Design and development of IIoT-based system for behavior profiling of nonlinear dynamic production systems based on energy flow theory

In this paper, a solution to effective energy consumption monitoring of fast-response energy systems in industrial environments was proposed, designed, and developed. Moreover, in this research, production systems are characterized as nonlinear dynamic systems, with the hypothesis that the identification and introduction of nonlinear members (variables) can have a significant impact on improving system performance by providing clear insight and realistic representation of system behavior due to a series of nonlinear activities that stimulate the system state changes, which can be spotted through the manner and intensity of energy use in the observed system. The research is oriented towards achieving favorable conditions to deploy dynamic energy management systems by means of the Internet of Things and Big Data, as highly prominent concepts of Industry 4.0 technologies into scientifically-driven industrial practice. The motivation behind this is driven by the transition that this highly digital modern age brought upon us, in which energy management systems could be treated as a continual, dynamic process instead of remaining characterized as static with periodical system audits. In addition, a segmented system architecture of the proposed solution was described in detail, while initial experimental results justified the given hypothesis. The generated results indicated that the process of energy consumption quantification, not only ensures reliable, accurate, and real-time information but opens the door towards system behavior profiling, predictive maintenance, event forensics, data-driven prognostics, etc. Lastly, the points of future investigations were indicated as well.

Big behavior: challenges and opportunities in a new era of deep behavior profiling

The assessment of rodent behavior forms a cornerstone of preclinical assessment in neuroscience research. Nonetheless, the true and almost limitless potential of behavioral analysis has been inaccessible to scientists until very recently. Now, in the age of machine vision and deep learning, it is possible to extract and quantify almost infinite numbers of behavioral variables, to break behaviors down into subcategories and even into small behavioral units, syllables or motifs. However, the rapidly growing field of behavioral neuroethology is experiencing birthing pains. The community has not yet consolidated its methods, and new algorithms transfer poorly between labs. Benchmarking experiments as well as the large, well-annotated behavior datasets required are missing. Meanwhile, big data problems have started arising and we currently lack platforms for sharing large datasets—akin to sequencing repositories in genomics. Additionally, the average behavioral research lab does not have access to the latest tools to extract and analyze behavior, as their implementation requires advanced computational skills. Even so, the field is brimming with excitement and boundless opportunity. This review aims to highlight the potential of recent developments in the field of behavioral analysis, whilst trying to guide a consensus on practical issues concerning data collection and data sharing.