Symbolic Aggregate approXimation (SAX) is an efficient symbolic representation method that has been widely used in time series data mining. Its major limitation is that it relies exclusively on the mean values of segm...Symbolic Aggregate approXimation (SAX) is an efficient symbolic representation method that has been widely used in time series data mining. Its major limitation is that it relies exclusively on the mean values of segmented time series to derive the symbols. So, many important features of time series are not considered, such as extreme value, trend, fluctuation and so on. To solve this issue, we propose in this paper an improved Symbolic Aggregate approXimation based on multiple features and Vector Frequency Difference (SAX_VFD). SAX_VFD discriminates between time series by adopting an adaptive feature selection method. Furthermore, SAX_VFD is endowed with a new distance that takes into account the vector frequency difference between the symbolic sequence. We demonstrate the utility of the SAX_VFD on the time series classification task. The experimental results show that the proposed method has a better performance in terms of accuracy and dimensionality reduction compared to the so far published SAX based reduction techniques.展开更多
Percutaneous vertebroplasty is a minimally invasive procedure that involves filling of a fractured vertebral body with bone cement to relieve pain and to restore the vertebral height. It is a safe and effective treatm...Percutaneous vertebroplasty is a minimally invasive procedure that involves filling of a fractured vertebral body with bone cement to relieve pain and to restore the vertebral height. It is a safe and effective treatment and is widely used for treating Osteoporotic Vertebral Compression Fracture. Despite of its beneficial advantages over primary conservative managements, adjacent level vertebral compression fracture remains the challenge for surgeons. Adjacent level vertebral compression fracture following percutaneous vertebroplasty using PMMA cement has been reported as a complication. Numerous risk factors have been reported for the occurrence of new adjacent VCFs after PVP. The multiple level osteoporotic vertebral compression fractures and the increasing age of the patients are directly proportional to the risk of developing new symptomatic adjacent vertebral compression fracture after PVP. Moreover, low BMD and cement leakage are other factors that directly affect the incidence of new symptomatic adjacent vertebral fractures. The aim of this review is to evaluate the adjacent level vertebral compression fracture following percutaneous vertebroplasty on the basis of radiographs, Kaplan-Meier Estimation index and also the factors that lead to adjacent level vertebral compression fractures.展开更多
文摘Symbolic Aggregate approXimation (SAX) is an efficient symbolic representation method that has been widely used in time series data mining. Its major limitation is that it relies exclusively on the mean values of segmented time series to derive the symbols. So, many important features of time series are not considered, such as extreme value, trend, fluctuation and so on. To solve this issue, we propose in this paper an improved Symbolic Aggregate approXimation based on multiple features and Vector Frequency Difference (SAX_VFD). SAX_VFD discriminates between time series by adopting an adaptive feature selection method. Furthermore, SAX_VFD is endowed with a new distance that takes into account the vector frequency difference between the symbolic sequence. We demonstrate the utility of the SAX_VFD on the time series classification task. The experimental results show that the proposed method has a better performance in terms of accuracy and dimensionality reduction compared to the so far published SAX based reduction techniques.
文摘Percutaneous vertebroplasty is a minimally invasive procedure that involves filling of a fractured vertebral body with bone cement to relieve pain and to restore the vertebral height. It is a safe and effective treatment and is widely used for treating Osteoporotic Vertebral Compression Fracture. Despite of its beneficial advantages over primary conservative managements, adjacent level vertebral compression fracture remains the challenge for surgeons. Adjacent level vertebral compression fracture following percutaneous vertebroplasty using PMMA cement has been reported as a complication. Numerous risk factors have been reported for the occurrence of new adjacent VCFs after PVP. The multiple level osteoporotic vertebral compression fractures and the increasing age of the patients are directly proportional to the risk of developing new symptomatic adjacent vertebral compression fracture after PVP. Moreover, low BMD and cement leakage are other factors that directly affect the incidence of new symptomatic adjacent vertebral fractures. The aim of this review is to evaluate the adjacent level vertebral compression fracture following percutaneous vertebroplasty on the basis of radiographs, Kaplan-Meier Estimation index and also the factors that lead to adjacent level vertebral compression fractures.