Study about Statistical Normalization and Back Propagation | Chapter 04 | Novel Research Aspects in Mathematical and Computer Science Vol. 2

 Artificial Neural Networks (ANNs) are a prominent machine learning technique that has lately been used in a variety of medical and medically related industries. Diabetes is a chronic condition that develops when blood sugar levels are too high. Early diagnosis of the condition may help to reduce consequences. The Artificial Neural Network is a well-known nonlinear data classifier. When building the network model, there are a few main aspects to consider. The input vectors' normalisation, learning rate parameter, and network structure. The proposed study examines several normalising approaches used in back propagation neural networks to improve the trained network's dependability. Based on the experimental results, the performance of the classifier model may be improved.

Author(S) Details

T. Jayalakshmi
LRG Government Arts College For Women, Tiruppur, India.

A. Santhakumaran
LRG Government Arts College For Women, Tiruppur, India.

View Book:- https://stm.bookpi.org/NRAMCS-V2/article/view/6790

Determination of Machine Learning and IOT Enabled Complete Architecture for Agriculture Applications | Chapter 2 | New Visions in Science and Technology Vol. 10

 Traditional agriculture models have some drawbacks, such as the risk cost and real execution without the necessary quality data. Soil additives such as moisture, nitrogen (N), phosphorus (P), and potassium are required for any crop's productivity improvement (K). To overcome the constraints of the traditional approach, we developed a model that uses deep learning and remote sensing to estimate soil fertility levels and productivity predictions. Current technological breakthroughs that provide foretelling form, which increases state-of-the-art precision agriculture. In the previous decade, the usage of machine learning (ML) techniques with IoT devices has developed in a variety of industries. The increasing accessibility of soil data enabled ML approaches to analyse and increase production, which was aided by the use of IoT. The first stage is to set up the physical environment, which includes placing IoT devices in the fields to gather soil parameters. In the second step, we create a dynamic model using a back-propagation neural network, a machine learning and deep learning method, to forecast soil attributes and evaluate the input data from the first phase using raw soil field data. Internet of Things (IoT) devices and connections for wireless communication with sensors are currently available for a variety of agricultural field work applications, including soil preparation, water management, and crop development status. State-of-the-art farm architecture based on IoT and deep learning identifies traditional limitations and provides relevant solutions. The major goal of this research paper is to look at how deep learning, specifically back propagation neural networks, may be used to predict soil attributes from spectral (raw) data from organic soils using inputs from various IoT sensors.

Author(S) Details

Shivnath Ghosh
Brainware University, Kolkata, West Bengal, India.

Santanu Koley
Haldia Institute of Technology, Haldia, West Bengal, India.

Pinaki Pratim Acharjya
Haldia Institute of Technology, Haldia, West Bengal, India.

Mihir Baran Bera
Haldia Institute of Technology, Haldia, West Bengal, India.

View Book:- https://stm.bookpi.org/NVST-V10/article/view/4881