rate in detecting unknown network attacks is relatively lower, an improved GHSOM method combined with mutual information is proposed. After theoretical analysis, experiments are conducted to illustrate the effectiveness of the proposed method by accurately clustering the input data. Based on different clusters, the complex relationship within the data can be revealed effectively.展开更多
基金supported by the Xi’an Science and Technology Plan Project(Nos.GXYD14.27 and GX2338)the Key Scientific Research Program of Shaanxi Provincial Depart-ment of Education(Nos.22JY046 and 21JY032)+1 种基金the Opening Project of Shanxi Key Laboratory of Advanced Manufacturing Tech-nology of North University of China(No.XJZZ202104)the General Project of Natural Science Basic Research Program of Shaanxi Provincial Department of Science and Technology(No.2023-JC-YB-424)。
文摘The conductive polymer poly(3,4-thylenedioxythiophene):poly(styrenesulfonate)(PEDOT:PSS)exhibits po-tential in the development of flexible devices due to its unique conjugated structure and water-solubility characteristics.To address the incompressibility of the original PEDOT:PSS aerogel without compromis-ing its high conductivity,a stable interpenetrating polymer network(IPN)was self-assembled by guiding the molecular motion within PEDOT:PSS and introducing multi-walled carbon nanotubes(MWCNTs).By combining critical surface removal,directional freeze-drying,and polydimethylsiloxane(PDMS)reinforce-ment processes,a hydrophobic PDMS@MWCNTs/PP aerogel with a highly oriented porous structure and high strength was prepared.Under the synergistic effect of MWCNTs/PEDOT:PSS electroactive scaffold,the composite aerogel exhibited a high sensitivity of up to 16.603 kPa^(-1) at 0-2 kPa,a fast response time of 74 ms,and excellent repeatability.Moreover,the sensor possessed hydrophobicity with a good water contact angle of 137°The sensor could serve as a wearable electronic monitoring device to achieve ac-curate and sensitive detection of human motion including large-scale human activities and tiny muscle movements.Therefore,our findings provide a new direction to fabricate high-performance piezoresistive sensors based on three-dimensional(3D)conductive polymer active scaffolds,demonstrating their great potential for flexible electronics,human-computer interaction,and a wide range of applications under special working conditions.
文摘[目的/意义]针对当前玫瑰鲜切花分级仍依赖人工进行简单分级,造成效率低、准确率低等问题,提出一种新的模型Flower-YOLOv8s来实现玫瑰鲜切花的分级检测。[方法]以单一背景下单支玫瑰花的花头作为检测目标,将鲜切花分为A、B、C、D四个等级,对YOLOv8s(You Only Look Once version 8 small)模型进行了优化改进。首先,构建了一个全新的玫瑰鲜切花分级检测数据集。其次,在YOLOv8s的骨干网络分别添加CBAM(Con⁃volutional Block Attention Module)和SAM(Spatial Attion Module)两个注意力机制模块进行对比实验;选择SAM模块并对其进一步优化,针对模型轻量化需求,再结合深度可分离卷积模块一起添加到C2f结构中,形成Flower-YOLOv8s模型。[结果和讨论]从实验结果来看YOLOv8s添加SAM的模型具有更高的检测精度,mAP@0.5达到86.4%。Flower-YOLOv8s相较于基线模型精确率提高了2.1%,达到97.4%,平均精度均值(mAP)提高了0.7%,同时降低了模型参数和计算量,分别降低2.26 M和4.45 MB;最后使用相同的数据集和预处理方法与Fast-RCNN、Faster-RCNN、SSD、YOLOv3、YOLOv5s和YOLOv8s进行对比实验,证明所提出的实验方法综合强于其他经典YOLO模型。[结论]提出的基于改进YOLOv8s的玫瑰鲜切花分级方法研究能有效提升玫瑰鲜切花分级检测的精准度,为玫瑰鲜切花分级检测技术提供一定的参考价值。
基金Supported by the Natural Science Foundation of Tianjin(No.15JCQNJC00200)
文摘Considering that growing hierarchical self-organizing map(GHSOM) ignores the influence of individual component in sample vector analysis, and its accurate rate in detecting unknown network attacks is relatively lower, an improved GHSOM method combined with mutual information is proposed. After theoretical analysis, experiments are conducted to illustrate the effectiveness of the proposed method by accurately clustering the input data. Based on different clusters, the complex relationship within the data can be revealed effectively.
