A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural Networks
The Internet of Railways (IoR) network is made up of a variety of sensors, actuators, network layers, and communication systems that work together to build a railway system. The IoR’s success depends on effective communication. A network of railways uses a variety of protocols to share and transmit...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/18/2813 |
| _version_ | 1797489143579672576 |
|---|---|
| author | Umar Islam Rami Qays Malik Amnah S. Al-Johani Muhammad. Riaz Khan Yousef Ibrahim Daradkeh Ijaz Ahmad Khalid A. Alissa Zulkiflee Abdul-Samad Elsayed M. Tag-Eldin |
| author_facet | Umar Islam Rami Qays Malik Amnah S. Al-Johani Muhammad. Riaz Khan Yousef Ibrahim Daradkeh Ijaz Ahmad Khalid A. Alissa Zulkiflee Abdul-Samad Elsayed M. Tag-Eldin |
| author_sort | Umar Islam |
| collection | DOAJ |
| description | The Internet of Railways (IoR) network is made up of a variety of sensors, actuators, network layers, and communication systems that work together to build a railway system. The IoR’s success depends on effective communication. A network of railways uses a variety of protocols to share and transmit information amongst each other. Because of the widespread usage of wireless technology on trains, the entire system is susceptible to hacks. These hacks could lead to harmful behavior on the Internet of Railways if they spread sensitive data to an infected network or a fake user. For the previous few years, spotting IoR attacks has been incredibly challenging. To detect malicious intrusions, models based on machine learning and deep learning must still contend with the problem of selecting features. k-means clustering has been used for feature scoring and ranking because of this. To categorize attacks in two datasets, the Internet of Railways and the University of New South Wales, we employed a new neural network model, the extended neural network (ENN). Accuracy and precision were among the model’s strengths. According to our proposed ENN model, the feature-scoring technique performed well. The most accurate models in dataset 1 (UNSW-NB15) were based on deep neural networks (DNNs) (92.2%), long short-term memory LSTM (90.9%), and ENN (99.7%). To categorize attacks, the second dataset (IOR dataset) yielded the highest accuracy (99.3%) for ENN, followed by CNN (87%), LSTM (89%), and DNN (82.3%). |
| first_indexed | 2024-03-10T00:13:17Z |
| format | Article |
| id | doaj.art-ac0f76b4975b4c5088b01303b0108c94 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T00:13:17Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-ac0f76b4975b4c5088b01303b0108c942023-11-23T15:57:03ZengMDPI AGElectronics2079-92922022-09-011118281310.3390/electronics11182813A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural NetworksUmar Islam0Rami Qays Malik1Amnah S. Al-Johani2Muhammad. Riaz Khan3Yousef Ibrahim Daradkeh4Ijaz Ahmad5Khalid A. Alissa6Zulkiflee Abdul-Samad7Elsayed M. Tag-Eldin8Department of Computer Science, Iqra National University, Swat Campus 19220, Peshawar 25100, PakistanMedical Instrumentation Techniques Engineering Department, Al-Mustaqbal University College, Babylon 51001, IraqMathematics Department, Faculty of Science, University of Tabuk, Tabuk 71491, Saudi ArabiaDepartment of Mathematics, Quaid-i-Azam University, Islamabad 44000, PakistanDepartment of Computer Engineering and Networks, College of Engineering in Wadi Alddawasir, Prince Sattam Bin Abdulaziz University, Al-Kharj 11942, Saudi ArabiaShenzhen Institute of Advanced Technology (SIAT), University of Chinese Academy of Sciences, Shenzhen 518055, ChinaSAUDI ARAMCO Cybersecurity, Networks and Communications Department, College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, P.O. Box 1982, Dammam 31441, Saudi ArabiaDepartment of Quantity Surveying, Faculty of Built Environment, University of Malaya, Lumpur 50603, MalaysiaElectrical Engineering Department, Faculty of Engineering, Technology, Future University in Egypt, New Cairo 11835, EgyptThe Internet of Railways (IoR) network is made up of a variety of sensors, actuators, network layers, and communication systems that work together to build a railway system. The IoR’s success depends on effective communication. A network of railways uses a variety of protocols to share and transmit information amongst each other. Because of the widespread usage of wireless technology on trains, the entire system is susceptible to hacks. These hacks could lead to harmful behavior on the Internet of Railways if they spread sensitive data to an infected network or a fake user. For the previous few years, spotting IoR attacks has been incredibly challenging. To detect malicious intrusions, models based on machine learning and deep learning must still contend with the problem of selecting features. k-means clustering has been used for feature scoring and ranking because of this. To categorize attacks in two datasets, the Internet of Railways and the University of New South Wales, we employed a new neural network model, the extended neural network (ENN). Accuracy and precision were among the model’s strengths. According to our proposed ENN model, the feature-scoring technique performed well. The most accurate models in dataset 1 (UNSW-NB15) were based on deep neural networks (DNNs) (92.2%), long short-term memory LSTM (90.9%), and ENN (99.7%). To categorize attacks, the second dataset (IOR dataset) yielded the highest accuracy (99.3%) for ENN, followed by CNN (87%), LSTM (89%), and DNN (82.3%).https://www.mdpi.com/2079-9292/11/18/2813Internet of Railwaysextended neural network |
| spellingShingle | Umar Islam Rami Qays Malik Amnah S. Al-Johani Muhammad. Riaz Khan Yousef Ibrahim Daradkeh Ijaz Ahmad Khalid A. Alissa Zulkiflee Abdul-Samad Elsayed M. Tag-Eldin A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural Networks Electronics Internet of Railways extended neural network |
| title | A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural Networks |
| title_full | A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural Networks |
| title_fullStr | A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural Networks |
| title_full_unstemmed | A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural Networks |
| title_short | A Novel Anomaly Detection System on the Internet of Railways Using Extended Neural Networks |
| title_sort | novel anomaly detection system on the internet of railways using extended neural networks |
| topic | Internet of Railways extended neural network |
| url | https://www.mdpi.com/2079-9292/11/18/2813 |
| work_keys_str_mv | AT umarislam anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT ramiqaysmalik anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT amnahsaljohani anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT muhammadriazkhan anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT yousefibrahimdaradkeh anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT ijazahmad anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT khalidaalissa anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT zulkifleeabdulsamad anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT elsayedmtageldin anovelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT umarislam novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT ramiqaysmalik novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT amnahsaljohani novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT muhammadriazkhan novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT yousefibrahimdaradkeh novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT ijazahmad novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT khalidaalissa novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT zulkifleeabdulsamad novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks AT elsayedmtageldin novelanomalydetectionsystemontheinternetofrailwaysusingextendedneuralnetworks |