Forecasting energy demand is essential for optimizing energy generation and effectively predicting power system needs.Recently,many researchers have developed various models on tabular datasets to enhance the effectiv...Forecasting energy demand is essential for optimizing energy generation and effectively predicting power system needs.Recently,many researchers have developed various models on tabular datasets to enhance the effectiveness of demand prediction,including neural networks,machine learning,deep learning,and advanced architectures such as CNN and LSTM.However,research on the CNN models has struggled to provide reliable outcomes due to insufficient dataset sizes,repeated investigations,and inappropriate baseline selection.To address these challenges,we propose a Tabular data-based Lightweight Convolutional Neural Network(TLCNN)model for predicting energy demand.It frames the problem as a regression task that effectively captures complex data trends for accurate forecasting.The BanE-16 dataset is preprocessed using normalization techniques for categorical and numerical data before training the model.The proposed approach dynamically selects relevant features through a two-dimensional convolutional structure that improves adaptability.The model’s performance is evaluated using MSE,MAE,and Accuracy metrics.Experimental results show that TLCNN achieves a 10.89%lower MSE than traditional ML algorithms,demonstrating superior predictive capability.Additionally,TLCNN’s lightweight structure enhances generalization while reducing computational costs,making it suitable for real-world energy forecasting tasks.This study contributes to energy informatics by introducing an optimized deep-learning framework that improves demand prediction by ensuring robustness and adaptability for tabular data.展开更多
The map folding method for the conversion between Boolean expression and COC expansions is analyzed. Based on it, the tabular techniques are proposed for the conversion between Boolean expression and COC expansion and...The map folding method for the conversion between Boolean expression and COC expansions is analyzed. Based on it, the tabular techniques are proposed for the conversion between Boolean expression and COC expansion and for the derivation of GOC expansions with fixed polarities. The Fast Tabular Technique (FTT) for the conversion from the Boolean expression to the GOC expansion with the required polarity is also proposed. The simulative result shows this FTT is faster than others in references because of its inherent parallelism.展开更多
Hydration mechanism of tabular alumina carbon composites reinforced by Al4C3 in situ reaction with Mg and Al was researched in water steam using super automatic thermostatic water bath from 25 ℃ to 85 ℃. It is shown...Hydration mechanism of tabular alumina carbon composites reinforced by Al4C3 in situ reaction with Mg and Al was researched in water steam using super automatic thermostatic water bath from 25 ℃ to 85 ℃. It is shown that hydration mechanism of the composites is chemical reaction control at 44.3 ℃-84 ℃ in H2O（g）. The hydration was controlled by diffusion from 24.7 ℃ to 33 ℃. The ratio of added Mg/Al influences the HMOR of the composites.The mechanism of HMOR of the composites with different ratios of Mg/Al can be discovered by means of SEM analysis. The active Mg/Al powder and flake graphite inside give the composites outstanding hot strength resulting from the interlocking structure of Al4C3 crystals at high temperature. Besides, the matrix changes into the Al4C3 with high refractoriness. The method of preventing the hydration of tabular alumina carbon composites reinforced by Al4C3 in situ reaction was immersed in the wax at suitable temperature or storing them below 33 ℃ in a dry place or storing them with paraffin-coating.展开更多
The corundum - spinel castables were prepared by six kinds of tabular corundum, as aggregates, respective- ly, and their linear change rate on heating, apparent porosity, bulk density, cold modulus of rupture, coht cr...The corundum - spinel castables were prepared by six kinds of tabular corundum, as aggregates, respective- ly, and their linear change rate on heating, apparent porosity, bulk density, cold modulus of rupture, coht crushing strength, hot modulus of rupture and thermal shock resistance were compared and studied. The results show that： 1） the six tabular corundum materials have similar main chemical composition but their physical properties vary for the different technical procedures which result in different properties of castables ; 2 ） the optimal properties of corundum - spinel castables corre- spotut to different tabular corundum types, so the corundum type shall be selected according to the application of the castables.展开更多
Saraikistan (South Punjab and surrounding) area of Pakistan is located in the central Pakistan. This area represents Triassic-Jurassic to Recent sedimentary marine and terrestrial strata. Most of the Mesozoic and Earl...Saraikistan (South Punjab and surrounding) area of Pakistan is located in the central Pakistan. This area represents Triassic-Jurassic to Recent sedimentary marine and terrestrial strata. Most of the Mesozoic and Early Cenozoic are represented by marine strata with rare terrestrial deposits, while the Late Cenozoic is represented by continental fluvial deposits. This area hosts significant mineral deposits and their development can play a significant role in the development of Saraikistan region and ultimately for Pakistan. The data of recently discovered biotas from Cambrian to Miocene age are tabulated for quick view. Mesozoic biotas show a prominent paleobiogeographic link with Gondwana and Cenozoic show Eurasian. Phylogeny and hypodigm of Poripuchian titanosaurs from India and Pakistan are hinted at here.展开更多
In recent years much attention has been devoted to AgCl emulsion owing to its se-rial advantages and inimitable potential.But in the research of this emulsion a thorny problem remains unsolved till now,which is the im...In recent years much attention has been devoted to AgCl emulsion owing to its se-rial advantages and inimitable potential.But in the research of this emulsion a thorny problem remains unsolved till now,which is the improvement in sensitivity is always accompanied with high fog density.In this work 5 nm Ag_(2)S particles were prepared and used as novel sensitizers in AgCl cubic and{100}tabular microcrystal emulsions.The novel sensitizer shows an effective sensitizing ability for silver chloride emulsion,and it is superior to the traditional Na_(2)S_(2)O_(3) sensi-tizer because by using it comparatively high sensitivity can be obtained with lower fog density.So the above sensitizing problem is going to be effectively solved.To discover the evolution mechanism of the sensitizer clusters and explain their excellent sensitizing properties,diffuse reflectance spectroscopy(DRS)was used as a probe on the AgCl microcrystal surface.展开更多
The effects of tabular stratified CO_(2)/O_(2)jet in cross flow on thermoacoustic instability and NO_(x)emission were experimentally studied.To explore the dependence of injection positions on flame stability,two fact...The effects of tabular stratified CO_(2)/O_(2)jet in cross flow on thermoacoustic instability and NO_(x)emission were experimentally studied.To explore the dependence of injection positions on flame stability,two factors were taken:the injection height and the injection direction of CO_(2)/O_(2)gas.Results show that the injection positions seriously affect the control effectiveness.The optimum acoustic amplitude-damped ratio of thermoacoustic instability can reach 76.61%with the first layer of horizontal direction.The sound pressure amplitude declined from 56 Pa to 13.1 Pa.The concentration-damped ratio of NO_(x)emission can achieve 66.67%with the first layer of vertical direction.The concentration of NO_(x)emission declined from 50.4 mg/m^(3)to 16.8mg/m^(3)as the jet in cross flow rate increased.Higher oxygen ratio of stratified CO_(2)/O_(2)jets can produce lower NO_(x)emission but higher combustion instability.The descending gradient of NO_(x)emissions is different among different injection positions.Frequency shifting of the sound pressure and flame CH*chemiluminescence emerged.The oscillation frequency declined as the flow rate of CO_(2)/O_(2)jets increased.The unsteady long and compact flame was dispersed after CO_(2)/O_(2)injection.The macrostructure of flame was characterized as flatter and short under jet in cross flow.The variation curves of the flame length and top view area are similar to the shape of half saddle lines.This research proved the optimal control of thermoacoustic instability and NO_(x)emissions with a passive method,which could be conducive to the realization of clean and secure combustion in industrial lean premixed combustors.展开更多
人工智能在信用风险评估中能有效识别风险并提升决策效率,然而,现有信用风险数据普遍存在类别不平衡问题,导致模型在预测时偏向多数类,影响评估的准确性和可靠性。针对数据不平衡问题,提出一种融合变分自编码器(VAE)和条件表格生成对抗...人工智能在信用风险评估中能有效识别风险并提升决策效率,然而,现有信用风险数据普遍存在类别不平衡问题,导致模型在预测时偏向多数类,影响评估的准确性和可靠性。针对数据不平衡问题,提出一种融合变分自编码器(VAE)和条件表格生成对抗网络(CTGAN)的混合生成模型(VCTGAN),用于合成高质量平衡数据集。通过VAE中的隐变量学习真实数据的关键特征和潜在分布,生成结构化隐变量作为原始CTGAN的输入;在数据生成器中引入自注意力机制用于更好地捕捉不平衡数据的突出特征;在判别器中加入对比损失模块来增强生成数据的类别间差异,达到提高生成数据质量的目的。通过在Taiwan Credit和Give Me Some Credit两个基准数据集上的系统实验验证,分别取得了89.91%和96.89%的最佳分类准确率,结果表明这种改进方法在处理信用数据不平衡方面明显优于传统方法。消融实验进一步验证了各组件对性能的贡献,证实了所提方法的合理性和有效性。它不仅生成高质量的平衡数据集,而且提高模型识别少数类别的能力,为解决金融领域的数据不平衡问题提供了新的技术方案。展开更多
Exploratory data analysis plays a major role in obtaining insights from data.Over the last two decades,researchers have proposed several visual data exploration tools that can assist with each step of the analysis pro...Exploratory data analysis plays a major role in obtaining insights from data.Over the last two decades,researchers have proposed several visual data exploration tools that can assist with each step of the analysis process.Nevertheless,in recent years,data analysis requirements have changed significantly.With constantly increasing size and types of data to be analyzed,scalability and analysis duration are now among the primary concerns of researchers.Moreover,in order to minimize the analysis cost,businesses are in need of data analysis tools that can be used with limited analytical knowledge.To address these challenges,traditional data exploration tools have evolved within the last few years.In this paper,with an in-depth analysis of an industrial tabular dataset,we identify a set of additional exploratory requirements for large datasets.Later,we present a comprehensive survey of the recent advancements in the emerging field of exploratory data analysis.We investigate 50 academic and non-academic visual data exploration tools with respect to their utility in the six fundamental steps of the exploratory data analysis process.We also examine the extent to which these modern data exploration tools fulfill the additional requirements for analyzing large datasets.Finally,we identify and present a set of research opportunities in the field of visual exploratory data analysis.展开更多
为解决网络货运平台价格预测不准确导致的成交率下降问题,提出基于Shingling检索的表格先验数据拟合网络(tabular prior-data fitted network,TabPFN)的局部上下文学习(local context learning with TabPFN based on shingling retrieva...为解决网络货运平台价格预测不准确导致的成交率下降问题,提出基于Shingling检索的表格先验数据拟合网络(tabular prior-data fitted network,TabPFN)的局部上下文学习(local context learning with TabPFN based on shingling retrieval,ShinglingPFN)模型。首先,该模型运用w-Shingling检索算法,从历史订单数据中匹配出与预测订单最相似的订单,构建局部关联的上下文数据。然后,加载并初始化预训练的TabPFN模型实例,将筛选出的订单数据输入模型,让TabPFN基于这些上下文信息学习货运特征与运费的关联模式。最后,输出该货运样本的运费预测结果。结果表明,ShinglingPFN模型相比随机森林(random forest,RF)模型减少了30.98%的平均绝对误差(mean absolute error,MAE)。通过全局敏感性分析,进一步增强了模型的可解释性。ShinglingPFN模型可为平台优化定价策略提供决策支撑。展开更多
文摘Forecasting energy demand is essential for optimizing energy generation and effectively predicting power system needs.Recently,many researchers have developed various models on tabular datasets to enhance the effectiveness of demand prediction,including neural networks,machine learning,deep learning,and advanced architectures such as CNN and LSTM.However,research on the CNN models has struggled to provide reliable outcomes due to insufficient dataset sizes,repeated investigations,and inappropriate baseline selection.To address these challenges,we propose a Tabular data-based Lightweight Convolutional Neural Network(TLCNN)model for predicting energy demand.It frames the problem as a regression task that effectively captures complex data trends for accurate forecasting.The BanE-16 dataset is preprocessed using normalization techniques for categorical and numerical data before training the model.The proposed approach dynamically selects relevant features through a two-dimensional convolutional structure that improves adaptability.The model’s performance is evaluated using MSE,MAE,and Accuracy metrics.Experimental results show that TLCNN achieves a 10.89%lower MSE than traditional ML algorithms,demonstrating superior predictive capability.Additionally,TLCNN’s lightweight structure enhances generalization while reducing computational costs,making it suitable for real-world energy forecasting tasks.This study contributes to energy informatics by introducing an optimized deep-learning framework that improves demand prediction by ensuring robustness and adaptability for tabular data.
基金Supported by the National Natural Science Foundation of China (No.60273093)the Natural Science Foundation of Zheiinag Province (No.Y104135)
文摘The map folding method for the conversion between Boolean expression and COC expansions is analyzed. Based on it, the tabular techniques are proposed for the conversion between Boolean expression and COC expansion and for the derivation of GOC expansions with fixed polarities. The Fast Tabular Technique (FTT) for the conversion from the Boolean expression to the GOC expansion with the required polarity is also proposed. The simulative result shows this FTT is faster than others in references because of its inherent parallelism.
基金Funded by the National Torch Plan of China(No.2005EB031110)the Key Scientific and Technical Innovation Project of Xi’an University of Architecture and Technology(No.zx 0402)
文摘Hydration mechanism of tabular alumina carbon composites reinforced by Al4C3 in situ reaction with Mg and Al was researched in water steam using super automatic thermostatic water bath from 25 ℃ to 85 ℃. It is shown that hydration mechanism of the composites is chemical reaction control at 44.3 ℃-84 ℃ in H2O（g）. The hydration was controlled by diffusion from 24.7 ℃ to 33 ℃. The ratio of added Mg/Al influences the HMOR of the composites.The mechanism of HMOR of the composites with different ratios of Mg/Al can be discovered by means of SEM analysis. The active Mg/Al powder and flake graphite inside give the composites outstanding hot strength resulting from the interlocking structure of Al4C3 crystals at high temperature. Besides, the matrix changes into the Al4C3 with high refractoriness. The method of preventing the hydration of tabular alumina carbon composites reinforced by Al4C3 in situ reaction was immersed in the wax at suitable temperature or storing them below 33 ℃ in a dry place or storing them with paraffin-coating.
文摘The corundum - spinel castables were prepared by six kinds of tabular corundum, as aggregates, respective- ly, and their linear change rate on heating, apparent porosity, bulk density, cold modulus of rupture, coht crushing strength, hot modulus of rupture and thermal shock resistance were compared and studied. The results show that： 1） the six tabular corundum materials have similar main chemical composition but their physical properties vary for the different technical procedures which result in different properties of castables ; 2 ） the optimal properties of corundum - spinel castables corre- spotut to different tabular corundum types, so the corundum type shall be selected according to the application of the castables.
文摘Saraikistan (South Punjab and surrounding) area of Pakistan is located in the central Pakistan. This area represents Triassic-Jurassic to Recent sedimentary marine and terrestrial strata. Most of the Mesozoic and Early Cenozoic are represented by marine strata with rare terrestrial deposits, while the Late Cenozoic is represented by continental fluvial deposits. This area hosts significant mineral deposits and their development can play a significant role in the development of Saraikistan region and ultimately for Pakistan. The data of recently discovered biotas from Cambrian to Miocene age are tabulated for quick view. Mesozoic biotas show a prominent paleobiogeographic link with Gondwana and Cenozoic show Eurasian. Phylogeny and hypodigm of Poripuchian titanosaurs from India and Pakistan are hinted at here.
文摘In recent years much attention has been devoted to AgCl emulsion owing to its se-rial advantages and inimitable potential.But in the research of this emulsion a thorny problem remains unsolved till now,which is the improvement in sensitivity is always accompanied with high fog density.In this work 5 nm Ag_(2)S particles were prepared and used as novel sensitizers in AgCl cubic and{100}tabular microcrystal emulsions.The novel sensitizer shows an effective sensitizing ability for silver chloride emulsion,and it is superior to the traditional Na_(2)S_(2)O_(3) sensi-tizer because by using it comparatively high sensitivity can be obtained with lower fog density.So the above sensitizing problem is going to be effectively solved.To discover the evolution mechanism of the sensitizer clusters and explain their excellent sensitizing properties,diffuse reflectance spectroscopy(DRS)was used as a probe on the AgCl microcrystal surface.
基金supported by The National Science Fund for Distinguished Young Scholars(51825605)。
文摘The effects of tabular stratified CO_(2)/O_(2)jet in cross flow on thermoacoustic instability and NO_(x)emission were experimentally studied.To explore the dependence of injection positions on flame stability,two factors were taken:the injection height and the injection direction of CO_(2)/O_(2)gas.Results show that the injection positions seriously affect the control effectiveness.The optimum acoustic amplitude-damped ratio of thermoacoustic instability can reach 76.61%with the first layer of horizontal direction.The sound pressure amplitude declined from 56 Pa to 13.1 Pa.The concentration-damped ratio of NO_(x)emission can achieve 66.67%with the first layer of vertical direction.The concentration of NO_(x)emission declined from 50.4 mg/m^(3)to 16.8mg/m^(3)as the jet in cross flow rate increased.Higher oxygen ratio of stratified CO_(2)/O_(2)jets can produce lower NO_(x)emission but higher combustion instability.The descending gradient of NO_(x)emissions is different among different injection positions.Frequency shifting of the sound pressure and flame CH*chemiluminescence emerged.The oscillation frequency declined as the flow rate of CO_(2)/O_(2)jets increased.The unsteady long and compact flame was dispersed after CO_(2)/O_(2)injection.The macrostructure of flame was characterized as flatter and short under jet in cross flow.The variation curves of the flame length and top view area are similar to the shape of half saddle lines.This research proved the optimal control of thermoacoustic instability and NO_(x)emissions with a passive method,which could be conducive to the realization of clean and secure combustion in industrial lean premixed combustors.
文摘人工智能在信用风险评估中能有效识别风险并提升决策效率,然而,现有信用风险数据普遍存在类别不平衡问题,导致模型在预测时偏向多数类,影响评估的准确性和可靠性。针对数据不平衡问题,提出一种融合变分自编码器(VAE)和条件表格生成对抗网络(CTGAN)的混合生成模型(VCTGAN),用于合成高质量平衡数据集。通过VAE中的隐变量学习真实数据的关键特征和潜在分布,生成结构化隐变量作为原始CTGAN的输入;在数据生成器中引入自注意力机制用于更好地捕捉不平衡数据的突出特征;在判别器中加入对比损失模块来增强生成数据的类别间差异,达到提高生成数据质量的目的。通过在Taiwan Credit和Give Me Some Credit两个基准数据集上的系统实验验证,分别取得了89.91%和96.89%的最佳分类准确率,结果表明这种改进方法在处理信用数据不平衡方面明显优于传统方法。消融实验进一步验证了各组件对性能的贡献,证实了所提方法的合理性和有效性。它不仅生成高质量的平衡数据集,而且提高模型识别少数类别的能力,为解决金融领域的数据不平衡问题提供了新的技术方案。
文摘Exploratory data analysis plays a major role in obtaining insights from data.Over the last two decades,researchers have proposed several visual data exploration tools that can assist with each step of the analysis process.Nevertheless,in recent years,data analysis requirements have changed significantly.With constantly increasing size and types of data to be analyzed,scalability and analysis duration are now among the primary concerns of researchers.Moreover,in order to minimize the analysis cost,businesses are in need of data analysis tools that can be used with limited analytical knowledge.To address these challenges,traditional data exploration tools have evolved within the last few years.In this paper,with an in-depth analysis of an industrial tabular dataset,we identify a set of additional exploratory requirements for large datasets.Later,we present a comprehensive survey of the recent advancements in the emerging field of exploratory data analysis.We investigate 50 academic and non-academic visual data exploration tools with respect to their utility in the six fundamental steps of the exploratory data analysis process.We also examine the extent to which these modern data exploration tools fulfill the additional requirements for analyzing large datasets.Finally,we identify and present a set of research opportunities in the field of visual exploratory data analysis.
文摘为解决网络货运平台价格预测不准确导致的成交率下降问题,提出基于Shingling检索的表格先验数据拟合网络(tabular prior-data fitted network,TabPFN)的局部上下文学习(local context learning with TabPFN based on shingling retrieval,ShinglingPFN)模型。首先,该模型运用w-Shingling检索算法,从历史订单数据中匹配出与预测订单最相似的订单,构建局部关联的上下文数据。然后,加载并初始化预训练的TabPFN模型实例,将筛选出的订单数据输入模型,让TabPFN基于这些上下文信息学习货运特征与运费的关联模式。最后,输出该货运样本的运费预测结果。结果表明,ShinglingPFN模型相比随机森林(random forest,RF)模型减少了30.98%的平均绝对误差(mean absolute error,MAE)。通过全局敏感性分析,进一步增强了模型的可解释性。ShinglingPFN模型可为平台优化定价策略提供决策支撑。
