Wyniki wyszukiwania - BazTech

1

Kontradyktoryjne uczenie maszynowe

Kuznetsov Phillip, Edmunds Riley, Xiao Ted, Iqbal Humza, Puri Raul, Golmant Noah, Shih Shannon

Napędy i Sterowanie

|

2021

|

R. 23, nr 7/8

80--89

PL

Dzięki ogromnej ilości zasobów oraz znacznego zainteresowania skupionego ostatnio na SI można zaobserwować liczne formy inteligentnych agentów wyposażonych w różnorodne unikatowe i nowatorskie możliwości. Potencjał oddziaływania jest nieograniczony, aczkolwiek odnotowywano już przykłady, w których decyzje podejmowane przez sztuczną inteligencję były niezrozumiałe.

2

Supervised probabilistic failure prediction of tuned mass damper-equipped high steel frames using machine learning methods

Farrokhi Farshid, Rahimi Sepideh

Studia Geotechnica et Mechanica

|

2020

|

Vol. 42, nr 3

179--190

EN

In this study, firstly, the behavior of a high steel frame equipped with tuned mass damper (TMD) due to several seismic records is investigated considering the structural and seismic uncertainties. Then, machine learning methods including artificial neural networks (ANN), decision tree (DT), Naïve Bayes (NB) and support vector machines (SVM) are used to predict the behavior of the structure. Results showed that among the machine learning models, SVM with Gaussian kernel has better performance since it is capable of predicting the drift of stories and the failure probability with R2 value equal to 0.99. Furthermore, results of feature selection algorithms revealed that when using TMD in high steel structures, seismic uncertainties have greater influences on drift of stories in comparison with structural uncertainties. Findings of this study can be used in design and probabilistic analysis of high steel frames equipped with TMDs.

3

Order estimation of japanese paragraphs by supervised machine learning and various textual features

Murata M., Ito S., Tokuhisa M., Ma Q.

Journal of Artificial Intelligence and Soft Computing Research

|

2015

|

Vol. 5, No. 4

247--255

EN

In this paper, we propose a method to estimate the order of paragraphs by supervised machine learning. We use a support vector machine (SVM) for supervised machine learning. The estimation of paragraph order is useful for sentence generation and sentence correction. The proposed method obtained a high accuracy (0.84) in the order estimation experiments of the first two paragraphs of an article. In addition, it obtained a higher accuracy than the baseline method in the experiments using two paragraphs of an article. We performed feature analysis and we found that adnominals, conjunctions, and dates were effective for the order estimation of the first two paragraphs, and the ratio of new words and the similarity between the preceding paragraphs and an estimated paragraph were effective for the order estimation of all pairs of paragraphs.

4

The effectiveness of applied treatment in Parkinson disease based on feature selection of motion activities

Świtoński A., Stawarz M., Boczarska-Jedynak M., Sieroń A., Polański A., Wojciechowski K.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 12b

103-106

EN

The analysis of effectiveness of deep brain stimulation and pharmacological treatment in Parkinson disease is presented. It is based on an examination of discriminative properties of distinctive motion features. The feature extraction and selection of kinematical motion data is carried out. The attribute ranking with entropy based attribute evaluation and greedy hill climbing search with assessment of an average inner class dissimilarity are applied. The obtained results show that deep brain stimulation has greater impact on investigated motion activities.

PL

W pracy zaprezentowano analizę skuteczności stymulacji prądowej jądra niskowzgórzowego oraz leczenia farmakologicznego w chorobie Parkinsona. W tym celu badano właściwości dyskryminacyjne, charakterystycznych cech ruchu. Dla danych kinematycznych przeprowadzono ekstrakcję, a następnie selekcję cech. Zastosowano ranking atrybutów bazujący na entropii i zachłanne przeszukiwanie wspinaczkowe z oceną średniej odległości wewnątrzgrupowej. Uzyskane wyniki wykazują większy wpływ stymulacji prądowej na badane czynności ruchowe. (Skuteczność leczenia w chorobie Parkinsona na podstawie selekcji charakterystycznych cech ruchu).

5

Research of Image Features for Classification of Wear Debris

Juránek R., Machalik S., Zemčik P.

Machine Graphics and Vision

|

2011

|

Vol. 20, No. 4

479-493

EN

The wear debris of engineering equipment (such as combustion engines, gearboxes, etc.) consists of metal particles which can be obtained from lubricants used in the equipment. The analysis of wear particles is very important for early detection and prevention of failures. The analysis is often done using classication of individual wear particles obtained by analytical ferrography. In this paper, we present a study of feature extraction methods for a classication of wear particles based on visual similarity. The main contribution of the paper is the comparison of nine selected feature types in the context of three state-of-the-art learning models. Another contribution is the large public database of particle images which can be used for further experiments. The paper describes the dataset, presents the methods of classication, demonstrates the experimental results, and draws conclusions.

6

Efficient Graph Kernels for Textual Entailment Recognition

Zanzotto F. M., Dell'Arciprete L., Moschitti A.

Fundamenta Informaticae

|

2011

|

Vol. 107, nr 2/3

199-222

EN

One of the most important research area in Natural Language Processing concerns the modeling of semantics expressed in text. Since foundational work in Natural Language Understanding has shown that a deep semantic approach is still not feasible, current research is focused on shallow methods combining linguistic models and machine learning techniques. The latter aim at learning semantic models, like those that can detect the entailment between the meaning of two text fragments, by means of training examples described by specific features. These are rather difficult to design since there is no linguistic model that can effectively encode the lexico-syntactic level of a sentence and its corresponding semantic models. Thus, the adopted solution consists in exhaustively describing training examples by means of all possible combinations of sentence words and syntactic information. The latter, typically expressed as parse trees of text fragments, is often encoded in the learning process using graph algorithms. In this paper, we propose a class of graphs, the tripartite directed acyclic graphs (tDAGs), which can be efficiently used to design algorithms for graph kernels for semantic natural language tasks involving sentence pairs. These model the matching between two pairs of syntactic trees in terms of all possible graph fragments. Interestingly, since tDAGs encode the association between identical or similar words (i.e. variables), it can be used to represent and learn first-order rules, i.e. rules describable by first-order logic. We prove that our matching function is a valid kernel and we empirically show that, although its evaluation is still exponential in the worst case, it is extremely efficient and more accurate than the previously proposed kernels.

7

A new algorithm for generation of decision trees

Grzymała-Busse J. W., Hippe Z. S., Knap M., Mroczek T.

TASK Quarterly : scientific bulletin of Academic Computer Centre in Gdansk

|

2004

|

Vol. 8, No 2

243-247

EN

A new algorithm for development of quasi-optimal decision trees, based on the Bayes theorem, has been created and tested. The algorithm generates a decision tree on the basis of Bayesian belief networks, created prior to the formation of the decision tree. The efficiency of this new algorithm was compared with three other known algorithms used to develop decision trees. The data set used for the experiments was a set of cases of skin lesions, histopatolgically verified.