IoT-Enabled Health Monitoring System for Real Time Patient Care: Design and Evaluation
An Efficient Routing Mechanism for IoT using Deep Learning
A Blockchain Based Cyber Thread Detection System for IIoT Networks
Implementation of IoT Based Forest Fire Detection and Prevention System
A Comprehensive Review of Internet of Things (IoT) in the Automobile Industry and its Diverse Applications
Smart Innovations in IoT Technology
Integrating IoT, ML and Cloud Computing for Sustainable Agriculture: Opportunities and Challenges
Real-Time Monitoring and Assessment of the Indoor Air Quality Hazard Index using Deep Learning Approach
Security Challenges and Measures of IoT Devices and its Networks
IoT-Based Overvoltage, Overcurrent, and Over-Temperature Fault Detector in Industries
An Efficient Routing Mechanism for IoT using Deep Learning
Security Challenges and Measures of IoT Devices and its Networks
A Comprehensive Review of Internet of Things (IoT) in the Automobile Industry and its Diverse Applications
Implementation of IoT Based Forest Fire Detection and Prevention System
A Blockchain Based Cyber Thread Detection System for IIoT Networks
This paper proposes an Internet of Things (IoT) based health monitoring system using wearable sensors for real-time patient monitoring. The system collects physiological data like heart rate, temperature and falls and transmits it to the cloud. A pilot study was conducted with 10 participants wearing the sensors for 24 hours. The system's accuracy was calculated by comparing its data against commercial devices. It achieved over 93% accuracy for heart rate, temperature and fall monitoring. The real-time analysis enabled early detection of health issues. Participants found the system user-friendly. Further work involves adding more sensors and analytics using machine learning for predictive capabilities. The proposed system has potential to improve outcomes through continuous remote monitoring. The prototype remote cardiac monitoring system was tested on 10 patients with heart conditions. It achieved 95% accuracy in detecting arrhythmias and abnormalities compared to hospital ECGs.
Vehicular Adhoc Networks (VANETs) are a new and exciting area of study. VANETs consist of many different entities that must coordinate with one another and with other services in order to function properly. Routing problems and security breaches are only two of the common problems that plague VANETs. Existing literature has a number of solutions to these problems, but most of them don't address routing and security problems at the same time. This paper identifies the restrictions imposed by routing behavior, such as control overhead, convergence, and erroneous location, and uses those constraints to determine the best paths for ensuring that no vehicles or packets collide with one another. Intrusions on the security of routed packets or vehicle nodes necessitate a selected security mechanism to ensure the privacy of sent information. To reduce this additional control load, this paper creates a routing system based on Deep Reinforcement Learning (DRL). The DRL speeds up convergence on dynamic vehicle density by optimizing the routing path. The DRL keeps a close eye on the transmission capacity and vehicles to analyze and anticipate routing behavior. As a result, V2I communication shortens the time it takes to transmit data by having the vehicles in close proximity to transport the packets.
One significant use of the Internet of Things (IoT) that is changing the face of industrial advancement is the Industrial Internet of Things (IIoT), which improves transparent communication across various items like hubs, developed facilities, and packing facilities. The IIoT can more efficiently analyze obtained data by incorporating data science approaches, which, IIoT systems require. Anomalies and assaults on networks pose a serious security risk for IIoT. In this study, a controller IoT device is chosen to calculate the expectations of IoT devices in order to avoid fraudulent devices from joining the network. Furthermore, implementing a blockchain-based data paradigm promotes data transparency. The suggested system's efficacy is rigorously tested using MATLAB against attack strength, message tampering, and fake authorization probability. The results of experiment indicate that the suggested technique improves IIoT network safety by recognizing hostile network threats.
This paper presents an implementation of Internet of Things (IoT)-based forest fire detection and prevention system. Forest fires are the most prevalent threat to forests and are toxic to forest resources and biodiversity. To avoid forest fires, early detection and prevention are crucial. An automated advance detection and prevention system for remote fire and weather-severe monitoring of culturally important areas is being suggested using various sensors. If a fire is detected, the control station receives sensor data. To activate the system, sensors detect smoke or fire, and the control center watches them, if a critical scenario occurs, drones are triggered. The proposed system employs various components, such as a Raspberry Pi 3 B, an Atmega328p microcontroller, a flame detection sensor, etc. These components are integrated into a two-part system, such as fire detection and fire prevention. The fire detection phase uses sensors to capture environmental data, triggering alerts at a central station. The fire prevention phase involves the deployment of drones to extinguish detected fires. The results show successful flame and smoke detection at Node 1, synchronization of data values between nodes, and the activation and progress of a drone towards the fire hotspot.
In essence, the internet is a means for people to connect with one another. When we consider the internet in relation to gadgets, we term it the Internet of Things (IoT). IoT is essentially the emerging world full of opportunities for everyone. It refers to devices connected to the internet that operate independently. One example of such a device is the Shrewd Bulb, which is connected to the internet and can be controlled by voice commands using Google or other voice assistants, or by using the manufacturer's app. Currently, this innovation is being applied in every industry, and automobiles equipped with IoT innovations are referred to as "associated vehicles", the vehicles that are driverless, intelligent, and autonomous. The auto industry is growing at a rate similar to how IoT innovation is emerging. In terms of driving with the utmost caution to reduce fatal accidents, IoT plays a significant role. This study primarily examines IoT innovation in the automotive business, including its applications, advantages, and disadvantages. Furthermore, the integration of IoT in the automotive industry not only enhances safety features but also revolutionizes the overall driving experience. As vehicles become more interconnected, they can communicate with each other, leading to the development of intelligent traffic management systems that optimize traffic flow and minimize congestion. This interconnected network of devices exemplifies the transformative power of IoT, creating a dynamic and efficient ecosystem within the automotive landscape.
