FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4379877962> ?p ?o ?g. }

• W4379877962 endingPage "144" @default.
• W4379877962 startingPage "132" @default.
• W4379877962 abstract "The Internet of Things, or IoT, refers to the ability of objects to communicate with one another via the Internet and these objects can transfer data using many types of sensors and mobile or web applications without the need for human intervention. This technology is becoming more important in several fields such as the field of transport and logistics to monitor the temperature of the warehouses of the materials to be transported or monitor the condition of the vehicles themselves. The health field for monitoring the health status of certain disease states, such as heart disease, using sensors. The field of general security as well to give alerts to water, electricity, and gas problems at homes or in factories, or alerts to the danger of forest incidents using sensors and web or mobile applications. Etc.……. Recently, the security of Internet of Things applications and data exchanged in Internet of Things networks will be a necessity with the increased use of this technology in our daily lives. Cybersecurity researchers are trying to offer solutions adapted to Internet of Things networks. Several solution paths have been proposed in recent years, including solutions based on cryptography to secure communication and data exchange, solutions based on Blockchain for the security of communication between devices in Internet of Things networks, and solutions based on Intrusion Detection Systems as well. Intrusion Detection Systems are considered one of the techniques most discussed by researchers to implement security solutions for the Internet of Things, especially IDSs based on artificial intelligence techniques such as Machine Learning. This paper presented a comparison between five Machine Learning algorithms (Support Vector Machine, J48, Random Forest, Decision Table, and Naive Bayes) in the context of intrusion detection. In this comparison, we used the NSL-KDD dataset (Network Security Laboratory - Knowledge Discovery in Databases). The main objective behind this comparison is to be aware of the most efficient Machine Learning algorithms in intrusion detection to put them as the main building blocks in the future modules of Intrusion Detection Systems. The results obtained show that Random Forest, J48, and Decision Table are the most efficient algorithms for Accuracy (respectively 99.92%, 99.72%, and 99.49%), Detection Rate (respectively 99.90%, 99.77%, and 99.29%), and False Alarm Rate (respectively 0.05%, 0.34%, and 0.27%). Therefore, these three algorithms can be considered a good basis for future solutions of intrusion detection systems to increase the security of Internet of Things." @default.
• W4379877962 created "2023-06-09" @default.
• W4379877962 creator A5044595555 @default.
• W4379877962 creator A5091460861 @default.
• W4379877962 creator A5092116063 @default.
• W4379877962 date "2023-01-01" @default.
• W4379877962 modified "2023-09-25" @default.
• W4379877962 title "Intrusion Detection Systems in Internet of Things Using Machine Learning Algorithms: A Comparative Study" @default.
• W4379877962 cites W1526458608 @default.
• W4379877962 cites W1535753778 @default.
• W4379877962 cites W1976262362 @default.
• W4379877962 cites W2253724380 @default.
• W4379877962 cites W2524655848 @default.
• W4379877962 cites W2581042172 @default.
• W4379877962 cites W2751399725 @default.
• W4379877962 cites W2809706118 @default.
• W4379877962 cites W2934386458 @default.
• W4379877962 cites W3002366890 @default.
• W4379877962 cites W3029996098 @default.
• W4379877962 cites W3160602119 @default.
• W4379877962 doi "https://doi.org/10.1007/978-3-031-35251-5_12" @default.
• W4379877962 hasPublicationYear "2023" @default.
• W4379877962 type Work @default.
• W4379877962 citedByCount "0" @default.
• W4379877962 crossrefType "book-chapter" @default.
• W4379877962 hasAuthorship W4379877962A5044595555 @default.
• W4379877962 hasAuthorship W4379877962A5091460861 @default.
• W4379877962 hasAuthorship W4379877962A5092116063 @default.
• W4379877962 hasConcept C110875604 @default.
• W4379877962 hasConcept C136764020 @default.
• W4379877962 hasConcept C202444582 @default.
• W4379877962 hasConcept C33923547 @default.
• W4379877962 hasConcept C35525427 @default.
• W4379877962 hasConcept C38652104 @default.
• W4379877962 hasConcept C41008148 @default.
• W4379877962 hasConcept C81860439 @default.
• W4379877962 hasConcept C9652623 @default.
• W4379877962 hasConceptScore W4379877962C110875604 @default.
• W4379877962 hasConceptScore W4379877962C136764020 @default.
• W4379877962 hasConceptScore W4379877962C202444582 @default.
• W4379877962 hasConceptScore W4379877962C33923547 @default.
• W4379877962 hasConceptScore W4379877962C35525427 @default.
• W4379877962 hasConceptScore W4379877962C38652104 @default.
• W4379877962 hasConceptScore W4379877962C41008148 @default.
• W4379877962 hasConceptScore W4379877962C81860439 @default.
• W4379877962 hasConceptScore W4379877962C9652623 @default.
• W4379877962 hasLocation W43798779621 @default.
• W4379877962 hasOpenAccess W4379877962 @default.
• W4379877962 hasPrimaryLocation W43798779621 @default.
• W4379877962 hasRelatedWork W2351252967 @default.
• W4379877962 hasRelatedWork W2373866020 @default.
• W4379877962 hasRelatedWork W2388271354 @default.
• W4379877962 hasRelatedWork W2618984630 @default.
• W4379877962 hasRelatedWork W2751166006 @default.
• W4379877962 hasRelatedWork W2921339519 @default.
• W4379877962 hasRelatedWork W3028453209 @default.
• W4379877962 hasRelatedWork W4225146958 @default.
• W4379877962 hasRelatedWork W4312168023 @default.
• W4379877962 hasRelatedWork W4362496848 @default.
• W4379877962 isParatext "false" @default.
• W4379877962 isRetracted "false" @default.
• W4379877962 workType "book-chapter" @default.