<p><span>A Botnet is one of many attacks that can execute malicious tasks and develop continuously. Therefore, current research introduces a comparison framework, called BotDetectorFW, with classification and complexity improvements for the detection of Botnet attack using CICIDS2017 dataset. It is a free online dataset consist of several attacks with high-dimensions features. The process of feature selection is a significant step to obtain the least features by eliminating irrelated features and consequently reduces the detection time. This process implemented inside BotDetectorFW using two steps; data clustering and five distance measure formulas (cosine, dice, driver & kroeber, overlap, and pearson correlation) using C#, followed by selecting the best N features used as input into four classifier algorithms evaluated using machine learning (WEKA); multilayerperceptron, JRip, IBK, and random forest. In BotDetectorFW, the thoughtful and diligent cleaning of the dataset within the preprocessing stage beside the normalization, binary clustering of its features, followed by the adapting of feature selection based on suitable feature distance techniques, and finalized by testing of selected classification algorithms. All together contributed in satisfying the high-performance metrics using fewer features number (8 features as a minimum) compared to and outperforms other methods found in the literature that adopted (10 features or higher) using the same dataset. Furthermore, the results and performance evaluation of BotDetectorFM shows a competitive impact in terms of classification accuracy (ACC), precision (Pr), recall (Rc), and f-measure (F1) metrics.</span></p>
By definition, the detection of protein complexes that form protein-protein interaction networks (PPINs) is an NP-hard problem. Evolutionary algorithms (EAs), as global search methods, are proven in the literature to be more successful than greedy methods in detecting protein complexes. However, the design of most of these EA-based approaches relies on the topological information of the proteins in the PPIN. Biological information, as a key resource for molecular profiles, on the other hand, acquired a little interest in the design of the components in these EA-based methods. The main aim of this paper is to redesign two operators in the EA based on the functional domain rather than the graph topological domain. The perturb
... Show MoreSlow cinema is a modern phenomenon conceptually. It is one of the most important contemporary features of the development of film art. Despite its roots extending back to previous cinematic schools, it is unique in its distinctive intellectual and visualaudio structures that tend towards slowness, simplicity, monotony, and calm in shaping the cinematic material it presents to the recipient, prompting them to contemplate and reflect on it, rather than receiving it passively. Thus, slow cinema becomes a revolutionary trend linked to philosophical structures broader than the world of film, attempting to resist the ideology of speed that dominates our contemporary lives. Based on this importance of slow cinema, the researcher definedthe topic o
... Show MoreA new, simple and sensitive method was used forevaluation of propranolol withphosphotungstic acidto prove the efficiency, reliability and repeatability of the long distance chasing photometer (NAG-ADF-300-2) using continuous flow injection analysis. The method is based on reaction between propranolol and phosphotungstic acid in an aqueous medium to obtain a yellow precipitate. Optimum parameters was studied to increase the sensitivity for developed method. A linear range for calibration graph was 0.007-13 mmol/L for cell A and 5-15 mmol/L for cell B, and LOD 207.4792 ng/160 µL and 1.2449 µg/160 µL respectively to cell A and cell B with correlation coefficient (r) 0.9988 for cell A, 0.9996 for cell B, RSD% was lower than 1%, (n=8) for the
... Show MoreThe development of information systems in recent years has contributed to various methods of gathering information to evaluate IS performance. The most common approach used to collect information is called the survey system. This method, however, suffers one major drawback. The decision makers consume considerable time to transform data from survey sheets to analytical programs. As such, this paper proposes a method called ‘survey algorithm based on R programming language’ or SABR, for data transformation from the survey sheets inside R environments by treating the arrangement of data as a relational format. R and Relational data format provide excellent opportunity to manage and analyse the accumulated data. Moreover, a survey syste
... Show MoreIn this work, a novel design for the NiO/TiO2 heterojunction solar cells is presented. Highly-pure nanopowders prepared by dc reactive magnetron sputtering technique were used to form the heterojunctions. The electrical characteristics of the proposed design were compared to those of a conventional thin film heterojunction design prepared by the same technique. A higher efficiency of 300% was achieved by the proposed design. This attempt can be considered as the first to fabricate solar cells from highly-pure nanopowders of two different semiconductors.
Correct grading of apple slices can help ensure quality and improve the marketability of the final product, which can impact the overall development of the apple slice industry post-harvest. The study intends to employ the convolutional neural network (CNN) architectures of ResNet-18 and DenseNet-201 and classical machine learning (ML) classifiers such as Wide Neural Networks (WNN), Naïve Bayes (NB), and two kernels of support vector machines (SVM) to classify apple slices into different hardness classes based on their RGB values. Our research data showed that the DenseNet-201 features classified by the SVM-Cubic kernel had the highest accuracy and lowest standard deviation (SD) among all the methods we tested, at 89.51 % 1.66 %. This
... Show MoreIn this article we analysis the data of Iraqi children aged 0-9 months covered in Multiple Indicator Cluster Survey (MICS6-2018) to evaluate the nutritional status . Weight for-age z-score (WAZ), height-for-age z-score (HAZ) and BMI-for-age z-score were compared with the z-scores WHO standards. The overall prevalence of underweight and stunting of the children were 4 % and 11% respectively. Prevalence of overweight based on BMI-for-age for the sexes combined was 21%. Comparing the results obtained from MICS-6 with the results obtained from MICS-4, we find that there is an improvement in the nutritional status of Iraqi children concerning weight, but as for height, we find that there is an increase in the percentage of children who suffer fr
... Show Moreهدفت الدراسة الى الاهتمام واستغلال ماهو جديد من تقنيات واجهزة حديثة في تعليم السباحة الحرة عن طريق توجيه الاطفال على تطوير مداركهم واستيعابهم بالتطور التكنولوجي الذي يتناوله العالم ،قامت الباحثتان باعداد منهج تعليمي باستخدام نظارة الواقع الافتراضي وذالك بتوفير بيئة مشابهة للبيئة الحقيقية تحاكي مدارك عقول الاطفال في عالم افتراضي لتتكون صورة كاملة عن مهارات السباحة الحرة ،ومن هنا اتت المشكلة نتيجة تعل
... Show MoreThis paper proposes a new approach, of Clustering Ultrasound images using the Hybrid Filter (CUHF) to determine the gender of the fetus in the early stages. The possible advantage of CUHF, a better result can be achieved when fuzzy c-mean FCM returns incorrect clusters. The proposed approach is conducted in two steps. Firstly, a preprocessing step to decrease the noise presented in ultrasound images by applying the filters: Local Binary Pattern (LBP), median, median and discrete wavelet (DWT), (median, DWT & LBP) and (median & Laplacian) ML. Secondly, implementing Fuzzy C-Mean (FCM) for clustering the resulted images from the first step. Amongst those filters, Median & Lap