Using Artificial Intelligence in Chemistry and Biology

Cartwright, Hugh M.

doi:10.1201/9780849384141

Cited by 30 publications

(28 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Cartwright [3] commented that the population size is not critical in the success of a GA, provided that the population size is not unreasonably small (i.e. \40 chromosomes).…”

Section: Discussionmentioning

confidence: 98%

Genetic Algorithm-Neural Network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection

Tong

Mintram

2010

Int. J. Mach. Learn. & Cyber.

130

View full text Add to dashboard Cite

Hybrid genetic algorithms (GA) and artificial neural networks (ANN) are not new in the machine learning culture. Such hybrid systems have been shown to be very successful in classification and prediction problems. However, little attention has been focused on this architecture as a feature selection method and the consequent significance of the ANN activation function and the number of GA evaluations on the feature selection performance. The activation function is one of the core components of the ANN architecture and influences the learning and generalization capability of the network. Meanwhile the GA searches for an optimal ANN classifier given a set of chromosomes selected from those available. The objective of the GA is to combine the search for optimum chromosome choices with that of finding an optimum classifier for each choice. The process operates as a form of co-evolution with the eventual objective of finding an optimum chromosome selection rather than an optimum classifier. The selection of an optimum chromosome set is referred to in this paper as feature selection. Quantitative comparisons of four of the most commonly used ANN activation functions against ten GA evaluation step counts and three population sizes are presented. These studies employ four data sets with high dimension and low significant datum instances. That is to say that each datum has a high attribute count and the unusual or abnormal data are sparse within the data set. Results suggest that the hyperbolic tangent (tanh) activation function outperforms other common activation functions by extracting a smaller, but more significant feature set. Furthermore, it was found that fitness evaluation sizes ranging from 20,000 to 40,000 within populations ranging from 200 to 300, deliver optimum feature selection capability. Again, optimum in this sense meaning a smaller but more significant feature set.

show abstract

“…Cartwright [3] commented that the population size is not critical in the success of a GA, provided that the population size is not unreasonably small (i.e. \40 chromosomes).…”

Section: Discussionmentioning

confidence: 98%

Genetic Algorithm-Neural Network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection

Tong

Mintram

2010

Int. J. Mach. Learn. & Cyber.

130

View full text Add to dashboard Cite

show abstract

“…Not only are they able to learn by inspection of data rather than having to be told what to do, but also they can construct a suitable relationship between input data and the target responses without any need for a theoretical or mathematical model. Unlike many conventional methods, they are able to assess absorption spectra without knowing about the underlying line shape of a spectral feature [15].…”

Section: Results and Suggestionsmentioning

confidence: 99%

“…Expert systems and neural networks were applied to learn site-specific conditions [14]. Most recent scientific applications involve the determination of direct relationships between input parameters and a known target response [15]. They used the methods of fuzzy logic, artificial neural networks, genetic algorithms, decision trees, and support vector machines to study soil and water regimes, analyze the operation of food processing, and support decision-making in precision farming [16] used decision support system to develop land suitability for agriculture.…”

Section: Introductionmentioning

confidence: 99%

Yapay Si̇ni̇r Ağlari Kullanilarak Bağ Budama Artiklarindan Üreti̇len Yonga Levhalarin Özelli̇kleri̇ni̇n Tahmi̇n Edi̇lmesi̇

Gürüler¹,

Ballı²,

Yeniocak³

et al. 2015

Mugla Journal of Science and Technology

View full text Add to dashboard Cite

In this study, chips of vine pruning stalks and wood chips in five various proportions were used as the raw material for three-layer particleboards. Primarily, small size sample panels (56x56x2 cm) were manufactured. The physical (thickness swelling (TS), water absorption (WA), and mechanical (modulus of rupture (MOR), modulus of elasticity (MOE), internal bond (IB), screw holding (SH) properties of particleboards were determined. Although direct measurement is the most reliable method, it is very complex and time consuming. Also every proportion is not applicable. So that, soft computing methods which are the powerful tools for input-output mapping were preferred. Artificial neural networks (ANNs) were used to estimation. The results show that ANN system capable to predict properties of particleboards in a time and cost effective way. Keywords: Neural networks, Agricultural residue, Particleboard, Prediction of properties YAPAY SİNİR AĞLARI KULLANILARAK BAĞ BUDAMA ARTIKLARINDAN ÜRETİLEN YONGA LEVHALARIN ÖZELLİKLERİNİN TAHMİN EDİLMESİ ÖzetBu çalışmada, yonga levha hammaddesi olarak beş farklı oranda, bağ budama yongaları ve odun yongaları kullanılmıştır. Öncelikle küçük boyutlu numune paneller üç katmanlı olarak (56x56x2 cm) üretilmiştir. Bu levhaların; fiziksel (kalınlığına şişme, su alma) ve mekaniksel (eğilme direnci, elastikiyet modülü, iç yapışma ve vida tutma) özellikleri belirlenmiştir. Direk ölçüm alma metodu en güvenilir metot olmasına rağmen çok karmaşık ve zaman alıcıdır. Üstelik her oran uygulanabilir değildir. Bu nedenle girdi-çıktı haritalamada en güçlü araçlar olan esnek (yazılımsal) hesaplama yöntemleri tercih edilmiştir. Bu aşamada, yapay sinir ağları (YSA) tahmin amaçlı kullanıldı. Sonuçlar yapay sinir ağları sisteminin zamandan ve maliyetten kazanç sağlayarak yonga levhaların özelliklerinin belirlenmesinde yetkin olduğunu göstermektedir.

show abstract

“…Os algoritmos inteligentes podem incluir, também, a lógica difusa ("fuzzy logic") 6,9 , uma área de notável interesse científico e industrial. Esta lógica generaliza as regras formais de raciocínio estabelecidas por Aristóteles, permitindo tratar inúmeros problemas complexos caraterizados por incertezas intrínsecas.…”

Section: Algoritmos Genéticosunclassified

Monkey Business: Um Algoritmo Genético

Fernandes

2018

Rev. Ciência Elem.

View full text Add to dashboard Cite

Using Artificial Intelligence in Chemistry and Biology

Cited by 30 publications

References 0 publications

Genetic Algorithm-Neural Network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection

Genetic Algorithm-Neural Network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection

Yapay Si̇ni̇r Ağlari Kullanilarak Bağ Budama Artiklarindan Üreti̇len Yonga Levhalarin Özelli̇kleri̇ni̇n Tahmi̇n Edi̇lmesi̇

Monkey Business: Um Algoritmo Genético

Contact Info

Product

Resources

About