Search

Feature selection is an essential stage in many data mining and machine learning and applications that find the proper subset of features from a set of irrelevant, redundant, noisy and high dimensional data. This dimensional reduction is a vital task to increase classification accuracy and thus reduce the processing time. An optimization algorithm can be applied to tackle the feature selection problem. In this paper, a $$\beta$$ -hill climbing optimizer is applied to solve the feature selection problem. $$\beta$$ -hill climbing is recently introduced as a local-search based algorithm that can obtain pleasing solutions for different optimization problems. In order to tailor $$\beta$$ -hill climbing for feature selection, it has to be adapted to work in a binary context. The S-shaped transfer function is used to transform the data into the binary representation. A set of 22 de facto benchmark real-world datasets are used to evaluate the proposed algorithm. The effect of the $$\beta$$ -hill climbing parameters on the convergence rate is studied in terms of accuracy, the number of features, fitness values, and computational time. Furthermore, the proposed method is compared against three local search methods and ten metaheuristics methods. The obtained results show that the proposed binary $$\beta$$ -hill climbing optimizer outperforms other comparative local search methods in terms of classification accuracy on 16 out of 22 datasets. Furthermore, it overcomes other comparative metaheuristics approaches in terms of classification accuracy in 7 out of 22 datasets. The obtained results prove the efficiency of the proposed binary $$\beta$$ -hill climbing optimizer.

Feature selection (FS) is considered to be a hard optimization problem in data mining and some artificial intelligence fields. It is a process where rather than studying all of the features of a whole dataset, some associated features of a problem are selected, the aim of which is to increase classification accuracy and reduce computational time. In this paper, a recent optimization algorithm, the monarch butterfly optimization (MBO) algorithm, is implemented with a wrapper FS method that uses the k-nearest neighbor (KNN) classifier. Experiments were implemented on 18 benchmark datasets. The results showed that, in comparison with four metaheuristic algorithms (WOASAT, ALO, GA and PSO), MBO was superior, giving a high rate of classification accuracy of, on average, 93% for all datasets as well as reducing the selection size significantly. Therefore, the use of the MBO to solve the FS problems has been proven through the results obtained to be effective and highly efficient in this field, and the results have also proven the strength of the balance between global and local search of MBO.

Background: Chronic low-grade inflammation is a common feature of obesity and polycystic ovary syndrome (PCOS). There is dysregulation of transforming growth factor (TGF)-β1 in women with PCOS, soluble endoglin (sEng) is a non-signaling coreceptor of the TGF-β modulating its responses. We aimed for the first time to investigate the impact of obesity on sEng and TGF-β1 in women with PCOS. Methods: Case control study enrolled seventy patients diagnosed with PCOS and50 control group. High sensitivity C-reactive protein (hs-CRP) and sEng levels were assessed using an enzyme-linked immunosorbent assay (ELISA). Results: Our results revealed that, PCOS patients had higher values of TGF-β1 and lower levels of sEng. Among both control and PCOS patients, obese subjects had higher values of TGF-β1 and lower levels of sEng. Receiver operating characteristic curve (ROC) analysis revealed that, the power of sEng was more sensitive and specific than TGF-β1 in diagnosis of PCOS and in differentiating obese from lean group. Nonetheless, the diagnostic power of both TGF-β1 and sEng was highly significant. Conclusion: Obese subjects of control and PCOS groups had higher values of TGF-β1 and lower values of plasma sEng level than lean subjects, the diagnostic power of both TGF-β1 and sEng was highly significant thus, sEng and TGF-β1 could be a useful diagnostic biomarker of PCOS. Keywords: Obesity, PCOS, TGF-β1, Soluble endoglin

Background: Polycystic ovary syndrome (PCOS) is associated with a high risk of cardiovascular diseases (CVD). Visfatin is an adipocytokine with insulin-like action and it’s closely related to the amount of visceral fats. The objective of our study was to evaluate serum visfatin levels among women with PCOS. Also, to evaluate the association between serum visfatin and cardio-metabolic risk factors as well as clinic-morphological features of PCOS. Methods: Case control study enrolled 120 women diagnosed with PCOS and 80 healthy control women. PCOS cases were stratified according to their fasting plasma glucose (FPG) into three subgroups: those with normal glucose tolerance (NGT), impaired glucose tolerance (IGT) and type 2 diabetes mellitus (T2DM). Serum visfatin levels (ng/ml) were assessed by ELISA. Results: Our results revealed higher values of cardio-metabolic risks; total cholesterol, triglycerides, LDL cholesterol, high-sensitivity C-reactive protein (hs-CRP), fasting serum insulin (FSI), HbA1c, HOMA-IR, and FPG in PCOS compared to healthy women. In addition, compared with healthy women (28.66 ± 10.63), PCOS patients (87.98 ± 17.96) had significantly higher levels of serum visfatin. Among PCOS group, T2DM patients (119.59 ± 14.52) had significantly higher levels of serum visfatin compared to IGT (81.03 ± 15.81) and NGT (85.09 ± 11.01). Receiver operating characteristic analyses revealed that serum visfatin was a useful biomarker discriminating PCOS from control, the AUC was 0.989 with sensitivity = 99.2%, specificity = 99.8%, Additionally, the sensitivities and the specificities of visfatin in differentiating T2DM from NGT were (93.3% and 98.2%). Stepwise multiple linear regression analysis revealed that androstenedione, LH, free androgen index and ovarian volume were the main predictors of visfatin levels among PCOS. Conclusion: Serum visfatin levels could discriminate PCOS from healthy control and T2DM from NGT PCOS women. Moreover, vesfatin was positive correlated to cardio-metabolic risk factors. Interestingly, the sensitivity and specificity power of vesfatin were high. Thus, it could be early predicting of cardio-metabolic risks among PCOS women and might be useful in therapeutic intervention in future. Keywords: Cardiometabolic, PCOS, Visfatin, T2DM

Background: Menopause associated with hormone-sensitive co-morbidity such as breast cancer, endometrial cancer, osteoporosis, and cardiovascular disease. Autoimmunity is one of the leading causes of primary ovarian insufficiency (POI). Thyroiditis is the most common associated autoimmune disease. The aim of our study was to estimate the role of Anti-Müllerian hormone (AMH) as predictor of POI among women with autoimmune thyroiditis and to assess the prevalence of thyroid dysfunction in different menopausal stages. Method of study: A cross-sectional study included 200 unrelated women with autoimmune thyroiditis classified according to menopausal stages, anti-thyroglobulin (anti-TG), anti-thyroid peroxidase (anti-TPO) and AMH were measured. Results: In postmenopausal women (natural and premature) AMH levels were significantly lower. Linear regression analysis test explored that AMH levels were independently correlated with age, anti TG and ovarian volume. The prevalence of subclinical hypothyroidism (SCHT) was the highest among thyroid disorders. Conclusion: AMH levels were decreased in both natural and premature postmenopausal women and could be used as predictor of menopause among women with autoimmune thyroiditis. Keywords: Anti-thyroglobulin, Anti-thyroid peroxidase, Postmenopausal

Searching for the optimal subset of features is known as a challenging problem in feature selection process. To deal with the difficulties involved in this problem, a robust and reliable optimization algorithm is required. In this paper, Grasshopper Optimization Algorithm (GOA) is employed as a search strategy to design a wrapper-based feature selection method. The GOA is a recent population-based metaheuristic that mimics the swarming behaviors of grasshoppers. In this work, an efficient optimizer based on the simultaneous use of the GOA, selection operators, and Evolutionary Population Dynamics (EPD) is proposed in the form of four different strategies to mitigate the immature convergence and stagnation drawbacks of the conventional GOA. In the first two approaches, one of the top three agents and a randomly generated one are selected to reposition a solution from the worst half of the population. In the third and fourth approaches, to give a chance to the low fitness solutions in reforming the population, Roulette Wheel Selection (RWS) and Tournament Selection (TS) are utilized to select the guiding agent from the first half. The proposed GOA_EPD approaches are employed to tackle various feature selection tasks. The proposed approaches are benchmarked on 22 UCI datasets. The comprehensive results and various comparisons reveal that the EPD has a remarkable impact on the efficacy of the GOA and using the selection mechanism enhanced the capability of the proposed approach to outperform other optimizers and find the best solutions with improved convergence trends. Furthermore, the comparative experiments demonstrate the superiority of the proposed approaches when compared to other similar methods in the literature.

Background: Endometrial polyps are a main cause of Abnormal Uterine Bleeding (AUB) in premenopausal & postmenopausal women and suggested by screening transvaginal ultrasound. Objectives: The aim of the current study was to determine the effectiveness and acceptability of outpatient hysteroscopic endometrial polypectomy by vaginoscopic approach, and if the technique confers any advantage in term of patient discomfort and reduction in procedure time over the traditional technique. Patients & Methods: This study is prospective randomized clinical trial, it was carried in Endoscopy Unit in the Department of Obstetrics and Gynecology at Zagazig University Hospitals, in period from May 2018 to April 2019. Results: there was a statistical significant difference between traditional and vaginoscopic groups in procedure time where traditional technique needs more time than vaginoscopic one (7.8 VS 6.1 minutes), and all cases had (100.0%) success rate of polypectomy in both groups without complication. but histopathology results discovered one case (2.5%) of all study groups adenocarcinoma and the patient sent to oncology unit for further evaluation and appropriate management. Conclusions: Office vaginoscopic polypectomy for small polyp is feasible and safe minimally invasive procedure.

Background: labor induction between 41 and 42 weeks of gestation reduce the adverse perinatal risks. Aim of work: to determine the effect of intravenous dexamethazone administration on preparing the cervix and duration of labor induction in term pregnancy. Patients and Methods: this randomized Case control study on 52 women who were primparous, with a gestational age (40- 42)weeks and had Bishop Score 4 or less, who were admitted to obstetrics and gynecology department, zagazig university hospital during period from (April 2018 – April 2019) for the termination of their pregnancy. 6 hours before induction, experimental group (26 participants) was given 8mg intravenous dexamethasone while control group (26 participants) was given 2 ml saline intravenously. Six hours after the injection, the Bishop Score of participant was measured, and labor induction done by using oxytocin. Interval between induction initiation and starting of the active labor phase, duration of first and second stage of labor and the neonatal outcome of two groups were compared. Results: Bishop Score statistically differ between the studied groups after 6 hours of dexamethasone injection (5.88±1.18, vs. 5.19±0.85 respectively). The interval between induction initiation and beginning of active labor phase was shorter in the dexamethasone group compared to control group (90±26.3 minutes vs. 112.88±48.87 minutes). Dexamethasone group has shorter duration of first stage and second stage of labor than control group. Conclusions: The administration of dexamethasone can play a role in cervical ripening and progress of labor.

As new devices and technologies are invented to access the internet, from computer desktops, laptops, mobile phones to smart TVs, there has been a great need to upgrade the techniques used in the field of website design, because these new devices come along with their own specific sizes and views. Although most devices & technologies try to be as compatible as possible with the common web design features, but there has been an absolute need for website designers to do a lit bit more to adapt to the fast growing race in internet devices and provide all their viewers with the best possible experience while accessing their websites. In this paper, different responsive website design techniques are presented that could adapt to different technologies and devices while at the same time focusing on cutting down the time and effort needed for a website designer or programmer to maintain and edit it. The code samples in this paper were implemented using the ASP.net programming language, but it can be implemented in other development languages and environments using the same concepts.

Rapid data growth presents many challenges for Machine Learning (ML) tasks as it can include lots of irrelevant, noisy, and redundant features. Thus, it is vital to select the most relevant features to the classification task, known as Feature Selection (FS). The main goal of FS techniques is to maximize the performance of a classification task while keeping the number of features to a minimum. In this study, a hybrid metaheuristic model is designed to solve FS problems based on Binary Biogeography Optimization (BBO) followed by the application of Support Vector Machine Recursive Feature Elimination (SVM-RFE), known as BBO-SVM-RFE. The SVM-RFE is embedded into the BBO to improve the quality of the obtained solutions in the mutation operator in order to enhance the exploitation capability as well as striking an adequate balance between exploitation and exploration of the original BBO. The proposed BBO-SVM-RFE method for solving FS problems was assessed on eighteen benchmark datasets. Comparative results showed that the BBO-SVM-RFE method outperforms the BBO method and other existing wrapper and filter methods in terms of accuracy and number of selected features. The obtained results reveal the high potentiality of BBO-SVM-RFE in reliably searching the feature space to obtain the optimal combination of features.

night vision has been the debate of extensive research during the last ten years, primarily due to its importance in many real applications. In this research a brightness compensation system in vision images and videos based on Evolutionary Algorithms (EAs) was proffered. Enhanced Particle Swarm Optimization (EPSO) has been proved to be effective at finding optimal solutions of the proposed visioning problem by adapting the best global parameters of a novel extension to a local adaptive vision technique. As well the framework of the proposed system is being accurately developed and tested, and the mathematical analysis is mainly depends on the fitness score being developed, peak-signal- noise-ratio and the averaged brightness. Where the feasibility of the proposed system is compared with Differential Evolution (DE) and Artificial Neural Networks (ANNs). At all, the prototype of the system is envisaged to be applicable in many domains, and the avail of this systems leads to a so- called color night vision system.

Objective: To compare the degree of difficulty and outcome measures of hysteroscopic myomectomy of submucous fibroid according to 2 classification systems. Methods: This prospective study conducted in the Cytogenetic & Endoscopy unit, Zagazig University Hospitals during the period from July 2009 to July 2012, included 100 patients candidates for hysteroscopic resection of submucous fibroids. All fibroids were diagnosed and assessed by saline infusion sonohysterography and diagnostic hysteroscopy. Presurgical classification was performed according to the two classification systems; the European Society of Endoscopic Surgery (ESES)–considering only the penetration of the fibroid into the myometrium – and STEPW considering size, topography, extension, penetration and wall affected. Primary outcome measure was incomplete resection of the fibroid. Secondary outcome measures were operating time (in minutes), the fluid deficit (in milliliters) and any intraoperative complications. Sensitivity, specificity and kappa measure of agreement were calculated for each classification at their best cut off. P value less than 0.05 is considered significant. Results: Myomectomy was considered incomplete in 8 out of 104 fibroids (7.7%) According to ESES, 2 belonged to type 0 and 6 belonged to type 1.Risk ratio and 95% confidence interval (CI) was 0.56 (0.07-3.3) and the difference was not significant (p=0.7); whereas according to the STEPW classification, the incomplete myomectomies were one in group I (1/8, 12.5%) and seven in group II (7/8, 87.5%). The risk ratio (95% CI) was 0.02 (0.0-0.18) and the difference was significant (p= 0.000). Considering the area under the ROC curve, the dichotomized STEPW scores performed better than the dichotomized ESES scores (P

A Comparison between applying two Techniques that compress document data in both languages Arabic and English is introduced. In order to compress the data document, two or more constituent's data documents in both languages are identified. The comparison takes to its consideration, for the first time to the best of our knowledge, the Arabic data compressing. The problem is solved using an efficient language that uses Borland C++ builder to ensure compression for any documents. Our numerical experiments show that Huffman technique can be better used for Arabic Documents. LZW algorithm is better to use for TIFF, GIF and English textual files.

The major aim of classification is to extract categories of inputs according to their characteristics. The literature contains several methods that aim to solve the time series classification problem, such as the artificial neural network (ANN) and the support vector machine (SVM). Time series classification is a supervised learning method that maps the input to the output using historical data. The primary objective is to discover interesting patterns hidden in the data. In this study, we use a new method called SVNN which combines the SVM and ANN classification techniques to solve the time series data classification problem. The proposed SVNN is applied to six benchmark UCR time series datasets. The results show that the proposed method outperforms the ANN and SVM on all datasets. Further comparison with other approaches in the literature also shows that the SVNN is able to maximise accuracy. It is believed that combining classification techniques can give better results in terms of accuracy and better solutions for time series classification.

Classification is a task of supervised learning whose aim is to identify to which of a set of categories a new input element belongs. Probabilistic neural network is a variant of artificial neural network, which is simple in structure, easy for training and often used in classification problems. In this paper, the authors propose an improved probabilistic neural network model that employs biogeography-based optimisation to enhance the accuracy of the classification. The proposed approach was tested on 11 standard benchmark medical datasets from the machine-learning repository. Results show that the classification accuracy of the proposed improved probabilistic neural network model outperforms that of the traditional probabilistic neural network model.

Wrapper feature selection methods aim to reduce the number of features from the original feature set to and improve the classification accuracy simultaneously. In this paper, a wrapper-feature selection algorithm based on the binary dragonfly algorithm is proposed. Dragonfly algorithm is a recent swarm intelligence algorithm that mimics the behavior of the dragonflies. Eighteen UCI datasets are used to evaluate the performance of the proposed approach. The results of the proposed method are compared with those of Particle Swarm Optimization (PSO), Genetic Algorithms (GAs) in terms of classification accuracy and number of selected attributes. The results show the ability of Binary Dragonfly Algorithm (BDA) in searching the feature space and selecting the most informative features for classification tasks.