Abstract:
Industrial wireless sensor networks (IWSNs) must track continuous objects in the petrochemical and nuclear industries because of their flammability, explosiveness, and toxicity. We propose a continuous object boundary tracking algorithm for IWSNs that fully exploits sensor nodes’ collective intelligence and machine learning.
The algorithm first sets an upper bound for the event region covered by continuous objects. Within the event region, a binary tree-based partition produces a coarse-grained boundary area mapping.
The boundary tracking problem is transformed into a binary classification problem to study the irregularity of continuous objects, and a hierarchical soft margin support vector machine training strategy is used to solve it distributedly.
Simulations show that the proposed algorithm reduces boundary tracking nodes by 50%. Even with 9% faulty nodes, the proposed algorithm is robust to false sensor readings without fault-tolerant mechanisms.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
