Search Results (42)

We present an offline-first edge telemedicine platform designed for clinics and outreach programs where internet access, power, and IT support are unreliable. The system runs local electronic health record (EHR) and clinical “plug-in” screening services on a single embedded device, accessed through a clinician-facing web app over local WiFi. Data are stored locally with role-based access control and record-level encryption, while interoperability is provided as a best-effort queued synchronization pathway to external systems using HL7 FHIR when connectivity is available. As a representative plug-in, we implement non-invasive anemia screening from fingernail photographs. Images are processed fully on-device: an INT8-quantized YOLOv8n detector extracts nail regions, lightweight color and summary-statistic features are computed per ROI and concatenated, and a supervised regressor estimates hemoglobin. On an NVIDIA Jetson Orin Nano, ROI extraction runs in 22 ms and hemoglobin inference in 34 ms. Across six training strategies (unbalanced, augmented, and KDE-balanced by remark or severity), test RMSE ranges from 2.05–3.13 g/dL; the strongest numeric performance is achieved by severity-balanced SVR (RMSE 2.048 g/dL) and remark-balanced Gradient Boosting (RMSE 2.091 g/dL). Raincloud analyses restricted to true-anemic test cases show that balancing primarily reduces systematic overestimation (which drives false negatives) while augmentation can widen error tails, highlighting the importance of selecting training strategy to match screening objectives rather than optimizing a single aggregate metric. Full article

Continuous cough monitoring provides valuable insights into respiratory health; however, conventional air-conduction microphones are highly susceptible to ambient noise and raise privacy concerns. This work presents BCough, a bone-conduction-based embedded AI platform for on-device cough detection, designed and evaluated on the MAX78000 neural accelerator. The system employs a skin-contact bone-conduction sensor worn on the chest to capture body vibrations transmitted through bone and tissue, detecting cough events while minimizing environmental interference. The custom prototype integrates a bone-conduction microphone, a synchronized 6-axis IMU, power management circuitry, and an embedded neural accelerator to support real-time inference and future multimodal extensions. A compact 8-bit quantized convolutional neural network was optimized for deployment on the MAX78000 and evaluated using leave-one-subject-out cross-validation on one-second cough and non-cough segments derived from a corpus of 19,955 labeled events collected from five participants under controlled conditions. The deployed model achieved 0.80 Macro-F1, 0.81 balanced accuracy, 0.74 cough F1, and 0.89 AUC, with 15–16 ms inference latency and approximately 20 $\mathsf{\mu }$J energy per inference on chip. These results demonstrate the feasibility of low-power, privacy-preserving, bone-conduction cough detection on embedded AI hardware within an initial five-participant study. The current design is a benchtop prototype; the findings should therefore be interpreted as an initial feasibility assessment rather than evidence of robust performance across diverse users and real-world conditions. Future work will extend this platform toward miniaturized wearable implementations combining bone-conduction and inertial sensing for continuous multimodal respiratory monitoring. Full article

Hybrid CNC and additive manufacturing platforms often rely on host-assisted or otherwise overdimensioned control architectures to achieve deterministic multi-axis motion, increasing system cost and complexity. This paper presents a fully microcontroller-based timer–DMA motion execution architecture that eliminates the need for external processors or FPGA-based execution, enabling deterministic multi-axis synchronization under the tested conditions in a simpler, more cost-effective way. The proposed framework integrates motion planning, precise step-time computation, and hardware-assisted pulse generation within a unified embedded control architecture. The main novelty lies in the systematic use of timer and DMA peripherals to offload time-critical pulse execution from the microcontroller core, allowing it to focus on motion planning and precise step-time computation. Unlike segmentation-based approaches, the duration of each individual step is calculated directly without fixed-interval segmentation, enabling high motion resolution while avoiding per-step interrupts that introduce jitter at high motion speeds. The architecture was validated on a hybrid platform capable of both milling and material extrusion. Experimental results confirmed real-time feasibility within practical on-chip memory limits and demonstrated very small interpolation errors caused mainly by timer quantization, comparable to those observed in host-processor-based motion systems. Machining and additive-manufacturing experiments further confirmed stable execution and accurate trajectory tracking under real operating conditions. Full article

Knee joint moment is an important biomechanical parameter for sports assessment, rehabilitation monitoring, and human–machine interaction. However, direct measurement is often restricted to laboratory-based settings. Surface electromyography (sEMG) offers a non-invasive alternative for indirect joint moment estimation, but many existing deep learning models remain too computationally demanding for potential wearable edge deployment. To address this gap, this study proposes Topo2DCNN-LSTM, a lightweight two-dimensional (2D) convolutional neural network model, designed for sagittal-plane knee flexion moment estimation. The model used a feature-based sequential representation, transforming raw sEMG signals into compact Root Mean Square (RMS) feature frames. The input was processed by a lightweight 2D convolutional neural network (CNN) encoder and paired with long short-term memory (LSTM) units. The model was trained on a public walking dataset of healthy subjects with synchronized sEMG and joint kinetics at two treadmill speeds. When compared with selected deep learning baselines, the quantized model achieved a mean RMS Error of 0.088 ± 0.020 Nm/kg at 1.2 m/s and 0.114 ± 0.034 Nm/kg at 1.8 m/s. On a SparkFun Thing Plus–SAMD51, it achieved an average inference latency of 28 ms using 71,316 bytes of random-access memory (RAM) and 257,172 bytes of flash. These results support its use as a proof of concept for personalized unilateral knee moment estimation with isolated on-device inference feasibility under resource-constrained and limited walking conditions. Full article

High-precision Doppler measurement is essential for deep-space Unified X-band (UXB) tracking systems, yet digital implementations suffer from finite word-length quantization errors that degrade performance. This study analyzes frequency offset errors in UXB transponder systems, focusing on the phase-locked loop (PLL) and system-level digital processing. A digital system model is presented, featuring an FFT-based coarse acquisition and a digital Costas loop for carrier synchronization. The simulation results reveal that 32-bit quantization yields unacceptable frequency offset errors. By extending critical paths to 48 bits, the system reduces frequency offset error by approximately 2¹⁶ and achieves sub-0.01 mm/s velocity accuracy, significantly improving coherence and meeting deep-space measurement requirements. Full article

This paper investigates dynamic event-triggered control (DETC) and encoding–decoding schemes to achieve the synchronization of T-S fuzzy neural networks (FNNs). DETC allows the transmission signals to be controlled aperiodically during the actual operation of the system, enabling a rapid response to practical control tasks. Meanwhile, during the event-triggered control process, an encoding–decoding scheme with externally injected noise is used to protect the signals. First, a dynamic event-triggered control mechanism is established, and an encoding–decoding scheme is used to optimize the transmission of controller signals. Subsequently, the Lyapunov–Krasovskii functional is constructed to derive the system’s synchronization criteria and calculate the controller gains. Finally, numerical simulation experiments are conducted to verify the effectiveness and feasibility of the proposed method. Full article

Municipal solid waste incineration (MSWI) is a typical complex industrial process for achieving sustainable development of the global environment. It implements the “perception-prediction–control” mode based on domain experts by using multimodal information. To harness the complementary value of different modal data, prevent information conflicts or fusion failures caused by misalignment, and ensure the availability of multimodal datasets and the reliability of analytical conclusions, constructing a benchmark operational condition multimodal dataset is essential. The objective of this work was to create a multimodal reference database for the operational status of IMSW processes. Based on the description of the MSWI process and the analysis of the characteristics of the multimodal data, the process data is first preprocessed under different missing scenarios, missing value processing and outlier processing. Then, single-frame images of the flame video are captured on a minute scale, and the missing combustion lines are quantized by using machine vision technology. Finally, the alignment of combustion line quantization (CLQ) values with the minute time scale of process data is achieved through the multimodal time synchronization module. Taking an MSWI power plant in Beijing as the research object, the combustion flame video and process data under the benchmark operating conditions were collected. The hybrid missing value management strategy combining linear interpolation with the LRDT model improved data integrity, and a spatiotemporal aligned multimodal dataset was constructed. The standardized benchmark operating condition multimodal data was obtained to support combustion state analysis during the incineration process, pollutant generation prediction, and process optimization. Therefore, the objectives of ‘reduction, harmlessness, and resource utilization’ of municipal solid waste, addressing land resource shortages, protecting the ecological environment, and promoting the dual carbon goal can be supported. Additionally, data and technical support for environmental and urban sustainable development are provided. Full article

This paper investigates bipartite synchronization in signed Lur’e networks influenced by semi-Markovian jump dynamics. A control strategy is proposed that adapts to mode-dependent switching by combining quantized feedback with selective pinning. The approach accommodates both leaderless and leader–following synchronization scenarios. For each switching mode, Lyapunov–Krasovskii-based analysis is employed to establish sufficient conditions using linear matrix inequalities (LMIs). The robustness and convergence of the method are confirmed through simulation studies, even in the presence of stochastic switching and limited communication precision. Full article

Missile-borne active phased array antennas have been widely used in missile guidance for their beam agility, multifunctionality, and strong anti-interference capabilities. However, due to space constraints on the platform and difficulty in heat dissipation, the thermal power consumption of the antenna array can easily lead to excessive temperature, causing two primary issues: first, temperature-induced drift in T/R components, resulting in amplitude and phase errors in the feed current; second, temperature-dependent ripple voltage in the array’s secondary power supply, which exacerbates feed errors. Both issues degrade the electromagnetic performance of the array antenna. To mitigate these effects, this paper investigates feed errors and compensation methods in high-temperature environments. First, a synchronous Buck circuit ripple coefficient model is developed, and an electromagnetic–temperature coupling model is established, incorporating temperature-dependent feed current characteristics, and the law of electromagnetic performance changes is analyzed. On this basis, an electromagnetic performance compensation method based on a genetic algorithm is proposed to optimize the quantization compensation amount of the amplitude and phase of each element under the effect of high temperature. Full article

This study addresses the preassigned-time (PDT) projective lag synchronization of octonion-valued BAM neural networks (OV-BAMNNs) through exponential quantized event-triggered control (ETC). First, an OV-BAMNN model incorporating discontinuous activation functions and time-varying delays is established. Subsequently, by introducing the octonion-valued sign function, several exponential quantized ETC schemes are designed, which employ solely a single exponential term while eliminating traditional linear and power-law components. Compared with conventional ETC designs, the proposed control schemes are simpler in form. Furthermore, within the framework of the non-separation method, several criteria for PDT projective lag synchronization are derived based on the Lyapunov method and Taylor expansion, proving that Zeno behavior is excluded. Finally, two simulation examples are given to verify the correctness of the theoretical results and to apply these results to image encryption. Full article

This study investigates the synchronization of coupled fractional-order Markovian reaction-diffusion neural networks (MRDNNs) with partially unknown transition rates. The novelty of this work is mainly reflected in three aspects: First, this study incorporates the Markovian switching model and reaction-diffusion term into a fractional-order system, which is a challenging and under-explored issue in existing literature, and effectively addresses the synchronization problem of fractional-order MRDNNs by introducing a continuous frequency distribution model of the fractional integrator. Second, it derives a new set of sufficient synchronization conditions with reduced conservatism; by utilizing the (extended) Wirtinger inequality and delay-partitioning techniques, abundant free parameters are introduced to significantly broaden the solution range. Third, it proposes an LMI-based optimal synchronization design by establishing an efficient offline optimization framework with semidefinite constraints, and achieves the precise solution of control gains. Finally, numerical simulations are conducted to validate the effectiveness of the proposed method. Full article

The rapid growth of Internet of Medical Things (IoMT) devices offers promising avenues for real-time, personalized healthcare while also introducing critical challenges related to data privacy, device heterogeneity, and deployment scalability. This paper presents E-DMFL (Enhanced Distributed Multimodal Federated Learning), an Enhanced Distributed Multimodal Federated Learning framework designed to address these issues. Our approach combines systems analysis principles with intelligent model design, integrating PyTorch-based modular orchestration and TensorFlow-style data pipelines to enable multimodal edge-based training. E-DMFL incorporates gated attention fusion, differential privacy, Shapley-value-based modality selection, and peer-to-peer communication to facilitate secure and adaptive learning in non-IID environments. We evaluate the framework using the EarSAVAS dataset, which includes synchronized audio and motion signals from ear-worn sensors. E-DMFL achieves a test accuracy of 92.0% in just six communication rounds. The framework also supports energy-efficient and real-time deployment through quantization-aware training and battery-aware scheduling. These results demonstrate the potential of combining systems-level design with federated learning (FL) innovations to support practical, privacy-aware IoMT applications. Full article

This paper proposed an adaptive bandwidth Phase-Locked Loop (PLL) that integrates integer-N and fractional-N switching for energy-efficient RF synthesis in IoT and mobile applications. The architecture exploits wide-bandwidth integer-N mode for rapid lock acquisition, then seamlessly transitions to narrow-bandwidth fractional-N mode for high-resolution synthesis and noise optimization. The architecture features a bandwidth-reconfigurable loop filter with intelligent switching control that monitors phase error dynamics. A novel adaptive digital noise filter mitigates $\Delta \Sigma$ quantization noise, replacing conventional synchronous delay lines. The multi-loop structure incorporates a high-resolution digital phase detector to enhance frequency accuracy and minimize jitter across both operating modes. With 180 nm CMOS technology, the PLL consumes 13.2 mW, while achieving $-119$ dBc/Hz in-band phase noise and 1 $p{s}_{rms}$ integrated jitter. With an operating frequency range at 2.9–3.2 GHz from a 1.8 V supply, the circuit achieves a worst case fractional spur of −62.7 dBc, which corresponds to a figure of merit (FOM) of −228.8 dB. Lock time improvements of 70% are demonstrated compared to single-mode implementations, making it suitable for high-precision, low-power wireless communication systems requiring agile frequency synthesis. Full article

Bridge Structural Health Monitoring (BSHM) is vital for assessing structural integrity and operational safety. Traditional wired systems are limited by high installation costs and complexity, while existing wireless systems still face issues with cost, synchronization, and reliability. Moreover, cloud-based methods for extreme event detection struggle to meet real-time and bandwidth constraints in edge environments. To address these challenges, this study proposes a lightweight wireless BSHM system based on edge computing, enabling local data acquisition and real-time intelligent detection of extreme events. The system consists of wireless sensor nodes for front-end acceleration data collection and an intelligent hub for data storage, visualization, and earthquake recognition. Acceleration data are converted into time–frequency images to train a MobileNetV2-based model. With model quantization and Neural Processing Unit (NPU) acceleration, efficient on-device inference is achieved. Experiments on a laboratory steel bridge verify the system’s high acquisition accuracy, precise clock synchronization, and strong anti-interference performance. Compared with inference on a general-purpose ARM CPU running the unquantized model, the quantized model deployed on the NPU achieves a 26× speedup in inference, a 35% reduction in power consumption, and less than 1% accuracy loss. This solution provides a cost-effective, reliable BSHM framework for small-to-medium-sized bridges, offering local intelligence and rapid response with strong potential for real-world applications. Full article

In the process of mosaicking regional synthetic aperture radar (SAR) intensity images, multiple images with significant brightness anomalies can cause a considerable number of pixels to exceed the grayscale quantization range. Applying traditional color harmonization methods increases this issue, causing a loss of brightness information. We propose a multi-objective gray consistency correction method designed explicitly for mosaicking regional SAR intensity images with brightness anomalies to address this. We constructed a two-objective optimization model to ensure regional image gray consistency and mitigate brightness information loss. The truncation values of brightness anomaly images were selected as decision variables, maximizing the overall gray consistency of overlapping image pairs and minimizing the number of pixels with grayscale values that were out of bounds as the objective functions. To synchronously solve the truncation values of brightness anomaly images and linear stretch parameters of all images, a hybrid framework that combines the non-dominated sorting genetic algorithm II (NSGA-II) with the quadratic programming (QP) algorithm was proposed. Two large-area experimental results show that the proposed method achieves a balanced optimization between gray consistency and brightness information loss for regional SAR intensity image mosaicking. Compared with the traditional method, our method reduces brightness information loss by 99.552–99.647% and 99.973–99.969%, respectively, while maintaining better peak signal-to-noise ratio performance. Full article