Intrusion detection has drawn considerable interest as researchers endeavor to produce efficient models that offer high detection accuracy. Nevertheless, the challenge remains in developing reliable and efficient Intrusion Detection System (IDS) that is capable of handling large amounts of data, with trends evolving in real-time circumstances. The design of such a system relies on the detection methods used, particularly the feature selection techniques and machine learning algorithms used. Thus motivated, this paper presents a review on feature selection and ensemble techniques used in anomaly-based IDS research. Dimensionality reduction methods are reviewed, followed by the categorization of feature selection techniques to illustrate their effectiveness on training phase and detection. Selection of the most relevant features in data has been proven to increase the efficiency of detection in terms of accuracy and computational efficiency, hence its important role in the design of an anomaly-based IDS. We then analyze and discuss a variety of IDS-based machine learning techniques with various detection models (single classifier-based or ensemble-based), to illustrate their significance and success in the intrusion detection area. Besides supervised and unsupervised learning methods in machine learning, ensemble methods combine several base models to produce one optimal predictive model and improve accuracy performance of IDS. The review consequently focuses on ensemble techniques employed in anomaly-based IDS models and illustrates how their use improves the performance of the anomaly-based IDS models. Finally, the paper laments on open issues in the area and offers research trends to be considered by researchers in designing efficient anomaly-based IDSs.

Purpose: The purpose of this study is to use linear and non-linear features extracted from Electroencephalography (EEG) signal to predict the Mini-Mental State Examination (MMSE) test score by machine learning algorithms. Materials and Methods: First, the MMSE test was taken from 20 subjects that were referred with the initial diagnosis of dementia. Then, the brain activity of subjects was recorded via EEG signal. After preprocessing this signal, various linear and non-linear features are extracted from it that are used as input to machine learning algorithms to predict MMSE test scores in three levels. Results: Based on the experiments, the best classification result is related to the Long Short-Term Memory (LSTM) network with 68% accuracy. Conclusion: Findings show that by using machine learning algorithms and features extracted from EEG signal the MMSE scores are predicted in three levels. Although deep neural networks require a lot of data for training, the LSTM network has been able to achieve the best performance. By increasing the number of subjects, it is expected that the classification results will also increase.

Assessing the prevalence of coeliac disease in patients with intellectual disabilities Previous studies have suggested a high prevalence of coeliac disease in patients with intellectual disabilities (Nisihara, 2005; Shamaly, 2007). To further explore any possible relationship, 196 patients with intellectual disabilities were identified in rehabilitation centres in the province of East Azerbaijan in Iran. They were matched with 196 healthy controls and screened for coeliac disease. Anti-tissue transglutaminase IgA antibodies (tTGA) and total serum IgA levels were measured, and the Marsh-Rostami criteria used to evaluate histological findings. Two patients (1%) were positive for tTG and duodenal biopsies showed Marsh I in one patient and Marsh 0 in the other. IgA deficiency was detected in three patients in the study group and tTGA was positive in one individual. Biopsies from this patient showed Marsh IIIc. From the control group only one individual had positive tTGA and five cases were IgA deficient. Two of these patients had positive tTG but both had normal histology. Coeliac disease was not found to be more prevalent in patients with intellectual disorders which suggests that screening for coeliac disease in these patients would not be cost effective.

Purpose To determine the prevalence of binocular anomalies among preschool children in Mashhad, Iran Methods In a cross‐sectional study with random cluster sampling, children aged 4 to 6 years old from kindergartens of Mashhad in Iran were selected. Examinations included: visual acuity, objective and subjective refractions, cover test, near point of convergence and stereopsis. Best corrected visual acuity worse than 8/10 or more than two Snellen lines difference between the eyes was defined as amblyopia. Anisometropia was defined as spherical equivalent refraction difference of 1.0 diopter and more between two eyes. Results Of the 3765 selected children, 98.3% of them participated in the study. The mean age of the subjects was 5.09 (range: 4‐6) years and 51.3% of them were boys. Strabiamus was found in 1.2 % of the children and intermittent exotropia had the highest prevalence. Prevalence of amblyopia and anisometropia were 0.5% and 6% respectively. Heterophoria was found in 62.7% and shift was toward esophoria.The mean near point of convergence was 5.09 ± cm. Stereopsis of 100 sec/arc and better was found in 94.6% of the subjects. Conclusion The results of this study indicated that the prevalence of strabismus was similar to other studies in Iran while there was a smaller prevalence of amblyopia. For preventing the incidence of binocular anomalies in children, a careful planning of the basic information is required to check the status of binocular vision.

Purpose To determine the prevalence and risk factors of refractive errors in Iranian university students. Methods In a randomized study, of 424 selected students from the six schools of Mashhad University of Medical Sciences (MUMS), 406 of them participated in the study (response rate: 95.7%). Refractive errors were corrected using auto refraction checked by retinoscopy and subjective refraction. Myopia defined as spherical equivalent (SE) refraction ‐0.50 dioptre (D) or worse, hyperopia as SE of +0.50D or more, and astigmatism as cylinder –1.0D or worse. Results The prevalence of myopia, hyperopia and astigmatism were 38.4%, 13.8% and 12.8% among the university students respectively. The prevalence of spherical refractive errors were different in males and females (P=0.038). Conclusion The results of this study indicated that nearly two‐third of the university students have refractive errors. Myopia appears to be more common among highly educated persons and unversity students are at high risk for it.