Variability and association among some pomological and physiochemical traits in spring frost tolerant genotypes of Persian walnut (Juglans regia L.) and selection of genotypes with superior traits based on machine learning algorithms

Automation is becoming an integral part of our daily lives as technology and techniques rapidly develop. Many automation workflows are now routinely being applied within the geoscience domain. The basic structure of automation and its success of modelling fundamentally hinges on the appropriate choice of parameters and speed of processing. The entire process demands that the data being fed into any machine learning model is essentially of good quality. The technological advances in well logging technology over decades have enabled the collection of vast amounts of data across wells and fields. This poses a major issue in automating petrophysical workflows. It necessitates to ensure that, the data being fed is appropriate and fit for purpose. The selection of features (logging curves) and parameters for machine learning algorithms has therefore become a topic at the forefront of related research. Inappropriate feature selections can lead erroneous results, reduced precision and have proved to be computationally expensive. Experienced Eye (EE) is a novel methodology, derived from Domain Transfer Analysis (DTA), which seeks to identify and elicit the optimum input curves for modelling. During the EE solution process, relationships between the input variables and target variables are developed, based on characteristics and attributes of the inputs instead of statistical averages. The relationships so developed between variables can then be ranked appropriately and selected for modelling process. This paper focuses on three distinct petrophysical data scenarios where inputs are ranked prior to modelling: prediction of continuous permeability from discrete core measurements, porosity from multiple logging measurements and finally the prediction of key geomechanical properties. Each input curve is ranked against a target feature. For each case study, the best ranked features were carried forward to the modelling stage, and the results are validated alongside conventional interpretation methods. Ranked features were also compared between different machine learning algorithms: DTA, Neural Networks and Multiple Linear Regression. Results are compared with the available data for various case studies. The use of the new feature selection has been proven to improve accuracy and precision of prediction results from multiple modelling algorithms.

Download Full-text

Optimized Classification Predictions with a New Index Combining Machine Learning Algorithms

International Journal of Artificial Intelligence Tools ◽

10.1142/s0218213018500124 ◽

2018 ◽

Vol 27 (03) ◽

pp. 1850012 ◽

Cited By ~ 6

Author(s):

Androniki Tamvakis ◽

Christos-Nikolaos Anagnostopoulos ◽

George Tsirtsis ◽

Antonios D. Niros ◽

Sofie Spatharis

Keyword(s):

Machine Learning ◽

Learning Algorithms ◽

Individual Performance ◽

Optimal Combination ◽

Machine Learning Algorithms ◽

Combined Effect ◽

Different Types ◽

Open Issue ◽

The Relationship ◽

Selection Of

Voting is a commonly used ensemble method aiming to optimize classification predictions by combining results from individual base classifiers. However, the selection of appropriate classifiers to participate in voting algorithm is currently an open issue. In this study we developed a novel Dissimilarity-Performance (DP) index which incorporates two important criteria for the selection of base classifiers to participate in voting: their differential response in classification (dissimilarity) when combined in triads and their individual performance. To develop this empirical index we firstly used a range of different datasets to evaluate the relationship between voting results and measures of dissimilarity among classifiers of different types (rules, trees, lazy classifiers, functions and Bayes). Secondly, we computed the combined effect on voting performance of classifiers with different individual performance and/or diverse results in the voting performance. Our DP index was able to rank the classifier combinations according to their voting performance and thus to suggest the optimal combination. The proposed index is recommended for individual machine learning users as a preliminary tool to identify which classifiers to combine in order to achieve more accurate classification predictions avoiding computer intensive and time-consuming search.

Download Full-text

A Comparative Study for the Selection of Machine Learning Algorithms based on Descriptive Parameters

Proceedings of the 8th International Conference on Data Science, Technology and Applications ◽

10.5220/0008117404080415 ◽

2019 ◽

Author(s):

Chettan Kumar ◽

Martin Käppel ◽

Nicolai Schützenmeier ◽

Philipp Eisenhuth ◽

Stefan Jablonski

Keyword(s):

Machine Learning ◽

Comparative Study ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Selection Of

Download Full-text

Improving Time Complexity and Accuracy of the Machine Learning Algorithms Through Selection of Highly Weighted Top k Features from Complex Datasets

Annals of Data Science ◽

10.1007/s40745-019-00217-4 ◽

2019 ◽

Vol 6 (4) ◽

pp. 599-621 ◽

Cited By ~ 1

Author(s):

Abdul Majeed

Keyword(s):

Machine Learning ◽

Time Complexity ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Selection Of ◽

Complex Datasets

Download Full-text

Identifying Benchmarks for Failure Prediction in Industry 4.0

Informatics ◽

10.3390/informatics8040068 ◽

2021 ◽

Vol 8 (4) ◽

pp. 68

Author(s):

Mouhamadou Saliou Diallo ◽

Sid Ahmed Mokeddem ◽

Agnès Braud ◽

Gabriel Frey ◽

Nicolas Lachiche

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Prediction Model ◽

Supervised Learning ◽

Industry 4.0 ◽

Learning Algorithms ◽

Failure Prediction ◽

Machine Learning Algorithms ◽

Predictive Maintenance ◽

Selection Of

Industry 4.0 is characterized by the availability of sensors to operate the so-called intelligent factory. Predictive maintenance, in particular, failure prediction, is an important issue to cut the costs associated with production breaks. We studied more than 40 publications on predictive maintenance. We point out that they focus on various machine learning algorithms rather than on the selection of suitable datasets. In fact, most publications consider a single, usually non-public, benchmark. More benchmarks are needed to design and test the generality of the proposed approaches. This paper is the first to define the requirements on these benchmarks. It highlights that there are only two benchmarks that can be used for supervised learning among the six publicly available ones we found in the literature. We also illustrate how such a benchmark can be used with deep learning to successfully train and evaluate a failure prediction model. We raise several perspectives for research.

Download Full-text

Decision Tree Ensembles to Predict Coronavirus Disease 2019 Infection: A Comparative Study

Complexity ◽

10.1155/2021/5550344 ◽

2021 ◽

Vol 2021 ◽

pp. 1-8

Author(s):

Amir Ahmad ◽

Ourooj Safi ◽

Sharaf Malebary ◽

Sami Alesawi ◽

Entisar Alkayal

Keyword(s):

Machine Learning ◽

Decision Tree ◽

Characteristic Curve ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Polymerase Chain Reaction Test ◽

Imbalanced Datasets ◽

Polymerase Chain ◽

Chain Reaction Test ◽

Selection Of

The coronavirus disease 2019 (Covid-19) pandemic has affected most countries of the world. The detection of Covid-19 positive cases is an important step to fight the pandemic and save human lives. The polymerase chain reaction test is the most used method to detect Covid-19 positive cases. Various molecular methods and serological methods have also been explored to detect Covid-19 positive cases. Machine learning algorithms have been applied to various kinds of datasets to predict Covid-19 positive cases. The machine learning algorithms were applied on a Covid-19 dataset based on commonly taken laboratory tests to predict Covid-19 positive cases. These types of datasets are easy to collect. The paper investigates the application of decision tree ensembles which are accurate and robust to the selection of parameters. As there is an imbalance between the number of positive cases and the number of negative cases, decision tree ensembles developed for imbalanced datasets are applied. F-measure, precision, recall, area under the precision-recall curve, and area under the receiver operating characteristic curve are used to compare different decision tree ensembles. Different performance measures suggest that decision tree ensembles developed for imbalanced datasets perform better. Results also suggest that including age as a variable can improve the performance of various ensembles of decision trees.

Download Full-text