Indication of COVID-19 and Inference Employing RFO Classifier

A Secured Data Sharing Protocol for Minimisation of Risk in Cloud Computing and Big Data in AI Application

Magnetic Resonance Images for Spinal Cord Location Detection Using a Deep-Learning Model

The conceptual and technological reasons, with the fast and reliable geographical categorization of crop kinds, can rely on remote sensing data is a critical task. Insurance policy, land leasing, supply-chain logistics, and financial market forecasts utilize spatial variability crop-type information to predict crop acreage for a range of monitoring and decision-making purposes. Cropland products derived from remote sensing have become much more accurate in depicting the location and size of agricultural fields. However, differentiating between actively agricultural areas and probably followed fields across agricultural lands, particularly in temperate zone grass barren structures, has received little attention. Crop-fallow rotation techniques are extensively utilized for soil fertility regeneration in the Sahel, one of the world's biggest dryland areas. Nevertheless, since fallow fields aren't clearly distinguished even within cropland class in any current remote sensing-based land use/cover maps, irrespective of the geographical resolution, nothing is recognized about their size. As one of the most precise metrics for evaluating regression modelling, the recently created Random Forest (RF) machine-learning method has gained widespread recognition. One study sought to determine whether the RF regression algorithm could be used to estimate crop solar energy digitally, assess a system's implementation, and compare the RF algorithm's productivity to the existing benchmarks. Results show that the RF-based technique is far better and outperforms the existing benchmarks in terms of performance. 

An advanced Machine Learning Techniques on Agriculture fileds for future level cultivations

A Smart Healthcare Cognitive Radio System for Future Wireless Commutation Applications with Test Methodology

Face recognition need is fine assured as enormous industrial relevance use them to implement one or another objective. As the programmes move closer to everyday usage to hold a database of actual events, an individual’s identification primarily demanded as an instance of consistency. As facial recognition has beating advantages over other industrial applications and human eyes can quickly evaluate performance, improved algorithms and smaller computing costs are continuously improving this methodology. This research takes the conventional algorithms of recognition in the first stage and uses hybrid approaches to counter their limitations. The study starts with basic computation of global face features using Principal Component Analysis (PCA), Discrete Wavelet Transform (DWT) and Independent Component Analysis (ICA), with some standard classifiers like Neural Network (NN) and Support Vector Machine (SVM). As the learning rate is high in machine learning, then the system’s accuracy goes high, but increases the area and cost overhead. Fusion-based methods have been proposed in further work to overcome that training limitation, based on Harris corner, Speed up Robust Features (SURF) and DWT + PCA system model where only 10% training sample has been taken on Essex database, and 99.45% accuracy is achieved. Creating the Fusion rule requires some hit and trial methods that may not be Universal in every database. To overcome this limitation further an efficient Hybrid method proposed which elaborates the local features Linear Binary Pattern (LBP), Histogram Oriented Gradients (HOG), Gabor wavelet and global features (DWT, PCA) of the face. Further, this feature trained with Neural Network classifier to obtained better accuracy nearly 99.40% with single image training from each class.

K. Saikumar

Papers

An Optimal Hybrid Solution to Local and Global Facial Recognition Through Machine Learning