Public transport has a significant role in the economy and modern city development. Today, public transport systems face many problems which should be solved, like real-time monitoring, data management, passengers flow optimization and road accident prediction. The Internet of Things (IoT) is a promising technology for the development of the modern public transport management system. IoT systems combine a wide range of technologies, such as sensors, edge devices, and cloud computing. Also as well as many communication infrastructures which can be applied to develop robust and automated public transport systems. The transfer of information from devices to the cloud is the most important part of an IoT system. All devices should use network standards and protocols to allow physical objects to interact with each other and the cloud. Information transfer from IoT devices to the cloud is only possible if devices are securely connected to a communication network. Network protocols and standards are policies that comprise certain rules that define communication between two or more devices over the network. This article aims to evaluate the possibilities of using IoT for monitoring and managing public transport data in modern Ukrainian realities. Specifically, in this study, we analyze general industry protocols and standards that are used by IoT devices and meet requirements like bandwidth, latency, and power consumption. This work describes a specific device that transmits information from a transport unit to the cloud. Lastly, this paper proposes an IoT system architecture for the public transport data monitoring and management system.
Accurately predicting the urban traffic passenger flow is of great importance for transportation resource scheduling, planning, public safety, and risk assessment. Traditional statistical approaches for forecasting time series are not effective in practice. They often require either strict or weak data stationarity, which is almost impossible to obtain with real data. An alternative method is time series forecasting using neural networks. By their nature, neural networks are non-linear and learn based on input and output data. With this approach, increasing the efficiency of the network is reduced to increasing the amount of data of the initial sample. Today, the class of recurrent neural networks is mainly used for forecasting time series. Another important stage is the choice of neural network architecture. In this article the use of long short term memory and gated recurrent units architecture is considered and also is compared their performance for passenger flow forecasting.
One of the most important things in IoT system development is the right communication technologies and protocols. Communication of modern IoT systems can be divided into two main parts: device-to-cloud communication and communication between cloud microservices (application level). In this study, the authors designed a test-system environment for evaluating the performance of the existing transmitting protocols for the cloud microservices communication. The proposed environment allows emulate of IoT systems with low network latency which allows evaluating and comparing protocols performance. The authors provide tests for the most popular application-level protocols: HTTP, MQTT, AMQP, and GRPC. The performance evaluation was performed based on such metrics: throughput, concurrency, scalability, transmitting size, and init connection time. The obtained experimental results and testing environment can be used for the efficient design of microservice communication.
The integration of computing containers into Internet of Things (IoT) systems created a lot of challenges and opportunities in the connected devices and cloud computing industries. In this paper, the author proposed a mathematical modeling method to analyze and optimize the deployment of computing containers into an IoT-based ecosystem. By implementing mathematical modeling techniques, such as queuing theory, optimization algorithms, and statistical analysis, we aim to address key concerns related to resource allocation, workload distribution, and performance optimization. Proposed models take the dynamic nature of an IoT system, considering factors such as real-time data streams and varying workloads for the satisfaction of scalability requirements. The author aids in identifying the optimal placement strategies for computing containers, ensuring efficient resource utilization and workload balancing across the IoT network.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.