Adaptive Fault-Tolerant System and Optimal Power Allocation for Smart Vehicles in Smart Cities Using Controller Area Network

Biswal, Anil Kumar; Singh, Debabrata; Pattanayak, Binod Kumar; Samanta, Debabrata; Chaudhry, Shehzad Ashraf; Irshad, Azeem

doi:10.1155/2021/2147958

Cited by 13 publications

(6 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, key features from the available data set are chosen utilizing recursive and backward elimination strategies to increase the model's power. [7] Random Forest Random forest is the most potent and popular algorithm in machine learning. It's a part of machine learning under supervision.…”

Section: Figure 1 Flow Diagram Of the Model Implementedmentioning

confidence: 99%

Heart Disease Prediction Using Machine Learning

Patricia Rufes,

J Sorna Jenita,

Mabel Rakshitha T

et al. 2024

Int Res J Adv Engg Hub

View full text Add to dashboard Cite

Over the past few decades, heart-related diseases, or cardiovascular diseases (CVDs) have emerged as the leading cause of death not only in India but worldwide. They are the main cause of many diseases in the world. Machine learning algorithms and techniques have been applied to various clinical trials to automate the analysis of large and complex data. Recently, many scientists have been using AI techniques to support life and experts to detect heart-related diseases in the care industry. Compared to the brain, which is the largest organ in the human body, the heart is the next largest organ. Blood is pumped and sent to all the organs of the body. Cardiovascular disease prediction plays an important role in clinical practice. Informative studies will be useful in anticipating more data that can help predict various diseases and focus on treatment. There is a lot of data about the patients that are seen each month. The stored data can be a source for predicting future disease outbreaks. Some methods of data mining and artificial intelligence are used to predict heart diseases, such as artificial neural networks (ANN), animation, etc. To reduce the number of people who die from heart disease, we need to do it quickly and have a way to detect it. Data mining techniques and artificial intelligence calculations help experts make better cancer predictions and diagnoses. The main goal of this research project is to use AI statistics to predict coronary heart disease in patients.

show abstract

Section: Figure 1 Flow Diagram Of the Model Implementedmentioning

confidence: 99%

Heart Disease Prediction Using Machine Learning

Patricia Rufes,

J Sorna Jenita,

Mabel Rakshitha T

et al. 2024

Int Res J Adv Engg Hub

View full text Add to dashboard Cite

show abstract

“…As WSNs require high data reliability for better performance in maintaining detection and response capability and to enhance this data reliability, retransmission is used. For each single-hop transmission, a recognition packet is sent after receiving a single data packet, and retransmission is caused by loss of the acknowledgement packet [33,34]. One-hop loss probability P hl for the loss of information acknowledgement (ACK) packet is expressed as…”

Section: Retransmission In Wireless Sensor Network (Wsns)mentioning

confidence: 99%

Approach for Collision Minimization and Enhancement of Power Allocation in WSNs

et al. 2021

Self Cite

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) have attracted much more attention in recent years. Hence, nowadays, WSN is considered one of the most popular technologies in the networking field. The reason behind its increasing rate is only for its adaptability as it works through batteries which are energy efficient, and for these characteristics, it has covered a wide market worldwide. Transmission collision is one of the key reasons for the decrease in performance in WSNs which results in excessive delay and packet loss. The collision range should be minimized in order to mitigate the risk of these packet collisions. The WSNs that contribute to minimize the collision area and the statistics show that the collision area which exceeds equivalents transmission power has been significantly reduced by this technique. This proposed paper optimally reduced the power consumption and data loss through proper routing of packets and the method of congestion detection. WSNs typically require high data reliability to preserve identification and responsiveness capacity while also improving data reliability, transmission, and redundancy. Retransmission is determined by the probability of packet arrival as well as the average energy consumption.

show abstract

“…These localities follow the Smart Cities methodology [1,2], which aims to promote sustainable and improved urban living. Examples of Smart Cities applications include technologies for public safety and managing crowd movement in cities, parking solutions [4], accessing information on accessible places [5], controlling household energy consumption [6], as well as community lighting, and utilization of smart grids, water management, waste management [3], healthcare, logistics, and a host of other fields. To enable the creation of such projects, new intelligent sensors have emerged, allowing for the concept of the "Internet of Things" and the connection between ordinary objects and the digital realm.…”

Section: Introductionmentioning

confidence: 99%

A Smart Waste Management System Framework Using IoT and LoRa for Green City Project

Laha,

Pattanayak,

Pattnaik

et al. 2023

IJRITCC

View full text Add to dashboard Cite

Waste management is a pressing concern for society, requiring substantial labor resources and impacting various social aspects. Green cities strive for achieving a net zero-carbon footprint, including efficient waste management. The waste management system deals with three problems that are interrelated: a) the timely checking of the status of bins to prevent overflow; b) checking the precise location of bins; and c) finding the optimal route to the filled bins. The existing systems fail to satisfy all three problem areas with a single solution. To track the overflow of the bin, the proposed model uses ultrasonic sensors, which are complemented with LoRa to transmit the exact location of the bins in a real-time environment. The existing models are not that efficient at calculating the exact bin-filled status along with the precise location of the bins. The Floyd-Warshall algorithm in the proposed model optimizes waste collection using the Floyd-Warshall algorithm to determine the shortest path. Leveraging low-cost IoT technologies, specifically LoRa modules for data transfer, our solution offers benefits such as simplicity, affordability, and ease of replacement. By employing the Floyd-Warshall algorithm with a time complexity of O (n^3), our method efficiently determines the most optimal waste pickup route, saving time and resources. This study presents a smart waste management solution utilising Arduino UNO microcontrollers, ultrasonic sensors, and LoRaWAN to measure waste levels accurately. The proposed strategy aims to create clean and pollution-free cities by addressing the problem of waste distribution caused by poor collection techniques.

show abstract

Adaptive Fault-Tolerant System and Optimal Power Allocation for Smart Vehicles in Smart Cities Using Controller Area Network

Cited by 13 publications

References 54 publications

Heart Disease Prediction Using Machine Learning

Heart Disease Prediction Using Machine Learning

Approach for Collision Minimization and Enhancement of Power Allocation in WSNs

A Smart Waste Management System Framework Using IoT and LoRa for Green City Project

Contact Info

Product

Resources

About