Browsing by Author "Kalayci, Ilker"

Now showing 1 - 2 of 2

Citation - WoS: 3
Citation - Scopus: 3
A Framework Model for Data Reliability in Wireless Sensor Networks
(IEEE, 2016) Ilker Kalayci; Tuncay Ercan; Ercan, Tuncay; Kalayci, Ilker
In this study a model for data reliability in wireless sensor networks is proposed in which machine learning methods are used. Proposed framework includes data modelling missing data prediction anomaly detection data fusion and trust mechanism phases. Thus temporal analysis is performed on the preprocessed sensor data and missing data are predicated. Then outliers on collected data are detected on the cluster head nodes by using Eta one-class Support Vector Machines. If an event is detected data are fused and then send to sink. If an anomaly is detected for a node's data the trust weight of the node is decreased.
Citation - WoS: 3
Anomaly Detection in Wireless Sensor Networks Data by Using Histogram Based Outlier Score Method
(IEEE, 2018) Ilker Kalayci; Tuncay Ercan; Ercan, Tuncay; Kalayci, Ilker
Data anomaly detection in wireless sensor networks which is one of the important technologies and study areas is a method that enhances data quality and data reliability. Besides data enhancing methods such as estimating missing data deduplication noise removal, anomaly detection is important in terms of finding data patterns which are out of normal data. This stage influences next analysis and decision processes and plays an important role in determining events faults or unexcepted but meaningful patterns. This study proposes the Histogram Based Outlier Score (HBOS) method to detect anomalies in data acquired by wireless sensor networks. In respect to anomaly detection methods used in this area such as data classification data clustering statistical distance based and support vector machines based approaches histogram based algorithms are unsupervised and provide fast solutions.