Internet of Things and Cyber-Physical Systems最新文献

The banking sector is widely acknowledged for its intrinsic unpredictability and susceptibility to risk. Bank loans have emerged as one of the most recent services offered over the past several decades. Banks typically serve as intermediaries for loans, investments, short-term loans, and other types of credit. The usage of credit cards is experiencing a steady increase, thereby leading to a rise in the default rate that banks encounter. Although there has been much research investigating the efficacy of conventional Machine Learning (ML) models, there has been relatively less emphasis on Deep Learning (DL) techniques. The application of DL approaches to credit card default prediction has not been extensively researched despite their considerable potential in numerous fields. Moreover, the current literature frequently lacks particular information regarding the DL structures, hyperparameters, and optimization techniques employed. To predict credit card default, this study evaluates the efficacy of a DL model and compares it to other ML models, such as Decision Tree (DT) and Adaboost. The objective of this research is to identify the specific DL parameters that contribute to the observed enhancements in the accuracy of credit card default prediction. This research makes use of the UCI ML repository to access the credit card defaulted customer dataset. Subsequently, various techniques are employed to preprocess the unprocessed data and visually present the outcomes through the use of exploratory data analysis (EDA). Furthermore, the algorithms are hypertuned to evaluate the enhancement in prediction. We used standard evaluation metrics to evaluate all the models. The evaluation indicates that the AdaBoost and DT exhibit the highest accuracy rate of 82 ​% in predicting credit card default, surpassing the accuracy of the ANN model, which is 78 ​%.

In recent years, the Internet of Things (IoT) has experienced extensive adoption in industrial environments, healthcare, smart cities, and more, playing a vital role in these domains. Within IoT-based systems, wireless sensor networks (WSNs) have emerged as a crucial method for collecting peripheral environmental data within industries, owing to their self-organizational attributes. Nevertheless, the enormous volume of heterogeneous data from various sensing devices presents many challenges for IoT-enabled WSNs, encompassing high transmission delay times (TD) and excessive battery energy consumption (EC). To address these challenges, it is imperative to prioritize efficiency and optimize energy utilization. Moreover, enhancing energy efficiency within the Industrial Internet of Things (IIoT) realm hinges significantly on factors such as data transmission modes and the allocation of cluster head nodes. Numerous researchers have proposed algorithms to minimize transmission time and energy consumption, specifically focusing on industrial environments. This paper introduces an inventive clustering-based data transmission algorithm for IIoT, LEACH-D, to enhance efficiency. The LEACH-D algorithm improves the transmission task duration while maintaining consistent battery energy consumption. It also seeks to elevate performance in metrics such as average transmission time during the first node death (FND). Numerous experimental results provide strong evidence that the algorithm introduced in this paper has effectively reduced the average transmission time by remarkable percentages: 51.32%, 12.12%, 12.96%, and 5.42%, while simultaneously increasing the number of FND rounds by significant margins: 222.43%, 36.63%, 33.72%, and 7.81%, respectively. These improvements stand in stark contrast to the performance of existing algorithms, including FREE_MODE, LEACH, EE-LEACH, and ETH-LEACH.

As the Internet of Things (IoT) evolves, it paves the way for vital smart city applications, with the Smart Parking Management System (SPMS) standing as a prime example. This research introduces a novel IoT-driven SPMS that leverages Long Range Wide Area Network (LoRaWAN) technology, termed as IoT-SPMS-LoRaWAN, to surmount typical restrictions related to communication range, energy usage, and implementation cost seen in traditional systems. IoT-SPMS-LoRaWAN features intelligent sensing nodes that incorporate an Arduino UNO microcontroller and two sensors—a triaxial magnetic sensor and a waterproof ultrasonic sensor. These components collaboratively detect vehicle occupancy and transmit this data to the server via a LoRaWAN gateway. Notably, the integration of LoRa technology enables extensive network coverage and energy efficiency. Users are provided with real-time updates on parking availability via the accessible AllThingsTalk Maker graphical user interface. Additionally, the system operates independently, sustained by a solar-powered rechargeable battery. Practical testing of IoT-SPMS-LoRaWAN under various scenarios validates its merits in terms of functionality, ease of use, reliable data transmission, and precision. Its urban implementation is expected to alleviate traffic congestion, optimize parking utilization, and elevate awareness about available parking spaces among users. Primarily, this study enriches the realm of smart city solutions by enhancing the efficiency of parking management and user experience via IoT.

The localization of moving targets in an underwater acoustic wireless sensor network (UAWSN) is inaccurate due to the various underwater forces (viscous, hydrodynamic forces, perturbation of underwater). The false measurements in the sensor network cause position errors and velocity errors which disrupt the localization of the moving target. A randomly fluctuated spillover effect is introduced in the present paper. The absorption losses generated due to the spillover effect cause false measurements of the moving target. Theorem 1 describes the genesis of these absorption losses and their consequences in UAWSN. The measurements from each moving target in the presence of absorption losses are formulated in the elliptical region. A joint probabilistic data association (JPDA) method is proposed to quantify the false measurements in the elliptical region. A moving target state estimation (MTSE) algorithm is proposed to eliminate the false measurements from the moving targets and to measure the localization of moving targets with the help of the propagation speed of targets. The theoretical measurements of position RMSE and velocity RMSE are verified with standard methods. The proposed MTSE method improves the localization performance of the moving targets by 29.42 % and reduces 32.16 % of position errors and 36.23 % of velocity errors up to 550 ​m. The proposed algorithm will be useful for the sub-aquatic Internet of underwater things (IoUT).

When consumers purchase toys from retail stores, the majority of toys are packaged, making it difficult for them to observe the toys comprehensively. This limitation may hinder their ability to make informed purchase decisions. To address this challenge, this paper introduces an immersive toy experience program utilizing augmented reality (AR) technology. The program utilizes the camera on mobile devices to scan and identify the toy's cover image, subsequently showcasing corresponding virtual toy models in a simulated environment. Additionally, interactive controls enable users to manipulate the viewing angles. In terms of methodology, we have specifically designed an expandable collection of toy images, allowing the recognition of recently introduced toys by adding them to the database, enhancing the scalability of our application. In comparison to previous research, our work transcends the constraints of traditional toy shopping, providing a more intuitive, interactive, and personalized experience through AR technology.

In response to an alarming shortage of workers in cybersecurity and a growing skills gap, the U.S. Department of Defense is taking steps to build cybersecurity capacity through workforce training and education. In this paper, we present an approach to address this shortage and skills gap through the development of cybersecurity education courseware for internet of things (IoT) applications.

To attract students and workers into the field of cybersecurity, it is important to design courseware that is exciting and tied to real-world problems. We describe our design for an embedded systems course taught at the graduate level for engineering and computer science students. The innovation in our approach is to select the fast-growing domain of healthcare and feature different IoT sensors that are seeing increased usage. These include barcode scanners, cameras, fingerprint sensors, and pulse sensors. These devices cover important functions such as patient identification, monitoring, and creating electronic health records. We use a password protected MySQL database as a model for electronic health records. We also demonstrate potential vulnerabilities of these databases to SQL injection attacks.

We administered these labs and collected survey data from the students. We found a significant increase in student understanding of cybersecurity issues. The mean confidence level of the students in cybersecurity issues increased from 2.5 to 4.1 on a 5-point scale after taking this course, which represents a 65% increase. The instructional lab material has been uploaded to the web portal https://clark.center designated by the National Security Agency for dissemination. Our approach, design, and experimental validation methodology will be useful for educators, researchers, students, and organizations interested in re-skilling their workforce.

Despite providing unparalleled connectivity and convenience, the exponential growth of the Internet of Things (IoT) ecosystem has triggered significant cybersecurity concerns. These concerns stem from various factors, including the heterogeneity of IoT devices, widespread deployment, and inherent computational limitations. Integrating emerging technologies to address these concerns becomes imperative as the dynamic IoT landscape evolves. Machine Learning (ML), a rapidly advancing technology, has shown considerable promise in addressing IoT security issues. It has significantly influenced and advanced research in cyber threat detection. This survey provides a comprehensive overview of current trends, methodologies, and challenges in applying machine learning for cyber threat detection in IoT environments. Specifically, we further perform a comparative analysis of state-of-the-art ML-based Intrusion Detection Systems (IDSs) in the landscape of IoT security. In addition, we shed light on the pressing unresolved issues and challenges within this dynamic field. We provide a future vision with Generative AI and large language models to enhance IoT security. The discussions present an in-depth understanding of different cyber threat detection methods, enhancing the knowledge base of researchers and practitioners alike. This paper is a valuable resource for those keen to delve into the evolving world of cyber threat detection leveraging ML and IoT security.

Natural disasters (NDs) have always been a major threat to human lives and infrastructure, causing immense damage and loss. In recent years, the increasing frequency and severity of natural disasters have highlighted the need for more effective and efficient disaster management strategies. In this context, the use of technology has emerged as a promising solution. In this survey paper, we explore the employment of recent technologies in order to relieve the impacts of various natural disasters. We provide an overview of how different technologies such as Remote Sensing, Radars and Satellite Imaging, internet-of-things (IoT), Smartphones, and Social Media can be utilized in the management of NDs. By utilizing these technologies, we can predict, respond, and recover from NDs more effectively, potentially saving human lives and minimizing infrastructure damage. The paper also highlights the potential benefits, limitations, and challenges associated with the implementation of these technologies for natural disaster management purposes. While the use of technology can significantly improve NDM, there are also various challenges that need to be addressed, such as the cost of implementation and the need for specialized knowledge and skills. Overall, this survey paper provides a comprehensive overview of the use of technology in managing NDs and sheds light on the important role such technologies can play in NDM. By exploring the potential applications of different technologies, this paper aims to contribute to the development of more effective and sustainable disaster management strategies.

Cloud computing leverages computing resources by managing these resources globally in a more efficient manner as compared to individual resource services. It requires us to deliver the resources in a heterogeneous environment and also in a highly dynamic nature. Hence, there is always a risk of resource allocation failure that can maximize the delay in task execution. Such adverse impact in the cloud environment also raises questions on quality of service (QoS). Resource management for cloud application and service have bigger challenges and many researchers have proposed several solutions but there is room for improvement. Clustering the resources clustering and mapping them according to task can also be an option to deal with such task failure or mismanaged resource allocation. Density-based spatial clustering of applications with noise (DBSCAN) is a stochastic approach-based algorithm which has the capability to cluster the resources in a cloud environment. The proposed algorithm considers high execution enabled powerful data centers with least fault probability during resource allocation which reduces the probability of fault and increases the tolerance. The simulation is cone using CloudsSim 5.0 tool kit. The results show 25% average improve in execution time, 6.5% improvement in number of task completed and 3.48% improvement in count of task failed as compared to ACO, PSO, BB-BC (Bib ​= ​g bang Big Crunch) and WHO(Whale optimization algorithm).