Cloud computing has emerged as an effective way to tackle the storage and processing challenges associated with large amounts of data. It offers cost-effective, fast, flexible, and scalable solutions. Despite significant advancements in cloud computing and its services, the development of environmentally-friendly "green clouds" is still in progress. This is largely due to limited research and various implementation barriers. Green clouds aim to be eco-friendly, energy-efficient, resource-efficient, low in carbon emissions, and sustainable. Cloud service providers are continually striving to meet the increasing demands of enterprise data storage and processing. To address the environmental implications associated with cloud computing, these providers are actively implementing innovative technologies such as Green Cloud Computing in
their architectural designs. The goal is to minimize power consumption, water usage, reliance on physical hardware peripherals, overall infrastructure, and the release of harmful carbon emissions. In order to protect our environment, service providers must adopt and enhance their cloud infrastructure to align with green computing principles. Extensive research in this field focuses on the development of efficient cloud systems that possess green characteristics,
including load balancing, virtualization, power management, computing, high performance green data centers, and promoting reusability and recyclability. This analysis report aims to provide a detailed overview of green cloud computing and its key features. It delves into the previous accomplishments in green computing, explores current trends in the field, and outlines future
research challenges. This comprehensive analysis report serves as a valuable resource for aspiring green researchers, offering insights into green cloud topics and the upcoming challenges in the field.
The paper proposes a scalable ensemble approach for forecasting the electricity consumption of households. SVM (support vector machine) based approach is a combination of different machine learning models, including linear regression, decision trees, and random forests, to improve the accuracy of the forecasts.
The study was conducted using real-world data from households in the Netherlands, and the results show that the proposed approach outperforms traditional singlemodel approaches and achieves better accuracy in electricity consumption forecasting. The approach is scalable and can be applied to large datasets, making it suitable for use in real-world applications. SVM (Support
vector machine) is a machine learning algorithm for load forecasting Long-term individual household forecasting may be used in a variety of applications, such as determining customer advance payments. Yet, there is a scarcity of literature on this form of forecasting current approaches either focus on short-term projections for individual families or long-term predictions at an aggregated level. To remedy this void, we describe a strategy that forecasts each monthly consumption over the future year using only a few months of consumption data from the current year. Utility providers may use this strategy to forecast any customer's use for the coming year even with limited data. Future forecasting of power consumption of linear regression for power consumption of data. Linear regression algorithm is implemented for future forecasting of data.
Land transportation in India heavily relies on railway stations,yet these stations face issues with parking due to manual methods, resulting in congestion and inefficiencies. Current approaches also face difficulties such as inadequate
real-time parking allocation, a deficiency in digital payment options, and issues related to user-friendliness. To address this, a cutting-edge solution is proposed which harnesses advanced technologies like image processing, Raspberry Pi, OCR for license plate recognition, and cashless transactions. Ultrasonic sensor verify vehicle presence, OCR deciphers license plates, and historical data manages parking logistics, slot detection is done using Pickle.Travelers can conveniently access parking fees on an OLED screen, receive a QR code for
exiting , simplifying payments and improving safety. The project places a strong emphasis on environmental sustainability and real-time updates. It is designed with potential for expansion and integration with other station services, offering an effective, eco-conscious parking system that can adapt to evolving transportation needs.
The Integrated Cool Warm Jacket represents a wearable technology, which seeks to give consumers with a personalized and adaptable comfort experience. In response to the challenges posed by varying environmental conditions, this innovative jacket seamlessly integrates intelligent heating and cooling elements to maintain an optimal body temperature. Equipped with Arduino UNO, Peltier module, Bluetooth module, Lithium ion Battery, Relay, Temperature sensor, LCD display, User Interference with fabric insulation materials. The jacket's design incorporates a network of embedded sensors that continuously monitor ambient temperature, humidity levels, and the wearer's body temperature. These sensors relay real-time data to a control unit, which employs sophisticated algorithms to analyse and interpret the information. Based on the analysis, the system dynamically adjusts the jacket's thermal features, ensuring the wearer remains
comfortable in any environment. The integration of these features allows for a fine-tuned balance, offering users a customizable and responsive thermal management system.
Keywords : Arduino UNO, Bluetooth module, lithium ion battery, LCD display, Peltier module, Relay, Temperature sensor, User Interface, Fabric and insulation material.
Author : ROSHAN KUMAR D, Mr. S. SATHISH, PRAVEEN K and SANTHOSH P
Because of an increase in the number of cars on the road in India, there is now a significant problem with traffic congestion at intersections. There is an immediate need for adaptive traffic signals that are able to perform real-time monitoring of traffic density due to the fact that the density of cars is steadily rising day by day. The purpose of this work is to present a system that employs image processing for the purpose of effectively managing traffic at a
junction by obtaining photographs of the traffic at the junction. At a traffic signal, a methodical approach that includes the collecting of images, the analysis of images, and the development of an algorithm to alter the length of the traffic light according to the density of cars on various routes is used. A given picture has its number of items tallied, and the route with the most things in its path is given precedence.
Keywords : Congestion in traffic, picture processing, converting RGB to grayscale, image scaling and enhancement, edge detection, image matching, and temporal allocation.
Author : Prabhakar Desamala, Ramesh Babu K, Raja Arumalla and Sk Mahaoob Subhani
Title : AN INTELLIGENT TRAFFIC CONTROL SYSTEM USING MORPHOLOGICAL OPERATIONS
net of Things (IoT) is a new and fast growing technology in which everything ( smart objects and smart devices) are connected to the internet for effective communication between these connected things. Internet of things serves as a catalyst for the healthcare and plays very important role in wide range of healthcare monitoring applications. Networked sensors devices, either worn on the body or embedded in living environments, make possible the gathering of rich information to evaluate physical and mental health condition of the patient by collecting body temperature, blood pressure, sugar level etc. Communicating this collected information to the doctor, making accurate decision on the data collected and notifying the patient is the challenging task in the Internet of things. In this paper author focus on review of IoT based Healthcare System and outline about Opportunities and Challenges for Internet of Things based Patient Health Monitoring System.
Keywords : Healthcare; Internet of Things; Wireless Sensor Network; Body Area Network
Author : K.Aruna Anushia and Dr. S. Arumuga Perumal
Title : INTERNET OF THINGS BASED HEALTH MONITORING SYSTEM : OPPORTUNITIES AND CHALLENGES
A solar tracker system positions the object at an angle relative to the Sun. The system maximizes the electricity production by moving solar panels to follow the sun throughout the day, optimizing the angle at which the panels receive solar
radiation. The goal of the project is to develop a laboratory prototype of a solar tracking system, which is able to enhance the performance of the photovoltaic modules in a solar energy system. The operating principle of the device is to keep the photovoltaic modules constantly aligned with the sunbeams,
which maximises the exposure of solar panel to the Sun’s radiation. As a result, more output power can be produced by the solar panel. The system utilises an ATmega328P microcontroller to control the motion of two servo motors, which rotate the solar panel in two axes. The amount of rotation is determined by the
microcontroller, based on inputs retrieved from the four photo sensors located next to solar panel. The objective of the project is to design and implement a functional solar tracking system which is able to keep the solar panel aligned with the sun, or any light source repetitively
Keywords : Solar Tracker, Microcontroller, Radiation, Bioenergy
Author : Margaret R E, Sunitha P, C. S Suresh Babu, Ragib R Sharief and Syed Ahmed Osama
Handwritten Alphanumeric Character Recognition is one of the significant areas of exploration and development with a streaming number of possibilities that could be attained. The applications of alphanumeric character recognition include postal correspondence sorting, bank cheque processing, form data entry,
etc. In most of the applications, major challenge lies in copying the contents from original file where the content may be in a noneditable format. The heart of the project lies within the ability to develop an efficient algorithm that can recognize handwritten alphanumeric characters which are submitted by users, which may vary in their font styles and font sizes. In order to implement
this, we used EMNIST Balanced Character Dataset to train the Machine Learning model using Deep Learning. Flask is used for API and user interface. The goal is to deploy whole system on Jetson Nano Developer Kit with an optimal solution and the best accuracy which is 87%
Keywords : Handwritten Alphanumeric Character Recognition, Character Image Processing, Deep Learning, Artificial Intelligence, Jetson Nano Development Kit
Author : Aruna Rao S. L, Chatragadda Bharani, Jaina Sri Laxmi, Soppadandi Spoorthi and Kummari Tejaswini
Title : Handwritten Alphanumeric Character Recognition using Jetson Nano
Deaf and hard-of-hearing people use sign language, a visual language, to communicate with one other and with people who do not know sign language. However, due to a lack of accessibility and communication hurdles, there is an increasing demand for technologies to help sign language users and the hearing community communicate. A system called sign language recognition with text and audio tries to fill this gap by automatically decoding sign language motions into spoken or written words. The procedure entails a number of processes, including image preprocessing, feature extraction, gesture detection, and translation into text or speech. The intricacy and variety of sign language
motions are one of the major obstacles to text and audio-based sign language recognition. As a result, creating precise and trustworthy identification systems involves both a vast and varied collection of sign language motions as well as powerful machine learning methods like Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The ability to recognise sign language using text and audio has the potential to significantly increase accessibility and communication for the deaf and hard-of-hearing community, allowing them to interact more freely with the hearing community and take part more completely in society. Along with other industries, it has uses in entertainment, healthcare, and education. Technology has the ability to revolutionise interpersonal communication and close the gap between groups speaking various languages as it develops and gets better.
Keywords : Face recognition, Convolutional Neural Network, and Hand motions are all used in sign language understanding.
Author : M Akilana and M F Akila Lourdes
Title : Sign Language Regonization using CNN Algorithm with Meachine Learning Techniques