Saffron, one of the most expensive crops on earth, having a vast domain of applications, has the potential to boost the economy of India. The cultivation of saffron has been immensely affected in the past few years due to the changing climate. Despite the use of different artificial methods for cultivation, hydroponic approaches using the IoT prove to give the best results. The presented study consists of potential artificial approaches used for cultivation and the selection of hydroponics as the best approach out of these based on different parameters. This paper also provides a comparative analysis of six present hydroponic approaches. The research work on different factors of saffron, such as the parameters responsible for growth, reasons for the decline in growth, and different agronomical variables, has been shown graphically. A smart hydroponic system for saffron cultivation has been proposed using the NFT (nutrient film technique) and renewable sources of energy.

Conjunctivitis is one of the most common eye disorders, and timely diagnoses are crucial to ensure no complications arise from such disorders. Manually examining the images to diagnose the disease often takes too much time and may result in inconsistent diagnosis. To overcome this problem, this paper presents a framework referred to as MOGONET, which is based on deep learning (DL) techniques and involves image preprocessing, image segmentation, data augmentation, transfer learning, and multi-objective optimization for diagnosing conjunctivitis eye disease. To increase the quality of the image for analysis, image contrast enhancements are employed. Furthermore, image multi-threshold segmentation techniques are used to identify vital areas of the eye. Also, an advanced Generalized Normal Distribution Optimization (GNDO) algorithm combined with a CNN is used to improve the efficiency and minimize computational complexity. The proposed model is tested using conjunctivitis eye image dataset from Kaggle and Shutterstock. According to the result findings, the accuracy, precision, recall, and F-score of the proposed model is 98.32%, 97.54%, 96.92%, and 96.22%, respectively. Moreover, the model is highly efficient as it resulted in minimized loss, floating-point operation, and fewer trainable parameters than some popular DL frameworks.