The microstructure of palygorskite from Longwang Mountain of Xuyu County, Jiangsu Province, was studied by energy dispersive X-ray analysis （EDX）, selected-area electron diffraction （SAED） and high-resolution tran...The microstructure of palygorskite from Longwang Mountain of Xuyu County, Jiangsu Province, was studied by energy dispersive X-ray analysis （EDX）, selected-area electron diffraction （SAED） and high-resolution transmission electron microscopy （HRTEM）. The average composition of the palygorskite studied is （Si7.38A10.62） （A10.96Fe^3＋ 0.62Mg2.86 0.56）Ca0.03K0.06O20（OH）2（OH2）4, which is rich in Mg. Several SAED patterns from a single crystal of palygorskite were obtained with different zone axes. The polymorphs （monoclinic and orthorhombic） are unequivocally distinguished by distant interplanar angles, even though they possess similar sets of d-values. High-resolution images of three principal zones （[010], [100] and [110]） were obtained. The lattice fringes on HRTEM images along [010] have spacings of 0.319 nm. These fringes are interpreted as periodic alterations of two tetrahedral （T） sheets and one octahedral （O） sheet （-TT-O-TT-O-）. We have directly observed trioctahedral and dioctahedral individual palygorskite particles along [100]. They are all presented as dark lines along [001], but the width of dark lines corresponding to trioctahedral crystals （0.913 nm） is twice that of the dioctahedral ones （0.456 nm）. This is because the trans.sites are occupied by cations in trioctahedral palygorskite. The width of dark lines along [110] is 1.024 nm, a bit thinner than the theoretical spacing （1.044 nm）. This is because water molecules quickly leave the structure upon the irradiation by the electron beam.展开更多
针对农业场景中草莓因枝叶遮挡、簇生分布及果面反光导致稀疏观测下难以三维重建的问题,本研究基于SA3D(Segment Anything in 3D)框架,在实验室条件下验证了自动化构建高保真草莓三维模型库的可行性。该方法融合DVGO与SAM,利用DVGO从14...针对农业场景中草莓因枝叶遮挡、簇生分布及果面反光导致稀疏观测下难以三维重建的问题,本研究基于SA3D(Segment Anything in 3D)框架,在实验室条件下验证了自动化构建高保真草莓三维模型库的可行性。该方法融合DVGO与SAM,利用DVGO从144张多视角图像中重建保留种子、果蒂等亚毫米细节的三维几何;结合SAM仅需1~2个提示点生成2D掩码,通过Mask逆渲染与跨视角自提示机制实现无标注的三维果实分割。为提升实用性,开发了基于Dash的交互式系统,集成图像上传、位姿估计、重建与分割全流程,支持非专业用户高效建模。实验表明,该方法平均PSNR达20.83 dB(较NeRF提升1.12 dB),IoU均值为0.803,显著增强遮挡与反光区域的重建鲁棒性。所构建的标准化点云库可为表型测量提供基准,并作为几何与语义先验支撑田间稀疏视角重建,服务于智能采摘系统的视觉感知。展开更多
With the increasing growth of online news,fake electronic news detection has become one of the most important paradigms of modern research.Traditional electronic news detection techniques are generally based on contex...With the increasing growth of online news,fake electronic news detection has become one of the most important paradigms of modern research.Traditional electronic news detection techniques are generally based on contextual understanding,sequential dependencies,and/or data imbalance.This makes distinction between genuine and fabricated news a challenging task.To address this problem,we propose a novel hybrid architecture,T5-SA-LSTM,which synergistically integrates the T5 Transformer for semantically rich contextual embedding with the Self-Attentionenhanced(SA)Long Short-Term Memory(LSTM).The LSTM is trained using the Adam optimizer,which provides faster and more stable convergence compared to the Stochastic Gradient Descend(SGD)and Root Mean Square Propagation(RMSProp).The WELFake and FakeNewsPrediction datasets are used,which consist of labeled news articles having fake and real news samples.Tokenization and Synthetic Minority Over-sampling Technique(SMOTE)methods are used for data preprocessing to ensure linguistic normalization and class imbalance.The incorporation of the Self-Attention(SA)mechanism enables the model to highlight critical words and phrases,thereby enhancing predictive accuracy.The proposed model is evaluated using accuracy,precision,recall(sensitivity),and F1-score as performance metrics.The model achieved 99%accuracy on the WELFake dataset and 96.5%accuracy on the FakeNewsPrediction dataset.It outperformed the competitive schemes such as T5-SA-LSTM(RMSProp),T5-SA-LSTM(SGD)and some other models.展开更多
文摘The microstructure of palygorskite from Longwang Mountain of Xuyu County, Jiangsu Province, was studied by energy dispersive X-ray analysis （EDX）, selected-area electron diffraction （SAED） and high-resolution transmission electron microscopy （HRTEM）. The average composition of the palygorskite studied is （Si7.38A10.62） （A10.96Fe^3＋ 0.62Mg2.86 0.56）Ca0.03K0.06O20（OH）2（OH2）4, which is rich in Mg. Several SAED patterns from a single crystal of palygorskite were obtained with different zone axes. The polymorphs （monoclinic and orthorhombic） are unequivocally distinguished by distant interplanar angles, even though they possess similar sets of d-values. High-resolution images of three principal zones （[010], [100] and [110]） were obtained. The lattice fringes on HRTEM images along [010] have spacings of 0.319 nm. These fringes are interpreted as periodic alterations of two tetrahedral （T） sheets and one octahedral （O） sheet （-TT-O-TT-O-）. We have directly observed trioctahedral and dioctahedral individual palygorskite particles along [100]. They are all presented as dark lines along [001], but the width of dark lines corresponding to trioctahedral crystals （0.913 nm） is twice that of the dioctahedral ones （0.456 nm）. This is because the trans.sites are occupied by cations in trioctahedral palygorskite. The width of dark lines along [110] is 1.024 nm, a bit thinner than the theoretical spacing （1.044 nm）. This is because water molecules quickly leave the structure upon the irradiation by the electron beam.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R195)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘With the increasing growth of online news,fake electronic news detection has become one of the most important paradigms of modern research.Traditional electronic news detection techniques are generally based on contextual understanding,sequential dependencies,and/or data imbalance.This makes distinction between genuine and fabricated news a challenging task.To address this problem,we propose a novel hybrid architecture,T5-SA-LSTM,which synergistically integrates the T5 Transformer for semantically rich contextual embedding with the Self-Attentionenhanced(SA)Long Short-Term Memory(LSTM).The LSTM is trained using the Adam optimizer,which provides faster and more stable convergence compared to the Stochastic Gradient Descend(SGD)and Root Mean Square Propagation(RMSProp).The WELFake and FakeNewsPrediction datasets are used,which consist of labeled news articles having fake and real news samples.Tokenization and Synthetic Minority Over-sampling Technique(SMOTE)methods are used for data preprocessing to ensure linguistic normalization and class imbalance.The incorporation of the Self-Attention(SA)mechanism enables the model to highlight critical words and phrases,thereby enhancing predictive accuracy.The proposed model is evaluated using accuracy,precision,recall(sensitivity),and F1-score as performance metrics.The model achieved 99%accuracy on the WELFake dataset and 96.5%accuracy on the FakeNewsPrediction dataset.It outperformed the competitive schemes such as T5-SA-LSTM(RMSProp),T5-SA-LSTM(SGD)and some other models.
