Improving IoT Predictions through the Identification of Graphical Features
IoT sensor networks have an inherent graph structure that can be used to extract graphical features for improving performance in a variety of prediction tasks. We propose a framework that represents IoT sensor network data as a graph, extracts graphical features, and applies feature selection method...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/15/3250 |
| _version_ | 1798041389959741440 |
|---|---|
| author | Syeda Akter Lawrence Holder |
| author_facet | Syeda Akter Lawrence Holder |
| author_sort | Syeda Akter |
| collection | DOAJ |
| description | IoT sensor networks have an inherent graph structure that can be used to extract graphical features for improving performance in a variety of prediction tasks. We propose a framework that represents IoT sensor network data as a graph, extracts graphical features, and applies feature selection methods to identify the most useful features that are to be used by a classifier for prediction tasks. We show that a set of generic graph-based features can improve performance of sensor network predictions without the need for application-specific and task-specific feature engineering. We apply this approach to three different prediction tasks: activity recognition from motion sensors in a smart home, demographic prediction from GPS sensor data in a smart phone, and activity recognition from GPS sensor data in a smart phone. Our approach produced comparable results with most of the state-of-the-art methods, while maintaining the additional advantage of general applicability to IoT sensor networks without using sophisticated and application-specific feature generation techniques or background knowledge. We further investigate the impact of using edge-transition times, categorical features, different sensor window sizes, and normalization in the smart home domain. We also consider deep learning approaches, including the Graph Convolutional Network (GCN), for the elimination of feature engineering in the smart home domain, but our approach provided better performance in most cases. We conclude that the graphical feature-based framework that is based on IoT sensor categorization, nodes and edges as features, and feature selection techniques provides superior results when compared to the non-graph-based features. |
| first_indexed | 2024-04-11T22:20:52Z |
| format | Article |
| id | doaj.art-46b1228b407f4f0e8caee2e244a952e9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:20:52Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-46b1228b407f4f0e8caee2e244a952e92022-12-22T04:00:08ZengMDPI AGSensors1424-82202019-07-011915325010.3390/s19153250s19153250Improving IoT Predictions through the Identification of Graphical FeaturesSyeda Akter0Lawrence Holder1School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA 99163, USASchool of Electrical Engineering and Computer Science, Washington State University, Pullman, WA 99163, USAIoT sensor networks have an inherent graph structure that can be used to extract graphical features for improving performance in a variety of prediction tasks. We propose a framework that represents IoT sensor network data as a graph, extracts graphical features, and applies feature selection methods to identify the most useful features that are to be used by a classifier for prediction tasks. We show that a set of generic graph-based features can improve performance of sensor network predictions without the need for application-specific and task-specific feature engineering. We apply this approach to three different prediction tasks: activity recognition from motion sensors in a smart home, demographic prediction from GPS sensor data in a smart phone, and activity recognition from GPS sensor data in a smart phone. Our approach produced comparable results with most of the state-of-the-art methods, while maintaining the additional advantage of general applicability to IoT sensor networks without using sophisticated and application-specific feature generation techniques or background knowledge. We further investigate the impact of using edge-transition times, categorical features, different sensor window sizes, and normalization in the smart home domain. We also consider deep learning approaches, including the Graph Convolutional Network (GCN), for the elimination of feature engineering in the smart home domain, but our approach provided better performance in most cases. We conclude that the graphical feature-based framework that is based on IoT sensor categorization, nodes and edges as features, and feature selection techniques provides superior results when compared to the non-graph-based features.https://www.mdpi.com/1424-8220/19/15/3250sensor networksgraph representationgraphical featuresfeature selectionactivity recognition |
| spellingShingle | Syeda Akter Lawrence Holder Improving IoT Predictions through the Identification of Graphical Features Sensors sensor networks graph representation graphical features feature selection activity recognition |
| title | Improving IoT Predictions through the Identification of Graphical Features |
| title_full | Improving IoT Predictions through the Identification of Graphical Features |
| title_fullStr | Improving IoT Predictions through the Identification of Graphical Features |
| title_full_unstemmed | Improving IoT Predictions through the Identification of Graphical Features |
| title_short | Improving IoT Predictions through the Identification of Graphical Features |
| title_sort | improving iot predictions through the identification of graphical features |
| topic | sensor networks graph representation graphical features feature selection activity recognition |
| url | https://www.mdpi.com/1424-8220/19/15/3250 |
| work_keys_str_mv | AT syedaakter improvingiotpredictionsthroughtheidentificationofgraphicalfeatures AT lawrenceholder improvingiotpredictionsthroughtheidentificationofgraphicalfeatures |