Stock market has a profound impact on the market economy,Hence,the prediction of future movement of stocks is of great significance to investors.Therefore,an efficient prediction system can solve this problem to a gre...Stock market has a profound impact on the market economy,Hence,the prediction of future movement of stocks is of great significance to investors.Therefore,an efficient prediction system can solve this problem to a great extent.In this paper,we used the stock price of Google Inc.as a prediction object,selected 3810 adjusted closing prices,and used long short-term memory(LSTM)method to predict the future price trend of the stock.We built a three-layer LSTM model and divided the entire data into a test set and a training set according to the ratio of 8 to 2.The final results show that while the LSTM model can predict the stock trend of Google Inc.very well,it cannot predict the specific price accurately.展开更多
Stock price fluctuation and prediction is a problem that has attracted much attention.There exist many mathematical and statistical problems behind it.In essence,the key to solving this problem lies in capturing the l...Stock price fluctuation and prediction is a problem that has attracted much attention.There exist many mathematical and statistical problems behind it.In essence,the key to solving this problem lies in capturing the linear and nonlinear characteristics in the time series to predict future price movements.This study investigates the predictive capabilities of two distinct methodologies—Long Short-Term Memory(LSTM)networks and Autoregressive Integrated Moving Average(ARIMA)models—using Apple Inc.(AAPL)stock price data spanning 2016 to 2024.By synthesizing theoretical frameworks with empirical analysis,the research evaluates how each model captures linear trends and nonlinear fluctuations,ultimately proposing a hybrid ARIMA-LSTM architecture to enhance forecasting accuracy.Finally,according to the principal characteristics of the two models,the ARIMA-LSTM hybrid model is constructed.The results show that the hybrid model significantly outperforms single models in terms of RMSE and directional accuracy.Combined with error distribution visualization and volatility analysis,the hybrid model demonstrates efficient performance in achieving prediction optimization through the decomposition of linear and nonlinear components.It provides a new methodological perspective for financial time series modeling.展开更多
针对工业装配任务,尤其是不规则轴孔工件装配中,基于学习的前期样本质量低、训练过程不稳定等问题,提出一种融合引斥力模型(Attraction-Repulsion Model,ARM)引导机制和长短期记忆网络(Long Short Term Memory,LSTM)的柔性演员-评论家(S...针对工业装配任务,尤其是不规则轴孔工件装配中,基于学习的前期样本质量低、训练过程不稳定等问题,提出一种融合引斥力模型(Attraction-Repulsion Model,ARM)引导机制和长短期记忆网络(Long Short Term Memory,LSTM)的柔性演员-评论家(Soft Actor-Critic,SAC)算法。首先,为解决训练初期探索效率低的问题,提出一种基于引斥力模型的策略引导机制,通过目标位置信息引导机械臂运动,加速收敛过程;其次,基于长短期记忆网络对算法的策略网络和价值网络进行改进,有效利用历史信息,增强策略学习能力,提高算法的收敛速度和稳定性。仿真结果表明,所提出的算法在行星减速器中心轴装配任务中取得显著的效果,装配成功率高达99.4%,与普通SAC算法相比,平均最大接触力和力矩分别降低了68.8%和79.2%。在物理环境中装配成功率达95%以上,最大接触力和力矩分别小于10 N和1.5 N·m,验证了算法的有效性。展开更多
针对“卡脖子”技术研究存在替代技术识别机制缺失与技术要素解析精度不足等局限,文章提出融合提示工程与BERT-LSTM模型的“卡脖子”替代技术识别方法。首先,基于商业管制清单(Commercial Control List,CCL)对ECCN物项进行解析,并开展...针对“卡脖子”技术研究存在替代技术识别机制缺失与技术要素解析精度不足等局限,文章提出融合提示工程与BERT-LSTM模型的“卡脖子”替代技术识别方法。首先,基于商业管制清单(Commercial Control List,CCL)对ECCN物项进行解析,并开展专利检索工作,通过SPC算法提取技术主路径的关键核心专利;其次,运用大语言模型提示工程抽取“问题-方案对”,借此解析技术功效,并结合功能导向搜索(Function-Oriented Search,FOS)初步查找可能具备技术替代功效的相关专利;再次,采用BERT-LSTM模型对专利文本实施二元分类,精准识别出具备技术替代功效的专利样本;通过提示工程抽取“方案-类别对”,系统识别替代技术方案;最后,建立科学-产业双维度评估体系完成替代技术潜力分级。文章以光刻技术为例,阐述该识别方法的应用流程,系统识别出极紫外(Extreme Ultra-violet,EUV)光刻技术的五种替代技术及其替代潜力。展开更多
在遥感海浪数据质量控制研究中,由于数据的复杂与不规则性,传统质量控制方法对海浪数据单点异常值的检测具有一定局限性。深度学习具有强大的特征学习能力,在解决非线性复杂问题方面具有一定优势,将其应用在数据质量控制领域可以提高异...在遥感海浪数据质量控制研究中,由于数据的复杂与不规则性,传统质量控制方法对海浪数据单点异常值的检测具有一定局限性。深度学习具有强大的特征学习能力,在解决非线性复杂问题方面具有一定优势,将其应用在数据质量控制领域可以提高异常值检测能力。本研究采用遥感海浪有效波高数据,构建双向长短期记忆网络(bi-directional long short term memory,Bi-LSTM)模型对有效波高进行预测,结合阈值方法进行异常检测,与3σ准则法、孤立森林模型法、 LSTM模型法以及VAE-LSTM模型法进行异常检测精度比较,探究基于Bi-LSTM的质量控制模型在遥感海浪数据异常值检测方面的能力。试验结果表明,Bi-LSTM质量控制模型具有良好的异常值检测效果,其精准率、召回率、 F1分数和运行时间分别为91%、 93%、 92和3.35 s,综合评价效果最佳,可有效对遥感海浪数据进行质量控制。展开更多
文摘Stock market has a profound impact on the market economy,Hence,the prediction of future movement of stocks is of great significance to investors.Therefore,an efficient prediction system can solve this problem to a great extent.In this paper,we used the stock price of Google Inc.as a prediction object,selected 3810 adjusted closing prices,and used long short-term memory(LSTM)method to predict the future price trend of the stock.We built a three-layer LSTM model and divided the entire data into a test set and a training set according to the ratio of 8 to 2.The final results show that while the LSTM model can predict the stock trend of Google Inc.very well,it cannot predict the specific price accurately.
文摘Stock price fluctuation and prediction is a problem that has attracted much attention.There exist many mathematical and statistical problems behind it.In essence,the key to solving this problem lies in capturing the linear and nonlinear characteristics in the time series to predict future price movements.This study investigates the predictive capabilities of two distinct methodologies—Long Short-Term Memory(LSTM)networks and Autoregressive Integrated Moving Average(ARIMA)models—using Apple Inc.(AAPL)stock price data spanning 2016 to 2024.By synthesizing theoretical frameworks with empirical analysis,the research evaluates how each model captures linear trends and nonlinear fluctuations,ultimately proposing a hybrid ARIMA-LSTM architecture to enhance forecasting accuracy.Finally,according to the principal characteristics of the two models,the ARIMA-LSTM hybrid model is constructed.The results show that the hybrid model significantly outperforms single models in terms of RMSE and directional accuracy.Combined with error distribution visualization and volatility analysis,the hybrid model demonstrates efficient performance in achieving prediction optimization through the decomposition of linear and nonlinear components.It provides a new methodological perspective for financial time series modeling.
文摘针对工业装配任务,尤其是不规则轴孔工件装配中,基于学习的前期样本质量低、训练过程不稳定等问题,提出一种融合引斥力模型(Attraction-Repulsion Model,ARM)引导机制和长短期记忆网络(Long Short Term Memory,LSTM)的柔性演员-评论家(Soft Actor-Critic,SAC)算法。首先,为解决训练初期探索效率低的问题,提出一种基于引斥力模型的策略引导机制,通过目标位置信息引导机械臂运动,加速收敛过程;其次,基于长短期记忆网络对算法的策略网络和价值网络进行改进,有效利用历史信息,增强策略学习能力,提高算法的收敛速度和稳定性。仿真结果表明,所提出的算法在行星减速器中心轴装配任务中取得显著的效果,装配成功率高达99.4%,与普通SAC算法相比,平均最大接触力和力矩分别降低了68.8%和79.2%。在物理环境中装配成功率达95%以上,最大接触力和力矩分别小于10 N和1.5 N·m,验证了算法的有效性。
文摘针对“卡脖子”技术研究存在替代技术识别机制缺失与技术要素解析精度不足等局限,文章提出融合提示工程与BERT-LSTM模型的“卡脖子”替代技术识别方法。首先,基于商业管制清单(Commercial Control List,CCL)对ECCN物项进行解析,并开展专利检索工作,通过SPC算法提取技术主路径的关键核心专利;其次,运用大语言模型提示工程抽取“问题-方案对”,借此解析技术功效,并结合功能导向搜索(Function-Oriented Search,FOS)初步查找可能具备技术替代功效的相关专利;再次,采用BERT-LSTM模型对专利文本实施二元分类,精准识别出具备技术替代功效的专利样本;通过提示工程抽取“方案-类别对”,系统识别替代技术方案;最后,建立科学-产业双维度评估体系完成替代技术潜力分级。文章以光刻技术为例,阐述该识别方法的应用流程,系统识别出极紫外(Extreme Ultra-violet,EUV)光刻技术的五种替代技术及其替代潜力。
文摘在遥感海浪数据质量控制研究中,由于数据的复杂与不规则性,传统质量控制方法对海浪数据单点异常值的检测具有一定局限性。深度学习具有强大的特征学习能力,在解决非线性复杂问题方面具有一定优势,将其应用在数据质量控制领域可以提高异常值检测能力。本研究采用遥感海浪有效波高数据,构建双向长短期记忆网络(bi-directional long short term memory,Bi-LSTM)模型对有效波高进行预测,结合阈值方法进行异常检测,与3σ准则法、孤立森林模型法、 LSTM模型法以及VAE-LSTM模型法进行异常检测精度比较,探究基于Bi-LSTM的质量控制模型在遥感海浪数据异常值检测方面的能力。试验结果表明,Bi-LSTM质量控制模型具有良好的异常值检测效果,其精准率、召回率、 F1分数和运行时间分别为91%、 93%、 92和3.35 s,综合评价效果最佳,可有效对遥感海浪数据进行质量控制。
