scholarly journals Rapid identification of wood species using XRF and neural network machine learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Aaron N. Shugar ◽  
B. Lee Drake ◽  
Greg Kelley
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Wood Species ◽  
Cost Effective ◽  
Rapid Identification ◽  
Invasive Technique ◽  
X Ray ◽  
Non Invasive ◽  
Cost Effective Alternative

AbstractAn innovative approach for the rapid identification of wood species is presented. By combining X-ray fluorescence spectrometry with convolutional neural network machine learning, 48 different wood specimens were clearly differentiated and identified with a 99% accuracy. Wood species identification is imperative to assess illegally logged and transported lumber. Alternative options for identification can be time consuming and require some level of sampling. This non-invasive technique offers a viable, cost-effective alternative to rapidly and accurately identify timber in efforts to support environmental protection laws and regulations.

scholarly journals Automating, Analyzing and Improving Pupillometry with Machine Learning Algorithms

2019 ◽  
Vol 24 (2) ◽  
pp. 197-209
Author(s):  
György Kalmár ◽  
Alexandra Büki ◽  
Gabriella Kékesi ◽  
Gyöngyi Horváth ◽  
László G. Nyúl
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Nervous System ◽  
Detection Method ◽  
Infrared Camera ◽  
Machine Learning Algorithms ◽  
Invasive Technique ◽  
Non Invasive ◽  
Pupillary Light ◽  
Pupil Detection

The investigation of the pupillary light reflex (PLR) is a well-known method to provide information about the functionality of the autonomic nervous system. Pupillometry, a non-invasive technique, was applied to study the PLR alterations in a new, schizophrenia-like rat substrain, named WISKET. The pupil responses to light impulses were recorded with an infrared camera; the videos were automatically processed and features were extracted. Besides the classical statistical analysis (ANOVA), feature selection and classification were applied to reveal the significant differences in the PLR parameters between the control and WISKET animals. Based on these results, the disadvantages of this method were analyzed and the measurement process was redesigned and improved. The automated pupil detection method has also been adapted to the new videos. 2564 images were annotated manually and used to train a fully-convolutional neural network to produce pupil mask images. The method was evaluated on 329 test images and achieved 4% median relative error. With the new setup, the pupil detection became reliable and the new data acquisition offers robustness to the experiments.

scholarly journals Impact of Training Sample Size on the Effects of Regularization in a Convolutional Neural Network-based Dental X-ray Artifact Prediction Model

2020 ◽  
Vol 14 (1) ◽  
pp. 5
Author(s):  
Adam Adli ◽  
Pascal Tyrrell
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Convolutional Neural Network ◽  
Sample Size ◽  
Training Sample ◽  
Training Data ◽  
Classification Model ◽  
Sample Sizes ◽  
X Ray ◽  
Training Sample Size

Introduction: Advances in computers have allowed for the practical application of increasingly advanced machine learning models to aid healthcare providers with diagnosis and inspection of medical images. Often, a lack of training data and computation time can be a limiting factor in the development of an accurate machine learning model in the domain of medical imaging. As a possible solution, this study investigated whether L2 regularization moderate s the overfitting that occurs as a result of small training sample sizes.Methods: This study employed transfer learning experiments on a dental x-ray binary classification model to explore L2 regularization with respect to training sample size in five common convolutional neural network architectures. Model testing performance was investigated and technical implementation details including computation times and hardware considerations as well as performance factors and practical feasibility were described.Results: The experimental results showed a trend that smaller training sample sizes benefitted more from regularization than larger training sample sizes. Further, the results showed that applying L2 regularization did not apply significant computational overhead and that the extra rounds of training L2 regularization were feasible when training sample sizes are relatively small.Conclusion: Overall, this study found that there is a window of opportunity in which the benefits of employing regularization can be most cost-effective relative to training sample size. It is recommended that training sample size should be carefully considered when forming expectations of achievable generalizability improvements that result from investing computational resources into model regularization.

Evaluation of Diagnostic Performance of Machine Learning Algorithms to Classify the Fetal Heart Rate Baseline from Cardiotocograph

2022 ◽  
Vol 9 (3) ◽  
pp. 0-0
Keyword(s):  
Machine Learning ◽  
Fetal Heart ◽  
Learning Algorithms ◽  
Cost Effective ◽  
Machine Learning Algorithms ◽  
Invasive Technique ◽  
Visual Estimation ◽  
Altman Plot ◽  
Non Invasive

Cardiotocography (CTG) is the widely used cost-effective, non-invasive technique to monitor the fetal heart and mother’s uterine contraction pressure to assess the wellbeing of the fetus. The most important parameters of fetal heart is the baseline upon which the other parameters viz. acceleration, deceleration and variability depend. Accurate classification of the baseline into either normal, bradycardia or tachycardia is thus important to assess the fetal-health. Since visual estimation has its limitations, the authors use various Machine Learning Algorithms to classify the baseline. 110 CTG traces from CTU-UHB dataset, were divided into three subsets using stratified sampling to ensure that the sample is the accurate depiction of the population. The results were analyzed using various statistical methods and compared with the visual estimation by three obstetricians. FURIA provided greatest accuracy of 98.11%. From the analysis of Bland-Altman Plot FURIA was also found to have best agreement with physicians’ estimation.

scholarly journals Pleural Effusion Classification Based on Chest X-Ray Images using Convolutional Neural Network

2021 ◽  
Vol 14 (1) ◽  
pp. 9-16
Author(s):  
Ahmad Rafiansyah Fauzan ◽  
Mohammad Iwan Wahyuddin ◽  
Sari Ningsih
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Pleural Effusion ◽  
Convolutional Neural Network ◽  
Learning Algorithm ◽  
Respiratory Infections ◽  
Severe Case ◽  
Machine Learning Algorithm ◽  
X Ray ◽  
Chest X Ray

Pleural effusion is a respiratory infection characterized by a buildup of fluid between the two layers of pleura, which causes specific symptoms such as chest pain and shortness of breath. In Indonesia, pleural effusion cases alone account for 2.7% of other respiratory infections, with an estimated number of sufferers in general at more than 3000 people per 1 million population annually. Pleural effusion is a severe case and can cause death if not treated immediately. Based on a study, as many as 15% of 104 patients diagnosed with pleural effusion died within 30 days. In this paper, we present a model that can detect pleural effusion based on chest x-ray images automatically using a Machine Learning algorithm. The machine learning algorithm used is Convolutional Neural Network (CNN), with the dataset used from ChestX-ray14. The number of data used was 2500 in the form of x-ray images, based on two different classes, x-ray with pleural effusion and x-ray with normal condition. The evaluation result shows that the CNN model can classify data with an accuracy of 95% of the test set data; thus, we hope it can be an alternative to assist medical diagnosis in pleural effusion detection.

Sign in / Sign up

Export Citation Format

Share Document