ABSTRACT
Abstract: Smart ocean is a term broadly used for monitoring the ocean surface, sea habitat monitoring, and mineral exploration to name a few. Development of an efficient routing protocol for smart oceans is a non-trivial task because of various challenges, such as presence of tidal waves, multiple sources of noise, high propagation delay, and low bandwidth. In this paper, we have proposed a routing protocol named adaptive node clustering technique for smart ocean underwater sensor network (SOSNET). SOSNET employs a moth flame optimizer (MFO) based technique for selecting a near optimal number of clusters required for routing. MFO is a bio inspired optimization technique, which takes into account the movement of moths towards light. The SOSNET algorithm is compared with other bio inspired algorithms such as comprehensive learning particle swarm optimization (CLPSO), ant colony optimization (ACO), and gray wolf optimization (GWO). All these algorithms are used for routing optimization. The performance metrics used for this comparison are transmission range of nodes, node density, and grid size. These parameters are varied during the simulation, and the results indicate that SOSNET performed better than other algorithms.
ABSTRACT
Lifelong machine learning (LML) models learn with experience maintaining a knowledge-base, without user intervention. Unlike traditional single-domain models they can easily scale up to explore big data. The existing LML models have high data dependency, consume more resources, and do not support streaming data. This paper proposes online LML model (OAMC) to support streaming data with reduced data dependency. With engineering the knowledge-base and introducing new knowledge features the learning pattern of the model is improved for data arriving in pieces. OAMC improves accuracy as topic coherence by 7% for streaming data while reducing the processing cost to half.
