Search Results (99)

Time-Sensitive Networking (TSN) has emerged as a critical communication protocol for automotive Ethernet to support the high-bandwidth, real-time, and deterministic transmission requirements of next-generation in-vehicle networks. However, a clear and effective TSN mechanism combination tailored to the mixed and bursty traffic characteristics of automotive scenarios remains lacking. To address this issue, this paper proposes a combined TSN scheduling mechanism for automotive scenarios. The highest-priority traffic is scheduled by class-based Time-Aware Shaper (TAS), periodic bursty sensor traffic is shaped by Credit-Based Shaper (CBS), and medium-priority traffic adopts Multi-Cyclic Queueing and Forwarding (MCQF). Based on Compositional Performance Analysis (CPA), this paper derives the worst-case latency upper bound expressions for CQF streams and optimizes the schedulability analysis to reduce conservative errors. Simulation verifies that the theoretically calculated bounds cover the maximum simulation latency, and the optimized analysis reduces conservatism, with peak conservative error of 3.07% in the ring scenario and 10.59% in the automotive scenario. Compared with the strict priority and TAMCQF (a combination of TAS and Multi-CQF), the proposed mechanism combination suppresses the latency jitter of mixed traffic, mitigates long-duration blocking of medium-priority traffic caused by high-priority burst data, and provides reliable deterministic transmission guarantees for automotive in-vehicle networks. Full article

Greenhouse microclimate regulation is challenging due to nonlinear coupling among temperature, humidity, soil moisture, and light intensity, which limits the effectiveness of conventional threshold-based and PID control strategies under time-varying environmental disturbances. This paper presents a forecast-augmented ensemble control framework that combines Random Forest, Gradient Boosting, and Support Vector Machine classifiers with one-hour-ahead weather forecasts for closed-loop greenhouse microclimate regulation. The proposed system was deployed and validated in a working greenhouse cultivating cucumber (cv. ‘Madora F1’) over 28 consecutive days. Sensor measurements and forecast inputs were processed through a unified preprocessing pipeline, while control actions were generated through majority voting and executed on Raspberry Pi 4B edge hardware with a worst-case inference latency below 18 ms. The proposed framework achieved a temperature RMSE of 0.83 °C during field deployment. For reference, RMSE values of 3.21 °C and 1.94 °C were obtained for the threshold-based and PID baseline controllers, respectively, under the adopted disturbance-consistent evaluation protocol. Compliance rates reached 96.4% for temperature, 94.1% for relative humidity, and 97.2% for soil moisture across 40,320 resampled observation intervals (60 s analysis grid) derived from the original 10 s acquisition stream. Integration of short-term weather forecasts enabled anticipatory irrigation management, reducing irrigation pump operation by 18% without compromising soil-moisture compliance and yielding an estimated annual energy saving of 158 kWh per greenhouse zone. Unlike prediction-oriented greenhouse artificial-intelligence studies, the proposed approach implements a deployable forecast-augmented closed-loop control architecture validated under continuous real-world greenhouse operation. Full article

We study real-time next-window badminton action prediction from wearable IMU streams where the system must predict the action label of the upcoming 100 ms window using past-only (causal) information. To handle severe class imbalance in continuous streams, we employ window-level downsampling of the dominant background class and compress multi-sensor time/frequency features using PCA before temporal modeling. We evaluate the full pipeline under a hop-based streaming protocol and show that our BiLSTM + MHSA model achieves high recognition performance (test accuracy 96.36%, Macro-F1 95.82%) while remaining deployable in real time, reaching 58.20 windows/s end to end (including preprocessing), i.e., 5.82× the real-time requirement (10 windows/s under a 100 ms output interval), on a Windows PC with an NVIDIA RTX 3080 GPU. These results support low-latency applications such as live coaching feedback and tactical analytics. Full article

Real-time simultaneous monitoring of cardiac and respiratory signals in wearable systems remains challenging due to motion artifacts under varying body postures. This paper proposes an edge wearable integrated with novel methods to acquire and process cardiac and respiratory signals simultaneously from the chest. For respiration monitoring, the system captures chest motion using an IMU and applies dynamic filtering with real-time axis selection in a custom mobile application. It automatically selects the best respiratory axis from six IMU vectors: x, y, z, xy, yz, and zx, improving robustness across body postures and device placements. The proposed system can also capture and process electrocardiogram (ECG) data simultaneously for cardiac monitoring. Cardiac and respiration data were taken from eight healthy subjects, including males and females, followed by five protocols. The overall mean absolute error (MAE) for eight subjects is found to be 0.64 breath per minute (BrPM) after validation by a commercial sensor. In real time, the wearable continuously provides ECG and breathing signal streaming, ECG beat detection, and cardiac and breathing rates with an overall latency of 13.8 ms. The results indicate that the system can monitor the cardio-respiratory signals in real time under static and light-movement conditions. Full article

Knee Osteoarthritis (KOA) is a leading contributor to global physical disability, where delayed diagnosis often results in irreversible joint damage and socio-economic cost. Early diagnosis remains challenging due to subtle radiographic biomarkers and limited access to specialized expertise, particularly in distributed healthcare settings. Within the evolving landscape of the Future Internet, characterized by Internet of Medical Things (IoMT), edge–cloud computing, and intelligent digital health infrastructures, there is an increasing demand for scalable, low-latency, and explainable AI-driven diagnostic solutions. In this work, we propose a Dual-Stream Wavelet Fusion Network (DS-WFN) alongside a distributed edge-cloud architectural roadmap tailored for deployment in distributed and edge-enabled healthcare ecosystems. The framework integrates a spatial morphological stream with a spectral wavelet stream, augmented by an Adaptive Wavelet Selection Mechanism (AWSM). The AWSM dynamically selects optimal frequency bases (Haar, Symlet, Daubechies) to preserve fine-grained diagnostic features typically lost in conventional CNN architectures. An Adaptive Spatial Alignment (ASA) module further ensures efficient fusion of heterogeneous representations, enabling robust feature integration across computational nodes. Experimental results across a five-fold patient-isolated cross-validation protocol demonstrate that the DS-WFN achieves a mean classification accuracy of 76.3% (95% CI: 71.6–80.8%) and a macro-averaged F1-score of 0.747 (95% CI: 0.697–0.795), consistently outperforming single-stream baselines while preventing patient-level data leakage. Furthermore, Grad-CAM visualizations provide interpretable outputs aligned with clinical diagnostic criteria, supporting trustworthy AI integration into digital healthcare workflows. Furthermore, we disclose a methodological framework for edge-based implementation, highlighting how localized inference ensures data sovereignty and real-time clinical support. By combining multiscale signal processing with deep learning under a Future Internet paradigm, this work contributes a scalable, explainable, and edge-ready diagnostic framework for early KOA detection, enabling intelligent, connected, and resource-efficient healthcare services. Full article

With the growing severity of water pollution, conventional treatment technologies are increasingly unable to satisfy the demand for deep purification. Catalytic wastewater treatment has emerged as an effective strategy for degrading refractory pollutants because of its high efficiency, mild operating conditions, and environmentally friendly nature. This review systematically summarizes recent progress in catalytic materials for wastewater treatment, covering four major categories: metal-based materials, carbon-based materials, multicomponent composites, and photo/electrocatalytic systems. Particular attention is given to their design strategies, structural characteristics, and performance advantages. On this basis, the full mechanistic chain is discussed, from interfacial adsorption and activation to reactive-species generation, including both radical and non-radical pathways, intermediate transformation, and macroscopic reaction kinetics. The review also highlights representative applications in practical wastewater streams, including textile dyeing and pharmaceutical, chemical, landfill leachate, and municipal tailwater treatment, thereby demonstrating the engineering potential of catalytic technologies. At the same time, several critical challenges remain, including insufficient long-term material stability, incomplete mechanistic understanding in complex water matrices, limited adaptability to real wastewater, and the high cost of large-scale preparation. Future research should therefore focus on the development of highly stable, low-cost, and interference-resistant catalytic materials, deeper mechanistic elucidation through in situ characterization and theoretical calculations, stronger integration with membrane separation, biological treatment, photovoltaic or electrochemical processes, and the establishment of standardized evaluation protocols and life-cycle assessment frameworks. These efforts will accelerate the transition of catalytic wastewater treatment toward greener, smarter, and more practical engineering applications. Full article

Machine learning-based intrusion detection systems (IDS) deployed in real-world environments frequently degrade due to concept drift, where evolving traffic patterns invalidate assumptions learned during training. This challenge is especially pronounced in Internet of Things (IoT) environments, where device behavior changes over time due to user interaction, firmware updates, and emerging attack strategies. Prior work introduced FIRCE, a framework that integrates conformal evaluation into streaming IDS pipelines to enable uncertainty-aware drift detection and adaptive retraining. In this journal extension, we present FADES, a framework for adaptive drift estimation that generalizes drift monitoring beyond prediction-space uncertainty by supporting both conformal evaluation and representation-space detectors within a unified streaming architecture. FADES incorporates multiple conformal evaluation variants, including Approximate Cross-Conformal Evaluation, which preserves the statistical structure of cross-conformal evaluation while eliminating repeated model training, as well as an Adaptive Chunking Controller that dynamically balances detection responsiveness and computational cost. We extend prior work through three major contributions: (i) a variance-aware evaluation protocol comprising 375 simulations across multiple seeds and runs, (ii) integration of a contrastive autoencoder-based detector to enable direct comparison between prediction-space and representation-space drift detection, and (iii) expanded evaluation across in-domain and cross-dataset transfer settings using UNSW-NB15, CICIDS2018, and a real-world IoT testbed. Approx-CCE achieves performance comparable to standard cross-conformal evaluation across hundreds of simulations, providing empirical evidence that the statistical benefits of CCE derive primarily from its disjoint calibration partition structure rather than fold-specific model diversity, a finding with implications for conformal evaluation in repeated recalibration settings more broadly. In contrast, representation-space drift detection via CADE incurs substantial computational cost under repeated retraining, limiting its practicality in streaming settings. These findings demonstrate that conformal evaluation provides a statistically grounded and computationally efficient foundation for real-time drift-aware intrusion detection, and that FADES enables flexible, unified evaluation of drift detection strategies under realistic deployment conditions. Full article

The Controller Area Network (CAN) protocol used in in-vehicle networks is vulnerable to external attacks because it lacks authentication and encryption mechanisms. Accordingly, CAN Intrusion Detection Systems (IDSs) have been studied. However, existing IDSs remain difficult to deploy in practical vehicles because of their limited real-time capability, complex preprocessing, and high computational cost. To overcome these limitations, this paper proposes an ultra-lightweight Convolutional Neural Network (CNN)-based IDS that significantly reduces parameters and computational complexity while maintaining high detection performance. The proposed IDS improves area efficiency through a streaming pipeline, computation-block reuse, and constrained Processing Element (PE) parallelism. In addition, its lightweighting effect was quantitatively evaluated against an RTL baseline implemented under identical platform and design constraints. When an attack is detected, an Intrusion Prevention System (IPS) integrated with the CAN controller generates an error frame to block it in real time. The proposed IDS achieved over 99.97% detection performance for known frame-level message-injection scenarios on the Car-Hacking Dataset. It also achieved branch-wise real-time feasibility with an 11.46 µs ID-branch precomputation latency and a 5.68 µs DATA-complete-to-decision latency at 50 MHz. In TSMC 28 nm ASIC synthesis, the proposed IDS required 70,592 gates, with an estimated ASIC power of 2.0231 mW and an active inference energy of 34.68 nJ. Full article

Insulation-material manufacturers face increasing pressure to improve productivity, cost efficiency, energy performance and worker safety while maintaining stable quality in highly constrained production environments. Existing lean and smart-manufacturing studies often examine isolated tools, individual monitoring technologies or material-level sustainability, but fewer studies provide conservative plant-level validation of an integrated intervention in insulation-material production. This study therefore examines the optimization of insulation-material production in a human-supervised cyber–physical manufacturing system through an industrial before–after intervention. The framework combines bottleneck identification, value stream mapping, SMED, selective automation, preventive maintenance and KPI-based digital monitoring. The baseline system was constrained by manual crusher loading, long changeovers, inefficient pallet transport, repeated breakdowns, scrap and limited real-time visibility. After implementation, productivity increased from 7864 to 9000 kg/day (+14.5%), monthly production costs decreased from EUR 200,000 to EUR 180,000 (−10%), breakdown frequency fell from 5 to 3 events/month (−40%), scrap decreased from 5% to 3% (−40%), crusher loading time fell from 30 to 10 min/pallet (−66%), annual energy use dropped from 500 to 450 MWh (−10%) and reported safety incidents decreased to zero during the 12-month post-implementation observation period. An OEE-based surrogate model yielded pre- and post-state theoretical capacity estimates differing by less than 1%, supporting internal consistency. The results are interpreted as descriptive and practically meaningful before–after differences because the full raw monthly dataset is commercially sensitive and classical inferential testing was not performed. The study contributes by presenting a reproducible, conservative and human-supervised CPS-oriented plant-intervention protocol rather than by claiming a fully autonomous closed-loop CPS. Full article

Human Activity Recognition (HAR) from inertial sensors must run continuously on battery-powered wearables under tight latency, memory, and energy budgets. While tiny Transformers can be effective on inertial time series, end-to-end co-design across quantized inference and heterogeneous low-power platforms remains underexplored. We present STORM (Small Transformer for On-node Recognition of Motion), a deployment-oriented 19.7k-parameter 1D Transformer co-designed with X-HEEP, an open-source low-power single-core RISC-V SoC, and a tightly coupled streaming CGRA for nonlinear primitives (e.g., softmax). We build a cross-source 8-class benchmark by harmonizing 3 public datasets under a stringent, deployment-aligned protocol that exposes both cross-subject and cross-source shift. Using 1.280 s windows with 0.640 s stride, the protocol models continuous on-node HAR under cross-dataset generalization. After quantization-aware training and INT8 C inference export, STORM achieves 0.799/0.801 accuracy/macro-F1 on this benchmark. Deployed on an FPGA prototype of X-HEEP with the streaming CGRA backend, STORM requires 67.4 ms per inference at 100 MHz, while activity-based power analysis estimates a total inference energy of 632.4 $\mathsf{\mu }$J, satisfying the stride-driven real-time constraint. These results support the practical viability of compact attention-based HAR on low-power wearable-class embedded platforms. Full article

Wireless sensor networks (WSNs) have increasing demand on lightweight, efficient, and secure encryption techniques for devices with limited resources, since traditional algorithms require high computation which make them impractical. This preliminary study presents an encryption algorithm based on chaos designed for transmitting short data, using the Lorenz system and Euler’s method for computation. It is combined with a synchronization model based on data array. It inserts iteration parameters within the ciphertext to ensure consistent key reproduction while decrypting. Within the broader context of e-health data streams, encryption efficiency is critical: continuous ECG signals generate large volumes of data that challenge real-time secure transmission, whereas individual blood pressure readings are far smaller and lightweight. While this work delimits its scope to short, low-power transmissions, simulations and hardware implementation on an nRF chip using the Enhanced ShockBurst (ESB) protocol demonstrated efficiency, with the lowest encryption speed of 0.154 ms for a 1-byte payload. Security analysis using the NIST Statistical Test Suite confirmed high statistical randomness of the generated keystream, and theoretical key-space analysis supports robustness. By focusing on short-stream encryption in preliminary form, the scheme contributes toward inclusive secure communication technologies for resource-constrained IoT healthcare systems and diverse user populations. Full article

Real-time coordination across OEM–Tier-1 manufacturing networks remains challenging due to delayed shop-floor data, stochastic machine availability, and the need for schedule stability. This paper presents a protocol-agnostic, two-stage mixed-integer linear programming (MILP) framework for real-time family-level scheduling. The method integrates MTConnect-like data streams without requiring adherence to any single communication standard. In Stage 1, a baseline plan is generated using expected capacity; in Stage 2, a rolling-horizon recourse model adapts the plan to observed (possibly lagged) capacity while incorporating a stability penalty to control resequencing. A synthetic OEM–Tier-1 testbed with three machines (two Tier-1, one OEM) is used to benchmark performance under real-time (L = 0) and delayed (L = 5) data scenarios. Across these scenarios, the real-time rolling scheduler improves strict on-time fulfillment by approximately 70% and eliminates terminal backlog relative to static planning, while MILP solve times remain under 0.1 s per cycle. Sensitivity experiments that vary disruption intensity, replanning interval (Δ), and stability weight (λ) show consistent qualitative trends and illustrate how the framework can be tuned to balance service performance against schedule stability without sacrificing computational tractability. Full article

The rapid inspection of urban road hazards, such as subsurface voids and pipeline damage, demands high efficiency and precision in detection technology. Conventional Ground Penetrating Radar (GPR) systems often face limitations in urban environments, including slow survey speeds, poor channel scalability, and the trade-off between shallow resolution and deep penetration. The proposed system integrates a dual-band antenna array (200 MHz and 400 MHz) to resolve the classical resolution–penetration trade-off, simultaneously capturing high-resolution shallow data and achieving deep subsurface penetration in a single pass. To overcome the sampling rate bottleneck inherent in low-cost microcontrollers, a custom Time-Division Step Multiplexing (TDSM) protocol extends the equivalent sampling period to 0.38 µs across 24 parallel channels while maintaining a 200 kHz pulse repetition rate—enabling real-time data streaming at vehicle speeds up to 70 km/h with 5 cm trace spacing. This capability directly addresses the critical challenge of traffic disruption on urban arterials caused by conventional slow-speed GPR surveys. Complementing this, a master-slave FPGA-MCU hierarchical architecture provides seamless channel scalability from 24 to 36 channels, adapting to diverse swath width requirements without hardware redesign. Laboratory physics model experiments demonstrate a penetration depth exceeding 3 m after convolutional sparse fusion of the dual-band data, covering the typical burial depth of urban utilities. This study provides a deployable high-resolution underground detection solution for rapid urban infrastructure surveys and emergency disease detection by breaking the traditional constraints of channel number, sampling rate, and detection speed, significantly reducing interference with urban main traffic. Full article

This study presents a simulation-based evaluation of a wall-following and mapping framework for autonomous underwater vehicles (AUVs) equipped with a single-line laser, targeting structured environments such as rectangular tanks and dam interiors. A hardware-in-the-loop (HIL) simulation platform is developed to integrate sensor emulation, vehicle dynamics, and image-based control while preserving the onboard data formats, update rates, and communication protocols of the AUV system. Using a single camera–laser pair, the framework estimates yaw angle and lateral wall distance from laser image geometry to support real-time wall-following and frontal obstacle avoidance. Wall mapping is performed by transforming laser image features into spatial coordinates and estimating the dimensions of geometric protrusions. The framework is evaluated on simulated walls with protruding features under two navigation conditions: ideal-motion and dynamic-control operation. Simulation results show stable wall-following performance, with lateral distance errors typically below 0.1 m. Under ideal-motion conditions, mapping errors range from 1% to 13%, while under dynamic-control navigation they increase to 10–35% due to attitude fluctuations and control-induced motion. Frontal obstacle avoidance maintains a minimum clearance of 1.04 m. The results demonstrate the feasibility of using a single-line laser and a unified image stream for both real-time wall-following control and post-mission geometric mapping within the defined simulation conditions. While the evaluation is limited to simulation and assumes idealized optical conditions without modeling hydrodynamic disturbances or optical degradation effects, the framework provides a system-level reference for laser-guided inspection strategies in confined underwater environments such as tanks, reservoirs, and dams. Full article

Most existing deep learning models for remote sensing scene classification (RSSC) adopt an offline learning paradigm, where all classes are jointly optimized on fixed-class datasets. In dynamic real-world scenarios with streaming data and emerging classes, such paradigms are inherently prone to catastrophic forgetting when models are incrementally trained on new data. Recently, a growing number of class-incremental learning (CIL) methods have been proposed to tackle these issues, some of which achieve promising performance by rehearsing training data from previous tasks. However, implementing such strategy in real-world scenarios is often challenging, as the requirement to store historical data frequently conflicts with strict memory constraints and data privacy protocols. To address these challenges, we propose a novel memory-efficient feature-replay CIL framework (FR-CIL) for RSSC that retains compact feature embeddings, rather than raw images, as exemplars for previously learned classes. Specifically, a progressive multi-scale feature enhancement (PMFE) module is proposed to alleviate representation ambiguity. It adopts a progressive construction scheme to enable fine-grained and interactive feature enhancement, thereby improving the model’s representation capability for remote sensing scenes. Then, a specialized feature calibration network (FCN) is trained in a transductive learning paradigm with manifold consistency regularization to adapt stored feature descriptors to the updated feature space, thereby effectively compensating for feature space drift and enabling a unified classifier. Following feature calibration, a bias rectification (BR) strategy is employed to mitigate prediction bias by exclusively optimizing the classifier on a balanced exemplar set. As a result, this memory-efficient CIL framework not only addresses data privacy concerns but also mitigates representation drift and classifier bias. Extensive experiments on public datasets demonstrate the effectiveness and robustness of the proposed method. Notably, FR-CIL outperforms the leading state-of-the-art CIL methods in mean accuracy by margins of 3.75%, 3.09%, and 2.82% on the six-task AID, seven-task RSI-CB256, and nine-task NWPU-45 datasets, respectively. At the same time, it reduces memory storage requirements by over 94.7%, highlighting its strong potential for real-world RSSC applications under strict memory constraints. Full article