Although social networking sites have emerged as the primary source of information for young peop... more Although social networking sites have emerged as the primary source of information for young people, there is a dearth of knowledge concerning the underlying associations between differential aspects of social media overload and whether social media overload ultimately influenced people’s negative coping strategies during the prolonged COVID-19 pandemic. In order to fill this gap in existing knowledge, the current research employed the stressor–strain–outcome (SSO) theoretical paradigm to explicate social media fatigue and negative coping strategies from a technostress perspective. The study used cross-sectional methodology, whereby 618 valid questionnaire responses were gathered from WeChat users to assess the conceptual model. The obtained outcomes demonstrated that information overload and communication overload positively impacted young people’s fatigue. Furthermore, these two patterns of perceived overload heighten social media fatigue, which ultimately leads to young people’s ...
Introduction Tumor immune microenvironment (TIME) plays a vital role in breast cancer development... more Introduction Tumor immune microenvironment (TIME) plays a vital role in breast cancer development, treatment resistance, and prognosis. This study evaluates the association of TIME profiling and 21-gene recurrence score (RS) in early Luminal breast cancer patients. Methods ER+ /HER2-, pN0 breast cancer patients with available RS results who received surgery between January 2009 and December 2013 were enrolled. TIME markers, including stromal tumor infiltrating lymphocytes (TILs), CD3, CD4, CD8, and tumor PD-L1 expression, were comprehensively analyzed. Association of TIME markers with RS, as well as their correlation with breast cancer-specific survival (BCSS) were tested. Results Overall, 385 patients were included, of whom 341 (88.6%) had TILs ≤10%. TIME markers were positively but moderately correlated with each other (Spearman r 0.28–0.53, all P < 0.05). Continuous RS showed a weak correlation with continuous TILs, CD3, CD8, and PD-L1. Regarding single gene mRNA level in the ...
Laryngeal cancer is a common head and neck malignant cancer type. However, effective biomarkers f... more Laryngeal cancer is a common head and neck malignant cancer type. However, effective biomarkers for diagnosis are lacking and pathogenesis is unclear. Lipidomics is a powerful tool for identifying biomarkers and explaining disease mechanisms. Hence, in this study, non-targeted lipidomics based on ultra-performance liquid chromatography–quadrupole time of flight–mass spectrometry (UHPLC-QTOF-MS) were applied to screen the differential lipid metabolites in serum and allowed for exploration of the remodeled lipid metabolism of laryngeal cancer, laryngeal benign tumor patients, and healthy crowds. Multivariate analysis and univariate analysis were combined to screen for differential lipid metabolites among the three groups. The results showed that, across a total of 57 lipid metabolic markers that were screened, the regulation of the lipid metabolism network occurred mainly in phosphatidylcholine (PC), lysophosphatidylcholine (LPC), and sphingomyelin (SM) metabolism. Of note, the concen...
BackgroundPrimary ovarian insufficiency (POI) is gaining awareness as its prevalence increases an... more BackgroundPrimary ovarian insufficiency (POI) is gaining awareness as its prevalence increases and its effect on patients is extremely negative. To date, several therapies have been designed to treat POI, but the conclusions are conflicting, in part, due to inconsistent evaluation methods. Thus, we explore a multi-index of ovarian function assessment methods to evaluate the recovery of ovarian function after various therapies in order to evaluate effectiveness in a more comprehensive manner.AimThe purpose of this review is to assess the effectiveness of various therapies to recover ovarian function in patients with POI. The primary outcome measures were anti-Müllerian hormone (AMH) levels, follicle stimulating hormone (FSH) levels, and antral follicle count (AFC). The secondary outcomes included the change of mean ovarian volume, menstruation recovery, and pregnancy rate.MethodsOur systematic searching including PubMed, Web of Science, Cochrane, and Embase databases was conducted to...
Chronic stress is an emotional experience that occurs when people encounter something they cannot... more Chronic stress is an emotional experience that occurs when people encounter something they cannot adapt to. Repeated chronic stress increases the risk of a variety of diseases, such as cardiovascular disease, depression, endocrine disease, inflammation and cancer. A growing body of research has shown that there is a link between chronic stress and tumor occurrence in both animal studies and clinical studies. Chronic stress activates the neuroendocrine system (hypothalamic-pituitary-adrenal axis) and sympathetic nervous system. Stress hormones promote the occurrence and development of tumors through various mechanisms. In addition, chronic stress also affects the immune function of the body, leading to the decline of immune monitoring ability and promote the occurrence of tumors. The mechanisms of chronic stress leading to tumor include inflammation, autophagy and epigenetics. These factors increase the proliferation and invasion capacity of tumor cells and alter the tumor microenvir...
The modern manufacturing industry is more and more large-scale, flexible and intelligent. The mac... more The modern manufacturing industry is more and more large-scale, flexible and intelligent. The machine failures are also more complicated. In order to analyze the importance levels of failures and focus on the most possible failure during the production process, this paper proposes a machine failure sorting model based on directed graph and DEMATEL, which can eliminate the uncertainty of expert judgment, determine the direction of failures and sort each failure according to its centrality degree. An empirical analysis is presented to show the calculation process step by step. We can find that this model can help decision-makers to quickly locate the important failure and reduce production problems and production costs caused by failure.
The Landslide,which is caused by mining activities, has become an important factor which constrai... more The Landslide,which is caused by mining activities, has become an important factor which constrains the sustainable development of mining area. Thus it becomes very important to predict the landslide in order to reduce and even to avoid the loss in hazards. The paper is to address the landslide prediction problem in the environment of GIS by establishing the landslide prediction model based on SVM (support vector machine). Through differentiating the stability, it achieves the prediction of the landslide hazard. In the process of modelling, the impact factors of the landslide are analyzed with the spatial analysis function of GIS. Since the model parameters are determined by cross validation and grid search, and the sample data are trained by LIBSVM, traditional support vector machine will be optimized, and its stability and accuracy will be greatly increased. This gives a strong support to the avoidance and reduction of the hazard in mining area. * Corresponding author. E-mail addr...
We are interested in designing a Project-Based Learning Management System (PBLMS) for high school... more We are interested in designing a Project-Based Learning Management System (PBLMS) for high school students. In this paper, we focus on the study of ergonomics of existing PBLMSs. We first analyze four different PBLMSs regarding three points: aims, functionalities and indicators. We particularly focus on the indicators and analyze their attributes: purpose(s), concept(s), data construction and visualization. Based on this analysis we discuss the utility, the usability and the acceptability of the studied systems according to their functionalities, the types of visualization and the users. We finally conclude with some directions of our future research work.
The data warehouse’s fact table can be considered as a multi-dimensional vector point dataset. In... more The data warehouse’s fact table can be considered as a multi-dimensional vector point dataset. In this dataset, each point’s measure property can be transformed as the influence power against its neighbor points. If one point’s measure is larger, it would have more influence power to attract its neighbor points, and its neighbors would have a trend to be absorbed by this point. Being inspired by the Gravitational Clustering Approach (GCA), the paper introduces a new method named IPCA (Influence Power-based Clustering Algorithm) for clustering these vector points. The paper first defines several concepts and names the local strongest power points as Self-Strong Points (SSPs). Using these SSPs as the initial clustering centers, IPCA constructs serials of hierarchical trees which are rooted by these SSPs. Because there are only a few SSPs left, by using each SSPs’ influence power, the paper adopts the neighbor function clustering method to define the clustering criteria function, and g...
Product quality is the lifeblood of manufacturing enterprises. Under the background of intelligen... more Product quality is the lifeblood of manufacturing enterprises. Under the background of intelligent manufacture, quality prediction is affected by lots of intricate elements. Furthermore, the customization level of products is one of the important factors which can support the enterprises in the increasingly fierce competition. Therefore, the high customization level means that it is impossible to collect a large quantity of quality data because of multi variety and small batch production mode. This paper proposes the principle and the framework of quality prediction in intelligent manufacturing. The framework adopts the theory of combinational prediction because it is more stable, more reliable and more accurate than single prediction model. The research of this paper will supply a new prediction method for the manufacturers and improve the accuracy of quality prediction and reduces the production risk.
BackgroundChemoresistance is emerging as a major barrier to successful treatment in acute myeloid... more BackgroundChemoresistance is emerging as a major barrier to successful treatment in acute myeloid leukemia (AML), and bone marrow stromal cells (BMSCs) protect leukemia cells from chemotherapy eventually leading to recurrence. This study was designed to investigate the role of p21-activated kinase 1 (PAK1) in AML progression and chemosensitivity, highlighting the mechanism of stroma-mediated chemoresistance.MethodsThe GEPIA and TCGA datasets were used to analyze the relationship between PAK1 mRNA expression and various clinical parameters of AML patients. Cell proliferation and apoptosis were examined to evaluate the role of PAK1 on chemosensitivity in AML by silencing PAK1 with shRNA or small molecular inhibitor. Human BMSC (HS-5) was utilized to mimic the leukemia bone marrow microenvironment (BMM) in vitro, and co-culture model was established to investigate the role of PAK1 in BMSC-mediated drug resistance.Resultsp21-activated kinase 1 high expression was shown to be associated ...
The building is an indispensable part of human life which provides a place for people to live, st... more The building is an indispensable part of human life which provides a place for people to live, study, work, and engage in various cultural and social activities. People are exposed to earthquakes, and damaged buildings caused by earthquakes are one of the main threats. It is essential to retrieve the detailed information of affected buildings after earthquakes. Very high-resolution satellite imagery plays a key role in retrieving building damage information since it captures imagery quickly and effectively after the disaster. In this paper, the pretrained Visual Geometry Group (VGG)Net model was applied for identifying collapsed buildings induced by the 2010 Haiti earthquake using pre- and post-event remotely sensed space imagery, and the fine-tuned pretrained VGGNet model was compared with the VGGNet model trained from scratch. The effects of dataset augmentation and freezing different intermediate layers were also explored. The experimental results demonstrated that the fine-tuned...
Earthquake is one of the most devastating natural disasters that threaten human life. It is vital... more Earthquake is one of the most devastating natural disasters that threaten human life. It is vital to retrieve the building damage status for planning rescue and reconstruction after an earthquake. In cases when the number of completely collapsed buildings is far less than intact or less-affected buildings (e.g., the 2010 Haiti earthquake), it is difficult for the classifier to learn the minority class samples, due to the imbalance learning problem. In this study, the convolutional neural network (CNN) was utilized to identify collapsed buildings from post-event satellite imagery with the proposed workflow. Producer accuracy (PA), user accuracy (UA), overall accuracy (OA), and Kappa were used as evaluation metrics. To overcome the imbalance problem, random over-sampling, random under-sampling, and cost-sensitive methods were tested on selected test A and test B regions. The results demonstrated that the building collapsed information can be retrieved by using post-event imagery. Sque...
The accurate and quick derivation of the distribution of damaged building must be considered esse... more The accurate and quick derivation of the distribution of damaged building must be considered essential for the emergency response. With the success of deep learning, there is an increasing interest to apply it for earthquake-induced building damage mapping, and its performance has not been compared with conventional methods in detecting building damage after the earthquake. In the present study, the performance of grey-level co-occurrence matrix texture and convolutional neural network (CNN) features were comparatively evaluated with the random forest classifier. Pre- and post-event very high-resolution (VHR) remote sensing imagery were considered to identify collapsed buildings after the 2010 Haiti earthquake. Overall accuracy (OA), allocation disagreement (AD), quantity disagreement (QD), Kappa, user accuracy (UA), and producer accuracy (PA) were used as the evaluation metrics. The results showed that the CNN feature with random forest method had the best performance, achieving an...
Soil spectra are often measured in the laboratory, and there is an increasing number of large-sca... more Soil spectra are often measured in the laboratory, and there is an increasing number of large-scale soil spectral libraries establishing across the world. However, calibration models developed from soil libraries are difficult to apply to spectral data acquired from the field or space. Transfer learning has the potential to bridge the gap and make the calibration model transferrable from one sensor to another. The objective of this study is to explore the potential of transfer learning for soil spectroscopy and its performance on soil clay content estimation using hyperspectral data. First, a one-dimensional convolutional neural network (1D-CNN) is used on Land Use/Land Cover Area Frame Survey (LUCAS) mineral soils. To evaluate whether the pre-trained 1D-CNN model was transferrable, LUCAS organic soils were used to fine-tune and validate the model. The fine-tuned model achieved a good accuracy (coefficient of determination (R2) = 0.756, root-mean-square error (RMSE) = 7.07 and ratio...
Aiming at reducing computed tomography (CT) scan radiation while ensuring CT image quality, a new... more Aiming at reducing computed tomography (CT) scan radiation while ensuring CT image quality, a new low-dose CT super-resolution reconstruction method based on combining a random forest with coupled dictionary learning is proposed. The random forest classifier finds the optimal solution of the mapping relationship between low-dose CT (LDCT) images and high-dose CT (HDCT) images and then completes CT image reconstruction by coupled dictionary learning. An iterative method is developed to improve robustness, the important coefficients for the tree structure are discussed and the optimal solutions are reported. The proposed method is further compared with a traditional interpolation method. The results show that the proposed algorithm can obtain a higher peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) and has better ability to reduce noise and artifacts. This method can be applied to many different medical imaging fields in the future and the addition...
Although social networking sites have emerged as the primary source of information for young peop... more Although social networking sites have emerged as the primary source of information for young people, there is a dearth of knowledge concerning the underlying associations between differential aspects of social media overload and whether social media overload ultimately influenced people’s negative coping strategies during the prolonged COVID-19 pandemic. In order to fill this gap in existing knowledge, the current research employed the stressor–strain–outcome (SSO) theoretical paradigm to explicate social media fatigue and negative coping strategies from a technostress perspective. The study used cross-sectional methodology, whereby 618 valid questionnaire responses were gathered from WeChat users to assess the conceptual model. The obtained outcomes demonstrated that information overload and communication overload positively impacted young people’s fatigue. Furthermore, these two patterns of perceived overload heighten social media fatigue, which ultimately leads to young people’s ...
Introduction Tumor immune microenvironment (TIME) plays a vital role in breast cancer development... more Introduction Tumor immune microenvironment (TIME) plays a vital role in breast cancer development, treatment resistance, and prognosis. This study evaluates the association of TIME profiling and 21-gene recurrence score (RS) in early Luminal breast cancer patients. Methods ER+ /HER2-, pN0 breast cancer patients with available RS results who received surgery between January 2009 and December 2013 were enrolled. TIME markers, including stromal tumor infiltrating lymphocytes (TILs), CD3, CD4, CD8, and tumor PD-L1 expression, were comprehensively analyzed. Association of TIME markers with RS, as well as their correlation with breast cancer-specific survival (BCSS) were tested. Results Overall, 385 patients were included, of whom 341 (88.6%) had TILs ≤10%. TIME markers were positively but moderately correlated with each other (Spearman r 0.28–0.53, all P < 0.05). Continuous RS showed a weak correlation with continuous TILs, CD3, CD8, and PD-L1. Regarding single gene mRNA level in the ...
Laryngeal cancer is a common head and neck malignant cancer type. However, effective biomarkers f... more Laryngeal cancer is a common head and neck malignant cancer type. However, effective biomarkers for diagnosis are lacking and pathogenesis is unclear. Lipidomics is a powerful tool for identifying biomarkers and explaining disease mechanisms. Hence, in this study, non-targeted lipidomics based on ultra-performance liquid chromatography–quadrupole time of flight–mass spectrometry (UHPLC-QTOF-MS) were applied to screen the differential lipid metabolites in serum and allowed for exploration of the remodeled lipid metabolism of laryngeal cancer, laryngeal benign tumor patients, and healthy crowds. Multivariate analysis and univariate analysis were combined to screen for differential lipid metabolites among the three groups. The results showed that, across a total of 57 lipid metabolic markers that were screened, the regulation of the lipid metabolism network occurred mainly in phosphatidylcholine (PC), lysophosphatidylcholine (LPC), and sphingomyelin (SM) metabolism. Of note, the concen...
BackgroundPrimary ovarian insufficiency (POI) is gaining awareness as its prevalence increases an... more BackgroundPrimary ovarian insufficiency (POI) is gaining awareness as its prevalence increases and its effect on patients is extremely negative. To date, several therapies have been designed to treat POI, but the conclusions are conflicting, in part, due to inconsistent evaluation methods. Thus, we explore a multi-index of ovarian function assessment methods to evaluate the recovery of ovarian function after various therapies in order to evaluate effectiveness in a more comprehensive manner.AimThe purpose of this review is to assess the effectiveness of various therapies to recover ovarian function in patients with POI. The primary outcome measures were anti-Müllerian hormone (AMH) levels, follicle stimulating hormone (FSH) levels, and antral follicle count (AFC). The secondary outcomes included the change of mean ovarian volume, menstruation recovery, and pregnancy rate.MethodsOur systematic searching including PubMed, Web of Science, Cochrane, and Embase databases was conducted to...
Chronic stress is an emotional experience that occurs when people encounter something they cannot... more Chronic stress is an emotional experience that occurs when people encounter something they cannot adapt to. Repeated chronic stress increases the risk of a variety of diseases, such as cardiovascular disease, depression, endocrine disease, inflammation and cancer. A growing body of research has shown that there is a link between chronic stress and tumor occurrence in both animal studies and clinical studies. Chronic stress activates the neuroendocrine system (hypothalamic-pituitary-adrenal axis) and sympathetic nervous system. Stress hormones promote the occurrence and development of tumors through various mechanisms. In addition, chronic stress also affects the immune function of the body, leading to the decline of immune monitoring ability and promote the occurrence of tumors. The mechanisms of chronic stress leading to tumor include inflammation, autophagy and epigenetics. These factors increase the proliferation and invasion capacity of tumor cells and alter the tumor microenvir...
The modern manufacturing industry is more and more large-scale, flexible and intelligent. The mac... more The modern manufacturing industry is more and more large-scale, flexible and intelligent. The machine failures are also more complicated. In order to analyze the importance levels of failures and focus on the most possible failure during the production process, this paper proposes a machine failure sorting model based on directed graph and DEMATEL, which can eliminate the uncertainty of expert judgment, determine the direction of failures and sort each failure according to its centrality degree. An empirical analysis is presented to show the calculation process step by step. We can find that this model can help decision-makers to quickly locate the important failure and reduce production problems and production costs caused by failure.
The Landslide,which is caused by mining activities, has become an important factor which constrai... more The Landslide,which is caused by mining activities, has become an important factor which constrains the sustainable development of mining area. Thus it becomes very important to predict the landslide in order to reduce and even to avoid the loss in hazards. The paper is to address the landslide prediction problem in the environment of GIS by establishing the landslide prediction model based on SVM (support vector machine). Through differentiating the stability, it achieves the prediction of the landslide hazard. In the process of modelling, the impact factors of the landslide are analyzed with the spatial analysis function of GIS. Since the model parameters are determined by cross validation and grid search, and the sample data are trained by LIBSVM, traditional support vector machine will be optimized, and its stability and accuracy will be greatly increased. This gives a strong support to the avoidance and reduction of the hazard in mining area. * Corresponding author. E-mail addr...
We are interested in designing a Project-Based Learning Management System (PBLMS) for high school... more We are interested in designing a Project-Based Learning Management System (PBLMS) for high school students. In this paper, we focus on the study of ergonomics of existing PBLMSs. We first analyze four different PBLMSs regarding three points: aims, functionalities and indicators. We particularly focus on the indicators and analyze their attributes: purpose(s), concept(s), data construction and visualization. Based on this analysis we discuss the utility, the usability and the acceptability of the studied systems according to their functionalities, the types of visualization and the users. We finally conclude with some directions of our future research work.
The data warehouse’s fact table can be considered as a multi-dimensional vector point dataset. In... more The data warehouse’s fact table can be considered as a multi-dimensional vector point dataset. In this dataset, each point’s measure property can be transformed as the influence power against its neighbor points. If one point’s measure is larger, it would have more influence power to attract its neighbor points, and its neighbors would have a trend to be absorbed by this point. Being inspired by the Gravitational Clustering Approach (GCA), the paper introduces a new method named IPCA (Influence Power-based Clustering Algorithm) for clustering these vector points. The paper first defines several concepts and names the local strongest power points as Self-Strong Points (SSPs). Using these SSPs as the initial clustering centers, IPCA constructs serials of hierarchical trees which are rooted by these SSPs. Because there are only a few SSPs left, by using each SSPs’ influence power, the paper adopts the neighbor function clustering method to define the clustering criteria function, and g...
Product quality is the lifeblood of manufacturing enterprises. Under the background of intelligen... more Product quality is the lifeblood of manufacturing enterprises. Under the background of intelligent manufacture, quality prediction is affected by lots of intricate elements. Furthermore, the customization level of products is one of the important factors which can support the enterprises in the increasingly fierce competition. Therefore, the high customization level means that it is impossible to collect a large quantity of quality data because of multi variety and small batch production mode. This paper proposes the principle and the framework of quality prediction in intelligent manufacturing. The framework adopts the theory of combinational prediction because it is more stable, more reliable and more accurate than single prediction model. The research of this paper will supply a new prediction method for the manufacturers and improve the accuracy of quality prediction and reduces the production risk.
BackgroundChemoresistance is emerging as a major barrier to successful treatment in acute myeloid... more BackgroundChemoresistance is emerging as a major barrier to successful treatment in acute myeloid leukemia (AML), and bone marrow stromal cells (BMSCs) protect leukemia cells from chemotherapy eventually leading to recurrence. This study was designed to investigate the role of p21-activated kinase 1 (PAK1) in AML progression and chemosensitivity, highlighting the mechanism of stroma-mediated chemoresistance.MethodsThe GEPIA and TCGA datasets were used to analyze the relationship between PAK1 mRNA expression and various clinical parameters of AML patients. Cell proliferation and apoptosis were examined to evaluate the role of PAK1 on chemosensitivity in AML by silencing PAK1 with shRNA or small molecular inhibitor. Human BMSC (HS-5) was utilized to mimic the leukemia bone marrow microenvironment (BMM) in vitro, and co-culture model was established to investigate the role of PAK1 in BMSC-mediated drug resistance.Resultsp21-activated kinase 1 high expression was shown to be associated ...
The building is an indispensable part of human life which provides a place for people to live, st... more The building is an indispensable part of human life which provides a place for people to live, study, work, and engage in various cultural and social activities. People are exposed to earthquakes, and damaged buildings caused by earthquakes are one of the main threats. It is essential to retrieve the detailed information of affected buildings after earthquakes. Very high-resolution satellite imagery plays a key role in retrieving building damage information since it captures imagery quickly and effectively after the disaster. In this paper, the pretrained Visual Geometry Group (VGG)Net model was applied for identifying collapsed buildings induced by the 2010 Haiti earthquake using pre- and post-event remotely sensed space imagery, and the fine-tuned pretrained VGGNet model was compared with the VGGNet model trained from scratch. The effects of dataset augmentation and freezing different intermediate layers were also explored. The experimental results demonstrated that the fine-tuned...
Earthquake is one of the most devastating natural disasters that threaten human life. It is vital... more Earthquake is one of the most devastating natural disasters that threaten human life. It is vital to retrieve the building damage status for planning rescue and reconstruction after an earthquake. In cases when the number of completely collapsed buildings is far less than intact or less-affected buildings (e.g., the 2010 Haiti earthquake), it is difficult for the classifier to learn the minority class samples, due to the imbalance learning problem. In this study, the convolutional neural network (CNN) was utilized to identify collapsed buildings from post-event satellite imagery with the proposed workflow. Producer accuracy (PA), user accuracy (UA), overall accuracy (OA), and Kappa were used as evaluation metrics. To overcome the imbalance problem, random over-sampling, random under-sampling, and cost-sensitive methods were tested on selected test A and test B regions. The results demonstrated that the building collapsed information can be retrieved by using post-event imagery. Sque...
The accurate and quick derivation of the distribution of damaged building must be considered esse... more The accurate and quick derivation of the distribution of damaged building must be considered essential for the emergency response. With the success of deep learning, there is an increasing interest to apply it for earthquake-induced building damage mapping, and its performance has not been compared with conventional methods in detecting building damage after the earthquake. In the present study, the performance of grey-level co-occurrence matrix texture and convolutional neural network (CNN) features were comparatively evaluated with the random forest classifier. Pre- and post-event very high-resolution (VHR) remote sensing imagery were considered to identify collapsed buildings after the 2010 Haiti earthquake. Overall accuracy (OA), allocation disagreement (AD), quantity disagreement (QD), Kappa, user accuracy (UA), and producer accuracy (PA) were used as the evaluation metrics. The results showed that the CNN feature with random forest method had the best performance, achieving an...
Soil spectra are often measured in the laboratory, and there is an increasing number of large-sca... more Soil spectra are often measured in the laboratory, and there is an increasing number of large-scale soil spectral libraries establishing across the world. However, calibration models developed from soil libraries are difficult to apply to spectral data acquired from the field or space. Transfer learning has the potential to bridge the gap and make the calibration model transferrable from one sensor to another. The objective of this study is to explore the potential of transfer learning for soil spectroscopy and its performance on soil clay content estimation using hyperspectral data. First, a one-dimensional convolutional neural network (1D-CNN) is used on Land Use/Land Cover Area Frame Survey (LUCAS) mineral soils. To evaluate whether the pre-trained 1D-CNN model was transferrable, LUCAS organic soils were used to fine-tune and validate the model. The fine-tuned model achieved a good accuracy (coefficient of determination (R2) = 0.756, root-mean-square error (RMSE) = 7.07 and ratio...
Aiming at reducing computed tomography (CT) scan radiation while ensuring CT image quality, a new... more Aiming at reducing computed tomography (CT) scan radiation while ensuring CT image quality, a new low-dose CT super-resolution reconstruction method based on combining a random forest with coupled dictionary learning is proposed. The random forest classifier finds the optimal solution of the mapping relationship between low-dose CT (LDCT) images and high-dose CT (HDCT) images and then completes CT image reconstruction by coupled dictionary learning. An iterative method is developed to improve robustness, the important coefficients for the tree structure are discussed and the optimal solutions are reported. The proposed method is further compared with a traditional interpolation method. The results show that the proposed algorithm can obtain a higher peak signal-to-noise ratio (PSNR) and structural similarity index measurement (SSIM) and has better ability to reduce noise and artifacts. This method can be applied to many different medical imaging fields in the future and the addition...
Uploads