Search Results (449)

Supervisory control theory (SCT), based on Petri nets, offers a robust framework for modeling and controlling discrete-event systems but faces significant challenges in scalability, expressiveness, and practical implementation. This paper introduces General-purpose Petri Net Simulator and Real-Time Controller (GPenSIM), a MATLAB version 24.1.0.2689473 (R2024a) Update 6-based modular Petri net framework, as a novel solution to these limitations. GPenSIM leverages modular decomposition to mitigate state-space explosion, enabling parallel execution of weakly coupled Petri modules on multi-core systems. Its programmable interfaces (pre-processors and post-processors) extend classical Petri nets’ expressiveness by enforcing nonlinear, temporal, and conditional constraints through custom MATLAB scripts, addressing the rigidity of traditional linear constraints. Furthermore, the integration of GPenSIM with MATLAB facilitates real-time control synthesis, performance optimization, and seamless interaction with external hardware and software, bridging the gap between theoretical models and industrial applications. Empirical studies demonstrate the efficacy of GPenSIM in reconfigurable manufacturing systems, where it reduced downtime by 30%, and in distributed control scenarios, where decentralized modules minimized synchronization delays. Grounded in systems theory principles of interconnectedness, GPenSIM emphasizes dynamic relationships between components, offering a scalable, adaptable, and practical tool for supervisory control. This work highlights the potential of GPenSIM to overcome longstanding limitations in SCT, providing a versatile platform for both academic research and industrial deployment. Full article

Industrial maintenance has shifted from reactive repairs and calendar-based servicing toward data-driven predictive strategies. This paper presents a non-intrusive, low-cost IoT hardware platform for sustainable predictive maintenance of rotating machinery. The system integrates an ESP32-S3 sensor node that captures vibration (100 kHz) and temperature data, performs local logging, and communicates wirelessly. An automated spectral band segmentation framework is introduced, comparing equal-energy, linear-width, nonlinear, clustering, and peak–valley partitioning methods, followed by a weighted feature scheme that emphasizes high-value bands. Three unsupervised one-class classifiers—transformer autoencoders, GANomaly, and Isolation Forest—are evaluated on these weighted spectral features. Experiments conducted on a custom pump test bench with controlled anomaly severities demonstrate strong anomaly classification performance across multiple configurations, supported by detailed threshold-characterization metrics. Among 150 model–segmentation configurations, 25 achieved perfect classification (100% precision, recall, and F1 score) with ROC-AUC = 1.0, 43 configurations achieved ≥90% accuracy, and the lowest-performing setup maintained 81.8% accuracy. The proposed end-to-end solution reduces the downtime, lowers maintenance costs, and extends the asset life, offering a scalable, predictive maintenance approach for diverse industrial settings. Full article

The increasing presence of non-cooperative targets poses significant challenges to the space environment and threatens the sustainability of aerospace operations. Accurate on-orbit perception of such targets, particularly those without cooperative markers, requires advanced algorithms and efficient system architectures. This study presents a hardware–software co-design framework for the pose estimation of non-cooperative targets. Firstly, a two-stage architecture is proposed, comprising object detection and pose estimation. YOLOv5s is modified with a Focus module to enhance feature extraction, and URSONet adopts global average pooling to reduce the computational burden. Optimization techniques, including batch normalization fusion, ReLU integration, and linear quantization, are applied to improve inference efficiency. Secondly, a customized FPGA-based accelerator is developed with an instruction scheduler, memory slicing mechanism, and computation array. Instruction-level control supports model generalization, while a weight concatenation strategy improves resource utilization during convolution. Finally, a heterogeneous DSP–FPGA system is implemented, where the DSP manages data pre-processing and result integration, and the FPGA performs core inference. The system is deployed on a Xilinx X7K325T FPGA operating at 200 MHz. Experimental results show that the optimized model achieves a peak throughput of 399.16 GOP/s with less than 1% accuracy loss. The proposed design reaches 0.461 and 0.447 GOP/s/DSP48E1 for two model variants, achieving a 2× to 3× improvement over comparable designs. Full article

Tiny Machine Learning (TinyML) extends edge AI capabilities to resource-constrained devices, offering a promising solution for real-time, low-power intelligence in smart cities. This review systematically analyzes 66 peer-reviewed studies from 2019 to 2024, covering applications across urban mobility, environmental monitoring, public safety, waste management, and infrastructure health. We examine hardware platforms and machine learning models, with particular attention to power-efficient deployment and data privacy. We review the approaches employed in published studies for deploying machine learning models on resource-constrained hardware, emphasizing the most commonly used communication technologies—while noting the limited uptake of low-power options such as Low Power Wide Area Networks (LPWANs). We also discuss hardware–software co-design strategies that enable sustainable operation. Furthermore, we evaluate the alignment of these deployments with the United Nations Sustainable Development Goals (SDGs), highlighting both their contributions and existing gaps in current practices. This review identifies recurring technical patterns, methodological challenges, and underexplored opportunities, particularly in the areas of hardware provisioning, usage of inherent privacy benefits in relevant applications, communication technologies, and dataset practices, offering a roadmap for future TinyML research and deployment in smart urban systems. Among the 66 studies examined, 29 focused on mobility and transportation, 17 on public safety, 10 on environmental sensing, 6 on waste management, and 4 on infrastructure monitoring. TinyML was deployed on constrained microcontrollers in 32 studies, while 36 used optimized models for resource-limited environments. Energy harvesting, primarily solar, was featured in 6 studies, and low-power communication networks were used in 5. Public datasets were used in 27 studies, custom datasets in 24, and the remainder relied on hybrid or simulated data. Only one study explicitly referenced SDGs, and 13 studies considered privacy in their system design. Full article

Predictive maintenance (PdM) is a proactive strategy that enhances safety, minimizes unplanned downtime, and optimizes operational costs by forecasting equipment failures before they occur. This study presents a novel Field Programmable Gate Array (FPGA)-accelerated predictive maintenance framework for UAV engines using a Singular Value Decomposition (SVD)-optimized Long Short-Term Memory (LSTM) model. The model performs binary classification to predict the likelihood of imminent engine failure by processing normalized multi-sensor data, including temperature, pressure, and vibration measurements. To enable real-time deployment on resource-constrained UAV platforms, the LSTM’s weight matrices are compressed using Singular Value Decomposition (SVD), significantly reducing computational complexity while preserving predictive accuracy. The compressed model is executed on a Xilinx ZCU-104 FPGA and uses a pipelined, AXI-based hardware accelerator with efficient memory mapping and parallelized gate calculations tailored for low-power onboard systems. Unlike prior works, this study uniquely integrates a tailored SVD compression strategy with a custom hardware accelerator co-designed for real-time, flight-safe inference in UAV systems. Experimental results demonstrate a 98% classification accuracy, a 24% reduction in latency, and substantial FPGA resource savings—specifically, a 26% decrease in BRAM usage and a 37% reduction in DSP consumption—compared to the 32-bit floating-point SVD-compressed FPGA implementation, not CPU or GPU. These findings confirm the proposed system as an efficient and scalable solution for real-time UAV engine health monitoring, thereby enhancing in-flight safety through timely fault prediction and enabling autonomous engine monitoring without reliance on ground communication. Full article

Kubernetes clusters are deployed across data centers for geo-redundancy and low-latency access, resulting in new challenges in scheduling workloads optimally. This paper presents a practical evaluation of network-aware scheduling in a distributed Kubernetes cluster that spans multiple network zones. A custom scheduling plugin is implemented within the scheduling framework to incorporate real-time network telemetry (inter-node ping latency) into pod placement decisions. The assessment methodology combines a custom scheduler plugin, realistic network latency measurements, and representative distributed benchmarks to assess the impact of scheduling on traffic patterns. The results provide strong empirical confirmation of the findings previously established through simulation, offering a validated path forward to integrate not only network metrics, but also other performance-critical metrics such as energy efficiency, hardware utilization, and fault tolerance. Full article

Thermal infrared (TIR) ground observations are a well-established method for investigating surface temperature variations in thermally anomalous areas. However, commercially available technical solutions are currently limited, often offering proprietary products with minimal customization options for establishing a permanent TIR monitoring network. This work presents the comprehensive development of a thermal infrared monitoring network, detailing everything from the hardware schematics of the remote monitoring station (RMS) to the code for the final data processing software. The procedures implemented in the RMS for managing TIR sensor operations, acquiring environmental data, and transmitting data remotely are thoroughly discussed, along with the technical solutions adopted. The processing of TIR imagery is carried out using ASIRA (Automated System of InfraRed Analysis), a free software package, now developed for GNU Octave. ASIRA performs quality filtering and co-registration, and applies various seasonal correction methodologies to extract time series of deseasoned surface temperatures, estimate heat fluxes, and track variations in thermally anomalous areas. Processed outputs include binary, Excel, and CSV formats, with interactive HTML plots for visualization. The system’s effectiveness has been validated in active volcanic areas of southern Italy, demonstrating high reliability in detecting anomalous thermal behavior and distinguishing endogenous geophysical processes. The aim of this work is to enable readers to easily replicate and deploy this open-source, low-cost system for the continuous, automated thermal monitoring of active volcanic and geothermal areas and environmental pollution, thereby supporting hazard assessment and scientific research. Full article

Integrated security stacks, which offer diverse security function chains in a single device, hold substantial potential to satisfy the security requirements of multiple tenants on a public cloud. However, it is difficult for the software-only or hardware-customized security stack to establish a good tradeoff between performance and flexibility. SmartNIC overcomes these limitations by providing a programmable platform for implementing these functions with hardware acceleration. Significantly, without a professional CPU/SmartNIC co-design, developing security function chains from scratch with low-level APIs is challenging and tedious for network operators. This paper presents PASS, a flexible programmable framework for the fast development of high-performance security stacks with SmartNIC acceleration. In the data plane, PASS provides modular abstractions to extract the shared security logic and eliminate redundant operations by reusing the intermediate results with the customized metadata. In the control plane, PASS offloads the tedious security policy conversion to the proposed security auxiliary plane. With well-defined APIs, developers only need to focus on the core logic instead of labor-intensive shared logic. We built a PASS prototype based on a CPU-FPGA platform and developed three typical security components. Compared to implementation from scratch, PASS reduces the code by 65% on average. Additionally, PASS improves security processing performance by 76% compared to software-only implementations and optimizes the latency of policy translation and distribution by 90% versus the architecture without offloading. Full article

Recycling plastic waste has emerged as one of the most pressing environmental challenges of the 21st century. One of the biggest challenges in polyethylene terephthalate (PET) recycling is the requirement to return bottles in their original, undeformed state. This necessitates storing large volumes of waste and takes up substantial space. Therefore, this paper seeks to address this issue and introduces a novel AIoT-based infrastructure that integrates the PET Bottle Identification Algorithm (PBIA), which can accurately recognize bottles regardless of color or condition and distinguish them from other waste. A detailed study of Azure Custom Vision services for PET bottle identification is conducted, evaluating its object recognition capabilities and overall performance within an intelligent waste management framework. A key contribution of this work is the development of the Algorithm for Citizens’ Trust Level by Recycling (ACTLR), which assigns trust levels to individuals based on their recycling behavior. This paper also details the development of a cost-effective prototype of the AIoT system, demonstrating its low-cost feasibility for real-world implementation, using the Asus Tinker Board as the primary hardware. The software application is designed to monitor the collection process across multiple recycling points, offering Microsoft Azure cloud-hosted data and insights. The experimental results demonstrate the feasibility of integrating this prototype on a large scale at minimal cost. Moreover, the algorithm integrates the allocation points for proper recycling and penalizes fraudulent activities. This innovation has the potential to streamline the recycling process, reduce logistical burdens, and significantly improve public participation by making it more convenient to store and return used plastic bottles. Full article

This review article examines the role of additive manufacturing (AM) in increasing energy efficiency and sustainability within the evolving framework of Industry 5.0 and 6.0. This review highlights the unique ability of additive manufacturing to deliver mass-customized products while minimizing material waste and reducing energy consumption. The integration of smart technologies such as AI and IoT is explored to optimize AM processes and support decentralized, on-demand manufacturing. Thisarticle discusses different AM techniques and materials from an environmental and life-cycle perspective, identifying key benefits and constraints. This review also examines the potential of AM to support circular economy practices through local repair, remanufacturing, and material recycling. The net energy efficiency of AM depends on the type of process, part complexity, and production scale, but the energy savings per component can be significant if implemented strategically.AM significantly improves energy efficiency in certain manufacturing contexts, often reducing energy consumption by 25–50% compared to traditional subtractive methods. The results emphasize the importance of innovation in both hardware and software to overcome current energy and sustainability challenges. This review highlights AM as a key tool in achieving a human-centric, intelligent, and ecological manufacturing paradigm. Full article

The increasing global demand for sustainable and high-quality agricultural products has driven interest in precision agriculture technologies. This study presents a novel approach to wild mushroom detection, particularly focusing on Macrolepiota procera as a focal species for demonstration and benchmarking. The proposed approach utilises unmanned aerial vehicles (UAVs) equipped with multispectral imaging and the YOLOv5 object detection algorithm. A custom dataset, the wild mushroom detection dataset (WOES), comprising 907 annotated aerial and ground images, was developed to support model training and evaluation. Our method integrates low-cost hardware with advanced deep learning and vegetation index analysis (NDRE) to enable real-time identification of mushrooms in forested environments. The proposed system achieved an identification accuracy exceeding 90% and completed detection tasks within 30 min per field survey. Although the dataset is geographically limited to Western Macedonia, Greece, and focused primarily on a morphologically distinctive species, the methodology is designed to be extendable to other wild mushroom types. This work contributes a replicable framework for scalable, cost-effective mushroom monitoring in ecological and agricultural applications. Full article

This paper addresses the critical challenge of time management in wireless sensor networks (WSNs) applied to industrial process control. Although wireless technologies have gained ground in industrial monitoring, their adoption in control applications remains limited due to concerns around reliability and timing accuracy. This study proposes a practical, low-cost solution based on commercial off-the-shelf (COTS) components, leveraging the IEEE 802.15.4-2020 standard in Time-Slotted Channel-Hopping (TSCH) mode. A custom time management algorithm is developed and implemented on STM32 microcontrollers paired with AT86RF212B transceivers. The proposed system ensures a sub-millisecond synchronization drift across nodes by dividing communication into a structured slot frame and implementing precise scheduling and enhanced beacon-based synchronization. Validation is performed through experimental setups monitored with logic analyzers, demonstrating a time drift consistently below 600 microseconds. The results confirm the feasibility of using synchronized wireless nodes for real-time industrial control tasks, suggesting that further improvements in hardware precision could enable even tighter synchronization and broader applicability in fast and critical processes. Full article

This paper presents the design and evaluation of a novel soft pneumatic actuator featuring two independent bending chambers, enabling independent joint actuation and localization for rehabilitation purposes. The actuator’s dual-chamber configuration provides flexibility for applications requiring customized bending profiles. To measure the bending angle of the finger joints in real time, a camera-based system is employed, utilizing a deep learning detection model to localize the joints and estimate their bending angles. This approach provides a non-intrusive, sensor-free alternative to hardware-based measurement methods, reducing complexity and wiring typically associated with wearable devices. Experimental results demonstrate the effectiveness of the proposed actuator in achieving bending angles of 105 degrees for the metacarpophalangeal (MCP) joint and 95 degrees for the proximal interphalangeal (PIP) joint, as well as a gripping force of 9.3 N. The vision system also captures bending angles with a precision of 98%, indicating potential applications in fields such as rehabilitation and human–robot interaction. Full article

With increasing complexity and the demand for electronic components, evaluation boards that allow the customer to assess the components themselves are required. However, the evaluation boards are normally tested manually, and manual testing methods have challenges in terms of time efficiency, human error, and scalability. Therefore, we formulated an automated testing system based on robotic process automation (RPA) to address the issues. The system integrates RPA with existing testing hardware for high-speed analog-to-digital converter (ADC) evaluation boards to simplify processes of configuration, data logging, and the analysis of key parameters such as the signal-to-noise ratio full scale (SNRFS) and spurious-free dynamic range (SFDR). The current hardware setup was modified for automation to develop an RPA-based software solution for efficient testing, and its performance was compared with traditional methods in terms of time and repeatability. A marked improvement in test time efficiency was observed, with a reduction of up to 69.68% for inexperienced operators and 41.4% for experienced ones. The RPA-based method demonstrated a high accuracy (99.9603%) and repeatability, with minimal variance between test runs. The system provides an efficient and cost-effective test process that minimizes human intervention. This reduces process complexity for evaluation board functional testing, providing an effective solution to meet the growing demands of electronic components. Full article

Background: Type 1 basilar invagination (BI) is caused by a structural instability at the craniovertebral junction (CVJ) and has been historically treated with distraction and stabilization through fusion of the C1–C2 vertebrae. Recent advances in 3D printed custom implants (3DPIs) have improved the array of available options for reaching distraction and alignment goals. Case Presentation: We report the case of a 15-year-old male who presented with early signs of cervical myelopathy. Radiographic evaluation revealed type 1 BI with a widened atlantodental interval (ADI) of 3.7 mm and a 9 mm McRae’s line violation (MLV) of the dens, resulting in severe narrowing at the CVJ and brainstem/spinal cord impingement. Of note, the patient had bilateral dysplastic C1 and C2 anatomy, thus requiring a patient-specific 3DPI to conform to this anatomy and enable sufficient distraction and fusion. Custom 3D printed C1–C2 interfacet spacers were created and implemented within 14 days to achieve sufficient distraction, osteoconduction, and stabilization of the C1–C2 joint. Outcome: Postoperatively, the patient remained neurologically intact with myelopathic symptom improvement before discharge on postoperative day 4. Postoperative imaging demonstrated the resolution of BI from successful C1–C2 joint distraction and confirmed intended implant placement with resolution of canal stenosis. During his 6-week follow-up, the patient remained neurologically stable with intact hardware and preserved alignment. Conclusions: This case is the first in the United States demonstrating the use of custom 3D printed interfacet spacers to achieve successful distraction, decompression, and stabilization of type 1 BI. These patient-specific 3DPIs were designed and created in a streamlined manner and serve as proof-of-concept of pragmatic implant design and manufacturing. Future optimization of the workflow and characterization of long-term patient outcomes should be explored for these types of 3DPI. Full article