Search Results (53)

Gas bubbles are one of the main disturbances encountered when dispensing drugs of microliter volumes using portable miniaturized systems based on piezoelectric diaphragm micropumps. The presence of a gas bubble in the pump chamber leads to the inaccurate administration of the required dose due to its impact on the flowrate. This is particularly important for highly concentrated drugs such as insulin. Different types of sensors are used to detect gas bubbles: inline on the fluidic channels or inside the pump chamber itself. These solutions increase the complexity, size, and cost of the microdosing system. To address these problems, a radically new approach is taken by utilizing the sensing capability of the piezoelectric diaphragm during micropump actuation. This work demonstrates the workflow to build a self-sensing micropump based on artificial intelligence methods on an embedded system. This is completed by the implementation of an electronic circuit that amplifies and samples the loading current of the piezoelectric ceramic with a microcontroller STM32G491RE. Training datasets of 11 micropumps are generated at an automated testbench for gas bubble injections. The training and hyper-parameter optimization of artificial intelligence algorithms from the TensorFlow and scikit-learn libraries are conducted using a grid search approach. The classification accuracy is determined by a cross-training routine, and model deployment on STM32G491RE is conducted utilizing the STM32Cube.AI framework. The finally deployed model on the embedded system has a memory footprint of 15.23 kB, a runtime of 182 µs, and detects gas bubbles with an accuracy of 99.41%. Full article

Dynamic harmonic estimation is important for the monitoring and control of power-electronic grids. But the high-precision dynamic harmonic estimation algorithms usually have a heavy computational burden and occupy a large memory space, making them difficult to implement in the embedded platform. Thus, the motivation of this paper lies in providing an estimator with low computational complexity and less storage space consumption. A purely real-valued fast dynamic harmonics estimator is proposed. Firstly, a purely real-valued estimation model is established based on the Taylor series expansion on the time-varying amplitude and phase angle. Secondly, the estimation filter bank is computed in the least-squares sense, and the corresponding estimation error is theoretically analyzed. Finally, the purely real-valued fast dynamic harmonics estimator is designed. The advantage includes significantly reducing the computational complexity and memory space consumption while maintaining high-precision estimation. The testing results show that the proposed estimator can achieve the highest harmonics estimation precision under dynamic conditions. The frequency error, magnitude error, and phase angle error are less than 5 × 10⁻² Hz, 7 × 10⁻¹%, and 8 × 10⁻² degrees, respectively, which verifies the advantage of high-precision estimation. The proposed estimator achieves a computational speed-up of approximately 430, 396, and 330 times compared to the Prony method, ESPRIT method, and iterative Taylor Fourier transform method, respectively. The computational load rate for executing the proposed estimator on the embedded prototype using C6748 DSP for estimating 50 harmonics is approximately only 2.05%, which verifies the advantage of a low computational load rate. Full article

Diabetes is a chronic condition, and traditional monitoring methods are invasive, significantly reducing the quality of life of the patients. This study proposes the design of an innovative system based on a microcontroller that performs real-time ECG acquisition and evaluates the presence of diabetes using an Edge-AI solution. A spectrogram-based preprocessing method is combined with a 1-Dimensional Convolutional Neural Network (1D-CNN) to analyze the ECG signals directly on the device. By applying quantization as an optimization technique, the model effectively balances memory usage and accuracy, achieving an accuracy of 89.52% with an average precision and recall of 0.91 and 0.90, respectively. These results were obtained with a minimal memory footprint of 347 kB flash and 23 kB RAM, showcasing the system’s suitability for wearable embedded devices. Furthermore, a custom PCB was developed to validate the system in a real-world scenario. The hardware integrates high-performance electronics with low power consumption, demonstrating the feasibility of deploying Edge-AI for non-invasive, real-time diabetes detection in resource-constrained environments. This design represents a significant step forward in improving the accessibility and practicality of diabetes monitoring. Full article

The field of physically interactive electronic games is rapidly evolving, driven by the fact that it combines the benefits of physical activities and the attractiveness of electronic games, as well as advancements in sensor technologies. In this paper, a new game was introduced, which is a special version of Bubble Soccer, which we named Q-eBall. It creates a dynamic and engaging experience by combining simulation and physical interactions. Q-eBall is equipped with a fall detection system, which uses an embedded electronic circuit integrated with an accelerometer, a gyroscopic, and a pressure sensor. An evaluation of the performance of the fall detection system in Q-eBall is presented, exploring its technical details and showing its performance. The system captures the data of players’ movement in real-time and transmits it to the game controller, which can accurately identify when a player falls. The automated fall detection process enables the game to take the required actions, such as transferring possession of the visual ball or applying fouls, without the need for manual intervention. Offline experiments were conducted to assess the performance of four machine learning models, which were K-Nearest Neighbors (KNNs), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM), for falls detection. The results showed that the inclusion of pressure sensor data significantly improved the performance of all models, with the SVM and LSTM models reaching 100% on all metrics (accuracy, precision, recall, and F1-score). To validate the offline results, a real-time experiment was performed using the pre-trained SVM model, which successfully recorded all 150 falls without any false positives or false negatives. These findings prove the reliability and effectiveness of the Q-eBall fall detection system in real time. Full article

In the era of ubiquitous connectivity facilitated by the Internet of Things (IoT), ensuring robust security mechanisms for communication channels among resource-constrained devices has become imperative. Elliptic curve Diffie–Hellman (ECDH) key exchange offers strong security assurances and computational efficiency. This paper investigates the challenges and opportunities of deploying ECDH key exchange protocols on resource-constrained IoT devices. We review the fundamentals of ECDH and explore optimization techniques tailored to the limitations of embedded systems, including memory constraints, processing power, and energy efficiency. We optimize the implementation of five elliptic curves and compare them using experimental results. Our experiments focus on electronic control units and sensors in vehicular networks. The findings provide valuable insights for IoT developers, researchers, and industry stakeholders striving to enhance the security posture of embedded IoT systems while maintaining efficiency. Full article

Underwater methane (CH₄) detection technology is of great significance to the leakage monitoring and location of marine natural gas transportation pipelines, the exploration of submarine hydrothermal activity, and the monitoring of submarine volcanic activity. In order to improve the safety of underwater CH₄ detection mission, it is necessary to study the effect of hydrogen sulfide (H₂S) in leaking CH₄ gas on sensor performance and harmful influence, so as to evaluate the health status and life prediction of underwater CH₄ sensor arrays. In the process of detecting CH₄, the accuracy decreases when H₂S is found in the ocean water. In this study, we proposed an explainable sorted-sparse (ESS) transformer model for concentration interval detection under industrial conditions. The time complexity was decreased to O (n log_n) using an explainable sorted-sparse block. Additionally, we proposed the Ocean X generative pre-trained transformer (GPT) model to achieve the online monitoring of the health of the sensors. The ESS transformer model was embedded in the Ocean X GPT model. When the program satisfied the special instructions, it would jump between models, and the online-monitoring question-answering session would be completed. The accuracy of the online monitoring of system health is equal to that of the ESS transformer model. This Ocean-X-generated model can provide a lot of expert information about sensor array failures and electronic noses by text and speech alone. This model had an accuracy of 0.99, which was superior to related models, including transformer encoder (0.98) and convolutional neural networks (CNN) + support vector machine (SVM) (0.97). The Ocean X GPT model for offline question-and-answer tasks had a high mean accuracy (0.99), which was superior to the related models, including long short-term memory–auto encoder (LSTM–AE) (0.96) and GPT decoder (0.98). Full article

The automotive sector faces escalating security risks due to advances in wireless communication technology. Expanding on our previous research using a sensor pairing technique and machine learning models to evaluate IoT sensor data reliability, this study broadens its scope to address security concerns in Connected and Autonomous Vehicles (CAVs). The objectives of this research include identifying and mitigating specific security vulnerabilities related to CAVs, thereby establishing a comprehensive understanding of the risks these vehicles face. Additionally, our study introduces two innovative pairing approaches. The first approach focuses on pairing Electronic Control Units (ECUs) within individual vehicles, while the second extends to pairing entire vehicles, termed as vehicle pairing. Rigorous preprocessing of the dataset was carried out to ensure its readiness for subsequent model training. Leveraging Support Vector Machine (SVM) and TinyML methods for data validation and attack detection, we have been able to achieve an impressive accuracy rate of 97.2%. The proposed security approach notably contributes to the security of CAVs against potential cyber threats. The experimental setup demonstrates the practical application and effectiveness of TinyML in embedded systems within CAVs. Importantly, our proposed solution ensures that these security enhancements do not impose additional memory or network loads on the ECUs. This is accomplished by delegating the intensive cross-validation to the central module or Roadside Units (RSUs). This novel approach not only contributes to mitigating various security loopholes, but paves the way for scalable, efficient solutions for resource-constrained automotive systems. Full article

With the development of the field of e-nose research, the potential for application is increasing in various fields, such as leak measurement, environmental monitoring, and virtual reality. In this study, we characterize electronic nose data as structured data and investigate and analyze the learning efficiency and accuracy of deep learning models that use unstructured data. For this purpose, we use the MOX sensor dataset collected in a wind tunnel, which is one of the most popular public datasets in electronic nose research. Additionally, a gas detection platform was constructed using commercial sensors and embedded boards, and experimental data were collected in a hood environment such as used in chemical experiments. We investigated the accuracy and learning efficiency of deep learning models such as deep learning networks, convolutional neural networks, and long short-term memory, as well as boosting models, which are robust models on structured data, using both public and specially collected datasets. The results showed that the boosting models had a faster and more robust performance than deep learning series models. Full article

Resistive random-access memory has emerged as a promising non-volatile memory technology, receiving substantial attention due to its potential for high operational performance, low power consumption, temperature robustness, and scalability. Two-dimensional nanostructured materials play a pivotal role in RRAM devices, offering enhanced electrical properties and physical attributes, which contribute to overall device improvement. In this study, the self-rectifying switching behavior in RRAM devices is analyzed based on molybdenum disulfide nanocomposites decorated with Pd on SiO₂/Si substrates. The switching layer integration of Pd and MoS₂ at the nanoscale effectively mitigates leakage currents decreasing from cross-talk in the RRAM array, eliminating the need for a separate selector device. The successful demonstration of the expected RRAM switching operation and low switching dispersion follows the application of a Pd nanoparticle embedding method. The switching channel layer is presented as an independent (Pd nanoparticle coating and MoS₂ nanosheet) nanocomposite. The switching layer length (4000 μm) and width (7000 μm) play an important role in a lateral-conductive-filament-based RRAM device. Through the bipolar switching behavior extraction of RRAM, the formation of the conductive bridges via electronic migration is explained. The fabricated Pd-MoS₂ synaptic RRAM device results in a high resistive current ratio for a forward/reverse current higher than 60 at a low resistance state and observes a memory on/off ratio of 10³, exhibiting stable resistance switching behavior. Full article

Electronic toll collection (ETC) data mining has become one of the hotspots in the research of intelligent expressway extension applications. Ensuring the integrity of ETC data stands as a critical measure in upholding data quality. ETC data are typical structured data, and although deep learning holds great potential in the ETC data restoration field, its applications in structured data are still in the early stages. To address these issues, we propose an expressway ETC missing transaction data restoration model considering multi-attribute features (MAF). Initially, we employ an entity embedding neural network (EENN) to automatically learn the representation of categorical features in multi-dimensional space, subsequently obtaining embedding vectors from networks that have been adequately trained. Then, we use long short-term memory (LSTM) neural networks to extract the changing patterns of vehicle speeds across several continuous sections. Ultimately, we merge the processed features with other features as input, using a three-layer multilayer perceptron (MLP) to complete the ETC data restoration. To validate the effectiveness of the proposed method, we conducted extensive tests using real ETC datasets and compared it with methods commonly used for structured data restoration. The experimental results demonstrate that the proposed method significantly outperforms others in restoration accuracy on two different datasets. Specifically, our sample data size reached around 400,000 entries. Compared to the currently best method, our method improved the restoration accuracy by 19.06% on non-holiday ETC datasets. The MAE and RMSE values reached optimal levels of 12.394 and 23.815, respectively. The fitting degree of the model to the dataset also reached its peak ($R^2$ = 0.993). Meanwhile, the restoration stability of our method on holiday datasets increased by 5.82%. An ablation experiment showed that the EENN and LSTM modules contributed 7.60% and 9% to the restoration accuracy, as well as 4.68% and 7.29% to the restoration stability. This study indicates that the proposed method not only significantly improves the quality of ETC data but also meets the timeliness requirements of big data mining analysis. Full article

This article presents the DTC-SVM approach for controlling a sensorless speed induction motor. To implement this approach, a practical prototype is built using a microcontroller, an embedded GPS module, and a memory card to collect real-time data during the driving route, such as road geographical data, speed, and time. These data are then utilized in the laboratory to implement the control law (DTC-SVM) on the electric vehicle. The d-q model of the induction motor is first presented to explain the requirements for calculating the rotor speed. Then, an adaptive model reference system speed estimator is developed based on the rotor flux, along with a controller and DTC-SVM strategy, which are implemented using the dSpace 1104 board to achieve the desired performance. The simulation results demonstrate satisfactory speed regulation with the proposed system. In this study too, an electronic differential system is modeled for the four wheels of an electric vehicle equipped with an integrated motor, all controlled by the DTC-SVM strategy. Vehicle speed and electrical vehicle steering angle variations, as well as wheel speeds estimated by code system, are verified using MATLAB/Simulink simulations. Full article

This paper introduces thorough comparative and interoperability analyses involving a browser-based P2P video streaming approach utilizing WebRTC (web real-time communication), along with WebRTC hybrid solutions developed using the React Native framework (for mobile) and the electron framework (for desktop and Raspberry Pi). The assessment is carried out based on various metrics, including CPU (central processing unit) load, RAM (random access memory) utilization, and network data consumption. The obtained findings highlight the potential of integrating WebRTC P2P video streaming into hybrid applications as a promising alternative for real-time video streaming applications in embedded systems; given that, compared to the current mainstreams, e.g., Chrome or Firefox, the proposed approach has superiority performance in terms of CPU load, RAM usage, and network occupancy. The results also demonstrated that interoperability is ensured between the two types of applications (web-based and hybrid-based one). Full article

The transition to sustainable or green(er) cities requires the development and implementation of many innovative technologies. It is vital to ensure that these technologies are themselves as sustainable and green as possible. In this context, smart materials offer excellent prospects for application. They are capable of performing a number of tasks (e.g., repair, opening/closing, temperature measurement, storage and release of thermal energy) without embedded electronics or power supplies. In this short review paper, we present some of the most promising smart material-based technologies for sustainable or green(er) cities. We will briefly present the state-of-the-art in smart concrete for the structural health monitoring and self-healing of civil engineering structures, phase-change materials (PCM) for passive air-conditioning, shape-memory materials (SMA) for various green applications, and meta-surfaces for green acoustics. To better illustrate the potential of some of the solutions discussed in the paper, we present, where appropriate, our most recent experimental results (e.g., embedded SAW sensors for the Structural Health Monitoring of concrete structures). The main aim of this paper is to promote green solutions based on smart materials to engineers and scientists involved in R&D projects for green(er) cities. Full article

The endurance of medium- and high-voltage electrical insulation is a key reliability element in a broad spectrum of applications that cover transmission and distribution levels, the transportation segment, the industrial environment, and power electronics-based energy-conversion systems. The high electric-field stress and high-frequency switching phenomena as well as the impact of environmental conditions lead to the occurrence of partial discharges (PD) and the subsequent deterioration of electrical insulation. Partial discharges usually occur inside solid insulation materials in tiny voids that may either be located adjacent to the electrodes or in the bulk of dielectric material. This effect refers to both AC and DC systems; however, AC voltage is usually much more intensive as compared to DC voltage. This paper describes a novel combined approach based on surface-resistance and potential mapping to reveal the effects of internal processes and the deterioration of insulating material due to the actions of partial discharges. To realize the research objective, the following two-step approach was proposed. Multi-point resistance mapping enables us to identify the spots of discharge channels, manifesting a-few-orders-of-magnitude-lower surface resistance as compared to untreated areas. In addition, surface-potential mapping that was stimulated by corona-charge deposition reflects quasi-equipotential clusters and the related polarity-dependent dynamics of charge decay. A high spatial and temporal resolution allows for the precise mapping and tracing of decay patterns. Experiments were carried out on polyethylene (PE) and Nomex specimens that contained embedded voids. During PD events, the effective discharge areas are identified along with the memory effects that originate from the accumulation of surface charges. Long-term aging processes may drive the formation of channels that are initiated from the deteriorated micro clusters, in turn, penetrating the bulk isolation. The presented methodology and experimental results extend the insight into PD mechanisms and internal surface processes. Full article

This work reports the first nanocrystalline SnON (7.6% nitrogen content) nanosheet n-type Field-Effect Transistor (nFET) with the transistor’s effective mobility (µ_eff) as high as 357 and 325 cm²/V-s at electron density (Q_e) of 5 × 10¹² cm⁻² and an ultra-thin body thickness (T_body) of 7 nm and 5 nm, respectively. At the same T_body and Q_e, these µ_eff values are significantly higher than those of single-crystalline Si, InGaAs, thin-body Si-on-Insulator (SOI), two-dimensional (2D) MoS₂ and WS₂. The new discovery of a slower µ_eff decay rate at high Q_e than that of the SiO₂/bulk-Si universal curve was found, owing to a one order of magnitude lower effective field (E_eff) by more than 10 times higher dielectric constant (κ) in the channel material, which keeps the electron wave-function away from the gate-oxide/semiconductor interface and lowers the gate-oxide surface scattering. In addition, the high µ_eff is also due to the overlapped large radius s-orbitals, low 0.29 m_o effective mass (m_e*) and low polar optical phonon scattering. SnON nFETs with record-breaking µ_eff and quasi-2D thickness enable a potential monolithic three-dimensional (3D) integrated circuit (IC) and embedded memory for 3D biological brain-mimicking structures. Full article