scholarly journals Assessment of Tomato Maturity in Different Layers by Spatially Resolved Spectroscopy

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7229
Author(s):  
Yuping Huang ◽  
Wan Si ◽  
Kunjie Chen ◽  
Ye Sun
Keyword(s):  
Model Performance ◽  
Classification Model ◽  
Support Vector ◽  
Eating Quality ◽  
Spatially Resolved ◽  
The Mean ◽  
Spatially Resolved Spectroscopy ◽  
Fruit Shelf Life ◽  
Measurement Location ◽  
Two Sides

Tomato maturity is important to determine the fruit shelf life and eating quality. The objective of this research was to evaluate tomato maturity in different layers by using a newly developed spatially resolved spectroscopic system over the spectral region of 550–1650 nm. Thirty spatially resolved spectra were obtained for 600 tomatoes, 100 for each of the six maturity stages (i.e., green, breaker, turning, pink, light red, and red). Support vector machine discriminant analysis (SVMDA) models were first developed for each of individual spatially resolved (SR) spectra to compare the classification results of two sides. The mean spectra of two sides with the same source-detector distances were employed to determine the model performance of different layers. SR combination by averaging all the SR spectra was also subject to comparison with the classification model performance. The results showed large source-detector distances would be helpful for evaluating tomato maturity, and the mean_SR 15 obtained excellent classification results with the total classification accuracy of 98.3%. Moreover, the classification results were distinct for two sides of the probe, which demonstrated even if in the same source-detector distances, the classification results were influenced by the measurement location due to the heterogeneity for tomato. The mean of all SR spectra could only improve the classification results based on the first three mean_SR spectra, but could not obtain the accuracy as good as the following mean_SR spectra. This study demonstrated that spatially resolved spectroscopy has potential for assessing tomato maturity in different layers.

scholarly journals The invasion depth measurement of bladder cancer using T2-weighted magnetic resonance imaging

2020 ◽  
Vol 19 (1) ◽  
Author(s):  
Yang Liu ◽  
Haojie Zheng ◽  
Xiaopan Xu ◽  
Xi Zhang ◽  
Peng Du ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Bladder Wall ◽  
Classification Model ◽  
Support Vector ◽  
Dice Similarity Coefficient ◽  
Wall Region ◽  
Feature Subset ◽  
Invasion Depth ◽  
Depth Measurement ◽  
The Mean

Abstract Background Invasion depth is an important index for staging and clinical treatment strategy of bladder cancer (BCa). The aim of this study was to investigate the feasibility of segmenting the BCa region from bladder wall region on MRI, and quantitatively measuring the invasion depth of the tumor mass in bladder lumen for further clinical decision-making. This retrospective study involved 20 eligible patients with postoperatively pathologically confirmed BCa. It was conducted in the following steps: (1) a total of 1159 features were extracted from each voxel of both the certain cancerous and wall tissues with the T2-weighted (T2W) MRI data; (2) the support vector machine (SVM)-based recursive feature elimination (RFE) method was implemented to first select an optimal feature subset, and then develop the classification model for the precise separation of the cancerous regions; (3) after excluding the cancerous region from the bladder wall, the three-dimensional bladder wall thickness (BWT) was calculated using Laplacian method, and the invasion depth of BCa was eventually defined by the subtraction of the mean BWT excluding the cancerous region and the minimum BWT of the cancerous region. Results The segmented results showed a promising accuracy, with the mean Dice similarity coefficient of 0.921. The “soft boundary” defined by the voxels with the probabilities between 0.1 and 0.9 could demonstrate the overlapped region of cancerous and wall tissues. The invasion depth calculated from proposed segmentation method was compared with that from manual segmentation, with a mean difference of 0.277 mm. Conclusion The proposed strategy could accurately segment the BCa region, and, as the first attempt, realize the quantitative measurement of BCa invasion depth.

scholarly journals Early prediction of putamen imaging features in HIV-associated neurocognitive impairment syndrome

BMC Neurology ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Yu Qi ◽  
Man Xu ◽  
Wei Wang ◽  
Yuan-Yuan Wang ◽  
Jiao-Jiao Liu ◽  
...  
Keyword(s):  
Cognitive Impairment ◽  
Treatment Group ◽  
Early Stage ◽  
Neurocognitive Impairment ◽  
Classification Model ◽  
Support Vector ◽  
Imaging Features ◽  
Asymptomatic Neurocognitive Impairment ◽  
Clinical Variables ◽  
The Mean

Abstract Background To explore the correlation between the volume of putamen and brain cognitive impairment in patients with HIV and to predict the feasibility of early-stage HIV brain cognitive impairment through radiomics. Method Retrospective selection of 90 patients with HIV infection, including 36 asymptomatic neurocognitive impairment (ANI) patients and 54 pre-clinical ANI patients in Beijing YouAn Hospital. All patients received comprehensive neuropsychological assessment and MRI scanning. 3D Slicer software was used to acquire volume of interest (VOI) and radiomics features. Clinical variables and volume of putamen were compared between patients with ANI and pre-clinical ANI. The Kruskal Wallis test was used to analysis multiple comparisons between groups. The relationship between cognitive scores and VOI was compared using linear regression. For radiomics, principal component analysis (PCA) was used to reduce model overfitting and calculations and then a support vector machine (SVM) was used to build a binary classification model. For model performance evaluation, we used an accuracy, sensitivity, specificity and receiver operating characteristic curve (ROC). Result There were no significant differences in clinical variables between ANI group and pre-clinical-ANI group (P>0.05). The volume of bilateral putamen was significantly different between AHI group and pre-clinical group (P<0.05), but there was only a trend in the left putamen between ANI-treatment group and pre-clinical treatment group(P = 0.063). Reduced cognitive scores in Verbal Fluency, Attention/Working Memory, Executive Functioning, memory and Speed of Information Processing were negatively correlated with the increased VOI (P<0.05), but the correlation was relatively low. In diagnosing the ANI from pre-clinical ANI, the mean area under the ROC curves (AUC) were 0.85 ± 0.22, the mean sensitivity and specificity were 63.12 ± 5.51 and 94.25% ± 3.08%. Conclusion The volumes of putamen in patients with ANI may be larger than patients with pre-clinical ANI, the change of the volume of the putamen may have a certain process; there is a relationship between putamen and cognitive impairment, but the exact mechanism is unclear. Radiomics may be a useful tool for predicting early stage HAND in patients with HIV.

Demonstration of the applicability of visible and near-infrared spatially resolved spectroscopy for rapid and nondestructive wood classification

Holzforschung ◽  
2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Te Ma ◽  
Tetsuya Inagaki ◽  
Satoru Tsuchikawa
Keyword(s):  
Light Scattering ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Short Wave ◽  
Physical Structure ◽  
Support Vector ◽  
Spatially Resolved ◽  
Standard Normal Variate ◽  
Spatially Resolved Spectroscopy

AbstractAlthough visible and near-infrared (Vis-NIR) spectroscopy can rapidly and nondestructively identify wood species, the conventional spectrometer approach relies on the aggregate light absorption due to the chemical composition of wood and light scattering originating from the physical structure of wood. Hence, much of the work in this area is still limited to further spectral pretreatments, such as baseline correction and standard normal variate to reduce the light scattering effects. However, it should be emphasized that the light scattering rather than absorption in wood is dominant, and this must be effectively utilized to achieve highly accurate and robust wood classification. Here a novel method based on spatially resolved diffuse reflectance (wavelength range: 600–1000 nm) was demonstrated to classify 15 kinds of wood. A portable Vis-NIR spectral measurement system was designed according to previous simulations and experimental results. To simplify spectral data analysis (i.e., against overfitting), support vector machine (SVM) model was constructed for wood sample classification using principal component analysis (PCA) scores. The classification accuracies of 98.6% for five-fold cross-validation and 91.2% for test set validation were achieved. This study offers enhanced classification accuracy and robustness over other conventional nondestructive approaches for such various kinds of wood and sheds light on utilizing visible and short-wave NIR light scattering for wood classification.

scholarly journals Multimodal Early Alzheimer’s Detection, a Genetic Algorithm Approach with Support Vector Machines

Healthcare ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 971
Author(s):  
Ana Sánchez-Reyna ◽  
José Celaya-Padilla ◽  
Carlos Galván-Tejada ◽  
Huizilopoztli Luna-García ◽  
Hamurabi Gamboa-Rosales ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Model Performance ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Brain Morphology ◽  
Support Vector ◽  
Machine Model ◽  
Blind Test ◽  
Measure Model ◽  
Genetic Algorithm Approach

Alzheimer’s disease (AD) is a neurodegenerative disease that mainly affects older adults. Currently, AD is associated with certain hypometabolic biomarkers, beta-amyloid peptides, hyperphosphorylated tau protein, and changes in brain morphology. Accurate diagnosis of AD, as well as mild cognitive impairment (MCI) (prodromal stage of AD), is essential for early care of the disease. As a result, machine learning techniques have been used in recent years for the diagnosis of AD. In this research, we propose a novel methodology to generate a multivariate model that combines different types of features for the detection of AD. In order to obtain a robust biomarker, ADNI baseline data, clinical and neuropsychological assessments (1024 features) of 106 patients were used. The data were normalized, and a genetic algorithm was implemented for the selection of the most significant features. Subsequently, for the development and validation of the multivariate classification model, a support vector machine model was created, and a five-fold cross-validation with an AUC of 87.63% was used to measure model performance. Lastly, an independent blind test of our final model, using 20 patients not considered during the model construction, yielded an AUC of 100%.

scholarly journals The invasion depth measurement of bladder cancer using T2-weighted magnetic resonance imaging

2020 ◽  
Author(s):  
Yang Liu ◽  
Haojie Zheng ◽  
Xiaopan Xu ◽  
Xi Zhang ◽  
Peng Du ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Bladder Wall ◽  
Classification Model ◽  
Support Vector ◽  
Dice Similarity Coefficient ◽  
Wall Region ◽  
Feature Subset ◽  
Invasion Depth ◽  
Depth Measurement ◽  
The Mean

Abstract Background: Invasion depth is an important index for staging and clinical treatment strategy of bladder cancer (BCa). The aim of this study was to investigate the feasibility of segmenting the BCa region from bladder wall region on MRI, and quantitatively measuring the invasion depth of the tumor mass in bladder lumen for further clinical decision-making. This retrospective study involved 20 eligible patients with postoperatively pathologically-confirmed BCa. It was conducted in the following steps: (1) a total of 1159 features were extracted from each voxel of both the certain cancerous and wall tissues with the T2-weighted (T2W) MRI data; (2) the support vector machine (SVM)-based recursive feature elimination (RFE) method was implemented to first select an optimal feature subset, and then develop the classification model for the precise separation of the cancerous regions; (3) after excluding the cancerous region from the bladder wall, the three-dimensional bladder wall thickness (BWT) was calculated using Laplacian method, and the invasion depth of BCa was eventually defined by the subtraction of the mean BWT excluding the cancerous region and the minimum BWT of the cancerous region.Results: The segmented results showed a promising accuracy, with the mean Dice similarity coefficient of 0.921. The “soft boundary” defined by the voxels with the probabilities between 0.1 and 0.9 could demonstrate the overlapped region of cancerous and wall tissues. The invasion depth calculated from proposed segmentation method was compared with that from manual segmentation, with a mean difference of 0.277 mm.Conclusion: The proposed strategy could accurately segment the BCa region, and, as the first attempt, realize the quantitative measurement of BCa invasion depth.

scholarly journals The Invasion Depth Measurement of Bladder Cancer based on MRI

2020 ◽  
Author(s):  
Yang Liu ◽  
Haojie Zheng ◽  
Xiaopan Xu ◽  
Xi Zhang ◽  
Peng Du ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Bladder Wall ◽  
Classification Model ◽  
Support Vector ◽  
Dice Similarity Coefficient ◽  
Wall Region ◽  
Feature Subset ◽  
Invasion Depth ◽  
Depth Measurement ◽  
The Mean

Abstract Background: Invasion depth is an important index for staging and clinical treatment strategy of bladder cancer (BCa). The aim of this study was to investigate the feasibility of segmenting the BCa region from bladder wall region on MRI, and quantitatively measuring the invasion depth of the tumor mass in bladder lumen for further clinical decision-making. This retrospective study involved 20 eligible patients with postoperatively pathologically-confirmed BCa. It was conducted in the following steps: (1) a total of 1159 features were extracted from each voxel of both the certain cancerous and wall tissues with the T2-weighted (T2W) MRI data; (2) the support vector machine (SVM)-based recursive feature elimination (RFE) method was implemented to first select an optimal feature subset, and then develop the classification model for the precise separation of the cancerous regions; (3) after excluding the cancerous region from the bladder wall, the three-dimensional bladder wall thickness (BWT) was calculated using Laplacian method, and the invasion depth of BCa was eventually defined by the subtraction of the minimum BWT of the cancerous region and the mean BWT other than the cancerous region.Results: The segmented results showed a promising accuracy, with the mean Dice similarity coefficient of 0.921. The “soft boundary” defined by the voxels with the probabilities between 0.1 and 0.9 could demonstrate the overlapped region of cancerous and wall tissues. The invasion depth calculated from proposed segmentation method was compared with that from manual segmentation, with a mean difference of 0.277 mm.Conclusion: The proposed strategy could accurately segment the BCa region, and, as the first attempt, realize the quantitative measurement of BCa invasion depth.

scholarly journals The Invasion Depth Measurement of Bladder Cancer using T2-weighted Magnetic Resonance Imaging

2020 ◽  
Author(s):  
yang liu ◽  
Haojie Zheng ◽  
Xiaopan Xu ◽  
Xi Zhang ◽  
Peng Du ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Bladder Wall ◽  
Classification Model ◽  
Support Vector ◽  
Dice Similarity Coefficient ◽  
Wall Region ◽  
Feature Subset ◽  
Invasion Depth ◽  
Depth Measurement ◽  
The Mean

Abstract Background: Invasion depth is an important index for staging and clinical treatment strategy of bladder cancer (BCa). The aim of this study was to investigate the feasibility of segmenting the BCa region from bladder wall region on MRI, and quantitatively measuring the invasion depth of the tumor mass in bladder lumen for further clinical decision-making. This retrospective study involved 20 eligible patients with postoperatively pathologically-confirmed BCa. It was conducted in the following steps: (1) a total of 1159 features were extracted from each voxel of both the certain cancerous and wall tissues with the T2-weighted (T2W) MRI data; (2) the support vector machine (SVM)-based recursive feature elimination (RFE) method was implemented to first select an optimal feature subset, and then develop the classification model for the precise separation of the cancerous regions; (3) after excluding the cancerous region from the bladder wall, the three-dimensional bladder wall thickness (BWT) was calculated using Laplacian method, and the invasion depth of BCa was eventually defined by the subtraction of the mean BWT excluding the cancerous region and the minimum BWT of the cancerous region.Results: The segmented results showed a promising accuracy, with the mean Dice similarity coefficient of 0.921. The “soft boundary” defined by the voxels with the probabilities between 0.1 and 0.9 could demonstrate the overlapped region of cancerous and wall tissues. The invasion depth calculated from proposed segmentation method was compared with that from manual segmentation, with a mean difference of 0.277 mm.Conclusion: The proposed strategy could accurately segment the BCa region, and, as the first attempt, realize the quantitative measurement of BCa invasion depth.

scholarly journals The Invasion Depth Measurement of Bladder Cancer based on MRI

2020 ◽  
Author(s):  
yang liu ◽  
Haojie Zheng ◽  
Xiaopan Xu ◽  
Xi Zhang ◽  
Peng Du ◽  
...  
Keyword(s):  
Bladder Cancer ◽  
Bladder Wall ◽  
Classification Model ◽  
Support Vector ◽  
Dice Similarity Coefficient ◽  
Wall Region ◽  
Feature Subset ◽  
Invasion Depth ◽  
Depth Measurement ◽  
The Mean

Abstract Background: Invasion depth is an important index for staging and clinical treatment strategy of bladder cancer (BCa). The aim of this study was to investigate the feasibility of segmenting the BCa region from bladder wall region on MRI, and quantitatively measuring the invasion depth of the tumor mass in bladder lumen for further clinical decision-making. This retrospective study involved 20 eligible patients with postoperatively pathologically-confirmed BCa. It was conducted in the following steps: (1) a total of 1159 features were extracted from each voxel of both the certain cancerous and wall tissues with the T2-weighted (T2W) MRI data; (2) the support vector machine (SVM)-based recursive feature elimination (RFE) method was implemented to first select an optimal feature subset, and then develop the classification model for the precise separation of the cancerous regions; (3) after excluding the cancerous region from the bladder wall, the three-dimensional bladder wall thickness (BWT) was calculated using Laplacian method, and the invasion depth of BCa was eventually defined by the subtraction of the minimum BWT of the cancerous region and the mean BWT other than the cancerous region. Results: The segmented results showed a promising accuracy, with the mean Dice similarity coefficient of 0.921. The “soft boundary” defined by the voxels with the probabilities between 0.1 and 0.9 could demonstrate the overlapped region of cancerous and wall tissues. The invasion depth calculated from proposed segmentation method was compared with that from manual segmentation, with a mean difference of 0.277 mm. Conclusion: The proposed strategy could accurately segment the BCa region, and, as the first attempt, realize the quantitative measurement of BCa invasion depth.

Comparison of SVM, RF and SGD Methods for Determination of Programmer's Performance Classification Model in Social Media Activities

2020 ◽  
Vol 4 (2) ◽  
pp. 329-335
Author(s):  
Rusydi Umar ◽  
Imam Riadi ◽  
Purwono
Keyword(s):  
Social Media ◽  
Gradient Descent ◽  
Classification Model ◽  
Stochastic Gradient Descent ◽  
Support Vector ◽  
Svm Algorithm ◽  
Vector Machines ◽  
Performance Patterns ◽  
A Company

The failure of most startups in Indonesia is caused by team performance that is not solid and competent. Programmers are an integral profession in a startup team. The development of social media can be used as a strategic tool for recruiting the best programmer candidates in a company. This strategic tool is in the form of an automatic classification system of social media posting from prospective programmers. The classification results are expected to be able to predict the performance patterns of each candidate with a predicate of good or bad performance. The classification method with the best accuracy needs to be chosen in order to get an effective strategic tool so that a comparison of several methods is needed. This study compares classification methods including the Support Vector Machines (SVM) algorithm, Random Forest (RF) and Stochastic Gradient Descent (SGD). The classification results show the percentage of accuracy with k = 10 cross validation for the SVM algorithm reaches 81.3%, RF at 74.4%, and SGD at 80.1% so that the SVM method is chosen as a model of programmer performance classification on social media activities.

Sign in / Sign up

Export Citation Format

Share Document