In this research, the photoplethysmogram (PPG) waveform analysis is utilized to develop a logistic regression‐based predictive model for the classification of diabetes. The classifier has three predictors age, b/a, and SP indices in which they achieved an overall accuracy of 92.3% in the prediction of diabetes. In this study, a total of 587 subjects were enrolled. A total of 459 subjects were used for model training and development, while the rest of the 128 subjects were used for model testing and validation. The classifier was able to diagnose 63 patients correctly as diabetes while 27 subjects were wrongly classified as nondiabetes with an accuracy of 70%. Again, the model classified 479 subjects as nondiabetes correctly while it incorrectly classified 18 subjects as diabetes with an accuracy of 96.4%. Finally, the proposed model revealed an overall predictive accuracy of 92.3% which makes it a reliable surrogate measure for diabetes classification and prediction in clinical settings.

The paper is regarding the fair distribution of several files having different sizes to several storage supports. With the existence of several storage supports and different files, we search for a method that makes an appropriate backup. The appropriate backup guarantees a fair distribution of the big data (files). Fairness is related to the used spaces of storage support distribution. The problem is how to find a fair method that stores all files on the available storage supports, where each file is characterized by its size. We propose in this paper some fairness methods that seek to minimize the gap between used spaces of all storage supports. In this paper, several algorithms are developed to solve the proposed problem, and the experimental study shows the performance of these developed algorithms.

This paper treats the maximization of the minimum completion time regarding the identical parallel machines problem. This problem is well known as follows. Our work concerns with industry field, when we have several identical and parallel machines and we have faced to many different jobs. The problem is how to find an appropriate solution that gives us a method to schedule the different jobs on the given machines. The objective function is the maximization of machine completion time which has the minimum time comparing with all other machines. This problem is shown as NP-hard. We propose some algorithms that give approximate solutions to the studied problem. Several instances were tested in this paper to show the performance of the proposed approximate solutions.

In this study, we investigate using deep learning, i.e., deep convolutional neural networks (DCNNs), for malware detection leveraging network traffic data. Signature-based detection techniques are now proven unable to cope with the extremely high rate of malware variants' evolution. For this reason, this research suggests a novel method of turning raw network traffic data input (APKS, CSVS, and PCAPS) into visual representations for better malware classification. The study trains a model using DCNNs and refines it using the VGG19 architecture and extra convolutional layers to achieve higher detection rates utilizing the CICAndMal2017 dataset. The key metrics of precision (98.5%), recall (99.4%), and F1 score (98.8%) are all observed with a high performance, along with the AUC of 0.93 and accuracy rate of 99.35%. Deep learning is demonstrated to be effective in detecting malware via image-based features, and there is a significant improvement compared to traditional approaches. The novelty in this work is the use of deep learning for malware detection via visual representations of network traffic. Future work will improve computational efficiency, extend the approach to dynamic environments, and learn to be more robust to evasion tactics through adversarial training.

Technology is rising on daily basis with the advancement in web and artificial intelligence (AI), and big data developed by machines in various industries. All of these provide a gateway for cybercrimes that makes network security a challenging task. There are too many challenges in the...

Sensitive data, such as financial, personal, or classified governmental information, must be protected throughout its cycle. This paper studies the problem of safeguarding transmitted data based on data categorization techniques. This research aims to use a novel routine as a new meta-heuristic to enhance a novel data categorization based-traffic classification technique where private data is classified into multiple confidential levels. As a result, two packets belonging to the same confidentiality level cannot be transmitted through two routers simultaneously, ensuring a high data protection level. Such a problem is determined by a non-deterministic polynomial-time hardness (NP-hard) problem; therefore, a scheduling algorithm is applied to minimize the total transmission time over the two considered routers. To measure the proposed scheme’s performance, two types of distribution, uniform and binomial distributions used to generate packets transmission time datasets. The experimental result shows that the most efficient algorithm is the Best-Random Algorithm ( B R ˜ ), recording 0.028 s with an average gap of less than 0.001 in 95.1% of cases compared to all proposed algorithms. In addition, B R ˜ is compared to the best-proposed algorithm in the literature which is the Modified decreasing Estimated-Transmission Time algorithm (MDETA). The results show that B R ˜ is the best one in 100% of cases where MDETA reaches the best results in only 48%.