PlantES: A Plant Electrophysiological Multi-Source Data Online Analysis and Sharing Platform

Abstract

At present, plant electrophysiological data volumes and complexity are increasing rapidly. It causes the demand for efficient management of big data, data sharing among research groups, and fast analysis. In this paper, we proposed PlantES (Plant Electrophysiological Data Sharing), a distributed computing-based prototype system that can be used to store, manage, visualize, analyze, and share plant electrophysiological data. We deliberately designed a storage schema to manage the multi-source plant electrophysiological data by integrating distributed storage systems HDFS and HBase to access all kinds of files efficiently. To improve the online analysis efficiency, parallel computing algorithms on Spark were proposed and implemented, e.g., plant electrical signals extraction method, the adaptive derivative threshold algorithm, and template matching algorithm. The experimental results indicated that Spark efficiently improves the online analysis. Meanwhile, the online visualization and sharing of multiple types of data in the web browser were implemented. Our prototype platform provides a solution for web-based sharing and analysis of plant electrophysiological multi-source data and improves the comprehension of plant electrical signals from a systemic perspective.

Graph Representation Integrating Signals for Emotion Recognition and Analysis

“…Several studies have focused on the storage and integration of biosignals, although these are not related to emotion recognition [23][24][25][26]. For example, approach proposed by Kokkinaki et al [27] is built on the definition of a global ontology that manipulates the source similarities and differences and thus creates mappings or enhances its structure.…”