ER Model Partitioning: Towards Trustworthy Automated Systems Development

Pieris, Dhammika; Wijegunesekera, M.C; Dias, N.G.J.

doi:10.14569/ijacsa.2020.0110638

Cited by 2 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The n_estimators parameter for Random Forest models was the number of Decision Trees used. 37,38 Previous studies have observed that a higher max_depth resulted in overfitting and convoluted decision-making. 31 The model did not generalize as well and prioritized making decisions on insignificant features.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Key Molecular Descriptors Distinguishing Between Synthetic and Natural Products

Thomas,

Bhatnagar,

Agarwal

et al. 2023

Preprint

View full text Add to dashboard Cite

The classification of natural products (NPs) from synthetic molecules (SMs) through machine learning techniques creates knowledge of differentiating features and therefore an impetus for possible research in natural product-based drug design. Natural products generally have a higher chemical diversity and biochemical specificity among other properties, making them favorable as lead structures for drug discovery and differentiating them from synthetic molecules. Here, we propose a machine-learning approach with the PaDEL descriptor software to develop a classification method to differentiate NPs and SMs with a variety of molecular features. An ensemble of supervised learning algorithms, including Logistic Regression, Naive Bayes, Random Forests, and Decision Trees, were tested to obtain the optimal feature importance amongst the molecular descriptors and highest accuracy. The experimental accuracy of the best-performing machine learning method outlined in this paper, Random Forests, reached an 89.19% accuracy, comparable with previous models performing the same classification. Identification and classification of distinguishable properties of natural products and synthetic compounds allows for a better understanding of available chemical data and better incorporation of such properties in small molecule drug discovery.

show abstract

Section: Methodsmentioning

confidence: 99%

“…A larger n_estimator value led to overfitting and insignificant feature decisions. 38 To prevent the model from overfitting, the optimal value was found to be at 36 after testing for the n_estimator in the range 1 to 45 (Figure 4b).…”

Section: Methodsmentioning

confidence: 99%

Key Molecular Descriptors Distinguishing Between Synthetic and Natural Products

Thomas,

Bhatnagar,

Agarwal

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Эти редакторы имеют специфическую функциональность, такую как генерация диаграмм из программного кода в сочетании с генерацией программного кода из диаграмм (roundtrip engineering). В доступных научных публикациях исследуется повышение надежности автоматизированных систем в ходе трансформации диаграмм за счет сегментирования модели [1]. Обсуждаются программные средства для автоматического создания визуальных композиций на основе диаграмм [2].…”

unclassified

Extracting Semantic Information from Graphic Schemes

Миронов¹,

Гусаренко²,

Тугузбаев³

2021

View full text Add to dashboard Cite

The problem of extracting semantic information from an electronic document specified in the vector graphics format and containing a graphic model (diagram) built using a graphic editor is considered. The problem is to program retrieving certain structural properties and parametric circuit and entering them into a database for later use. Based on the analysis of the capabilities of graphic editors, a conclusion has made about the relevance of this task for universal editors that are not tied to specific graphic notations and use open graphic document formats, which allows program processing. The proposed approach considers graphic documents at three levels of abstraction: conceptual (semantic properties of a schema), logical (presentation of semantic properties at the internal level of the document) and physical (internal organization of a graphic document). The solution to the problem is based on the construction of a conceptual-logical mapping, i.e., mapping a conceptual model of a circuit to a logical model of a graphic document, according to its physical model. Within the framework of the approach, an algorithm for constructing the indicated mapping is developed, presented in the form of an object-oriented pseudocode. The study of internal markup in open graphic formats made it possible to build models for identifying circuit elements and their connections to each other, which is necessary for a specific application of the algorithm. Expressions for addressing schema elements and accessing their properties are obtained. The proposed approach is implemented on the base of a situation-oriented paradigm, within which the extraction process is driven by a hierarchical situational model. The processed data is specified in the situational model in the form of virtual documents displayed on heterogeneous external data sources. For the problem being solved, we consider the mapping to two variants of vector graphics formats: to a "flat" markup file and to a set of such files in an electronic archive. The practical use of the results is illustrated by the example of extracting semantic information from graphical models developed at various stages of database design.

show abstract

ER Model Partitioning: Towards Trustworthy Automated Systems Development

Cited by 2 publications

References 16 publications

Key Molecular Descriptors Distinguishing Between Synthetic and Natural Products

Key Molecular Descriptors Distinguishing Between Synthetic and Natural Products

Extracting Semantic Information from Graphic Schemes

Contact Info

Product

Resources

About