An Approach to Automated Recognition of Pavement Deterioration Through Machine Learning

2019 ◽  
pp. 124-140
Author(s):  
Rodrigo Huincalef ◽  
Guillermo Urrutia ◽  
Gabriel Ingravallo ◽  
Diego C. Martínez
Keyword(s):  
Machine Learning ◽  
Automated Recognition ◽  
Pavement Deterioration

scholarly journals ChemPix: Automated Recognition of Hand-drawn Hydrocarbon Structures Using Deep Learning

2021 ◽  
Author(s):  
Hayley Weir ◽  
Keiran Thompson ◽  
Amelia Woodward ◽  
Benjamin Choi ◽  
Augustin Braun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Quantum Chemistry ◽  
Automated Recognition ◽  
Domain Expertise

Inputting molecules into chemistry software, such as quantum chemistry packages, currently requires domain expertise, expensive software and/or cumbersome procedures. Leveraging recent breakthroughs in machine learning, we develop ChemPix: an offline,...

scholarly journals Neural Network Recognition of Marine Benthos and Corals

Diversity ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 29 ◽  
Author(s):  
Alina Raphael ◽  
Zvy Dubinsky ◽  
David Iluz ◽  
Nathan S. Netanyahu
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Coral Reefs ◽  
Image Recognition ◽  
Live Coral ◽  
Automated Recognition ◽  
Field Point ◽  
Unique Potential

We present thorough this review the developments in the field, point out their current limitations, and outline its timelines and unique potential. In order to do so we introduce the methods used in each of the advances in the application of deep learning (DL) to coral research that took place between the years: 2016–2018. DL has unique capability of streamlining the description, analysis, and monitoring of coral reefs, saving time, and obtaining higher reliability and accuracy compared with error-prone human performance. Coral reefs are the most diverse and complex of marine ecosystems, undergoing a severe decline worldwide resulting from the adverse synergistic influences of global climate change, ocean acidification, and seawater warming, exacerbated by anthropogenic eutrophication and pollution. DL is an extension of some of the concepts originating from machine learning that join several multilayered neural networks. Machine learning refers to algorithms that automatically detect patterns in data. In the case of corals these data are underwater photographic images. Based on “learned” patterns, such programs can recognize new images. The novelty of DL is in the use of state-of-art computerized image analyses technologies, and its fully automated methodology of dealing with large data sets of images. Automated Image recognition refers to technologies that identify and detect objects or attributes in a digital video or image automatically. Image recognition classifies data into selected categories out of many. We show that Neural Network methods are already reliable in distinguishing corals from other benthos and non-coral organisms. Automated recognition of live coral cover is a powerful indicator of reef response to slow and transient changes in the environment. Improving automated recognition of coral species, DL methods already recognize decline of coral diversity due to natural and anthropogenic stressors. Diversity indicators can document the effectiveness of reef bioremediation initiatives. We explored the current applications of deep learning for corals and benthic image classification by discussing the most recent studies conducted by researchers. We review the developments in the field, point out their current limitations, and outline their timelines and unique potential. We also discussed a few future research directions in the fields of deep learning. Future needs are the age detection of single species, in order to track trends in their population recruitment, decline, and recovery. Fine resolution, at the polyp level, is still to be developed, in order to allow separation of species with similar macroscopic features. That refinement of DL will allow such comparisons and their analyses. We conclude that the usefulness of future, more refined automatic identification will allow reef comparison, and tracking long term changes in species diversity. The hitherto unused addition of intraspecific coral color parameters, will add the inclusion of physiological coral responses to environmental conditions and change thereof. The core aim of this review was to underscore the strength and reliability of the DL approach for documenting coral reef features based on an evaluation of the currently available published uses of this method. We expect that this review will encourage researchers from computer vision and marine societies to collaborate on similar long-term joint ventures.

scholarly journals Recognizing Human Facial Expressions with Machine Learning

2019 ◽  
Vol 8 (3) ◽  
pp. 4500-4502
Keyword(s):  
Machine Learning ◽  
Support Vector Machines ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Outward Appearance ◽  
Discriminate Analysis ◽  
Automated Recognition ◽  
Facial Emotions ◽  
Learning Techniques ◽  
Vector Machines

we develop a organized correlation of machine learning techniques connected to the issue of completely programmed acknowledgment of facial emotions. We investigate consequences on a progress of researches looking at acknowledgment engines, combining AdaBoost, support vector machines, linear discriminate analysis. We likewise investigated highlight choice strategies, including the utilization of AdaBoost for highlight choice before order through SVM or else LDA. Best outcomes are gotten through prefering a subset of Gabor conduit develop AdaBoost pursued through order with Support Vector Machines. The framework works continuously, within addition to got 93% right speculation novel matters intended for a 7-way compelled alternative going the Cohn-Kanade articulation information. The yields of the classier alteration easily an element of time and in this way can be utilized to gauge outward appearance elements. We connected the framework to fully automated recognition of facial activities (FACS). The current framework arranges 17 activity units, regardless of even those coming as one or else within combine with different activities, with a mean precision of 94.8%. The design fundamental consequences intended for applying this framework to facial emotions.

scholarly journals Automated Recognition of Diabetic Retinopathy using Machine Learning Techniques

2019 ◽  
Vol 8 (4S2) ◽  
pp. 602-606
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Diabetic Retinopathy ◽  
Machine Learning Techniques ◽  
Learning Approaches ◽  
Automated Recognition ◽  
Image Contrast Enhancement ◽  
Artificial Neural Network Ann ◽  
Learning Machine ◽  
Sensitivity Specificity

Diabetic Retinopathy (DR) is the illness due to severe polygenic disorders that result in loss of vision for the patients. The development in computer science leads to the timely recognition of DR through an automatic system that is more advantageous than the diagnosis done by a doctor. This paper reviews the DR diagnosis technique that includes deep learning, machine learning and image processing based approaches and their performance. Among the machine learning approaches, the Artificial Neural Network (ANN) classification technique results in high accuracy. The green channel extraction based image contrast enhancement has high classification accuracy, which outperforms the image processing techniques. The performance of the model is estimated by the metrics including sensitivity, specificity and accuracy. This study presents depth insights of techniques for automated DR diagnosis.

scholarly journals End-to-end platform evaluation for Spanish Handwritten Text Recognition

2021 ◽  
pp. 81-95
Author(s):  
Eduardo Xamena ◽  
Héctor Emanuel Barboza ◽  
Carlos Ismael Orozco
Keyword(s):  
Machine Learning ◽  
Spanish Language ◽  
Text Recognition ◽  
Automated Recognition ◽  
Handwritten Text ◽  
Handwritten Text Recognition ◽  
New Models ◽  
Original Contribution ◽  
Comprehensive Manner ◽  
End To End

The task of automated recognition of handwritten texts requires various phases and technologies both optical and language related. This article describes an approach for performing this task in a comprehensive manner, using machine learning throughout all phases of the process. In addition to the explanation of the employed methodology, it describes the process of building and evaluating a model of manuscript recognition for the Spanish language. The original contribution of this article is given by the training and evaluation of Offline HTR models for Spanish language manuscripts, as well as the evaluation of a platform to perform this task in a complete way. In addition, it details the work being carried out to achieve improvements in the models obtained, and to develop new models for different complex corpora that are more difficult for the HTR task.

scholarly journals Application of Machine Learning for Partial Discharge Classification under DC Voltage

2019 ◽  
pp. 16-21 ◽  
Author(s):  
Bernhard Schober ◽  
Uwe Schichler
Keyword(s):  
Machine Learning ◽  
Partial Discharge ◽  
Pulse Sequences ◽  
The Other ◽  
Machine Learning Techniques ◽  
Statistical Parameters ◽  
Automated Recognition ◽  
Dc Voltage ◽  
Learning Techniques ◽  
Defects Classification

Partial discharge measurement is one of the most important diagnosis methods and well investigated under AC voltage. Furthermore, machine learning is established and has been used successfully already many years for automated recognition of PD defects. For AC voltage, there are several diagnosis methods and interpretation tools. In the field of DC voltage this is not the case, so it needs significant tools to interpret the results. In this contribution typical PD defects of HVDC GIS/GIL are investigated, but the methods can be adopted to other HV equipment as well. The machine learning techniques were realized with MATLAB and WEKA. Statistical parameters, derived from the PD pulse sequences, were used as features. A hierarchical clustering of the features was performed to analyse the separability between the PD defects. Classification was done with three popular algorithms (SVM, k-NN, ANN). The parameters of these algorithms were varied and compared to each other’s. SVM clearly outperformed the other classifiers.

Performance of Machine Learning Algorithms in Predicting the Pavement International Roughness Index

2021 ◽  
pp. 036119812098617
Author(s):  
Mohammad Z. Bashar ◽  
Cristina Torres-Machi
Keyword(s):  
Machine Learning ◽  
Sample Size ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Minimum Sample Size ◽  
International Roughness Index ◽  
Pavement Deterioration ◽  
Roughness Index ◽  
Overall Performance ◽  
Minimum Sample

Significant research efforts have documented the capabilities of machine learning (ML) algorithms to model pavement performance. Several challenges, however, limit the implementation of ML by practitioners and transportation agencies. One of these challenges is related to the high variability in the performance of ML models as reported by different studies and the lack of quantitative evidence supporting the true effectiveness of these techniques. The objective of this paper is twofold: to assess the overall performance of traditional and ML techniques used to predict pavement condition, and to provide guidance on the optimal architecture and minimum sample size required to develop these models. This paper analyzes three ML algorithms commonly used to predict International Roughness Index (IRI)—Artificial Neural Network (ANN), Random Forest (RF), and Support Vector Machine (SVM)—and compares their performance to traditional techniques. An inverse variance heterogeneity based meta-analysis is performed on 20 studies conducted between 2001 and 2020. The results indicate that ML algorithms capture on average 15.6% more variability than traditional techniques. RF is the most accurate technique with an overall performance value of 0.995. ANN is also identified as a highly effective technique that has been widely used and provides accurate predictions with both small and large sample sizes. For ANN algorithms, a single hidden layer with nodes equal to 0.3–2 times the number of input features is found to be sufficient in predicting pavement deterioration. A minimum sample size equal to 50 times the number of input variables is recommend to model pavement deterioration using ML.

Sign in / Sign up

Export Citation Format

Share Document