IoT Based Data Analytics for the Healthcare Industry: Techniques and Applications explores recent advances in the analysis of healthcare industry data through IoT data analytics. The book covers the analysis of ubiquitous data generated by the healthcare industry, from a wide range of sources, including patients, doctors, hospitals, and health insurance companies. The book provides AI solutions and support for healthcare industry end-users who need to analyze and manipulate this vast amount of data. These solutions feature deep learning and a wide range of intelligent methods, including simulated annealing, tabu search, genetic algorithm, ant colony optimization, and particle swarm optimization. The book also explores challenges, opportunities, and future research directions, and discusses the data collection and pre-processing stages, challenges and issues in data collection, data handling, and data collection set-up. Healthcare industry data or streaming data generated by ubiquitous sensors cocooned into the IoT requires advanced analytics to transform data into information. With advances in computing power, communications, and techniques for data acquisition, the need for advanced data analytics is in high demand.

A set of 44 genotypes of lentil, grown in two different cropping systems viz., monocropping and intercropping were studied for assessment of nature and magnitude of variability, identification of yield attributes and genetic divergence among genotypes at the experimental farm of the Department of Plant Breeding and Genetics, CSK HPKV, Palampur. Sufficient variability was observed for all the twelve characters studied in both the cropping systems except plant height, primary branches per plant and pods per cluster in monocropping. High PCV and GCV observed for pod cluster per plant, pods per plant, seeds per plant and seed yield per plant in both the systems while 100-seed weight, biological yield per plant recorded high PCV and GCV in monocropping only. High heritability coupled with high genetic advance was recorded for days to 50% flowering. Correlation and path analysis studies indicated that days to 50% flowering, days to 75% maturity, pod cluster per plant, pods per plant, 100-seed weight, biological yield per plant, seeds per plant and harvest index were important for selection of high yielding and early maturing genotypes of lentil.