Enhancing genetic algorithms using multi mutations

Hassanat, Ahmad B. A.; Alkafaween, Esra’a; Alnawaiseh, Nedal; Abbadi, Mohammad Ali; Alkasassbeh, Mouhammd; Alhasanat, Mahmoud B.

doi:10.7287/peerj.preprints.2187v1

Cited by 10 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average precision value improvement by our approach over all baseline approaches is 0.051%, 0.049%, 0.019%, 0.04%, 0.034%, and 0.016% compared with LDA [2], [20][21][22][23], SVM [2,24], KNN [2,[25][26][27], LR [2,28], NB [2,29], and DT [2,30], respectively. In terms of recall, our approach obtains 0.988%.…”

Section: Resultsmentioning

confidence: 99%

“…In terms of accuracy, our approach obtains 0.988%. The average accuracy value improvement by our approach over all baseline approaches is 0.081%, 0.069%, 0.031%, 0.072%, 0.08%, and 0.026% compared with LDA [2,31], SVM [2,24], KNN [2,[25][26][27], LR [2,28], NB [2,29], and DT [2,30], respectively. All of these results indicate that the unified learning approach is more effective compared with the baseline approaches.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

A Unified Learning Approach for Malicious Domain Name Detection

Wagan,

Li,

Zaland

et al. 2023

Axioms

View full text Add to dashboard Cite

The DNS firewall plays an important role in network security. It is based on a list of known malicious domain names, and, based on these lists, the firewall blocks communication with these domain names. However, DNS firewalls can only block known malicious domain names, excluding communication with unknown malicious domain names. Prior research has found that machine learning techniques are effective for detecting unknown malicious domain names. However, those methods have limited capabilities to learn from both textual and numerical data. To solve this issue, we present a novel unified learning approach that uses both numerical and textual features of the domain name to classify whether a domain name pair is malicious or not. The experiments were conducted on a benchmark domain names dataset consisting of 90,000 domain names. The experimental results show that the proposed approach performs significantly better than the six comparative methods in terms of accuracy, precision, recall, and F1-Score.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

A Unified Learning Approach for Malicious Domain Name Detection

Wagan,

Li,

Zaland

et al. 2023

Axioms

View full text Add to dashboard Cite

show abstract

“…To avoid the influence of sample imbalance on KNN classification, our dataset has an equal number of positive and negative samples. When testing the dataset, considering the square root rule [27,28], the value of parameter K is set to 35.…”

Section: Knnmentioning

confidence: 99%

A Contour-Based Feature Extraction Algorithm

Liuă,

Ralescu

2024

AAIML

View full text Add to dashboard Cite

Human body recognition is a common problem in computer vision. Currently, most artificial intelligence methods are dependent on the scale of the extracted feature values from the target images during classification, thereby limiting the image size. However, in image recognition, the object’s contour alone is sufficient for humans to distinguish image content. This paper proposes a feature extraction algorithm based on image contours. By utilizing only the contour features of the target image and combining them with machine learning algorithms for classification, it achieves good results even on relatively complex images.

show abstract

“…It was observed that as the number of nodes increased, the processing speed increased and more unsuccessful results were obtained. Hassanat et al (2016), compared several mutation operators in their study and observed that using of more than one mutation, increased the success of the algorithm. Therefore, in this study, the algorithm has been developed by using flip, swap and slide mutation operators together.…”

Section: Travelling Salesman Problem and Genetic Algorithmmentioning

confidence: 99%

Indoor Navigation with Visible Light Communication using Genetic Algorithm

Gözüaçik¹,

Altıok²,

Gökrem³

2021

European Journal of Science and Technology

View full text Add to dashboard Cite

Today, people prefer supermarkets where they can meet all their needs today for their daily needs. People prefer large markets where they can meet all their needs today for their daily needs. These markets, which have a lot of product capacity, mean more waste of time for the consumer. In such indoor and large areas, it is necessary to plan a route to prevent loss of time. In this study, location determination process was made with visible light communication (VLC) in closed areas and the most suitable route was determined by using Genetic Algorithm (GA) with these locations. It is thought that wireless communication resources will not be sufficient in the future due to the density. VLC systems, developed to solve this problem, are a communication system that uses the light source for data transmission. It has been seen in related studies that this system is quite successful in terms of speed, reliability and energy efficiency. VLC systems basically use a transmitter, receiver and microcontroller for their control. In this study, LED light source, TEMP6000 phototransistor-light sensor and ATMEGA328P (Arduino) are used. Due to its very fast on and off feature, the data sent from the LED light source, is detected by the light sensor TEMP6000. After that, it was modulated using On-Off Keying (OOK). In addition to data transmission, VLC systems, which can be used to determine location especially in indoor areas, can also be used for indoor navigation. Also in this study, indoor positioning is designed on the basis of a market application with VLC. The location data was obtained according to the signal strength, which was transferred from the receiver to Matlab. The operation of the system has been tested on the basis of light sources, products under these sources and the shortest path to the products selected by the user. The shortest distance between the stops selected for this navigation process was found by the Floyd-Warshall algorithm. The shortest path was determined by using a GA for the stops with known distance between them, as in the Traveling Salesman Problem (TSP). In this way, the customer will be able to minimize the time and energy consumed in the market.

show abstract

Enhancing genetic algorithms using multi mutations

Cited by 10 publications

References 1 publication

A Unified Learning Approach for Malicious Domain Name Detection

A Unified Learning Approach for Malicious Domain Name Detection

A Contour-Based Feature Extraction Algorithm

Indoor Navigation with Visible Light Communication using Genetic Algorithm

Contact Info

Product

Resources

About