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.
Background: Oral SCC is a complex malignancy where environmental factors, viral infections and genetic alterations most likely interact, and thus give rise to the malignant condition. The HSP70 play a direct role in apoptosis inhibition by aligning the improved integrity of a cell’s proteins with the improved chances of that particular cell’s survival.P21 gene produces p21 protein which is a potent cyclin-dependent kinase inhibitor that plays a significant role in carcinogenesis. The aims of the study were to evaluate and compare the immun-histochemical expression of the HSP70 and cell cycle protein p21in NOM, OED, and OSCC. Correlate both marker expressions with each other. Materials and methods: Forty six formalin-fixed, par
... Show MoreDiabetic mellitus is one of the main risk factors of fungal infections because poor glycemic control is associated with a high level of glucose in blood and saliva which could be treated as nutrient to fungi. This study aimed to isolate and identification of pathogenic fungi from diabetic patient. 140 samples were taken from different places of human body from the national center of diabetic patients that related to Mustansiriyah University / college of medicine and Al-yarmuk Hospital in Baghdad. 84 sample (60%) tested positive to fungi and 56 sample (40%) tested negative to fungi. The most frequented fungi isolated have been chosen for molecular identification by PCR (Millerozyma farinosa and Candida orthopsilosis) using specific pri
... Show MoreA total number of 33 isolates of Pseudomoans aeruginosa were collected from different clinical samples, such as: burn, wound and urine from patients attending Al-Yarmouk teaching hospital and some private clinical laboratories in Baghdad city through the period from October to December 2016. On the other hand, 21 isolates of P. aeruginosa were collected from 38 different food samples; such as: vegetables and fruits, from different local markets in Baghdad city during the period from November to December 2016. All isolates were identified by using different bacteriological and biochemical assays and confirmed by Vitek-2 identification system. The antimicrobial susceptibility test for clinical and food isolates towards 17 antimicrobial a
... Show MoreIn this research an Artificial Neural Network (ANN) technique was applied for the prediction of Ryznar Index (RI) of the flowing water from WTPs in Al-Karakh side (left side) in Baghdad city for year 2013. Three models (ANN1, ANN2 and ANN3) have been developed and tested using data from Baghdad Mayoralty (Amanat Baghdad) including drinking water quality for the period 2004 to 2013. The results indicate that it is quite possible to use an artificial neural networks in predicting the stability index (RI) with a good degree of accuracy. Where ANN 2 model could be used to predict RI for the effluents from Al-Karakh, Al-Qadisiya and Al-Karama WTPs as the highest correlation coefficient were obtained 92.4, 82.9 and 79.1% respectively. For
... Show MoreLead acetate as one of the environmental pollutants can threats the life of living creatures in many ways, it has a long half-life, accumulates mainly in the soft tissue and leads to adverse effects in these tissues. An experiment was conducted to study the effect of oral feeding of lead acetate on histological features of liver, kidney, testis and muscle of albino mice. Mice were treated with 0.05 mg/100 ml lead acetate (LA) for 10 days (group A) and for and for 20 days (group B) and for 30 days (group C). The histological section of liver of mice group A characterized by slightly blurred trabecular structure with foci of hepatitis which increased with cytoplasmic vacules in group B but in group C liver reveal necrosis, heamorrhage,
... Show MoreIntroduction and Aim: Klebsiella pneumoniae is a Gram-negative bacterium responsible for a wide range of infections, including respiratory tract infections (RTIs). This research was aimed to study the antibacterial and anti-biofilm effect of AgNPs produced by Gram positive and negative bacteria on RTIs associated with K. pneumoniae. Materials and Methods: The biofilm formation of K. pneumoniae was determined by tube method qualitatively from select bacterial species characterized by UV-Visible spectroscopy. The antibacterial susceptibility of the bacteria AgNPs was tested for their antibacterial and antibiofilm activity on a clinical isolate of K. pneumoniae. Results: K. pneumoniae isolated from RTIs were strong biofilm prod
... Show More