Search

This paper investigates the prototyping and implementation of an output feedback-based robust controller on a Field Programmable Gate Array (FPGA) platform. The Smart System under Test (SSuT) in this submission is a flexible cantilever beam bonded with Piezoelectric (PZT 5H) patches that act as a sensor as well as an actuator (perturbance creation as well as control actuation). For ease of modeling and subsequent controller design in the laboratory studies, the low-frequency dynamics of the smart system are approximated to only a Single Degree of Freedom (SDOF) in terms of flexural vibrations. The SSuT is modeled analytically through finite element modeling and experimentally through sub-space system identification process. The developed models’ accuracy is compared with the experimental results of non - parametric modeling. The developed models are then used to conduct the simulation studies with the designed robust output feedback controller in the closed loop. Apart from the simulation studies, the designed controller was also prototyped on an FPGA platform using LabVIEW FPGA with the associated hardware in loop to carry out the experimental validation of its performance. The robustness and efficiency of the prototype controller to control the system vibrations in real-time were proved through extensive tests at single resonant frequencies and a range of frequencies encompassing the dominant resonant regions in the flexural mode. Findings from this study are further used to ensure satisfactory active vibration control of smart cantilever systems in various heavy/aerospace industries by approximating them to suitable benchmark systems in the laboratory.

Deep Neural Networks (DNNs) have shown impressive performance in computer vision tasks; however, their vulnerability to adversarial attacks raises concerns regarding their security and reliability. Extensive research has shown that DNNs can be compromised by carefully crafted perturbations, leading to significant performance degradation in both digital and physical domains. Therefore, ensuring the security of DNN-based systems is crucial, particularly in safety-critical domains such as autonomous driving, robotics, smart homes/cities, smart industries, video surveillance, and healthcare. In this paper, we present a comprehensive survey of the current trends focusing specifically on physical adversarial attacks. We aim to provide a thorough understanding of the concept of physical adversarial attacks, analyzing their key characteristics and distinguishing features. Furthermore, we explore the specific requirements and challenges associated with executing attacks in the physical world. Our article delves into various physical adversarial attack methods, categorized according to their target tasks in different applications, including classification, detection, face recognition, semantic segmentation and depth estimation. We assess the performance of these attack methods in terms of their effectiveness, stealthiness, and robustness. We examine how each technique strives to ensure the successful manipulation of DNNs while mitigating the risk of detection and withstanding real-world distortions. Lastly, we discuss the current challenges and outline potential future research directions in the field of physical adversarial attacks. We highlight the need for enhanced defense mechanisms, the exploration of novel attack strategies, the evaluation of attacks in different application domains, and the establishment of standardized benchmarks and evaluation criteria for physical adversarial attacks. Through this comprehensive survey, we aim to provide a valuable resource for researchers, practitioners, and policymakers to gain a holistic understanding of physical adversarial attacks in computer vision and facilitate the development of robust and secure DNN-based systems.

An investigation was conducted to examine the impact of training in intelligent systems within engineering courses at the university level, considering the parameters and reports on business trends for 2030, as well as the Sustainable Development Goals (SDGs). The study analyzed 2309 subjects across 66 undergraduate degrees offered at nine universities in the Andalusia region, which is the most populous region in Spain. The objective of this research is to assess whether the training in intelligent systems, specifically in the fields of electrical engineering, electronics, computer science, and telecommunications, adequately prepares students in their final years of study to meet the demands of the labor and business market. Reports and trend studies have identified the urgent areas that require attention, including training in sensors, smart grids, smart cities, IoT, artificial intelligence, embedded systems, among others. The investigation provides insights into the current state of training in intelligent systems within the final years of engineering programs. These findings will inform future curriculum development and teaching guidelines, with the goal of enhancing students’ knowledge and skills in line with technological and engineering trends. The study will analyze subjects across various Spanish universities in Andalusia, considering their rankings. Based on the analysis of the results, recommendations for improvement actions and strategies to strengthen the curriculum will be proposed.

Machine learning (ML) and the internet of things (IoT) are among the most booming research directions. Smart cities, smart campuses (SCs), smart homes, smart cars, early warning systems (EWSs), etc.; or it could be called “Smart x” systems are implemented using ML and IoT. Those systems will alter how various world entities communicate with one another. This paper spots light on the significant roles of the IoT in SS. Also, it focuses on the importance of ML in IoT-based SS. Besides, an overview of smartness and IoT is presented. Then, this paper offers ML benchmarking along with a taxonomy that categorizes the ML models into linear and non-linear ones depending on the problem type (classification or regression). Afterward, the commonly utilized evaluation metrics are provided. In addition, this paper considers the trust techniques used for mitigating different security aspects in IoT networks, which play a crucial part in regulating the new era of communication. Moreover, two case studies devoting ML for IoT-based SS, namely IoT-based SC and IoT-based EWS, are considered for data collection and manipulation with guided research directions. Finally, the paper presents effective recommendations of ML’s significant roles in SC and earthquake EWS for interested scholars.

Blockchain technologies have recently come to the forefront of the research and industrial communities as they bring potential benefits for many industries. This is due to their practical capabilities in solving many issues currently inhibiting further advances in various industrial domains. Securely recording and sharing transactional data, establishing automated and efficient supply chain processes, and enhancing transparency across the whole value chain are some examples of these issues. Blockchain offers an effective way to tackle these issues using distributed, shared, secure, and permissioned transactional ledgers. The employment of blockchain technologies and the possibility of applying them in different situations enables many industrial applications through increased efficiency and security; enhanced traceability and transparency; and reduced costs. In this paper, different industrial application domains where the use of blockchain technologies has been proposed are reviewed. This paper explores the opportunities, benefits, and challenges of incorporating blockchain in different industrial applications. Furthermore, the paper attempts to identify the requirements that support the implementation of blockchain for different industrial applications. The review reveals that several opportunities are available for utilizing blockchain in various industrial sectors; however, there are still some challenges to be addressed to achieve better utilization of this technology.

Cyber-physical systems (CPSs) were envisaged as a way to manipulate the objects in the physical world through computer intelligence. This is usually done by providing a communication bridge between actuation and computing elements. This sought after control is hampered not only by the unavoidable certainty found in the physical world but also by the limitations of contemporary communication networks. These limitations hamper fine-grained control of elements that may be separated by large-scale distances. In this regard, soft computing is an emerging paradigm that can help to manage the unreliability of CPS by using techniques, including fuzzy systems, neural networks, evolutionary computation, probabilistic reasoning, and rough sets. We present a comprehensive contemporary review of soft computing techniques for CPS dependability modeling, analysis, and improvement. This paper provides an overview of CPS applications, explores the foundations of dependability engineering, and highlights the potential role of soft computing techniques for CPS dependability with various case studies while also identifying common pitfalls and future directions. In addition, this paper provides a comprehensive survey of the use of various soft computing techniques for making CPS dependable. This paper is timely due to the increasingly central role that CPSs are beginning to play in modern societies and the need to leverage all the relevant methodologies and tools (such as those provided by soft computing) for the development of highly dependable CPS.

Today's best-effort (BE) Internet of Things (IoT) faces challenges in providing the end-to-end-performance, security, and energy efficiency needed for the Smart Systems of the 21st century. These future smart systems will include smart cities, smart transportation systems, and smart manufacturing. This paper surveys the security weaknesses of the BE IoT. The BE-IoT cannot be partitioned into distinct interference-free virtual networks, which compromises performance, cyber-security, and energy efficiency. The design of a secure deterministic industrial-tactile IoT core network, which can embed millions of distinct secure deterministic virtual networks (SD-VNs) in layer 2, is then presented. Deterministic communications, combined with low-jitter scheduling, offers several benefits: 1) the removal of all congestion, interference, and DOS attacks; 2) a significant reduction in IoT router buffer sizes; 3) a significant reduction in IoT energy use; 4) a reduction of end-to-end IoT delays to the speed of light in fiber; and 5) deterministic packet-switches are relatively easy to synthesize using FPGA technologies. These benefits apply to optical and 5G wireless networks. Future smart systems can reserve their own congestion-free SD-VNs in layer 2 to manage their traffic, with significantly improved performance, security, and energy efficiency. A speed-of-light deterministic IoT core network can transform cloud services in the 21st century by exploiting a new technology: FPGAs combined with silicon photonics transceivers to achieve terabits/second of optical bandwidth. To illustrate the transformational potential, Big Data green cloud computing over a secure deterministic IoT spanning the European Union is explored.