In data mining and machine learning methods, it is traditionally assumed that training data, test data, and the data that will be processed in the future, should have the same feature space distribution. This is a condition that will not happen in the real world. In order to overcome this challenge, domain adaptation-based methods are used. One of the existing challenges in domain adaptation-based methods is to select the most efficient features so that they can also show the most efficiency in the destination database. In this paper, a new feature selection method based on deep reinforcement learning is proposed. In the proposed method, in order to select the best and most appropriate features, the essential policies in deep reinforcement learning are defined, and then the selection features are applied for training random forest, k-nearest neighborhood and support vector machine classifiers. The trained classifiers with the considered features are evaluated on the target database. The results are evaluated with the criteria of accuracy, sensitivity, positive and negative predictive rates in the classifiers. The achieved results show the superiority of the proposed method of feature selection when used in domain adaptation. By implementing the RF classifier on the VisDA-2018 database and the Syn2Real database, the classification accuracy in the feature selection of the proposed deep learning reinforcement has increased compared to the two-feature selection of Laplace monitoring and feature selection states. The classification sensitivity with the help of SVM classifier on the Syn2Real databases had the highest values in the feature selection state of the proposed deep learning reinforcement. The obtained number 100 is a positive predictive rate in the Syn2Real database with the help of SVM classifier and in the case of selecting the proposed feature, it indicates its superiority. The negative predictive rate in the Syn2Real database in the state of feature selection of the proposed deep reinforcement learning was 100%, which showed its superiority in comparison with 90.1% in the state of selecting the Laplace monitoring feature. Gmean in KNN classifier on the Syn2Real database has improved in the feature selection state of the proposed deep learning reinforcement in comparison to without feature selection state.
Plasma physics and digital image processing technique (DIPT) were utilized in this research to show the effect of the cold plasma (plasma needle) on blood cells. The second order statistical features were used to study this effect. Different samples were used to reach the aim of this paper; the patients have leukemia and their leukocytes number was abnormal. By studying the results of statistical features (mean, variance, energy and entropy), it is concluded that the blood cells of the sample showed a good response to the cold plasma.
Theoretical calculation of the electronic current at N 3 contact with TiO 2 solar cell devices ARTICLES YOU MAY BE INTERESTED IN Theoretical studies of electronic transition characteristics of senstizer molecule dye N3-SnO 2 semiconductor interface AIP Conference. Available from: https://www.researchgate.net/publication/362813854_Theoretical_calculation_of_the_electronic_current_at_N_3_contact_with_TiO_2_solar_cell_devices_ARTICLES_YOU_MAY_BE_INTERESTED_IN_Theoretical_studies_of_electronic_transition_characteristics_of_senstiz [accessed May 01 2023].
In this manuscript, the effect of substituting strontium with barium on the structural properties of Tl0.8Ni0.2Sr2-xBrxCa2Cu3O9-δcompound with x= 0, 0.2, 0.4, have been studied. Samples were prepared using solid state reaction technique, suitable oxides alternatives of Pb2O3, CaO, BaO and CuO with 99.99% purity as raw materials and then mixed. They were prepared in the form of discs with a diameter of 1.5 cm and a thickness of (0.2-0.3) cm under pressures 7 tons / cm2, and the samples were sintered at a constant temperature o
... Show MoreLoss of drilling fluid in the Nasiriyah oil field can be considered as a big,
serious, and expensive problem at the same time, therefore accurate and integrated
program must be prepared before start drilling in layers that are likely to get loss
circulation. From the available data of well Ns-13, the area of loss was detected in
five layers, which are Dammam, Um- radoma, Tayarat, Shiranish and Hartha since
these layers contain natural cracks and high porosity represented by vugs.
Methods of prevention have been identified by specifying the minimum values
of drilling parameters to reduce hydrostatic pressure, thus reducing equivalent
density of drilling mud during the circulation, depths of casing shoes is
deter
The huge amount of information in the internet makes rapid need of text
summarization. Text summarization is the process of selecting important sentences
from documents with keeping the main idea of the original documents. This paper
proposes a method depends on Technique for Order of Preference by Similarity to
Ideal Solution (TOPSIS). The first step in our model is based on extracting seven
features for each sentence in the documents set. Multiple Linear Regression (MLR)
is then used to assign a weight for the selected features. Then TOPSIS method
applied to rank the sentences. The sentences with high scores will be selected to be
included in the generated summary. The proposed model is evaluated using dataset
Construction projects are complicated in nature and require many considerations in contractor selection. One of the complicated interactions is that between performance with the project size, and contractor financial status, and size of projects contracted. At the prequalification stage, the financial requirements restrict the contractors to meet minimum limits in financial criteria such as net worth, working capital and annual turnover, etc. In construction projects, however, there are cases when contractors meet these requirements but show low performance in practice. The model used in the study predicts the performance by training of a neural network. The data used in the study are 72 of the most recent roadw
... Show MoreIn this article, we propose a Bayesian Adaptive bridge regression for ordinal model. We developed a new hierarchical model for ordinal regression in the Bayesian adaptive bridge. We consider a fully Bayesian approach that yields a new algorithm with tractable full conditional posteriors. All of the results in real data and simulation application indicate that our method is effective and performs very good compared to other methods. We can also observe that the estimator parameters in our proposed method, compared with other methods, are very close to the true parameter values.
In this paper, the proposes secure system to improving security of ID card and passports is by generating cubic spline co-occurrence code (CCO code) for each ID card. The authentication part, begins passing ID card through the checkpoint then the checkpoint will check the information of card or passport by also extracting features in order to generate the cubic spline co-occurrence code (CCO code), finally comparison is made between extracted CCO code at the checkpoint and CCO code that has been printed on ID card or passport (type of fraud like change personal picture or fraud it’s information). Several tests were conducted to evaluate the performance of the proposed security system. Furthermore, the experiment results reveal that the
... Show MoreThis search has introduced the techniques of multi-wavelet transform and neural network for recognition 3-D object from 2-D image using patches. The proposed techniques were tested on database of different patches features and the high energy subband of discrete multi-wavelet transform DMWT (gp) of the patches. The test set has two groups, group (1) which contains images, their (gp) patches and patches features of the same images as a part of that in the data set beside other images, (gp) patches and features, and group (2) which contains the (gp) patches and patches features the same as a part of that in the database but after modification such as rotation, scaling and translation. Recognition by back propagation (BP) neural network as com
... Show More