Search

Developing and evaluating a new intrusion detection system (IDS) that combines random forest component removal with naive bayes is the main goal of the study. We used the NSL-KDD Dataset to evaluate the system and methodology. In each group, 19 out of the 38 samples that were gathered were used. We performed the statistical analysis using the SPSS software. For both groups, an independent sample T test was run at an accuracy level of 0.002 (p<0.05). When features are eliminated from an Innovative Naive Bayes Intrusion Detection System (IDS), the average accuracy is 0.7432; when features are maintained, the average accuracy is 0.5874. Thus, there is no appreciable difference in the two groups' mean accuracy when employing the Innovative Naive Bayes with Random Forest Feature Elimination Intrusion Detection System (IDS). [ABSTRACT FROM AUTHOR]

Group 2 will use one class of support vector machines (SVMs) to build an intrusion detection system, and Group 1 will use support vector machines (SVMs) to compare the two groups' performance. Two types of intrusion detection systems (IDS) are covered in the study; one uses a support vector machine (SVM) method, while the other is an innovative IDS. There are a total of 38 samples used to assess the research, with 19 samples in each group. The statistical analysis was conducted using the SPSS utility. Using G power and a pretest power of 80%, we determined the sample size. The high degree of significance (p<0.05) demonstrates the outstanding functionality of the IDSs. The accuracy of One class SVM IDS has been significantly enhanced, with a value of 0.0 (p<0.05), as shown by the percentage. Accuracy mean for Group 2 using one-class support vector machines (SVMs) is 0.9946, whereas Group 1's mean accuracy with an innovative intrusion detection system employing SVMs is 0.9853. The results show that when comparing the two types of intrusion detection systems, the one based on one class support vector machines (SVMs) performs far better. [ABSTRACT FROM AUTHOR]

The goal of this research is to create a new intrusion detection system (IDS) by comparing two groups: one that uses Naive Bayes without feature removal and another that uses Naive Bayes with Fisher's Score Feature removal. The study divides Deep Machine Learning and Naive Bayes according to their use of intrusion detection systems. A significant level of 0.044 (p<0.05) was found for accuracy after an independent sample T test on both groups. To build an IDS, data was used from the NSL-KDD Dataset. We employed 38 samples in total, 19 from each group, for the analysis. For the statistical analysis, we relied on the SPSS program. Using G power, we approximated the sample size with an 80% pretest power. An increase in the percentage results in a statistically significant improvement (0.044) in the accuracy of IDS. Intruder detection systems (IDS) that use Naive Bayes with fisher's score feature elimination have an average accuracy of 0.7437, compared to 0.7432 when it is not used. using or not using fisher's score feature removal has no discernible effect on Naive Bayes performance. [ABSTRACT FROM AUTHOR]

In this study, design of an Innovative Intrusion Detection System using Naive Bayes (Group 2) as compared to the efficiency of SVM, (Group 1). Naive Bayes and Support Vector Machines were the two intrusion detection systems (IDS) used by the researchers. The research uses a total of 38 samples for evaluation, including 19 samples in each group. We used the SPSS program for statistical analysis. A sample size of 80% was determined by combining G power with the pretest power. Using SVM to improve IDS accuracy by a certain percentage is a statistically significant improvement (p = 0.007). The typical level of precision of an Innovative Intrusion Detection System using Naive Bayes (Group 2) is 62.26% and with SVM (Group 1) is 98.73%. The Innovative Intrusion Detection System is more effective than the Naive Bayes-based system since it uses Support Vector Machine (SVM). In any case, it's crucial. [ABSTRACT FROM AUTHOR]

The effectiveness of Naive Bayes in conjunction with and without feature removal will be investigated using an IDS that generates a unique IDS by using backward feature deletion. The intrusion detection system was tested using the NSL-KDD Dataset. 38 sources, or 19 samples from each category, provided the data. We chose the sample size with an 80% power in mind. We ran our statistical analysis using the SPSS program. An independent sample T test with a p-value larger than 0.05 and a significance level of 0.692 was performed on the two groups. There will be a substantial association between them if p<0.05. When compared with and without feature reduction, the Innovative Naive Bayes Intrusion Detection System has an average accuracy of 0.7495 and 0.7432. There is no statistically significant difference between the two intrusion detection approaches, and the new approach that combines backward feature reduction with Naive Bayes works just as well. [ABSTRACT FROM AUTHOR]

By contrasting the older 5*5 dipole array antenna with the more recent 2*2 dipole array antenna, this study aims to enhance the Specific Absorption Rate (SAR) and thereby investigate the potential radiation health risks to humans. In order to conduct statistical analysis, samples were collected from two groups. Forty samples are provided by two organizations. Unlike Group 1, which used a 5*5 dipole array, Group 2 opted for a 2*2 dipole array antenna. When determining the sample size using G-power 0.8, a 95% confidence interval, an alpha of 0.05, and a beta of 0.2 were all thought about. The antenna works admirably, as shown by a significance level of p<0.05. The Specific Absorption Rate (SAR) of a 2*2 dipole array antenna is 0.633 times higher than that of a 5*5 dipole array antenna (0.4188). Because p<0.05, the value of significance is 0.0334. In comparison to a 5*5 dipole array antenna, a 2*2 dipole array produces greater Specific Absorption Rate (SAR) values (0.6338) while investigating the effects of radiation on humans. [ABSTRACT FROM AUTHOR]

Examining the effects of radiation on humans, this study contrasts an older 5*5 dipole array antenna with a modern 4*4 antenna that increases the Specific Absorption Rate (SAR). Two sets of samples were used for the statistical analysis. Forty tissue samples were provided by researchers from two separate organizations. Two groups of dipole arrays were employed to build the antennas: one group used 5X5 arrays and the other group used the more modern 4*4 arrays. We use G-power 0.8, an alpha of 0.05, a beta of 0.2, and a 95% confidence interval to estimate the sample size. Antennas are deemed effective when the significance level is lower than 0.05. Consequently, a 4*4 dipole array antenna has a SAR that is 0.4328 times higher than a 5*5 models. A statistically significant influence (p<0.05) was shown by the research, with a p-value of 0.0735. Instead of 5*5 arrays, researchers now employ 4*4 dipole array antennas to monitor Specific Absorption Rates (SARs), which helps them understand radiation's effects on humans better. [ABSTRACT FROM AUTHOR]

This study compares the Specific Absorption Rate (SAR) of a 5*5 dipole array antenna with that of a brand new 3*3 dipole array antenna in an effort to learn how various kinds of dipole array antennas impact live organisms. Approach and Materials: Two groups were sampled for the purpose of statistical analysis. Two different sets of people contributed forty samples. A 5X5 dipole array antenna was used by Group 1, whereas an Innovative 3*3 dipole arrays were employed by Group 2. Researchers used an enhanced body. The forty-person sample consisted of twenty from Group 1 and twenty from Group 2. When utilizing G-power 0.8, the calculations were done using a 95% confidence interval, alpha = 0.05, and beta = 0.2. With an enhanced Specific Absorption Rate (SAR) and a 3*3 dipole array antenna, researchers may analyze radiation impacts on the human body with a sample size of 20. A 5*a 5 dipole array antenna may likewise be effectively used with twenty samples. According to the findings, the Specific Absorption Rate (SAR) of the 3*3 dipole array antenna is 0.5935% more than that of the 5*5 dipole array antenna, which is 0.4188. The research could be legitimate if the p-value is less than 0.05, which is 0.0300. If you want to know how radiation affects living things, the Specific Absorption Rate (SAR) shows that 3*3 dipole array antennas are better than 5*5 dipole arrays. [ABSTRACT FROM AUTHOR]

Building two intrusion detection systems (IDSs) is the goal of this project so that wireless ad hoc networks may be protected against denial-of-service assaults. A Bayesian network and a novel one-class support vector machine (SVM) will be used by one system for feature selection, while the other will depend on information gain. What You'll Need and How to Do It: In order to create an IDS model, the 2017 CIC-IDS dataset was used. We utilize SPSS to examine the results after modeling the IDSs using the aforementioned methods, with 19 instances in each group. Finally, a combination of an Information Gain Algorithm-based intrusion detection system with a one-class support vector machine (SVM) using Bayesian network feature selection led to a significant increase in discovery rates and accuracy. The latter was the product of original thought, whereas the former attained 82% and 88%, respectively. Since the significance level is less than 0.05 and the detection rate and accuracy are both 0.00, it may be deduced that IDS is successful. The findings from the comparison between the two types of IDS point to the Information Gain Algorithm-based and the Bayesian network feature selection-based systems as being the better choices. [ABSTRACT FROM AUTHOR]

Aim: The aim of the study is to design a prediction system for the cyclone using the Support Vector Machine (Group 1) and comparing its performance with the Linear Regression Model (Group 2). Materials and Methods : The number of rainy days and the rain density data set (1901-2015) is collected from http://www.imdchennai.gov.in and the cyclone period data is collected from kaggle.com. For each group 19 samples were collected. For statistical analysis the SPSS tool is used. The significance for accuracy and detection rate is 0.00 (p<0.05) indicates the performance of the IDS is good. Result: The cyclone prediction system has the maximum prediction accuracy while using the support vector machine of 100 % and has the detection rate of 65 % and the minimum accuracy is obtained by using the linear regression model 65% and detection rate of 90%. Conclusion : The cyclone prediction system in chennai city using SVM classifier significantly performs better than the Regression model. [ABSTRACT FROM AUTHOR]

Aim: The aim of the work is to design two intrusion detection systems to detect black hole attack in the wireless ad-hoc network using the Random Forest technique (Group 1) and Decision tree algorithm (Group 2). Then to compare its performance metrics. Materials and Methods: In a wireless ad-hoc network, a dataset is generated with 90 nodes and 12 network layer features in NS-2. Above mentioned intrusion detection systems are developed and analyzed by using the SPSS. For each group 19 samples were collected. The significance 0.006 (p<0.05) indicates the performance of IDS. Results: IDS using Random Forest algorithm achieved accuracy and detection rate of 99.4% and 99.1% respectively. And 99.5% and 97.3% for IDS with decision tree algorithms. Conclusion: In this study, it is found that the random forest algorithm significantly performs better when compared with the decision tree algorithm in the detection of black hole attack. [ABSTRACT FROM AUTHOR]

Aim: The aim of this work is to design two intrusion detection systems to detect black hole attack in a wireless ad-hoc network using the K-Means cluster algorithm (Group 1) and Decision tree algorithm (Group 2). Materials and methods: A dataset was generated to design an intrusion detection system model to detect black hole attack by NS2 tool with 90 nodes and 12 network layer features. By using above mentioned algorithms the IDSs are modeled and are analysed with the SPSS tool with 19 samples in each group. The significance p<0.05 (Accuracy-0.014; Detection rate-0.001) indicates the good performance of IDS. Results: The IDS with Decision tree has 98.75% accuracy, 99.60% detection rate whereas the IDS with K-Means cluster has 98.48% accuracy and 99.30% detection rate. Conclusion: The results show that the Intrusion detection system designed with decision tree algorithm significantly performs better than the IDS designed using K-Means cluster algorithm. [ABSTRACT FROM AUTHOR]

The main aim of this work is to design two intrusion detection systems to detect black hole attack in a wireless ad-hoc network using the Principal component analysis algorithm (Group 1) and Decision tree algorithm (Group 2). Materials and methods: Using NS-2 with 90 nodes in wireless ad-hoc networks, 12 network layer features are collected. The dataset was trained and tested by using above mentioned algorithms in python software. 19 samples are collected from each group. The performance measurements of the IDS like Accuracy, Detection rate and false positive rate are computed. The significance p<0.05 (for Accuracy 0.0, for Detection rate 0.01) indicates the good performance of the IDS. Result: The IDS with decision tree classifier has 98.21% accuracy, 99.29% detection rate whereas the IDS with Principal component analysis has 80.33% accuracy and 99.07% detection rate. Conclusion: The results show that the intrusion detection system designed with a decision tree algorithm significantly performs better than the IDS designed using Principal component analysis classifier. [ABSTRACT FROM AUTHOR]

The aim of the study is to design an intrusion detection system (IDS) for wireless ad hoc network to detect Denial of Service attack using K-Means cluster and to compare its performance with an intrusion detection system which is designed using K-NN algorithm. To design an IDS model CIC-IDS 2017 dataset was taken. K-Means cluster (Group1) is used to classify the normal and abnormal nodes. This IDS performance is compared with (Group2) IDS which is designed using the K-NN algorithm. For the analysis with the SPSS tool, 19 samples were taken for each group. The performance of the IDS is measured by using accuracy, detection rate and false positive rate. The significance p<0.05 shows the performance of the IDS (Detection Rate significance is 0.06). The experimental results show that the IDS which is designed using the K-Means cluster has reached the accuracy 86%, detection rate 75% and the false positive rate is 0.09%. The IDS which is designed using the K-NN algorithm has accuracy 99%, detection rate 72% and false positive rate 0.03%. IDS which uses the K-NN algorithm appears to perform significantly better than the IDS which is designed using the K-Means cluster in the detection of DOS attack. [ABSTRACT FROM AUTHOR]

The aim of this study is to design a Microstrip Patch Textile antenna using Jeans substrate (Dielectric constant - 1.7) at 2.4GHz and it is compared with Paper substrate antenna (Dielectric constant - 3.6). The Rectangular microstrip patch antenna which uses Jeans substrate with the thickness of 1.6mm (Group1) and 1.4mm (Group 2) and the Paper substrate Antenna with the thickness 1.4mm (Group3) and 1.6mm(Group 4) are designed and simulated with HFSS software. For each group 10 samples are taken for the analysis. If significance p<0.05, then it indicates that the performance of the Antenna is good. The antenna directivity analysis is done for 2 GHz to 2.8 GHz. The Experimental results shows that the jean substrate antenna which is designed at 2.4GHz is having the directivity of 2.31dB. The Rectangular Microstrip patch antenna which is designed using Paper Substrate having directivity of 2.2dB at 2.4GHz. The microstrip patch antenna which is designed using jeans substrate is having significantly better performance when compared to the microstrip patch antenna using Paper substrate while considering its directivity parameter. [ABSTRACT FROM AUTHOR]

The aim of study is to design a Microstrip Patch Textile antenna using Jeans substrate (Dielectric constant is 1.7) to obtain the Return loss and it is compared with Paper substrate antenna (Dielectric constant is 3.6) which was designed at 2.4GHz. The Rectangular microstrip patch antenna which uses Jeans substrate with the thickness as 1.6mm (Group1) and with the thickness 1.4mm (Group 2) and patch antenna which uses Paper substrate with thickness 1.4mm (Group3) and with the thickness 1.6mm (Group 4) are designed and simulated with HFSS. For each group 10 samples are taken for the analysis using SPSS. The significance p<0.05, indicates that the antenna performance is good. The Experimental results show that the Jean substrate antenna (1.6 mm) which is designed at 2.4GHz is having the Return loss of -0.0338dB and (1.4 mm) is having Return loss of -0.006dB. The Rectangular Microstrip patch antenna which is designed using Paper Substrate (1.6 mm) having Return loss of -0.0756dB and paper substrate (1.4 mm) is having Return loss of -0.037dB at 2.4GHz. The microstrip patch antenna which is designed using jeans substrate is having significantly better performance when compared to the microstrip patch antenna using Paper substrate while considering its Return loss parameter. [ABSTRACT FROM AUTHOR]

The aim of the study is to design an intrusion detection system for wireless ad hoc network to detect Denial of Service attack using principal component analysis method and to compare its performance with an intrusion detection system which is designed using K-NN algorithm. To design and test the IDS model CIC-IDS 2017 dataset was taken. This dataset contains 79 features. These intrusion detection systems were designed and tested in machine learning. Total 19 samples were taken for each group to analyse with SPSS. The significance p<0.05 shows the performance of IDS. The experimental results show that design of intrusion detection system using principal component analysis method is having the accuracy 77%, detection rate 73% and the false positive rate is 0.75%. Intrusion detection system which is designed using the K-NN algorithm has accuracy 99%, detection rate 72% and false positive rate 0.03%. The intrusion detection system which is designed by the K-NN algorithm appears to perform significantly better than the IDS using principal component analysis. [ABSTRACT FROM AUTHOR]