Document Details

Document Type : Thesis 
Document Title :
USING MACHINE LEARNING APPROACHES FOR ANOMALY DETECTION IN IOT
استخدام مناهج التعلم الآلي للكشف عن الشذوذ في البيانات في إنترنت الأشياء
 
Subject : Faculty of Computing and Information Technology 
Document Language : Arabic 
Abstract : The Internet of Things (IoT) is a network of distributed devices or sensors connected via the Internet to allow gathering and sharing of data. The data generated by these devices is affected by anomalies or abnormal behaviour for different reasons, such as attacks or breakdown in devices. However, current anomaly detection systems based on the supervised mode rely on labelled data, while class labels for IoT data are usually unavailable. More importantly, the data in IoT grows fast, creating a need to predict the classification labels for the future data. This study proposes a Hybrid Learning Model which uses both Clustering and Classification methods (HLMCC) to automate the labelling process and detect anomalies in IoT data. The model consists of two practical phases, automatic labelling and detecting anomalies. First, the HLMCC groups the data into normal and anomaly clusters by adopting hierarchical affinity propagation (HAP) clustering. Second, the labelled data obtained from the clustering phase is used to train the decision trees (DTs) and classify future unseen data. The HLMCC is applied to two existing IoT datasets, the Labelled Wireless Sensor Network Data Repository (LWSNDR) and Landsat satellite datasets, respectively. The results show that the HLMCC is able to automate labelling of data, which can be beneficial to minimize human involvement. Moreover, the HLMCC outperforms the DTs on the originally labelled datasets and the state-of-the-art model over a wide range of evaluation metrics, based on the average ranks. The HLMCC shows the highest average ranks compared to other models in terms of false positive rate (FPR), recall, precision, and the area under the precision-recall curve (AUCPR) with 1.8, 1.6, 1.8 and 1.8, respectively. 
Supervisor : Dr. Reem Moteab Alotaibi Dr. Seyed Mohamed Buhari 
Thesis Type : Master Thesis 
Publishing Year : 1441 AH
2019 AD 
Co-Supervisor : Dr. Seyed Mohamed Buhari 
Added Date : Monday, December 9, 2019 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
نسيبه رجا الله الغانميAlghanmi, Nusaybah RajaallahResearcherMaster 

Files

File NameTypeDescription
 45660.pdf pdf 

Back To Researches Page