The applications of IoT have been employed in diverse domains like industries, clinical care, and farming, and so forth. Nowadays, the constitution of this technology is more prevalent in clinical observation, where the wearable devices have stimulated the development of the Internet of Medical Things (IoMT). In the process of reducing the death rate, it is necessary to detect the disease at an earlier stage. The cardiac disease prediction is a major defect in the examination of the dataset in clinics. The research proposed aims to recognize the important cardiac complaint prediction characteristics by utilizing machine‐learning methodologies. Numerous projects have been established regarding the diagnosis of cardiac complaints, which results in low accuracy rate. Thus, for improving the accuracy of prediction and for cardiac complaint investigation this article utilized a fuzzy c‐means neural network (FNN) and a deep convolution neural network for feature extraction. From the clinical dataset, data were obtained for the risk prediction of cardiac complaints that includes blood pressure (BP), age, sex, chest pain, cholesterol, blood sugar, and so forth. The hearts condition is recognized by categorizing the sensor data received by FNN. The evaluation performances were carried out and the results revealed that FNN is good in predicting the cardiac complaints. In addition to this, the proposed model achieves better accuracy than the other approaches through the demonstration of simulation results. The proposed approach attains the accuracy rate of 86.4% and F1‐score of 97%, precision 76.2%, and 64.6% of FPR.

The study presents an approach to map Land Use / Land Cover Change (LULCC) at large scale and processing techniques that permit higher accuracy. IRS RESOURCESAT-2 LISS-IV images of Nellore district of Andhra Pradesh were used to apply the classification technique. In multi-scale feature extraction approach LULCC takes two forms i.e. conversion from one category of LULCC to another and modification of condition within a category. Thus, major LULCC classes were extracted using object based approach and uncertain classes were identified using onscreen knowledge based method. The results showed in 2009, the accuracy of cropland, water body and built-up segments were 99.3%, 94.79% and 89.72%, respectively, whereas, in 2013 the accuracies were 94.31%, 88.26% and 81.20%, respectively. Hence, this classification approach can be useful in different landscape structure over the time, which can be quantified and assessed to achieve a better understanding of the land cover.

No abstract

Proper calculation of rice cultivation area well before harvest is critical for projecting rice yields and developing policies to assure food security. This research looks at how Remote Sensing (RS) and Geographic Information System (GIS) can be used to map rice fields in Palakkad district of Kerala. The area was delineated using three multi-temporal cloud free Sentinel-2 data with 10 m spatial resolution, matching to crop's reproductive stage during mundakan season (September-October to December-January), 2020-21. To make classification easier, the administrative boundary of district was placed over the mosaicked image. The rice acreage estimation and land use classification of the major rice tract of Palakkad district comprising five blocks was done using Iterative Self-Organisation Data Analysis Technique (ISODATA) unsupervised classification provision in ArcGIS 10.1 software, employing False Colour Composite (FCC) including Blue (B2), Green (B3), Red (B4) and Near-infrared (B8) Bands of Sentinel-2 images. The classification accuracy was determined by locating a total of 60 validation points throughout the district, comprising 30 rice and 30 non-rice points. The total estimated area was 24742.76 ha, with an average accuracy of 88.33% and kappa coefficient 0.766 in five blocks of Palakkad district. The information generated will be helpful in assessing the anticipated production as well as the water demand of the rice fields.