Empowering Cybersecurity: A Deep Dive into AI-Driven Security Intelligence Modelling
Smart Incubator for Empowering Poultry Farmers by Maximizing Egg Hatching Success
Early Disease Detection of Black Gram Plant Leaf using Cloud Computing Based YOLO V8 Model
Data Retrieval in Cancer Documents using Various Weighting Schemes
Securing Healthcare Data in Smart Cities: A Machine Learning Approach
Diabetes is a chronic condition that has the potential to wreak havoc on the global healthcare system. Diabetes mellitus, or just diabetes, is a condition characterized by a rise in blood glucose levels. Diagnosing diabetes can be done using a variety of traditional approaches based on physical and chemical testing. However, due to the complicated interdependence of different elements and the fact that diabetes affects human organs such as the kidney, eye, heart, nerves, and foot, early diabetes prediction is challenging for medical practitioners. Machine learning is a new discipline of data science that studies how machines learn from their past experiences. The goal of this research is to create a system that can combine the findings of several machine learning approaches to conduct early diabetes prediction and advice for a patient with greater accuracy. The goal of this study was to create a system based on three classification algorithms such as Decision Tree, Naive Bayes, and Support Vector Machine. In comparison to an individual classifier, classification techniques are widely employed in the medical sector for categorizing data into distinct classes based on specified constraints. Diabetes is a disease that impairs the capacity of the body to produce the hormone insulin, which causes carbohydrate metabolism to become abnormal and blood glucose levels to rise. High blood sugar is the most common symptom of diabetes. Among other symptoms, high blood sugar can induce increased thirst, hunger, and frequent urination, among other symptoms. If diabetes is not managed, it can lead to various problems. Diabetic ketoacidosis and nonketotic hyperosmolar coma are two of the most serious consequences. Diabetes is considered a major health problem in which the amount of sugar in the blood cannot be regulated. Diabetes is influenced by various factors such as height, weight, genetic factors, and insulin, but the most important aspect to consider is sugar concentration. The best way to avoid difficulties is to detect the problem at an early stage.
IoT is a large network of physical devices that are connected with various types of sensors and may share information with the help of internet access. The internet has now reached practically every possible thing in our environment and IoT is no longer limited to our personal computers and mobile phones. Gas leaks, whether in open or enclosed spaces, can be harmful and deadly. Traditional gas leakage detecting systems, despite their high precision, miss a few key aspects in warning people about a leak. As a result, IoT technology is used to create a gas leakage detector with smart alerting techniques such as calling, sending text messages and sending an e-mail to the appropriate authority. The ability to predict dangerous situations so that people can be warned ahead of time is done by performing data analytics on sensor readings.
Technology is now making life easier and more pleasant, as manual processes are being replaced by automated systems. Increasing internet usage enables us to share new technology with people all over the world, the Internet of Things (IoT) is the most current and fastest-growing internet technology. The Internet of Things (IoT) enables anybody to control a device from any location. When a person is engaged in other tasks, the Internet of Things is in-charge of carrying out his or her responsibilities. An automated system based on the IoT that utilises internet-connected devices to control the operation and features of a house from anywhere in the world is known as Smart Home Management (SHM). Electricity, time, and human energy conservation are among the primary objectives of this technological advancement. The IoT-based automation system varies from prior wireless automation systems in that it can be operated from any location on the planet.
The main goal of this paper is to get an instant notification if a user's breath contains an amount of alcohol that exceeds a certain limit. When a person is recognised as having a high amount of alcohol in their bloodstream, the system sends out a warning signal to their phone. Whenever the amount of alcohol in the blood comes within the detection range of a high alcohol level, the device generates an alert sound and flashes the LED. According to the manufacturer, this technology is only an upgrade to the existing alcohol detection systems that are now in use across the world. An alcohol-detecting sensor measures the quantity of alcohol in a person's breath and transmits the information to an Arduino, which subsequently controls the light and buzzer by sending commands to and from the sensor. This strategy provides low-cost development as well as attention to detail.
The term "urban heat island" (UHI) refers to a temperature that is greater than the surrounding rural or suburban region. The urban heat factor is directly proportional to the land surface temperature. UHI is a much warmer urban region than the neighbouring rural areas. Heat is produced in large cities by the combined energy of all the people, automobiles, buses, and trains. In heat balance research and as a control for climate models, the land surface temperature is an essential component for predicting the radiation budget. In this research, an effort was made to estimate surface temperature across the Almora city region using Landsat-5 and Landsat-8 satellite data. The Lands at visible and Near Infrared (NIR) channels were used to explore the variability of these Land Surface Temperatures (LST) about distinct land use/land cover types. The emissivity per pixel was derived directly from the satellite data and calculated as narrowband emissivity at the satellite sensor channel to reduce the estimation error in surface temperature. The findings imply that the approach may be used to predict the surface temperature and emissivity using the Normalized Difference Vegetation Index (NDVI) with good accuracy in various metropolitan regions.
