Lithium-ion batteries are the most widely accepted type of battery in the electric vehicle industry because of some of their positive inherent characteristics. However, the safety problems associated with inaccurate e...Lithium-ion batteries are the most widely accepted type of battery in the electric vehicle industry because of some of their positive inherent characteristics. However, the safety problems associated with inaccurate estimation and prediction of the state of health of these batteries have attracted wide attention due to the adverse negative effect on vehicle safety. In this paper, both machine and deep learning models were used to estimate the state of health of lithium-ion batteries. The paper introduces the definition of battery health status and its importance in the electric vehicle industry. Based on the data preprocessing and visualization analysis, three features related to actual battery capacity degradation are extracted from the data. Two learning models, SVR and LSTM were employed for the state of health estimation and their respective results are compared in this paper. The mean square error and coefficient of determination were the two metrics for the performance evaluation of the models. The experimental results indicate that both models have high estimation results. However, the metrics indicated that the SVR was the overall best model.展开更多
BACKGROUND: Survivin is known to be overexpressed in various human malignancies, including pancreatic cancer, and mediates cancer cell proliferation and tumor growth, so the regulation of this molecule could be a new ...BACKGROUND: Survivin is known to be overexpressed in various human malignancies, including pancreatic cancer, and mediates cancer cell proliferation and tumor growth, so the regulation of this molecule could be a new strategy for treating pancreatic cancer. In this study, short hairpin RNAs (shRNAs) specific to survivin were introduced into human pancreatic cancer Patu8988 cells to investigate the inhibitory effects on survivin expression and cell proliferation in vitro and in vivo. METHODS: Three kinds of shRNA specific to the survivin gene were designed and cloned into eukaryotic expression plasmid pGenesil-1 vector. Subsequently the recombinant plasmids were transfected into human pancreatic cancer Patu8988 cells with lipfectamine (TM) 2000 reagent. The mRNA and protein expressions of survivin in the transiently transfected Patu8988 cells were determined by RT-PCR, flow cytometry, and Western blotting analysis. The proliferation inhibition rates of stably transfected Patu8988 cells were determined by MTT assay. The antitumor activities of the three kinds of survivin-shRNA plasmids were evaluated in BALB/c nude mice inoculated with Patu8988 cells and bearing human pancreatic cancer. RESULTS: The three survivin-shRNA plasmids named pGenesil-1-survivin-1, pGenesil-1-survivin-2 and pGenesil-1-survivin-1+2 (with double interfering RNA sites) were successfully constructed, and were confirmed by restriction enzyme cutting and sequencing. At 48 hours after transfection, the expression of survivin mRNA and protein was inhibited in Patu8988 cells transfected with pGenesil-1-survivin-1, pGenesil-1-survivin-2, and pGenesil-1-survivin-1+2 when compared with that of either pGenesil-1-NC (with scrambled small interfering RNA) transfected cells or control cells (P<0.05). The MTT results showed that the proliferation rates of Patu8988 cells stably transfected with survivin-shRNA plasmids were reduced when compared with that of either pGenesil-1-NC transfected cells or control cells (P<0.01). Furthermore, when Patu8988 cells stably transfected with survivin-shRNA were injected into BALB/c nude mice, tumor growth was dramatically lower and the tumor was smaller than that of either pGenesil-1-NC transfected cells or control cells (P<0.01). The inhibitory effect of pGenesil-1-survivin-1 was the best among the three kinds of survivin-shRNA plasmids, but no combination of inhibitory effects was found in pGenesil-1-survivin-1+2. CONCLUSIONS: shRNAs specific to survivin have gene silencing effects and inhibit pancreatic cancer cell proliferation. shRNA activity against survivin could be of potential value in gene therapy for pancreatic cancer. However, shRNAs with double combining sites did not significantly enhance the interference compared with single site shRNAs, therefore further studies on this are needed.展开更多
The 10 920 stress indicators collected so far by the WSM (World Stress Map) project represent the observed ori-entations of the maximum horizontal principal stress (sHmax) in a certain region. Assuming that the long-w...The 10 920 stress indicators collected so far by the WSM (World Stress Map) project represent the observed ori-entations of the maximum horizontal principal stress (sHmax) in a certain region. Assuming that the long-wave component of sHmax is expressed by the absolute direction of plate motions, we can get the relative orientation and the magnitude of the short-wave component resulted from the local tectonic process or other factors with vector analytical technique. The global surface was divided into basic element bins by 2.52.5 dimensions and the WSM indicators were statistically analyzed for each element by weight coefficient method in order to determine the mean orientation of the stress. We calculated the long-wave component of the global stress field using HS2-NUVEL1 model. The relative magnitude or the direction limitation of short-wave component, which reflect the local contribution to the observed stresses, was determined by the angle between the mean sHmax and the orien-tation of the long-wave component. The results of this paper show that the contribution of either the long-wave component or the short-wave component is approximately equal to most of the global plates on the basis of the mean effect of the observed stresses. For some of continental regions, the local active tectonics plays an important role in the observed stresses and controls the generation and occurrence of earthquakes.展开更多
Forecasts can either be short term, medium term or long term. In this work we considered short term forecast because of the problem of limited data or time series data that is often encounter in time series analysis. ...Forecasts can either be short term, medium term or long term. In this work we considered short term forecast because of the problem of limited data or time series data that is often encounter in time series analysis. This simulation study considered the performances of the classical VAR and Sims-Zha Bayesian VAR for short term series at different levels of collinearity and correlated error terms. The results from 10,000 iteration revealed that the BVAR models are excellent for time series length of T=8 for all levels of collinearity while the classical VAR is effective for time series length of T=16 for all collinearity levels except when ρ = -0.9 and ρ = -0.95. We therefore recommended that for effective short term forecasting, the time series length, forecasting horizon and the collinearity level should be considered.展开更多
为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD...为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD)的无监督异常检测方法。利用LSTM网络提取可变长度飞行轨迹的关键特征,并将其转化为固定长度的序列表示;通过SVDD算法构建多维超球分类器,对正常飞行轨迹进行建模,从而识别潜在异常轨迹。为进一步提升模型性能,引入基于梯度的优化算法(Gradient-Based training algorithm, GB),实现LSTM与SVDD参数的联合训练,大幅度提高检测精度和计算效率。仿真实验结果表明,新提出的基于梯度优化的长短时记忆网络和支持向量数据描述模型(Long Short-Term Memory network and Support Vector Data Description model based on Gradient-Based training algorithm optimization, LSTM-GBSVDD)的飞行轨迹异常检测方法在处理复杂、多变的飞行轨迹异常检测任务中表现出较好的有效性和优越性,有较强的应用前景。展开更多
For natural language processing problems, the short text classification is still a research hot topic, with obviously problem in the features sparse, high-dimensional text data and feature representation. In order to ...For natural language processing problems, the short text classification is still a research hot topic, with obviously problem in the features sparse, high-dimensional text data and feature representation. In order to express text directly, a simple but new variation which employs one-hot with low-dimension was proposed. In this paper, a Densenet-based model was proposed to short text classification. Furthermore, the feature diversity and reuse were implemented by the concat and average shuffle operation between Resnet and Densenet for enlarging short text feature selection. Finally, some benchmarks were introduced to evaluate the Falcon. From our experimental results, the Falcon method obtained significant improvements in the state-of-art models on most of them in all respects, especially in the first experiment of error rate. To sum up, the Falcon is an efficient and economical model, whilst requiring less computation to achieve high performance.展开更多
Accurate load prediction plays an important role in smart power management system, either for planning, facing the increasing of load demand, maintenance issues, or power distribution system. In order to achieve a rea...Accurate load prediction plays an important role in smart power management system, either for planning, facing the increasing of load demand, maintenance issues, or power distribution system. In order to achieve a reasonable prediction, authors have applied and compared two features extraction technique presented by kernel partial least square regression and kernel principal component regression, and both of them are carried out by polynomial and Gaussian kernels to map the original features’ to high dimension features’ space, and then draw new predictor variables known as scores and loadings, while kernel principal component regression draws the predictor features to construct new predictor variables without any consideration to response vector. In contrast, kernel partial least square regression does take the response vector into consideration. Models are simulated by three different cities’ electric load data, which used historical load data in addition to weekends and holidays as common predictor features for all models. On the other hand temperature has been used for only one data as a comparative study to measure its effect. Models’ results evaluated by three statistic measurements, show that Gaussian Kernel Partial Least Square Regression offers the more powerful features and significantly can improve the load prediction performance than other presented models.展开更多
基于Wi-Fi感知的室内入侵检测系统是一种无需在移动实体上附加任何设备即可检测移动实体的系统。针对目前检测方法忽略复杂的幅度变化和相位变化引起的潜在影响,提出了融合长短期记忆网络和支持向量机的室内入侵检测新方法LSID(Long Sho...基于Wi-Fi感知的室内入侵检测系统是一种无需在移动实体上附加任何设备即可检测移动实体的系统。针对目前检测方法忽略复杂的幅度变化和相位变化引起的潜在影响,提出了融合长短期记忆网络和支持向量机的室内入侵检测新方法LSID(Long Short-Term Memory and Support Vector Machine Intrusion Detection)。LSID方法采用一种新的特征值建模方式,利用长短期记忆网络可以学习到时序特征并且能捕捉时序信号长期的依赖关系,将信道状态信息真实值与长短期记忆神经网络的预测值之差作为特征值,能更准确地捕捉入侵者对信号状态信息的影响。该检测方法在学校实验室环境下经过多次实验验证,最终检测准确率达到99.21%,通过多组实验比对,结果显示LSID方法具有有效性和可行性,相比于其他入侵检测方法准确率明显提升。展开更多
文摘Lithium-ion batteries are the most widely accepted type of battery in the electric vehicle industry because of some of their positive inherent characteristics. However, the safety problems associated with inaccurate estimation and prediction of the state of health of these batteries have attracted wide attention due to the adverse negative effect on vehicle safety. In this paper, both machine and deep learning models were used to estimate the state of health of lithium-ion batteries. The paper introduces the definition of battery health status and its importance in the electric vehicle industry. Based on the data preprocessing and visualization analysis, three features related to actual battery capacity degradation are extracted from the data. Two learning models, SVR and LSTM were employed for the state of health estimation and their respective results are compared in this paper. The mean square error and coefficient of determination were the two metrics for the performance evaluation of the models. The experimental results indicate that both models have high estimation results. However, the metrics indicated that the SVR was the overall best model.
基金supported by grants from the Social Bureau Foundation of Suzhou (SZD0614)the Foundation of Health Bureau of Jiangsu Province (Z200622)
文摘BACKGROUND: Survivin is known to be overexpressed in various human malignancies, including pancreatic cancer, and mediates cancer cell proliferation and tumor growth, so the regulation of this molecule could be a new strategy for treating pancreatic cancer. In this study, short hairpin RNAs (shRNAs) specific to survivin were introduced into human pancreatic cancer Patu8988 cells to investigate the inhibitory effects on survivin expression and cell proliferation in vitro and in vivo. METHODS: Three kinds of shRNA specific to the survivin gene were designed and cloned into eukaryotic expression plasmid pGenesil-1 vector. Subsequently the recombinant plasmids were transfected into human pancreatic cancer Patu8988 cells with lipfectamine (TM) 2000 reagent. The mRNA and protein expressions of survivin in the transiently transfected Patu8988 cells were determined by RT-PCR, flow cytometry, and Western blotting analysis. The proliferation inhibition rates of stably transfected Patu8988 cells were determined by MTT assay. The antitumor activities of the three kinds of survivin-shRNA plasmids were evaluated in BALB/c nude mice inoculated with Patu8988 cells and bearing human pancreatic cancer. RESULTS: The three survivin-shRNA plasmids named pGenesil-1-survivin-1, pGenesil-1-survivin-2 and pGenesil-1-survivin-1+2 (with double interfering RNA sites) were successfully constructed, and were confirmed by restriction enzyme cutting and sequencing. At 48 hours after transfection, the expression of survivin mRNA and protein was inhibited in Patu8988 cells transfected with pGenesil-1-survivin-1, pGenesil-1-survivin-2, and pGenesil-1-survivin-1+2 when compared with that of either pGenesil-1-NC (with scrambled small interfering RNA) transfected cells or control cells (P<0.05). The MTT results showed that the proliferation rates of Patu8988 cells stably transfected with survivin-shRNA plasmids were reduced when compared with that of either pGenesil-1-NC transfected cells or control cells (P<0.01). Furthermore, when Patu8988 cells stably transfected with survivin-shRNA were injected into BALB/c nude mice, tumor growth was dramatically lower and the tumor was smaller than that of either pGenesil-1-NC transfected cells or control cells (P<0.01). The inhibitory effect of pGenesil-1-survivin-1 was the best among the three kinds of survivin-shRNA plasmids, but no combination of inhibitory effects was found in pGenesil-1-survivin-1+2. CONCLUSIONS: shRNAs specific to survivin have gene silencing effects and inhibit pancreatic cancer cell proliferation. shRNA activity against survivin could be of potential value in gene therapy for pancreatic cancer. However, shRNAs with double combining sites did not significantly enhance the interference compared with single site shRNAs, therefore further studies on this are needed.
基金MOST contract of 2001BA601B02 and State Natural Science Foundation of China (49804006).
文摘The 10 920 stress indicators collected so far by the WSM (World Stress Map) project represent the observed ori-entations of the maximum horizontal principal stress (sHmax) in a certain region. Assuming that the long-wave component of sHmax is expressed by the absolute direction of plate motions, we can get the relative orientation and the magnitude of the short-wave component resulted from the local tectonic process or other factors with vector analytical technique. The global surface was divided into basic element bins by 2.52.5 dimensions and the WSM indicators were statistically analyzed for each element by weight coefficient method in order to determine the mean orientation of the stress. We calculated the long-wave component of the global stress field using HS2-NUVEL1 model. The relative magnitude or the direction limitation of short-wave component, which reflect the local contribution to the observed stresses, was determined by the angle between the mean sHmax and the orien-tation of the long-wave component. The results of this paper show that the contribution of either the long-wave component or the short-wave component is approximately equal to most of the global plates on the basis of the mean effect of the observed stresses. For some of continental regions, the local active tectonics plays an important role in the observed stresses and controls the generation and occurrence of earthquakes.
文摘Forecasts can either be short term, medium term or long term. In this work we considered short term forecast because of the problem of limited data or time series data that is often encounter in time series analysis. This simulation study considered the performances of the classical VAR and Sims-Zha Bayesian VAR for short term series at different levels of collinearity and correlated error terms. The results from 10,000 iteration revealed that the BVAR models are excellent for time series length of T=8 for all levels of collinearity while the classical VAR is effective for time series length of T=16 for all collinearity levels except when ρ = -0.9 and ρ = -0.95. We therefore recommended that for effective short term forecasting, the time series length, forecasting horizon and the collinearity level should be considered.
文摘为解决传统检测方法在处理复杂、动态以及数据长度实时变化的飞行轨迹数据时特征提取不准确、检测效率较低的问题,提出一种结合长短时记忆(Long Short-Term Memory, LSTM)网络和支持向量数据描述(Support Vector Data Description, SVDD)的无监督异常检测方法。利用LSTM网络提取可变长度飞行轨迹的关键特征,并将其转化为固定长度的序列表示;通过SVDD算法构建多维超球分类器,对正常飞行轨迹进行建模,从而识别潜在异常轨迹。为进一步提升模型性能,引入基于梯度的优化算法(Gradient-Based training algorithm, GB),实现LSTM与SVDD参数的联合训练,大幅度提高检测精度和计算效率。仿真实验结果表明,新提出的基于梯度优化的长短时记忆网络和支持向量数据描述模型(Long Short-Term Memory network and Support Vector Data Description model based on Gradient-Based training algorithm optimization, LSTM-GBSVDD)的飞行轨迹异常检测方法在处理复杂、多变的飞行轨迹异常检测任务中表现出较好的有效性和优越性,有较强的应用前景。
文摘For natural language processing problems, the short text classification is still a research hot topic, with obviously problem in the features sparse, high-dimensional text data and feature representation. In order to express text directly, a simple but new variation which employs one-hot with low-dimension was proposed. In this paper, a Densenet-based model was proposed to short text classification. Furthermore, the feature diversity and reuse were implemented by the concat and average shuffle operation between Resnet and Densenet for enlarging short text feature selection. Finally, some benchmarks were introduced to evaluate the Falcon. From our experimental results, the Falcon method obtained significant improvements in the state-of-art models on most of them in all respects, especially in the first experiment of error rate. To sum up, the Falcon is an efficient and economical model, whilst requiring less computation to achieve high performance.
文摘Accurate load prediction plays an important role in smart power management system, either for planning, facing the increasing of load demand, maintenance issues, or power distribution system. In order to achieve a reasonable prediction, authors have applied and compared two features extraction technique presented by kernel partial least square regression and kernel principal component regression, and both of them are carried out by polynomial and Gaussian kernels to map the original features’ to high dimension features’ space, and then draw new predictor variables known as scores and loadings, while kernel principal component regression draws the predictor features to construct new predictor variables without any consideration to response vector. In contrast, kernel partial least square regression does take the response vector into consideration. Models are simulated by three different cities’ electric load data, which used historical load data in addition to weekends and holidays as common predictor features for all models. On the other hand temperature has been used for only one data as a comparative study to measure its effect. Models’ results evaluated by three statistic measurements, show that Gaussian Kernel Partial Least Square Regression offers the more powerful features and significantly can improve the load prediction performance than other presented models.
文摘基于Wi-Fi感知的室内入侵检测系统是一种无需在移动实体上附加任何设备即可检测移动实体的系统。针对目前检测方法忽略复杂的幅度变化和相位变化引起的潜在影响,提出了融合长短期记忆网络和支持向量机的室内入侵检测新方法LSID(Long Short-Term Memory and Support Vector Machine Intrusion Detection)。LSID方法采用一种新的特征值建模方式,利用长短期记忆网络可以学习到时序特征并且能捕捉时序信号长期的依赖关系,将信道状态信息真实值与长短期记忆神经网络的预测值之差作为特征值,能更准确地捕捉入侵者对信号状态信息的影响。该检测方法在学校实验室环境下经过多次实验验证,最终检测准确率达到99.21%,通过多组实验比对,结果显示LSID方法具有有效性和可行性,相比于其他入侵检测方法准确率明显提升。
