| Autor: |
Amjad Sheikh, Moath Awawdeh, Anees Bashir, Tarig Faisal |
| Rok vydání: |
2019 |
| Předmět: |
|
| Zdroj: |
2019 Advances in Science and Engineering Technology International Conferences (ASET). |
| Popis: |
The problem of outlier detection for measurements extracted from IoT platform has been addressed. An approach to validate the detected values via the coefficient of determination analysis is presented by applying a combination procedure of weighted least square, bisquare algorithm and robust fit. We fit the model firstly by weighted least square then we used the method of bisquare weight where the weight of each measure is assigned based on the distance of that value to the generated best fit. The map of weights for each measure in the dataset determine if the value is a possible outlier by searching for those measures with zero weight. In the second part of the paper we apply some of the most common method of outlier processing with logarithmic and square root transformation where the reweighted least square has been used to detect the outliers. We Analyze three cases of dealing with outliers including transformation and outlier removal then we measure the coefficient of determination for each case together with other statistic. The results are shown by mean of simulation with estimation result and weight labeling. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
