Industrial processes such as batch distillation columns, supply chain, level control etc. integrate dead times in the wake of the transportation times associated with energy, mass and information. The dead time, the cause for the rise in loop variability, also results from the process time and accumulation of time lags. These delays make the system control poor in its asymptotic stability, i.e. its lack of self-regulating savvy. The haste of the controller’s reaction to disturbances and congruence with the design specifications are largely influenced by the dead time; hence it exhorts a heed. This article is aimed at answering the following question: “How can a fractional order proportional integral derivative controller (FOPIDC) be tuned to become a perfect dead time compensator apposite to the dead time integrated industrial process?” The traditional feedback controllers and their tuning methods do not offer adequate resiliency for the controller to combat out the dead time. The whale optimization algorithm (WOA), which is a nascent (2016 developed) swarm-based meta-heuristic algorithm impersonating the hunting maneuver of a humpback whale, is employed in this paper for tuning the FOPIDC. A comprehensive study is performed and the design is corroborated in the MATLAB/Simulink platform using the FOMCON toolbox. The triumph of the WOA tuning is demonstrated through the critical result comparison of WOA tuning with Bat and particle swarm optimization (PSO) algorithm-based tuning methods. Bode plot based stability analysis and the time domain specification based transient analysis are the main study methodologies used.

Nowadays in e-commerce applications, aspect-based sentiment analysis has become vital, and every consumer started focusing on various aspects of the product before making the purchasing decision on online portals like Amazon, Walmart, Alibaba, etc. Hence, the enhancement of sentiment classification considering every aspect of products and services is in the limelight. In this proposed research, an aspect-based sentiment classification model has been developed employing sentiment whale-optimized adaptive neural network (SWOANN) for classifying the sentiment for key aspects of products and services. The accuracy of sentiment classification of the product and services has been improved by the optimal selection of weights of neurons in the proposed model. The promising results are obtained by analyzing the mobile phone review dataset when compared with other existing sentiment classification approaches such as support vector machine (SVM) and artificial neural network (ANN). The proposed work uses key features such as the positive opinion score, negative opinion score, and term frequency-inverse document frequency (TF-IDF) for representing each aspect of products and services, which further improves the overall effectiveness of the classifier. The proposed model can be compatible with any sentiment classification problem of products and services.