scholarly journals Creating a Diagnostic Assistance System for Diseases in Kampo Medicine

2021 ◽  
Vol 11 (21) ◽  
pp. 9716
Author(s):  
Reimei Koike ◽  
Keiko Ogawa-Ochiai ◽  
Akiko Shirai ◽  
Katsumi Hayashi ◽  
Junsuke Arimitsu ◽  
...  
Keyword(s):  
Data Augmentation ◽  
Mean Absolute Error ◽  
Polarized Light ◽  
Absolute Error ◽  
Assistance System ◽  
Kampo Medicine ◽  
Data Set ◽  
Diagnostic Use ◽  
Yin Deficiency ◽  
Diagnostic Support

The aim of this study was to propose a method to assess images of the tongue captured using a polarized light camera for diagnostic use in Kampo medicine. Glossy and non-glossy images of the tongue were captured simultaneously using a polarizing camera and a polarizing plate. Data augmentation was performed by modulating the color and gloss, resulting in an increase in the number of images from 11 to 275. To create a data set, the values for which diseases were evaluated by Kampo doctors for all tongue images were taken as the correct values and combined with the features extracted from the tongue images. Using this data set, we constructed a diagnostic support module to evaluate diseases. The resulting mean absolute error of the assessment was 0.44 for qi deficiency, 0.42 for blood deficiency, 0.33 for blood stagnation, 0.36 for yin deficiency, and 0.55 for fluid stagnation, suggesting that the diagnostic assistance module was accurate, and our proposed learning and data augmentation methods were effective.

scholarly journals Using images of the tongue for diagnostic assistance in Kampo Medicine

2020 ◽  
Vol 2020 (28) ◽  
pp. 221-226
Author(s):  
Reimei Koike ◽  
Keiko Ogawa-Ochiai ◽  
Hongyang Li ◽  
Norimichi Tsumura
Keyword(s):  
Machine Learning ◽  
Data Augmentation ◽  
Mean Absolute Error ◽  
Polarized Light ◽  
Absolute Error ◽  
Kampo Medicine ◽  
Machine Learning Technique ◽  
Diagnostic Use ◽  
Learning Technique ◽  
Feature Values

In this research, we propose a method to assess images of the tongue captured using a polarized light camera for diagnostic use in Kampo Medicine. The polarized light camera is used to simultaneously capture glossy and non-glossy images of the tongue. Data augmentation was performed by modulating the color and gloss, through which the number of images was increased from 11 to 275. A diagnostic assistance module was built to evaluate a given disease by learning a specialist's assessment of it along with feature values obtained from the captured image using a machine learning technique. The resulting mean absolute error of the assessment of five diseases was sufficiently small for it to be accurate.

scholarly journals A Predictive Model Implemented in KNIME Based on Learning Analytics for Timely Decision Making in Virtual Learning Environments

2022 ◽  
Vol 12 (2) ◽  
pp. 91-99
Author(s):  
Maraza-Quispe Benjamín ◽  
◽  
Enrique Damián Valderrama-Chauca ◽  
Lenin Henry Cari-Mogrovejo ◽  
Jorge Milton Apaza-Huanca ◽  
...  
Keyword(s):  
Academic Performance ◽  
Predictive Model ◽  
Mean Absolute Error ◽  
Simple Random Sampling ◽  
Absolute Error ◽  
Analysis Data ◽  
Problem Analysis ◽  
Data Set ◽  
Behavioral Indicators ◽  
The Mean

The present research aims to implement a predictive model in the KNIME platform to analyze and compare the prediction of academic performance using data from a Learning Management System (LMS), identifying students at academic risk in order to generate timely and timely interventions. The CRISP-DM methodology was used, structured in six phases: Problem analysis, data analysis, data understanding, data preparation, modeling, evaluation and implementation. Based on the analysis of online learning behavior through 22 behavioral indicators observed in the LMS of the Faculty of Educational Sciences of the National University of San Agustin. These indicators are distributed in five dimensions: Academic Performance, Access, Homework, Social Aspects and Quizzes. The model has been implemented in the KNIME platform using the Simple Regression Tree Learner training algorithm. The total population consists of 30,000 student records from which a sample of 1,000 records has been taken by simple random sampling. The accuracy of the model for early prediction of students' academic performance is evaluated, the 22 observed behavioral indicators are compared with the means of academic performance in three courses. The prediction results of the implemented model are satisfactory where the mean absolute error compared to the mean of the first course was 3. 813 and with an accuracy of 89.7%, the mean absolute error compared to the mean of the second course was 2.809 with an accuracy of 94.2% and the mean absolute error compared to the mean of the third course was 2.779 with an accuracy of 93.8%. These results demonstrate that the proposed model can be used to predict students' future academic performance from an LMS data set.

scholarly journals Adaptive Data Structure Based Oversampling Algorithm for Ordinal Classification

2018 ◽  
Vol 12 (3) ◽  
pp. 1063
Author(s):  
Dhanalakshmi Kasiraja ◽  
Anna Saro Vijendran
Keyword(s):  
Data Structure ◽  
Predictive Accuracy ◽  
Mean Absolute Error ◽  
Rank Order ◽  
Geometric Mean ◽  
Absolute Error ◽  
Training Data ◽  
Data Set ◽  
Average Accuracy ◽  
Learning Machine

<p>The main objective of this research is to improve the predictive accuracy of classification in ordinal multiclass imbalanced scenario. The methodology attempts to uplift the classifier performance through synthesizing sophisticated objects of immature classes.  A novel Adaptive Data Structure based oversampling algorithm is proposed to create synthetic objects and Extreme Learning Machine for Ordinal Regression (ELMOP) classifier is adopted to validate our work.   The proposed method generating new objects by analyzing the characteristics and intricacy of immature class objects. On the whole, the data set is divided into training and test data. Training data set is updated with new synthetic objects.  The experimental analysis is performed on testing data set to check the efficiency of the proposed methodology by comparing it with the existing work.    The performance evaluation is conducted in terms of the parameters called Mean Absolute Error, Maximum Mean Absolute Error, Geometric Mean, Kappa and Average Accuracy.  The measures prove that the proposed methodology can produce authentic synthetic objects than the existing techniques.  The Proposed technique can synthesize the new effective objects through evaluating the structure of immature class.  It boosts the global precision and class wise precision especially preserves rank order of the classes.</p>

scholarly journals Deep Learning based Intraretinal Layer Segmentation using Cascaded Compressed U-Net

2021 ◽  
Author(s):  
Sunil K Yadav ◽  
Rahele Kafieh ◽  
Hanna G Zimmermann ◽  
Josef Kauer-Bonin ◽  
Kouros Nouri-Mahdavi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Mean Absolute Error ◽  
Severe Disease ◽  
Unmet Need ◽  
Reference Method ◽  
Absolute Error ◽  
Hole Filling ◽  
Tissue Segmentation ◽  
Data Set ◽  
Layer Segmentation

Intraretinal layer segmentation on macular optical coherence tomography (OCT) images generates non invasive biomarkers querying neuronal structures with near cellular resolution. While first deep learning methods have delivered promising results with high computing power demands, a reliable, power efficient and reproducible intraretinal layer segmentation is still an unmet need. We propose a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments 8 intraretinal layers with high fidelity. By compressing U-Net, we achieve 392- and 26-time reductions in model size and parameters in the first and second network, respectively. Still, our method delivers almost similar accuracy compared to U-Net without additional constraints of computation and memory resources. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. We trained our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e. multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3mu, which is 2.5x better than the device's own segmentation. Voxel-wise comparison against external multicenter data leads to a mean absolute error of 2.6mu for glaucoma data using the same gold standard segmentation approach, and 3.7mu mean absolute error compared against an externally segmented reference data set. In 20 macular volume scans from patients with severe disease, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method.

Evapotranspiration Prediction Using M5T Method and Ritchie Equation for St. Johns, FL, USA

2017 ◽  
Author(s):  
Yunus Ziya Kaya ◽  
Mustafa Mamak ◽  
Fatih Ünes ◽  
Mustafa Demirci
Keyword(s):  
Wind Speed ◽  
Meteorological Parameters ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Mean Square ◽  
Weather Station ◽  
Data Set ◽  
Test Set ◽  
Determination Coefficient ◽  
Agricultural Yield

Evapotranspiration (ET) estimation takes an important role in hydraulic designs and agricultural yield. Even it is non-negligible for hydraulic designers and irrigation engineers it is not clear enough to estimate or calculate ET because of direct and indirect parameters effects. In this study Solar Radiation (SR), Air Temperature (AT), Relative Humidity (RH) and Wind Speed (U) meteorological parameters are used to create a M5T model. 1158 daily RH, U, AT and SR records are used to create model and 385 daily values are used to test it. Data set is taken from St. Johns, Florida, USA weather station. The test set is also applied to the Ritchie empirical formula. M5T model and Ritchie formula Results are compared with daily ET records using determination coefficient. Determination coefficient is found 0.966 for M5T model and 0.913 for Ritchie formula. According to the determination coefficient, Mean Square Error (MSE) and Mean Absolute Error (MAE) statistics, it is understood that M5T method can be used for daily ET estimation effectively.

scholarly journals Copula-based synthetic data augmentation for machine- learning emulators

2021 ◽  
Vol 14 (8) ◽  
pp. 5205-5215
Author(s):  
David Meyer ◽  
Thomas Nagler ◽  
Robin J. Hogan
Keyword(s):  
Machine Learning ◽  
Physical Model ◽  
Data Augmentation ◽  
Mean Absolute Error ◽  
Synthetic Data ◽  
Longwave Radiation ◽  
Absolute Error ◽  
Weather And Climate ◽  
The Mean ◽  
Network Emulator

Abstract. Can we improve machine-learning (ML) emulators with synthetic data? If data are scarce or expensive to source and a physical model is available, statistically generated data may be useful for augmenting training sets cheaply. Here we explore the use of copula-based models for generating synthetically augmented datasets in weather and climate by testing the method on a toy physical model of downwelling longwave radiation and corresponding neural network emulator. Results show that for copula-augmented datasets, predictions are improved by up to 62 % for the mean absolute error (from 1.17 to 0.44 W m−2).

scholarly journals Composite Model Fabrication of Classification with Transformed Target Regressor for Customer Segmentation using Machine Learning

2019 ◽  
Vol 8 (6) ◽  
pp. 962-966
Keyword(s):  
Machine Learning ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Customer Segmentation ◽  
Composite Model ◽  
Experimental Results ◽  
Data Set ◽  
Product Description ◽  
Day By Day

In Current internet world, the customers prefer to buy the products through online rather than spending their time on show rooms. The online customers of wine increases day by day due to the availability of high brands in online sellers. So the customers buy the wine products based on the product description and the satisfaction of other customers those who have bought before. This makes the industries to focus on machine learning that concentrates on target transformation of the dependent variable. This paper endeavor to forecast the customer segmentation for the wine data set extracted from UCI Machine learning repository. The raw wine data set is subjected to target transformation for various classifiers like Huber Regressor, SGD Regressor, RidgeCV Regression, Logistic RegressionCV and Passive Aggressive Regressor. The performance of the various classifiers is analyzed with and without target transformation using the metrics like Mean Absolute Error and R2 Score. The implementation is done in Anaconda Navigator with Python. Experimental results shows that after applying target transformation RidgeCV Regression is found to be effective with the R2 Score of 82% and Mean Absolute Error of 0.0 compared to other classifiers.

scholarly journals Machine Learning Based Target Transformation using Regressor Classification for Heart Disease Envisage

2020 ◽  
Vol 8 (5) ◽  
pp. 1526-1531
Keyword(s):  
Machine Learning ◽  
Heart Disease ◽  
Mean Absolute Error ◽  
Economic Status ◽  
Absolute Error ◽  
Background Information ◽  
World Population ◽  
Data Set ◽  
Technological Growth ◽  
The Mean

In the modern scenario of technological growth, the life style of an individual varies with the economic status. The world population is prone towards chronic deadly diseases due to the variety of food habits. The usages of electronic equipments have raised the population to waste their quality time towards exercise. The lack of physical activity has symptoms towards bad quality of life. With this background information, this paper concentrates on predicting the type of heart disease by applying target transformation using various machine learning regression models. This paper uses the Heart disease data set extracted from UCI Machine Learning Repository. The anaconda Navigator IDE along with Spyder is used for implementing the Python code. Our contribution is folded is folded in three ways. First, the data segregation is done and it is preprocessed to extract the relationship and dependency of each parameters. Second, the dataset is subjected to process to identify the target distribution of classes in the dependent variable. Third, the dataset is fitted to the Ridge regressor, Huber regressor, SGD regressor and PerceptronCV regressor by applying with and without target transformation. Fourth, dataset is feature scaled and then fitted to the Ridge regressor, Huber regressor, SGD regressor and PerceptronCV regressor by applying with and without target transformation. Fifth, the performance analysis is done by analyzing the Mean Absolute Error and R2 Score. Experimental results show that, the Perceptron regressor CV has the effectiveness with the mean absolute error of 1.00 and R2 score of 0.04 for the heart disease prediction.

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

2020 ◽  
Vol 17 (3) ◽  
pp. 299-305 ◽  
Author(s):  
Riaz Ahmad ◽  
Saeeda Naz ◽  
Muhammad Afzal ◽  
Sheikh Rashid ◽  
Marcus Liwicki ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Recognition System ◽  
Learning Approach ◽  
Arabic Text ◽  
Data Set ◽  
Processing Step ◽  
Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

Contactless Core-Temperature Monitoring by Infrared Thermal Sensor using Mean Absolute Error Analysis

2020 ◽  
Vol 15 ◽  
Author(s):  
Fahad Layth Malallah ◽  
Baraa T. Shareef ◽  
Mustafah Ghanem Saeed ◽  
Khaled N. Yasen
Keyword(s):  
Body Temperature ◽  
Embedded System ◽  
Core Temperature ◽  
Integrated Circuit ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Thermal Sensor ◽  
Human Face ◽  
Body Contact ◽  
Arduino Microcontroller

Aims: Normally, the temperature increase of individuals leads to the possibility of getting a type of disease, which might be risky to other people such as coronavirus. Traditional techniques for tracking core-temperature require body contact either by oral, rectum, axillary, or tympanic, which are unfortunately considered intrusive in nature as well as causes of contagion. Therefore, sensing human core-temperature non-intrusively and remotely is the objective of this research. Background: Nowadays, increasing level of medical sectors is a necessary targets for the research operations, especially with the development of the integrated circuit, sensors and cameras that made the normal life easier. Methods: The solution is by proposing an embedded system consisting of the Arduino microcontroller, which is trained with a model of Mean Absolute Error (MAE) analysis for predicting Contactless Core-Temperature (CCT), which is the real body temperature. Results: The Arduino is connected to an Infrared-Thermal sensor named MLX90614 as input signal, and connected to the LCD to display the CCT. To evaluate the proposed system, experiments are conducted by participating 31-subject sensing contactless temperature from the three face sub-regions: forehead, nose, and cheek. Conclusion: Experimental results approved that CCT can be measured remotely depending on the human face, in which the forehead region is better to be dependent, rather than nose and cheek regions for CCT measurement due to the smallest

Sign in / Sign up

Export Citation Format

Share Document