Preferred Language
Articles
/
ijs-4145
A New Method in Feature Selection based on Deep Reinforcement Learning in Domain Adaptation

    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.

Scopus Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Tue May 09 2023
Journal Name
Karbala International Journal Of Modern Science
Scopus (1)
Crossref (1)
Scopus Crossref
View Publication
Publication Date
Wed May 17 2023
Journal Name
College Of Islamic Sciences
Dignity in the books of faith

The issue of dignity is one of the topics that do not pass as long as the earths and the heavens remain; Because the earth is not devoid of the righteous, the believers, the saints, and the pious, and these do not cease from them aid, dignity, insight, or good vision, and from here the authorship in this section was continuous; Because the people’s need for it is confirmed as time progresses, and in that, Ibn Taymiyyah says in the sum of his fatwas, “And from what it should be known is that dignities may be according to the man’s need, so if the weak needs them Faith or the needy, he is given from it what strengthens his faith and fulfills his needs, and he who is more complete is the guardianship of God than him. He is independent

... Show More
View Publication Preview PDF
Publication Date
Thu Jun 15 2023
Journal Name
Journal Of Legal Sciences
Investment of Mortgage in Pledged Property

The investment of something mortgaged is defined as the creditor's use of the mortgaged object within the possessed guarantee, so that it will produce certain profit increasing its produce when he uses that for himself or rents it to somebody else or to the creditor himself after discounting his produce from the debt of the mortgagee. The investment of the object mortgaged is the right of the creditor and a commitment imposed upon him simultaneously. If he execute his commitment of investing the mortgaged object which adds a fruit to the produce, the fruit can be discounted from the debt of the mortgaged object; that is to say, a clearing is made between the fruit of the mortgaged object and debt that stands for the object mortgaged. If

... Show More
Crossref
View Publication Preview PDF
Publication Date
Tue Mar 15 2022
Journal Name
Al-academy
Forecasting in international logos' design styles

Forecasting has become common process and reality. Since man has found multiple forms of simple predictive predictions, fruitful predictive results have emerged, such as weather forecasting or trading on stock exchange. The research was organized by defining the problem, which was manifested by the question:
(What is the prediction in global logo design methods?)
The aim of the research: (revealing design prediction in the methods of global logos). The theoretical framework was: (the concept of prediction in the design of global logos), (methods of global logos), (types of prediction) and then were attached to indicators, results and conclusions, including:
- The color value of international logos came with human needs: a

... Show More
Crossref
View Publication Preview PDF
Publication Date
Thu Sep 15 2022
Journal Name
Al-academy
Actor's skills in pantomime theater performances

The art of pantomime mime is one of the arts that has taken a wide space in theater performances, and because it is one of the spectacle shows that relies on an acting performance that is unique from the traditional acting performance, because of the peculiarity of pantomime art in that it is a silent performance that assumes the clarity of meaning, and for the purpose of clarifying the actor’s work in such kind of performances, the art of pantomime must be We have to know the skills that the actor can possess in order to produce a silent show that has the elements of a successful presentation, so there was a need to study the skills of the actor in this type of acting performance. The researchers divided this study into an introductio

... Show More
Crossref
View Publication Preview PDF
Publication Date
Fri Feb 01 2019
Journal Name
Journal Of The College Of Education For Women
Presupposition in Fitzgerald the Rough Crossing

Presupposition in Fitzgerald the Rough Crossing

View Publication Preview PDF
Publication Date
Sun Jan 02 2011
Journal Name
Journal Of The Faculty Of Medicine Baghdad
Microvessel density in Renal Cell Carcinoma

Background: Prognostic histological evaluation of many cancers have recently concentrated on angiogenesis.
Materials &Methods: A total of twenty formaline-fixed, paraffin embedded blocks of renal cell carcinoma were included in this study. Sections were subjected for immunohistochemical staining of CD34. The median of the MVD of all cases of RCC were obtained to divide the cases into high- and low-MVD score groups and were correlated with the tumor stage and grade.
Results: there was a significant correlation of the high MVD score with tumor stage (P=0.02).
Conclusion: MVD may be considered as a potential prognostic marker for RCC.

Crossref
View Publication Preview PDF
Publication Date
Sun Dec 30 2012
Journal Name
Al-kindy College Medical Journal
Analgesic Effect of Melatonin in Mice

Background: Melatonin is the main hormone secreted by the pineal gland. This indole compound (N-acetyl-5-methoxytryptamine) is derived from serotonin after two biochemical steps. Melatonin has been implicated in some pharmacological effects including sedative/hypnotic, anticonvulsant activity and others. The aim of this study was to investigate the antinociceptive effect of different doses of melatonin administered i.p. to mice, and then, to find the dose- response line of melatonin in mice as analgesic agent.
Methods: The dose response effect of melatonin (10, 50, and 100mg/kg) were assessed against control using tail flick test in mice as a model of nociceptive pain. In this model, all doses of melatonin were given intraperitoneally

... Show More
View Publication Preview PDF
Publication Date
Sun Mar 15 2020
Journal Name
Journal Of Baghdad College Of Dentistry
Canine malposition in Iraqi dental students

Background: This study aims to assess the prevalence of malposed canines among students of College of Dentistry/ University of Baghdad and evaluate the relation between canine malposition and occlusal features.

Material and method: The prevalence of buccally malposed canines was estimated by intra-oral visual examination of 250 young adult subjects (106 males and 144 females), their ages were between 19-24 years.

Results: The prevalence of the mandibular malposed canine (12%) was higher than the maxillary buccally malposed canine (10%). Generally, malposed canines were found higher in f

... Show More
Scopus Crossref
View Publication Preview PDF
Publication Date
Thu Mar 14 2019
Journal Name
Al-khwarizmi Engineering Journal
Cellulose Fibers Dissolution in Alkaline Solution

In this study, NaOH dissolution method was applied to dissolve cellulose fibers which extracted from date palm fronds (type Al-Zahdi) taken from Iraqi gardens. In this process, (NaOH)-solution is brought into contact with the cellulose fibers at low temperature. Experiments were conducted with different concentrations of NaOH (4%, 6%, 8% and12%) weight percent at two cooling bath temperatures (-15 oC) and (-20oC). Maximum cellulose dissolution was 23 wt% which obtained at 8 wt% concentration of NaOH and at cooling bath temperature of -20oC. In order to enhance the cellulose fibers dissolution, the sample was pretreated with Fenton's reagent which consists of

... Show More
Crossref (4)
Crossref
View Publication Preview PDF