In the area of pattern recognition and machine learning, features play a key role in prediction. The famous applications of features are medical imaging, image classification, and name a few more. With the exponential growth of information investments in medical data repositories and health service provision, medical institutions are collecting large volumes of data. These data repositories contain details information essential to support medical diagnostic decisions and also improve patient care quality. On the other hand, this growth also made it difficult to comprehend and utilize data for various purposes. The results of imaging data can become biased because of extraneous features present in larger datasets. Feature selection gives a chance to decrease the number of components in such large datasets. Through selection techniques, ousting the unimportant features and selecting a subset of components that produces prevalent characterization precision. The correct decision to find a good attribute produces a precise grouping model, which enhances learning pace and forecast control. This paper presents a review of feature selection techniques and attributes selection measures for medical imaging. This review is meant to describe feature selection techniques in a medical domain with their pros and cons and to signify its application in imaging data and data mining algorithms. The review reveals the shortcomings of the existing feature and attributes selection techniques to multi-sourced data. Moreover, this review provides the importance of feature selection for correct classification of medical infections. In the end, critical analysis and future directions are provided.

Breast cancer is a highly prevalent disease in females that may lead to mortality in severe cases. The mortality can be subsided if breast cancer is diagnosed at an early stage. The focus of this study is to detect breast malignancy through computer-aided diagnosis (CADx). In the first phase of this work, Hilbert transform is employed to reconstruct B-mode images from the raw data followed by the marker-controlled watershed transformation to segment the lesion. The methods based only on texture analysis are quite sensitive to speckle noise and other artifacts. Therefore, a hybrid feature set is developed after the extraction of shape-based and texture features from the breast lesion. Decision tree, k-nearest neighbor (KNN), and ensemble decision tree model via random under-sampling with Boost (RUSBoost) are utilized to segregate the cancerous lesions from the benign ones. The proposed technique is tested on OASBUD (Open Access Series of Breast Ultrasonic Data) and breast ultrasound (BUS) images collected at Baheya Hospital Egypt (BHE). The OASBUD dataset contains raw ultrasound data obtained from 100 patients containing 52 malignant and 48 benign lesions. The dataset collected at BHE contains 210 malignant and 437 benign images. The proposed system achieved promising accuracy of 97% with confidence interval (CI) of 91.48% to 99.38% for OASBUD and 96.6% accuracy with CI of 94.90% to 97.86% for the BHE dataset using ensemble method.

Optimizing the detection of intrusions is becoming more crucial due to the continuously rising rates and ferocity of cyber threats and attacks. One of the popular methods to optimize the accuracy of intrusion detection systems (IDSs) is by employing machine learning (ML) techniques. However, there are many factors that affect the accuracy of the ML-based IDSs. One of these factors is noise, which can be in the form of mislabelled instances, outliers, or extreme values. Determining the extent effect of noise helps to design and build more robust ML-based IDSs. This paper empirically examines the extent effect of noise on the accuracy of the ML-based IDSs by conducting a wide set of different experiments. The used ML algorithms are decision tree (DT), random forest (RF), support vector machine (SVM), artificial neural networks (ANNs), and Naïve Bayes (NB). In addition, the experiments are conducted on two widely used intrusion datasets, which are NSL-KDD and UNSW-NB15. Moreover, the paper also investigates the use of these ML algorithms as base classifiers with two ensembles of classifiers learning methods, which are bagging and boosting. The detailed results and findings are illustrated and discussed in this paper.

The connection between collaborative learning and the new mobile technology has become tighter. Mobile learning enhances collaborative learning as learners can access information and learning materials from anywhere and at any time. However, supporting efficient mobile learning in education is a critical challenge. In addition, incorporating technological and educational components becomes a new, complex dimension. In this paper, an efficient collaborative mobile-learning architecture based on mobile agents is proposed to enhance learning activity and to allow teachers and students to collaborate in knowledge and information transfer. A mobile agent can control its own actions, is able to communicate with other agents, and adapts in accordance with previous experience. The proposed model consists of four components: the learner agent, the teacher agent, the device agent and the social agent. The social agent plays the main role in the collaborative tasks since it is responsible for evaluating the collaborative interactions among different learners. Additionally, it offers an evaluation indicator for the learners’ collaboration and supplies the teacher with learner’s collaboration reports. The proposed model is evaluated by introducing a collaborative mobile-learning case study applied to two full classes of undergraduate students. To conduct the model experiments, students were asked to complete a questionnaire after they used the proposed model. The questionnaire results statistically revealed that the proposed architecture is easy to use and access, well-organized, convenient, and facilitates the learning process. The students thought the proposed m-learning application should complement rather than replace the traditional lectures. Moreover, the experimental results show that the proposed collaborative mobile learning model enhances the learner’s skills in problem solving, increases the learner’s knowledge in comparison with individual learning, and social agent encourages learners for more participation in the learning tasks. Based on the experiments conducted, the authors found that the proposed model can improve the quality of the learning process by assessing learners’ and groups’ collaboration, and it can help teachers make learners improve how they work in groups. This also provides various ways of assessing learners abilities and skills in groups. It is also possible to integrate the collaborative e-learning with the proposed collaborative m-learning.

Glaucoma is a major cause of blindness. Most patients start to observe that late after the disease causes a high level of damage in the optic nerve head and the high percentage of vision loss. Early diagnosis and treatment are essential and must be taken. Image processing mass-screening and machine learning classification can support early and automatic diagnosis of Glaucoma symptoms so as to take protective measures and to extend symptom-free life of patients. This paper proposes improved techniques to extract disease-related and image-based features. Support Vector Machines and Genetically-Optimized Artificial Neural Networks, pronounced machine learning algorithms, are fine-tuned to combine the two set of features in one automated image classification system. The proposed methodology was applied to a dataset of 106 retina images obtained from three hospitals. The proposed system automatically detected Glaucoma using Support Vector Machines technique with 100% specificity and 87% accuracy. Artificial Neural Network classified the images with 98% accuracy.

Background: Domain Name System (DNS) is considered the phone book of the Internet. Its main goal is to translate a domain name to an IP address that the computer can understand. However, DNS can be vulnerable to various kinds of attacks, such as DNS poisoning attacks and DNS tunneling attacks. Objective: The main objective of this paper was to allow researchers to identify DNS tunnel traffic using machine-learning algorithms. Training machine-learning algorithms to detect DNS tunnel traffic and determine which protocol was used will help the community to speed up the process of detecting such attacks. Method: In this paper, we considered the DNS tunneling attack. In addition, we discussed how attackers can exploit this protocol to infiltrate data breaches from the network. The attack starts by encoding data inside the DNS queries to the outside of the network. The malicious DNS server will receive a small chunk of data decoding the payload and put it together at the server. The main concern is that the DNS is a fundamental service that is not usually blocked by a firewall and receives less attention from systems administrators due to a vast amount of traffic. Results: This paper investigates how this type of attack happens using the DNS tunneling tool by setting up an environment consisting of compromised DNS servers and compromised hosts with the Iodine tool installed in both machines. The generated dataset contains the traffic of HTTP, HTTPS, SSH, SFTP, and POP3 protocols over the DNS. No features were removed from the dataset so that researchers could utilize all features in the dataset. Conclusion: DNS tunneling remains a critical attack that needs more attention to address. DNS tunneled environment allows us to understand how such an attack happens. We built the appropriate dataset by simulating various attack scenarios using different protocols. The created dataset contains PCAP, JSON, and CSV files to allow researchers to use different methods to detect tunnel traffic.