Virtual fencing exploits the transformation of a dynamic environment into a cyber-physical traceable system to restrict dangerous movements and create early warning zones. While most real-life applications rely on GPS...
详细信息
ISBN:
(纸本)9798350375367
Virtual fencing exploits the transformation of a dynamic environment into a cyber-physical traceable system to restrict dangerous movements and create early warning zones. While most real-life applications rely on GPS systems, this article explores the use of computer vision to regulate the distribution of human crowds. The proposal includes utilizing Unmanned Aircraft systems (UAS) to create risk-based ranked early warning zones to enhance the resilience of critical infrastructures and citizen safety/security in smart cities. The proposed system conducts surveillance of labeled areas comprising infrastructure and/or populated by citizens. In the current research, a physical testbed is constructed to monitor human mobility, which simulates human behavior as a part of the cyber-physical-social dynamic environment, triggering an alert whenever a person enters a warning zone. These warning zones are categorized based on their level of risk, ranging from low to high depending on the distance from the risky area. The different warning levels can be dynamically set to leave sufficient time to react and mitigate potential hazards. The experiments to simulate the crossing of various virtual fences in the testbed demonstrate the system's high efficiency for early warning purposes. Finally, the main challenges of bringing EWZ into action are identified and discussed.
Gated recurrent unit (GRU) is a variant of recurrent neural network (RNN), which is widely used in applications and tasks related to sequence data processing. However, traditional GRU networks based on von Neumann com...
详细信息
ISBN:
(纸本)9781665491303
Gated recurrent unit (GRU) is a variant of recurrent neural network (RNN), which is widely used in applications and tasks related to sequence data processing. However, traditional GRU networks based on von Neumann computing construction, have been facing challenges such as big data dimension and high real-time requirements. Meanwhile, limited internal storage resources and external storage bandwidth have jointly limited the overall performance of hardware implementation of GRU networks. Based on these, a compact scheme for the hardware circuit design of memristor-based GRU network is presented, along with the concrete circuit design of nonlinear activation and the linear matrix operation. The entire scheme is validated by the application of the Lithium ion battery state of charge (SOC) estimation. This work is expected to integrate the neuromorphic electronics and battery management systems, and further promote the development of electric vehicles in smart cities.
real-time surface analysis is becoming increasingly important in various fields, including industry, medicine, and transportation. This article examines the problem of remote monitoring of surface texture in realtime...
详细信息
The rapid development and increasing popularity of wearable technologies have drawn substantial attention from firms seeking to expand into new markets and innovate in the healthcare industry. As electronic devices em...
详细信息
Acoustic emission (AE) is a widely used nondestructive test method in structural health monitoring applications to identify the damage type in the material. Usually, the analysis of the AE signal is done by using trad...
详细信息
ISBN:
(纸本)9781665453837
Acoustic emission (AE) is a widely used nondestructive test method in structural health monitoring applications to identify the damage type in the material. Usually, the analysis of the AE signal is done by using traditional parameter-based methods. Recently, machine learning methods showed promising results for the analysis of AE signals. However, these machine learning models are complex, slow, and consume significant amounts of energy. To address these limitations and to explore the trade-off between model complexity and the classification accuracy, this paper presents a lightweight artificial neural network model to classify damage types in concrete material using raw acoustic emission signals. The model consists of one hidden layer with four neurons and is trained on a public acoustic emission signal dataset. The created model is deployed to several microcontrollers and the performance of the model is evaluated and compared with a state-of-the-art machine learning model. The model achieves 98.4% accuracy on the test data with only 4019 parameters. In terms of evaluation metrics, the proposed tiny machine learning model outperforms previously proposed models 10 to 1000 times. The proposed model thus enables machine learning in real-time structural health monitoring applications.
Predictive maintenance: A game changer in infrastructure and vehicle management, and able to cut maintenance expenses and downtime of smart transportation systems. This study explores ways in which smart transportatio...
详细信息
This paper introduces a novel approach for optimizing Internet of Things (IoT) network performance by employing machine learning techniques to predict network types based on measurable properties of network traffic. W...
详细信息
ISBN:
(纸本)9798350330656;9798350330649
This paper introduces a novel approach for optimizing Internet of Things (IoT) network performance by employing machine learning techniques to predict network types based on measurable properties of network traffic. While traditional studies have primarily focused on either reducing latency or enhancing network redundancy, our work integrates these aspects by dynamically predicting network conditions that facilitate the selection of optimal communication pathways. This methodology not only significantly reduces latency and improves redundancy but also enhances the overall efficiency and reliability of IoT networks. By analyzing a synthesized dataset reflective of real-world IoT environments, our model achieves high accuracy in network-type prediction, demonstrating its potential for real-time network management applications. Furthermore, the study delves into error analysis and feature sensitivity, providing insights into the reliability of network predictions and their implications for network design and operation. This paper aims to serve as a cornerstone for future explorations into optimizing IoT networks, setting the stage for more resilient, efficient, and responsive IoT ecosystems.
Plant diseases cause significant crop damage, leading to economic losses for farmers and food shortages. Traditional disease detection methods are often inefficient, expensive, and inaccurate. Recently, there has been...
详细信息
Today embeddedsystems are becoming more and more sophisticated and are being used in a wide range of technologies across an array of industries. Therefore its security has become a major concern. Security is always a...
详细信息
The secure generation of cryptographic keys holds significant importance in safeguarding the confidentiality, authenticity, and integrity of data stored in the cloud. Traditionally, Key Generation Centers have been tr...
详细信息
暂无评论