The use of household solid energy for cooking is a key factor of environmental health risk. China still has a large share of households relying on solid fuels as a primary source of energy. Clarifying the determinants...
详细信息
The use of household solid energy for cooking is a key factor of environmental health risk. China still has a large share of households relying on solid fuels as a primary source of energy. Clarifying the determinants that drive energy choice in China's households is fundamental to promote household energy transition. We integrate the least absolute shrinkage and selection operator (lasso) algorithm and multinomial Logit model into identifying the determinants of energy choice for household cooking in China by the Chinese Family Panel Studies (CFPS) data. The economic situation is an important factor of household cooking energy transition. Household expenditure is more important than household income. Income is an important factor, but the influence of off-farm employment is more important than income. Higher levels of health and household heads with children are more inclined to use clean energy. The education level of household head, living conditions, and the accessibility and affordability of energy are important factors of energy choice for household cooking. Our study expands the literature on the determinants of energy choice for household cooking and provides valuable supports for policy formulation of household cooking energy transition in China.
Active noise control (ANC) can be applied to attenuate the scattered sound from an object, rendering it invisible to incident waves. This study proposes two secondary loudspeaker placement optimization methods for mul...
详细信息
Active noise control (ANC) can be applied to attenuate the scattered sound from an object, rendering it invisible to incident waves. This study proposes two secondary loudspeaker placement optimization methods for multizone ANC of impulsive scattered sound from a rigid cylinder. The first method is frequency-domain weighted least absolute shrinkage and selection operator (lasso) algorithm, and the second method is a time-domain iterative algorithm. Based on the two methods, a broadband feedforward ANC system is presented to suppress impulsive forward-scattered and backward-scattered sound. The experimental results show that compared with the configuration of uniformly placed loudspeakers and traditional lasso algorithms, the proposed weighted lasso algorithm and iterative algorithm achieve better control performance in the target and observing areas with less power when controlling 500 Hz-1000 Hz impulsive scattered sound.
Esophageal cancer is a heterogeneous malignant tumor. Considering the impact on the postoperative survival with esophageal cancer patients of the blood indicators, constructing a staging system which is superior to th...
详细信息
Esophageal cancer is a heterogeneous malignant tumor. Considering the impact on the postoperative survival with esophageal cancer patients of the blood indicators, constructing a staging system which is superior to the TNM staging system would be helpful to improve the prognosis of patients. In this paper, the blood indicators of esophageal cancer patients are analyzed by lasso algorithm, Receiver Operating Characteristic curve analysis, and Kaplan-Meier survival analysis. Neutrophil count (NEUT) and prothrombin time (PT) are found to be related to postoperative survival of esophageal cancer patients. Based on TNM stages, NEUT, and PT, the TNM-NPT esophageal cancer prognosis model is established by multiple logistic regression method. The established TNM-NPT prognostic model is superior to the TNM stages in predicting the survival rate of patients with esophageal cancer. The TNM-NPT prognostic staging system is constructed by ROC curve, and TNM-NPT stages are proved to have great classification accuracy by Kaplan-Meier survival analysis. The TNM-NPT prognostic staging system is well predicted by Cuckoo search algorithm-support vector machine with 98.43% accuracy. Therefore, the constructed TNM-NPT prognostic staging system can be successfully used in future clinical studies of esophageal cancer.
Nitrogen is the main nutrient element in the growth process of white radish, and accurate monitoring of radish leaf nitrogen content (LNC) is an important guide for precise fertilization decisions for radish in the fi...
详细信息
Nitrogen is the main nutrient element in the growth process of white radish, and accurate monitoring of radish leaf nitrogen content (LNC) is an important guide for precise fertilization decisions for radish in the field. Using white radish LNC monitoring as an object, research on radish nitrogen hyperspectral estimation methods was carried out based on leaf hyperspectral and field sample nitrogen data at multiple growth stages using feature selection and integrated learning algorithm models. First, the Vegetation Index (VI) was constructed from hyperspectral data. We extracted sensitive features of hyperspectral data and VI response to radish LNC based on Pearson's feature-selection approach. Second, a stacking-integrated learning approach is proposed using machine learning algorithms such as Support Vector Machine (SVM), Random Forest (RF), and Ridge and K-Nearest Neighbor (KNN) as the base model in the first layer of the architecture, and the lasso algorithm as the meta-model in the second layer of the architecture, to realize the hyperspectral estimation of radish LNC. The analysis results show the following: (1) The sensitive bands of the radish LNC are mainly centered around 600-700 nm and 1950 nm, and the constructed sensitive VIs are also concentrated in this band range. (2) The Stacking model with spectral features as inputs achieved good prediction accuracy at the radish spectral leaf, with R2 = 0.7, MAE = 0.16, MSE = 0.05 estimated over the whole growth stage of radish. (3) The lasso algorithm with variable filtering function was chosen as the meta-model, which has a redundant model-selection effect on the base model and helps to improve the quality of the integrated learning framework. This study demonstrates the potential of the stacking-integrated learning method based on hyperspectral data for spectral estimation of nitrogen content in radish at multiple growth stages.
The objectives of this Perspective paper are to review some recent advances in sparse feature selection for regression and classification, as well as compressed sensing, and to discuss how these might be used to devel...
详细信息
The objectives of this Perspective paper are to review some recent advances in sparse feature selection for regression and classification, as well as compressed sensing, and to discuss how these might be used to develop tools to advance personalized cancer therapy. As an illustration of the possibilities, a new algorithm for sparse regression is presented and is applied to predict the time to tumour recurrence in ovarian cancer. A new algorithm for sparse feature selection in classification problems is presented, and its validation in endometrial cancer is briefly discussed. Some open problems are also presented.
LF(LADLE FURNACE) refining technology is the key process to regulate the temperature in steelmaking process. To predict the end temperature of molten steel in LF, this paper proposes a new data preprocessing technique...
详细信息
LF(LADLE FURNACE) refining technology is the key process to regulate the temperature in steelmaking process. To predict the end temperature of molten steel in LF, this paper proposes a new data preprocessing technique based on feature extraction and clustering. Firstly, random forest algorithm was used to predict the temperature, the predictive hit rate of error within ± 10°C was 73.18%. The lasso algorithm and K-means algorithm was used for feature extraction and clustering. After improvement, the prediction accuracy of the LF end temperature of error within ± 10°C was about 88.16%. The results show that this improvement has high prediction accuracy in the prediction about the end temperature of molten steel in LF refining.
暂无评论