Bøger af Punit Gupta

Nell'Internet delle cose (IoT), i dispositivi raccolgono e condividono informazioni direttamente tra loro e con il cloud, rendendo possibile la raccolta, la registrazione e l'analisi di nuovi flussi di dati in modo più rapido e accurato. Il rapido sviluppo della tecnologia dell'Internet delle cose (IoT) consente di collegare tra loro vari oggetti intelligenti attraverso Internet e di fornire più metodi di interoperabilità dei dati a scopo applicativo. Recenti ricerche mostrano un maggior numero di potenziali applicazioni dell'IoT in settori industriali ad alta intensità di informazioni, come i servizi commerciali. In questo progetto, presentiamo un sistema basato sull'IoT per un sistema di punti vendita intelligente ed efficiente, per dimostrare come raccogliere, integrare e interoperare i dati IoT in modo flessibile, al fine di fornire nuovi ambiti ai servizi commerciali.

Focuses on fundamental concepts of gathering, processing, analyzing the dataset from rich healthcare and biomedical sources. Covers interdisciplinary techniques such as data science, deep learning, statistics, big data analytics, smart devices, computer vision and IoT.

This book proposes a learning-based cost efficient algorithm for cloud Infrastructure. The proposed algorithm uses a genetic algorithm for cost-efficient task allocation to minimize cost and high utilization to provide better QoS (Quality of Service) to the client. Proposed strategy has proven to have better performance in term of execution cost, execution time, scheduling time as compared to previously proposed task allocation algorithms.

ANT Colony Optimization is a task scheduling algorithm in which we schedule tasks by allocating them to resources. In this project, resources are designated as virtual machines and tasks are designated as cloudlets. Earlier many task scheduling algorithms are proposed to improve the performance but have not cost efficient at the same time. PSO and Round Robin are efficient solutions but not cost effective. So to overcome the issues We have proposed learning based cost efficient algorithm for cloud infrastructure.

In the Internet of Things (IoT), devices gather and share information directly with each other and the cloud, making it possible to collect, record and analyse new data streams faster and more accurately. The rapid development of Internet of things (IoT) technology makes it possible for connecting various smart objects together through the Internet and providing more data interoperability methods for application purpose. Recent research shows more potential applications of IoT in information intensive industrial sectors such as commercial services. In this project, we present an IoT-based system for smart and efficient point of sale system to demonstrate how to collect, integrate, and interoperate IoT data flexibly in order to provide new realms to commercial services.

The model which we have presented is a Linear Regression Model. In the results above we see that predictions can be done on the basis of the data available and is approximately accurate. An accurate forecast is very important for the demand planning team. The data used in this project and building the model is using the sales-in data for different stores. The important factor to be considered is the stability of the model and removing the game-playing. A community version of a platform is used to build the model. Linear Regression model is developed in pyspark. After the results are generated, dataframe of results is validated and generated and is sent backto the Azure SQL database to be used in Power BI.In the future work, different techniques will be considered and researched. Time-Series and Machine Learning to be built in one platform and check how the minimization of mse produces the forecast. The predictions can be hyper parameterized to give more accurately tuned results. Also, in the PowerBI report more measures and visualizations can be made on basis of individual¿s thought process.

This book discusses various aspects of cloud computing, in which trust and fault-tolerance models are included in a multilayered, cloud architecture.