针对人脸检测问题的特点,提出一种基于改进型深度LLE(Locally Linear Embedding)算法和随机森林相结合的人脸检测算法。首先,通过采集图像的深度信息,结合图像的颜色信息,构建三维图像信息数据库,再通过改进的LLE算法得到最优降维结果,...针对人脸检测问题的特点,提出一种基于改进型深度LLE(Locally Linear Embedding)算法和随机森林相结合的人脸检测算法。首先,通过采集图像的深度信息,结合图像的颜色信息,构建三维图像信息数据库,再通过改进的LLE算法得到最优降维结果,按一定比例选取训练集,输入随机森林算法建立数据分类器;最后,将测试集输入到训练完成的分类器中,实现人脸图像的检测。选取Yale,JAFFE 2类数据集与传统算法进行对比实验,验证算法的优越性和可行性。实验结果表明:所提出的算法可以有效地完成人脸检测,检测率高于传统算法7%左右。展开更多
:Social media data are rapidly increasing and constitute a source of user opinions and tips on a wide range of products and services.The increasing availability of such big data on biased reviews and blogs creates cha...:Social media data are rapidly increasing and constitute a source of user opinions and tips on a wide range of products and services.The increasing availability of such big data on biased reviews and blogs creates challenges for customers and businesses in reviewing all content in their decision-making process.To overcome this challenge,extracting suggestions from opinionated text is a possible solution.In this study,the characteristics of suggestions are analyzed and a suggestion mining extraction process is presented for classifying suggestive sentences from online customers’reviews.A classification using a word-embedding approach is used via the XGBoost classifier.The two datasets used in this experiment relate to online hotel reviews and Microsoft Windows App Studio discussion reviews.F1,precision,recall,and accuracy scores are calculated.The results demonstrated that the XGBoost classifier outperforms—with an accuracy of more than 80%.Moreover,the results revealed that suggestion keywords and phrases are the predominant features for suggestion extraction.Thus,this study contributes to knowledge and practice by comparing feature extraction classifiers and identifying XGBoost as a better suggestion mining process for identifying online reviews.展开更多
邻域嵌入超分辨率重构算法在空间邻域选取过程中,细节特征易被大幅度特征分量淹没,为此,提出了基于方向字典子图的初始邻域嵌入重构算法.对输入图像及邻域利用方向字典进行稀疏分解,从大、小幅值表示系数中分别重构大、小幅度特征子图,...邻域嵌入超分辨率重构算法在空间邻域选取过程中,细节特征易被大幅度特征分量淹没,为此,提出了基于方向字典子图的初始邻域嵌入重构算法.对输入图像及邻域利用方向字典进行稀疏分解,从大、小幅值表示系数中分别重构大、小幅度特征子图,保护邻域计算中的小幅度特征;同时,为降低多子图重构的运算量,通过随机森林机制,将输入图像在分类树森林中对应叶子节点图像子库的并集作为初始邻域,减小实际参与运算的图像库大小.实验结果表明,相对于邻域嵌入超分辨率算法,基于方向字典子图的初始邻域嵌入重构的峰值信噪比值平均提升了1.095 9 d B,有效改善了重构效果;重构时间仅为邻域嵌入超分辨率的13.3%,降低了重构复杂度.展开更多
文摘针对人脸检测问题的特点,提出一种基于改进型深度LLE(Locally Linear Embedding)算法和随机森林相结合的人脸检测算法。首先,通过采集图像的深度信息,结合图像的颜色信息,构建三维图像信息数据库,再通过改进的LLE算法得到最优降维结果,按一定比例选取训练集,输入随机森林算法建立数据分类器;最后,将测试集输入到训练完成的分类器中,实现人脸图像的检测。选取Yale,JAFFE 2类数据集与传统算法进行对比实验,验证算法的优越性和可行性。实验结果表明:所提出的算法可以有效地完成人脸检测,检测率高于传统算法7%左右。
文摘目的骨质疏松性骨折(osteoporotic fracture,OF)的预测对于骨折防范具有重要的临床指导意义。针对传统logistic回归预测模型存在的精度不高和未考虑遗传因子问题,本文引入多粒度级联森林(multi-grained cascade forest,gcForest)并结合遗传因子来预测OF。方法首先基于 t 分布邻域嵌入( t -distributed stochastic neighbor embedding, t -SNE)算法对OF关联基因位点进行非线性降维,降维后的基因位点与临床因素构成特征组。然后构建gcForest模型对OF进行预测。最后通过10次十折分层交叉验证与logistic、梯度提升决策树、随机森林进行对比。结果基于gcForest的模型分类精度为0.892 7,AUC值为0.92±0.05,泛化性能最优。结论在考虑遗传因素的条件下,gcForest分类效果优于其他模型,验证了本文方法的高效性和实用性。
基金This research is funded by Taif University, TURSP-2020/115.
文摘:Social media data are rapidly increasing and constitute a source of user opinions and tips on a wide range of products and services.The increasing availability of such big data on biased reviews and blogs creates challenges for customers and businesses in reviewing all content in their decision-making process.To overcome this challenge,extracting suggestions from opinionated text is a possible solution.In this study,the characteristics of suggestions are analyzed and a suggestion mining extraction process is presented for classifying suggestive sentences from online customers’reviews.A classification using a word-embedding approach is used via the XGBoost classifier.The two datasets used in this experiment relate to online hotel reviews and Microsoft Windows App Studio discussion reviews.F1,precision,recall,and accuracy scores are calculated.The results demonstrated that the XGBoost classifier outperforms—with an accuracy of more than 80%.Moreover,the results revealed that suggestion keywords and phrases are the predominant features for suggestion extraction.Thus,this study contributes to knowledge and practice by comparing feature extraction classifiers and identifying XGBoost as a better suggestion mining process for identifying online reviews.
文摘邻域嵌入超分辨率重构算法在空间邻域选取过程中,细节特征易被大幅度特征分量淹没,为此,提出了基于方向字典子图的初始邻域嵌入重构算法.对输入图像及邻域利用方向字典进行稀疏分解,从大、小幅值表示系数中分别重构大、小幅度特征子图,保护邻域计算中的小幅度特征;同时,为降低多子图重构的运算量,通过随机森林机制,将输入图像在分类树森林中对应叶子节点图像子库的并集作为初始邻域,减小实际参与运算的图像库大小.实验结果表明,相对于邻域嵌入超分辨率算法,基于方向字典子图的初始邻域嵌入重构的峰值信噪比值平均提升了1.095 9 d B,有效改善了重构效果;重构时间仅为邻域嵌入超分辨率的13.3%,降低了重构复杂度.
