My post PhD work primarily focussed on understanding the effects of resources and data centers on the cloud computing environment. I intended to investigate and design an adaptive resource management to provide effective, efficient and reliable support for applications across all elements of the application platform while attaining economic, sustainability, and other high-level objectives. A dynamic resource management system by incorporating VM provisioning strategies (as soon as possible and as full as possible) has been developed to provide efficient resource utilization, low-power consumption and improved ability of the system to adapt to changes in workloads in Fog assisted cloud environments.

Apart from the cloud environment, another research work in the directions for sentiment analysis is completed. As social media users are increasingly using both images and text to express their opinions and share their experiences. Consequently, the conventional text-based sentiment analysis has evolved into more complicated studies of multimodal sentiment analysis. To exploit the information from both visual content and textual content, an Improved Coyote Optimization Algorithm (ICOA) is proposed that optimally chooses the features from the extracted feature set of the input image. For performing efficient feature learning for the input textual comments, an adaptive Embedding for Language Models (ELMo) is proposed. For classifying the visual-textual data into positive and negative polarity, an optimal BMMCA-Dense Net classifier is proposed. The various evaluation metrics are identified to undertake the performance analysis of the proposed model. BMMCA-Dense Net attains greater accuracy (97 %) and a lesser error rate than the existing techniques