Data mining has the potential to provide information for improving clinical acupuncture strategies by uncovering hidden rules between acupuncture manipulation and therapeutic effects in a data set. In this study, we p...
详细信息
Data mining has the potential to provide information for improving clinical acupuncture strategies by uncovering hidden rules between acupuncture manipulation and therapeutic effects in a data set. In this study, we performed acupuncture on 30 patients with hemiplegia due to acute ischemic stroke. All participants were pre-screened to ensure that they exhibited immediate responses to acupuncture. We used a twirling reinforcing acupuncture manipulation at the specific lines between the bilateral Baihui（GV20） and Taiyang（EX-HN5）. We collected neurologic deficit score, simplified Fugl-Meyer assessment score, muscle strength of the proximal and distal hemiplegic limbs, ratio of the maximal H-reflex to the maximal M-wave（Hmax/Mmax）, muscle tension at baseline and immediately after treatment, and the syndromes of traditional Chinese medicine at baseline. We then conducted data mining using an association algorithm and an artificialneuralnetwork backpropagation algorithm. We found that the twirling reinforcing manipulation had no obvious therapeutic difference in traditional Chinese medicine syndromes of ＂Deficiency and Excess＂. The change in the muscle strength of the upper distal and lower proximal limbs was one of the main factors affecting the immediate change in Fugl-Meyer scores. Additionally, we found a positive correlation between the muscle tension change of the upper limb and Hmax/Mmax immediate change, and both positive and negative correlations existed between the muscle tension change of the lower limb and immediate Hmax/Mmax change. Additionally, when the difference value of muscle tension for the upper and lower limbs was 〉 0 or 〈 0, the difference value of Hmax/Mmax was correspondingly positive or negative, indicating the scalp acupuncture has a bidirectional effect on muscle tension in hemiplegic limbs. Therefore, acupuncture with twirling reinforcing manipulation has distinct effects on acute ischemic stroke patients with different symptoms or stages of
This paper presents the development of a Machine learning model through implementation of two algorithms namely Logistic Regression and artificialneuralnetworks to recognize handwritten digits from 0 to 9. The Train...
详细信息
ISBN:
(纸本)9781467385886
This paper presents the development of a Machine learning model through implementation of two algorithms namely Logistic Regression and artificialneuralnetworks to recognize handwritten digits from 0 to 9. The Training efficiency of both the algorithms is compared at the end of implementation. Logistic Regression is generally used for binary classification however;multiclass classification has been achieved by using One-vs-All approach. artificialneuralnetworks are used for feed forward propagation to build the hypothesis function and back propagation is used for calculation of weights. The weights for both the models are minimized using advanced optimization algorithm such as fmiunc and fmincg. The formulas are implemented in vectorized format that is the formulas are solely expressed in matrix form and nowhere for loops are required. Vectorization does involve a lot of formulations to be done on paper beforehand but it ultimately serves the optimization purpose because higher programming languages such as MATLAB are very efficient to implement vectorized codes and this property should be exploited. The database consists of five thousand handwritten digits. The final result shows the program predicting the number on the display. The system is well trained and effective in recognizing the number.
This article combines with the engineering machinery of diesel engine, the hydraulic system, the gear system, the hydraulic transmission system using oil of performance requirements;in order to meet the need of engine...
详细信息
ISBN:
(纸本)9783037857267
This article combines with the engineering machinery of diesel engine, the hydraulic system, the gear system, the hydraulic transmission system using oil of performance requirements;in order to meet the need of engineering machinery actual using condition. Through the study of base oil, antioxidant and corrosion inhibitor, detergent and dispersant additive, extreme pressure and anti-wear agent, rust inhibitor, anti-emulsifier, anti-foam agent, etc composite additives. using Poly-alpha-olefin (PAO) and dioctyl sebacate composite act as the engineering machinery general oil of base oil, and by using the artificial neural network algorithm targeted to a variety of the functional additive of screening and prediction, and using the genetic algorithm optimists the selection of formula, develop the environment-friendly and energy-saving engineering machinery general oil.
Background: Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR...
详细信息
Background: Machine learning has a vast range of applications. In particular, advanced machine learning methods are routinely and increasingly used in quantitative structure activity relationship (QSAR) modeling. QSAR data sets often encompass tens of thousands of compounds and the size of proprietary, as well as public data sets, is rapidly growing. Hence, there is a demand for computationally efficient machine learning algorithms, easily available to researchers without extensive machine learning knowledge. In granting the scientific principles of transparency and reproducibility, Open Source solutions are increasingly acknowledged by regulatory authorities. Thus, an Open Source state-of-the-art high performance machine learning platform, interfacing multiple, customized machine learning algorithms for both graphical programming and scripting, to be used for large scale development of QSAR models of regulatory quality, is of great value to the QSAR community. Results: This paper describes the implementation of the Open Source machine learning package AZOrange. AZOrange is specially developed to support batch generation of QSAR models in providing the full work flow of QSAR modeling, from descriptor calculation to automated model building, validation and selection. The automated work flow relies upon the customization of the machine learning algorithms and a generalized, automated model hyper-parameter selection process. Several high performance machine learning algorithms are interfaced for efficient data set specific selection of the statistical method, promoting model accuracy. Using the high performance machine learning algorithms of AZOrange does not require programming knowledge as flexible applications can be created, not only at a scripting level, but also in a graphical programming environment. Conclusions: AZOrange is a step towards meeting the needs for an Open Source high performance machine learning platform, supporting the efficient development of hig
Magnesium alloy matrix quality is important for the quality of coating oil the surface, and thus affecting the final performance of magnesium alloy. This paper developed a method to the abrasive belt grinding as a pre...
详细信息
ISBN:
(纸本)9780878493401
Magnesium alloy matrix quality is important for the quality of coating oil the surface, and thus affecting the final performance of magnesium alloy. This paper developed a method to the abrasive belt grinding as a pre-treatment process for magnesium alloy. Based oil the orthogonal test in the abrasive belt grinding of magnesium alloy, the effect of the processing parameters oil grinding force and roughness has been studied. Finally. a predicting model of the grinding force and surface roughness was established by means of the neuralnetworks. This model was verified from both the theoretical and experimental facets. The results showed that the model call be used to describe the influence of some machine tool inputs
暂无评论