Название: IoT-enabled Convolutional Neural Networks Techniques and Applications
Автор: Mohd Naved, V. Ajantha Devi, Loveleen Gaur
Издательство: River Publishers
Год: 2023
Страниц: 409
Язык: английский
Формат: pdf (true)
Размер: 32.7 MB

Convolutional neural networks (CNNs), a type of deep neural network that has become dominant in a variety of computer vision tasks, in recent few years has attracted interest across a variety of domains due to their high efficiency at extracting meaningful information from visual imagery. Convolutional neural networks (CNNs) excel at a wide range of Machine Learning and Deep Learning tasks. As sensor-enabled internet of things (IoT) devices pervade every aspect of modern life, it is becoming increasingly critical to run CNN inference, a computationally intensive application, on resource-constrained devices.

Through this edited volume we aim to provide a structured presentation of CNN enabled IoT applications in vision, speech, and natural language processing (NLP). This book discusses a variety of CNN techniques and applications, including but not limited to, IoT enabled CNN for speech de-noising, a smart app for visually impaired people, disease detection, ECG signal analysis, weather monitoring, texture analysis, etc.

CNNs, a type of artificial neural network that has been popular in computer vision, are gaining popularity in a variety of fields, including radiology. CNN uses several building blocks like as convolution layers, pooling layers, and fully connected layers to learn spatial hierarchies of information automatically and adaptively through backprop­ agation. A neural network is a hardware and/or software system modelled after the way neurons in the human brain work. Traditional neural networks aren’t designed for image processing and must be fed images in smaller chunks. CNN’s “neurons” are structured more like those in the frontal lobe, the area in humans and other animals responsible for processing visual inputs. Traditional neural networks’ piecemeal image processing difficulty is avoided by arranging the layers of neurons in such a way that they span the whole visual field. A CNN employs a technology similar to a multilayer perceptron that is optimised for low processing requirements. An input layer, an output layer, and a hidden layer with several convolutional layers, pooling layers, fully connected layers, and normalising layers make up a CNN’s layers. The removal of constraints and improvements in image processing efficiency result in a system that is significantly more effective and easier to train for image processing and natural language processing. This Book article explains the core concepts of CNN and how they are used to diverse jobs, as well as their problems and future directions.

Unlike other books on the market, this book covers the tools, techniques, and challenges associated with the implementation of CNN algorithms, computation time, and the complexity associated with reasoning and modelling various types of data. We have included CNN's current research trends and future directions.