Robust genetic machine learning ensemble model for intrusion detection in network traffic.

Network security has developed as a critical research subject as a result of the Rapid advancements in the development of Internet and communication technologies over the previous decades. The expansion of networks and data has caused cyber-attacks on the systems, making it difficult for network security to detect breaches effectively. Current Intrusion Detection Systems (IDS) have several flaws, including their inability to prevent attacks on their own, the requirement for a professional engineer to administer them, and the occurrence of false alerts. As a result, a plethora of new attacks are being created, making it harder for network security to properly detect breaches. Despite the best efforts, IDS continues to struggle with increasing detection accuracy while lowering false alarm rates and detecting new intrusions. Therefore, network intrusion detection enhancement by preprocessing and generation of highly reliable algorithms is the main focus nowadays. Machine learning (ML) based IDS systems have recently been implemented as viable solutions for quickly detecting intrusions across the network. In this study, we use a combined data analysis technique with four Robust Machine learning ensemble algorithms, including the Voting Classifier, Bagging Classifier, Gradient Boosting Classifier, and Random Forest-based Bagging algorithm along with the proposed Robust genetic ensemble classifier. For each algorithm, a model is created and tested using a Network Dataset. To assess the performance of both algorithms in terms of their ability to anticipate the anomaly occurrence, graphs of performance rates have been evaluated. The suggested algorithm outperformed other methods as it shows the lowest values of mean square error (MSE) and mean absolute error (MAE). The experiments were conducted on the Network traffic dataset available on Kaggle, on the Python platform, which has limited samples. The proposed method can be applied in the future with more machine learning ensemble classifiers and deep learning techniques.

Prevalence of dilated mid-ascending aorta in individuals 15 years and older: In search of optimal diagnostic criteria and their effect on the burden of disease.

BACKGROUND: Controversy regarding the definition of the upper limit of normal (ULN) for dilated mid-ascending aorta (mAA) stems from variation in criteria, based on several small-sized studies with small datasets of normal subjects (DONS). The present study was carried out to demonstrate this variation in the prevalence of mAA dilation and to identify the optimal definition by creating the largest DONS. METHODS: Echocardiographic studies of patients ≥ 15 years of age performed at a large tertiary care center over 4 years (n = 49,330) were retrospectively evaluated. The leading-edge-to-leading-edge technique was used to measure the mAA in diastole. The largest-to-date DONS (n = 2334) was created, including those who were normal on medical record review, did not have any of the 28 causes of dilated aorta, and had normal echocardiograms. Because age had the strongest correlation with mAA (multivariate adjusted R2 = 0.26), as compared with sex, height, and weight, we created a new ULN based on the DONS with narrow age stratification (10-year intervals). RESULTS: The prevalence of dilated mAA varied between 17% and 23% when absolute criteria were used with sex stratification, and it varied between 6% and 11% when relative criteria (relative to age, body surface area, and sex) were used. Based on new criteria from the DONS, it was 7.6%, with a ULN of 3.07-3.64 cm in women and 3.3-3.91 cm in men. CONCLUSIONS: These data demonstrate the undesirable variation in the prevalence of dilated mAA based on prior criteria and propose a new ULN for dilated mAA.

Hypertrophic cardiomyopathy is associated with dilated sinus of Valsalva: A case-control study.

Background: We aimed to test the hypothesis that there is an association between hypertrophic cardiomyopathy and dilated aorta in a case-control, matched-design fashion. Methods: Of 65,843 studies done from November 2011 to December 2015, we found, after detailed evaluation by a single author, 153 cases of hypertrophic cardiomyopathy and 3,213 controls who were classified as normal clinically and echocardiographically. Controls were defined as normal patients referred to the echocardiography laboratory with no diagnoses and no known risk factors for dilated aorta (e.g., aortic stenosis, hypertension, aortic regurgitation). Clinical chart review showed none of the risk factors for dilated aorta, and echocardiography did not reveal any abnormalities. Of these 3,213 patients, 153 controls were matched to cases by age and sex by propensity score. Dilated aorta was defined according to clinical, Goldstein, and Lang's criteria. Results: The prevalence of a dilated sinus of Valsalva was 9 times higher in hypertrophic cardiomyopathy patients than controls (OR = 9.4, P = 0.003). The 9-fold higher prevalence in hypertrophic cardiomyopathy patients persisted after adjusting for height, weight, and aortic pathology. Association of dilated mid-ascending aorta with hypertrophic cardiomyopathy was significant after adjustment for height and body surface area but became borderline insignificant after adjusting for weight and aortic valve pathology. Conclusion: Hypertrophic cardiomyopathy appears to be associated with a dilated sinus of Valsalva, even after adjusting for height, weight, and aortic valve pathology.

Refining the upper limit of normal for the ascending aorta: In search of optimal criteria -- a large database study of normal individuals.

OBJECTIVES: The cutoff for dilated mid-ascending aorta (mAA) is controversial and has several definitions. The present study was carried out to determine the prevalence of mAA dilation based on published definitions and to identify the optimal cutoff. METHODS: Echocardiographic studies of patients >15 years of age performed at a large tertiary care center over 4 years, n = 49,330, were retrospectively evaluated. Leading-edge-to-leading-edge technique was used to measure the mAA in diastole. Several cutoff criteria were included. In addition, we defined normals in our database as those who, after 28 causes of dilated aorta were excluded, were normal both clinically and echocardiographically (n = 2334). RESULTS: The mean age was 64.2 ± 17.1 years, and 31.5% were men. The prevalence of dilated mAA based on absolute criteria with sex stratification varied between 17% and 23% and based on relative criteria (to age, body surface area, and sex) varied between 6% and 11%. It further decreased to 7.6% on the addition of narrow age stratification (10 year intervals) performed on normals in our database. The multivariate adjusted R2 (for variation in mAA diameter) was 0.25 for age, decreasing to 0.12 for weight and 0.07 for sex and height. CONCLUSIONS: The lowest prevalence of 7.6% probably represents the optimal cutoff for dilated mAA because it includes age, which explains most of the variation in mAA, in narrow (10 year) intervals only performed in our normals, which represents the largest sample size to date.

Proactive approach for preamble detection in 5G-NR PRACH using supervised machine learning and ensemble model.

The physical random access channel (PRACH) is used in the uplink of cellular systems for initial access requests from the users. It is very hard to achieve low latency by implementing conventional methods in 5G. The performance of the system degrades when multiple users try to access the PRACH receiver with the same preamble signature, resulting in a collision of request signals and dual peak occurrence. In this paper, we used two machine learning classification technique models with signals samples as big data to obtain the best proactive approach. First, we implemented three supervised learning algorithms, Decision Tree Classification (DTC), naïve bayes (NB), and K-nearest neighbor (KNN) to classify the outcome based on two classes, labeled as 'peak' and 'false peak'. For the second approach, we constructed a Bagged Tree Ensembler, using multiple learners which contributes to the reduction of the variance of DTC and comparing their asymptotes. The comparison shows that Ensembler method proves to be a better proactive approach for the stated problem.

Influence of Differential Calcification in the Descending Thoracic Aorta on Aortic Pulse Pressure.

PURPOSE: Multiple studies have shown pulse pressure (PP) to be a strong predictor of aortic calcification. However, no studies are available that correlate PP with aortic calcification at the segmental level. METHODS: We identified 37 patients with aortic PP measured during cardiac catheterization. Their noncontrast chest computed tomography scans were evaluated for the presence of calcium in different segments (ascending aorta, arch of aorta [arch], descending aorta) and quantified. Patients with calcification (Calcified Group A) were compared against patients without calcification (Noncalcified Group B) in terms of PP, calcification and compliance. RESULTS: The mean of the total calcium score was higher in the descending aorta than the arch or ascending aorta (691 vs 571 vs 131, respectively, P<0.0001). PP had the strongest correlation with calcification in the descending aorta (r=0.47, P=0.004). Calcified Group A had a much higher PP than Noncalcified Group B, with the greatest difference in the descending aorta (20 mmHg, P<0.0001), lesser in the ascending aorta (10 mmHg, P=0.12) and the least in the arch (5 mmHg, P=0.38). Calcified Group A patients also had much lower compliance than Noncalcified Group B patients, with the greatest difference among groups seen in the descending aorta (0.7 mL/mmHg, P=0.002), followed by the ascending aorta, then arch. CONCLUSIONS: These are the first data to evaluate the relative impact of aortic segments in PP. Finding the greatest amount of calcification along with greatest change in PP and compliance in the descending aorta makes a case that the descending aorta plays a major role in PP as compared to other segments of the thoracic aorta.