Search

While existing research has explored control strategies in multi-dimensional fields, the interconnectedness between electromagnetic and vibrational fields remains relatively uncharted. To explore this intersection and harness its potential, we propose an intelligent programmable metasurface that modulates electromagnetic fields based on vibration intensity information. This paper introduces a groundbreaking approach that synergizes the physical fields of mechanical (vibrational) waves with electromagnetic waves, facilitating the detection and manipulation of information from both fields. By combining a programmable metasurface, vibration sensors, and microcontroller units, we have achieved regulation of the electromagnetic field through utilization of vibration intensity information. In this work, we have introduced six coding patterns that facilitate dual-beam scanning with variable deflection angles. A 20 × 20 metasurface is fabricated and measured, and the measured results are in good agreement with the simulated results. This research opens a new avenue for manipulating electromagnetic waves. Furthermore, the findings have the potential to impact a wide range of fields, including building structuralhealth monitoring, industrial production, mechanical equipment monitoring, and earthquake monitoring. [ABSTRACT FROM AUTHOR]

The demand for accurate health status assessment of bearings in rotating electrical machines is rising. However, traditional fault diagnosis methods based on deep learning are not effective in efficiently and intelligently determining the health condition of the bearings and also requires large memory, hence constraining their use in low-cost microcontrollers. In this work, combination of short time Fourier transform (STFT) with Ostu's threshold method and MobileNet-V2 with U-Net (MV2UNet) is proposed for rolling bearing fault health status. The proposed method obtains the STFT images of the raw vibration signals from the laboratory experimental setup. Then the Ostu's threshold method is used to make the labels for STFT images. Finally, the proposed method is trained with these labelled images to detect the health status of each bearing fault. The proposed model achieved the Dice coefficient is 0.9834 and the intersection over union is 0.9479. The main advantage of the proposed model has low memory requirements, which makes it well-suited for implementation in affordable hardware devices like microcontrollers. Finally, the proposed method result is compared with U-Net, DeepLabV3+ with MobileNet-V2 and DeepLabV3+ with ResNet-50. [ABSTRACT FROM AUTHOR]

Generation of hidden attractor with complicated phase portrait in chaotic system with no equilibrium has presented a new research focus in the past decade. However, the existing approaches usually follow the rule that you reap what you sow, i.e., taking an no-equilibrium chaotic system as the seed. In this paper, a novel approach to the generation of no-equilibrium multi-fold hidden attractors is presented. The offset boosting and the operation of complex number are applied to several cases, including the seed chaotic systems with no equilibrium, with single unstable node, or with single stable node-focus. In specific, the offset boosting shifts the single non-zero equilibrium to the origin, then the operation of complex number rules out the equilibrium in the folded system and generates multi-fold trajectories. The highlight is that the proposed approach is not limited to the no-equilibrium seed system, but also applicable for different types of single-equilibrium seed systems, even the seed system with a single line of equilibrium. The detailed numerical simulations and experiments confirmed the feasibility of the proposed approach. Finally, an image encryption algorithm and its practical microcontroller-based implementation are presented to support the potential application. • Systematic approach for folding trajectory of chaotic system. • New multi-fold chaotic hidden attractors with no equilibrium. • New chaos-based encryption algorithm for image security. • Dynamic memory scheme for microcontroller implementation. [ABSTRACT FROM AUTHOR]

This proposed work investigates the performance of dc voltage of a three-phase Active Front-End (AFE) Sinusoidal Pulse Width Modulated (SPWM) rectifier during load switching. To obtain desired performances, a transfer function is derived in synchronous reference frame (dq), from which the gain of the PI controllers are estimated and observed the performance accordingly. In this research, the load current is feed-forwarded with d-axis current by a suitable choice of gain factor, which results a fractional feedback d-axis current control and improves the transient behaviour simultaneously. This will unalter the other performance parameters of the system such as, UPF operation, less Total Harmonic Distortion (THD) of input current, dc voltage boost etc. All the simulation results exhibits satisfactory performance and validated with a prototype developed using STM32F303RE microcontroller accordingly. [ABSTRACT FROM AUTHOR]

Copyright of Przegląd Elektrotechniczny is the property of Przeglad Elektrotechniczny and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Emergency alert systems (EASs) have been deployed in some countries in order to broadcast emergency alerts and warning messages to the public. In this letter, we describe an innovative electronic embedded solution, named Firetec switch, intended to be placed in the FM radio stations. This switch will be supported by a server placed at the authorized officials, with the capability to generate the audio alerting messages. One interesting challenge is to deliver the messages only to the local public, in the catastrophe neighborhood, by using FM radio stations. This letter focuses on the description of the Firetec switch hardware and software. [ABSTRACT FROM AUTHOR]

INTRODUCTION: The widespread use of smart wearable devices in various fields, including healthcare and sports, underscores the importance of their application in enhancing physical exercise among college students. Recent advancements in technology have facilitated the development of sophisticated methods to assess and predict physical activity outcomes, making their evaluation increasingly critical. OBJECTIVES: This study aims to develop a reliable assessment model for smart wearable devices used in college students' sports activities. The objective is to accurately predict and evaluate the effectiveness of these devices in improving students' physical health and promoting lifelong sports habits. Ultimately, the research seeks to integrate advanced computational methods to enhance the accuracy of physical exercise assessments. METHODS: The research introduces a novel assessment model that combines a zebra behavior-based heuristic optimization algorithm with a convolutional neural network (CNN). By analyzing user behavior data from wearable devices, the model constructs an evaluation index system tailored for college sports activities. The approach optimizes the parameters of the CNN using the zebra optimization algorithm, ensuring enhanced prediction accuracy. RESULTS: The evaluation model demonstrated high accuracy, with a significant improvement in predicting the outcomes of physical exercises among college students. Comparative analyses with traditional methods revealed that the new model reduced prediction errors and increased real-time performance metrics. Specifically, the model achieved a lower root mean square error (RMSE) in simulation tests, indicating more precise assessments. Figures and statistical data provided in the study illustrate the model's superior performance across various parameters. CONCLUSION: The developed assessment model significantly advances the application of smart wearable devices in monitoring and enhancing college students' physical activities. By integrating cutting-edge algorithms, the study not only improves the accuracy of exercise assessments but also contributes to the broader understanding of technology's role in health and fitness education. Future research could further refine this model by incorporating additional sensors and data points to expand its applicability and robustness. [ABSTRACT FROM AUTHOR]

The concept of a global Internet of Things (IoT), as proposed by Bart, revolutionizes connectivity by assigning unique digital identities to everyday objects, thereby enabling the development of smarter devices. However, the advancement and expansion of the IoT face significant obstacles and constraints, including energy efficiency and memory usage, which require further investigation. To address these challenges, this study presents a novel framework named IoT.js. This framework aims to facilitate the interconnection of lightweight devices within the web-based IoT ecosystem. These devices, ranging from microcontrollers to those with limited memory capacities, stand to benefit from IoT.js’s utilization of JavaScript for IoT application development. By promoting collaboration among lightweight devices with small memory sizes, IoT.js offers a promising solution to the resource constraints encountered in IoT deployments. This study contributes to the advancement of the IoT landscape by introducing a new approach that not only enables the efficient use of limited resources but also facilitates the seamless interconnection of lightweight devices within the IoT network. Additionally, the study conducts performance analysis to measure the efficacy of the proposed framework. Through rigorous evaluation of key metrics, such as energy efficiency and memory usage, the research findings validate the effectiveness of IoT.js in addressing the challenges associated with IoT deployment. Overall, the proposed IoT.js based approach represents a significant step forward in enhancing interconnectivity within the IoT ecosystem, thereby unlocking new possibilities for the development of innovative IoT applications and services. [ABSTRACT FROM AUTHOR]

In recent years, various solutions have been developed to control power electronic converters using devices available on the market that are powerful and easy to use. These solutions, in most cases, offer high performance. However, these have high implementation costs because the required devices are expensive. For this reason, this document presents the implementation of two discrete-time controllers widely used in the literature for a boost converter implemented on a low-cost platform. The objective is to obtain a constant voltage at the converter's output for photovoltaic system applications. The proportional-integral control is implemented as the first case, and the second case is a sliding mode control. In addition, a prior analysis is presented through simulation. Both control algorithms are implemented on the TMS320F28379D microcontroller from Texas Instruments through the same manufacturer's integrated development software based on an optimized C/C++ language compiler. The results of the non-linear algorithm reveal better performance in reducing the time response, the overshoot of the transient state, and the steady-state error. Finally, the significant economic savings associated with the implementation costs of the controllers tested on a low-cost platform differentiate this work from other similar ones. [ABSTRACT FROM AUTHOR]

With the rapid development of the Industrial Internet of Things in rotating machinery, the amount of data sampled by mechanical vibration wireless sensor networks (MvWSNs) has increased significantly, straining bandwidth capacity. Concurrently, the safety requirements for rotating machinery have escalated, necessitating enhanced real-time data processing capabilities. Conventional methods, reliant on experiential approaches, have proven inefficient in meeting these evolving challenges. To this end, a fault detection method for rotating machinery based on mobileNet in MvWSNs is proposed to address these intractable issues. The small and light deep learning model is helpful to realize nearly real-time sensing and fault detection, lightening the communication pressure of MvWSNs. The well-trained deep learning is implanted on the MvWSNs sensor node, an edge computing platform developed via embedded STM32 microcontrollers (STMicroelectronics International NV, Geneva, Switzerland). Data acquisition, data processing, and data classification are all executed on the computing- and energy-constrained sensor node. The experimental results demonstrate that the proposed fault detection method can achieve about 0.99 for the DDS dataset and an accuracy of 0.98 in the MvWSNs sensor node. Furthermore, the final transmission data size is only 0.1% compared to the original data size. It is also a time-saving method that can be accomplished within 135 ms while the raw data will take about 1000 ms to transmit to the monitoring center when there are four sensor nodes in the network. Thus, the proposed edge computing method shows good application prospects in fault detection and control of rotating machinery with high time sensitivity. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive guide for the design and development of a power electronic converter, specifically focusing on the Buck converter. The guide aims to bridge the gap between theoretical knowledge and practical application, providing engineering students with a hands-on experience in digital control using the STM32 microcontroller. The workshop experience described covers all necessary steps, from the initial design and simulation using tools like MATLAB-Simulink and Plecs to the final implementation and testing of the converter. The educational value of this approach is highlighted, emphasizing the importance of practical engagement in understanding complex concepts related to power electronics. [ABSTRACT FROM AUTHOR]

This paper presents a high-frequency (HF) magnetic pulse generator designed for low-intensity transcranial magnetic stimulation (LI-TMS) applications. HF pulse stimulation can induce a strong electric field with minimal current and enhance the penetration depth of the electric field in human tissue. The HF magnetic pulse generator was designed and fabricated using a microcontroller unit, gate driver, full-bridge coil driver, and stimulation coil. Measurements with a full-bridge circuit supply voltage of 10 V demonstrated an electric field intensity of 6.8 Vpp/m at a frequency of 1 MHz with a power dissipation of 2.45 W. Achieving a similar electric field intensity at a frequency of 100 kHz required approximately ten times the coil current. Additionally, a quasi-resonant LC load was introduced by connecting a capacitor in series with the stimulation coil, which set the resonant frequency to approximately 10% higher than the frequency of 1 MHz. This approach reduced the coil impedance, achieving higher current with the same bias supply voltage. Experimental results showed an enhanced electric field intensity of 19.1 Vpp/m with a supply voltage of only 1.8 V and reduced power dissipation of 1.11 W. The proposed HF pulse train with quasi-resonant coil system is expected to enable a low-power LI-TMS system. [ABSTRACT FROM AUTHOR]

This paper presents a single-phase Full-Bridge (FB) inverter with a hybrid commutation technique designed to reduce the harmonic distortion caused by the loss of the controller capability around the zero-crossing point in the unipolar commutation region. The hybrid modulation changes from unipolar to bipolar commutation under the loss of the reference control, improving the robustness and efficiency of the method. The commutation technique improves the switching performance and reduces the switching losses. Simulation models are developed in MATLAB/Simulink R2023b to evaluate their performance under different operating conditions. The results show that the proposed commutation technique can achieve high efficiency, low total harmonic distortion (THD), and fast dynamic response. The experimental implementation of sliding mode control (SMC) implemented in an STM32 microcontroller confirms that the hybrid commutation technique can reduce the THD by 0.96 percentage points for local (off-grid) loads and up to 2.45 in an industrial grid-tie network, compared with unipolar commutation. These findings highlight the potential of the proposed modulation technique for applications like solar panels and offer crucial insights for ongoing research and development in this field. [ABSTRACT FROM AUTHOR]

This study aims to design and evaluate a wireless electronic stethoscope that can transmit heart sound using Bluetooth HC-05 and Bluetooth 5.0 transmitter. This novel design contributes to the remote diagnosis and monitoring of heart conditions, especially for patients with infectious diseases. The heart sound signals are captured using a mic condenser mic, amplified, filtered, and converted to digital data by a microcontroller. The data are then transmitted by Bluetooth HC-05 to a module and by Bluetooth 5.0 transmitter to a headset. The quality-of-service parameters such as throughput, delay, and packet loss ratio (PLR) of the data transmission at different distances are measured. The results show that the wireless electronic stethoscope can transmit heart sound data with a small PLR of 0.10% and a throughput of 1002.5 bps. The study concludes that the wireless electronic stethoscope is an effective and useful device for examining heart conditions remotely, without compromising the functionality of the device. [ABSTRACT FROM AUTHOR]

Chips must be reliably segmented and evacuated from the cutting zone for effective deep hole drilling. Drilling with low-frequency axial vibrations ensures these useful effects because cutting edges periodically leave the cutting zone. Useful tool vibrations can be maintained using a special self-vibratory drilling head. The drilling head has an elastic element and ensures the self-excitation of vibrations due to the regenerative effect. However, high damping in the cutting zone suppresses axial self-vibrations and renders such a drilling head inexpedient for industry. This study develops a novel system of adaptive control for the vibration drilling process. The control objective is to maintain a specified peak-to-peak (PTP) value of vibration displacements. Due to the in-process adaptation of the feedback gain, the control system supplies additional energy if vibrations are not self-excited and removes energy if the PTP vibration displacements are greater than the specified value. To test the workability of the system, an experimental setup was made. In the setup, the actuator force acts on an elastically fixed workpiece. The dynamic properties of the setup are equivalent to those of the vibration drilling head. The algorithm of feedback gain adaptation was implemented with a microcontroller. A number of experiments for different drilling regimes revealed that the control system successfully maintains the specified PTP value of displacements. The developed control system can be implemented on a vibration drilling head because only an accelerometer is required for control and the required actuator force is under 100 N. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have been applied in many pattern recognition or object detection applications. DNNs generally consist of millions or even billions of parameters. These demanding computational storage and requirements impede deployments of DNNs in resource-limited devices, such as mobile devices, micro-controllers. Simplification techniques such as pruning have commonly been used to slim DNN sizes. Pruning approaches generally quantify the importance of each component such as network weight. Weight values or weight gradients in training are commonly used as the importance metric. Small weights are pruned and large weights are kept. However, small weights are possible to be connected with significant weights which have impact to DNN outputs. DNN accuracy can be degraded significantly after the pruning process. This paper proposes a roulette wheel-like pruning algorithm, in order to simplify a trained DNN while keeping the DNN accuracy. The proposed algorithm generates a branch of pruned DNNs which are generated by a roulette wheel operator. Similar to the roulette wheel selection in genetic algorithms, small weights are more likely to be pruned but they can be kept; large weights are more likely to be kept but they can be pruned. The slimmest DNN with the best accuracy is selected from the branch. The performance of the proposed pruning algorithm is evaluated by two deterministic datasets and four non-deterministic datasets. Experimental results show that the proposed pruning algorithm generates simpler DNNs while DNN accuracy can be kept, compared to several existing pruning approaches. [ABSTRACT FROM AUTHOR]

In this study, a new low-cost, three-degree-of-freedom force sensor is developed to measure Ground Reaction Forces (GRFs) and to be used in the safe control of active transfemoral prosthesis. Initially, the proposed sensor was designed with the Finite Element Method (FEM). Then, the sensor's control board was developed to include an electronic circuit with its microcontroller module, four load cell amplifiers, and an orientation sensor. A test platform was also developed to conduct the sensor tests. To test the accuracy of the results obtained from the developed test platform, the same tests were also carried out with a commercial sensor and similar results were obtained, thus proving that the sensor is suitable for use in prosthetics. [ABSTRACT FROM AUTHOR]

Crop yield prediction is a crucial area in agriculture that has a large impact on the economy of a country. This article proposes a crop yield prediction framework based on Internet of Things and edge computing. We have used a fifth generation network device referred to as femtolet as the edge device. The femtolet is a small cell base station that has high storage and high processing ability. The sensor nodes collect the soil and environmental data, and then the collected data is sent to the femtolet through the microcontrollers. The femtolet retrieves the weather‐related data from the cloud, and then processes the sensor data and weather‐related data using Bi‐LSTM. The femtolet after processing the data sends the generated results to the cloud. The user can access the results from the cloud to predict the suitable crop for his/her land. This is observed that the suggested framework provides better accuracy, precision, recall, and F1‐score compared to the state‐of‐the‐art crop yield prediction frameworks. This is also demonstrated that the use of femtolet reduces the latency by ˜25% than the conventional edge‐cloud framework. [ABSTRACT FROM AUTHOR]

In recent years, there has been a trend towards integrating functions using a small number of microcontrollers instead of employing multiple microcontrollers across various environments. This shift underscores the need for a hypervisor capable of efficiently utilizing resources while imposing minimal overhead. Addressing this demand, this paper introduces a hypervisor employing dynamic round-robin scheduling, which flexibly adjusts time quantum allocation based on the urgency of each OS. Furthermore, a monitor mode is devised to oversee resource allocation among multiple OSs. To enhance responsiveness while managing these OSs, ultra-light context-switching is implemented within the monitor mode. The proposed system demonstrates a notable reduction in execution time, approximately 19% compared to traditional round-robin scheduling. Additionally, in terms of energy efficiency, the proposed system yields a 34% reduction in energy consumption compared to existing methods. Notably, the ultra-light context-switching mechanism consumes only about 5% of the processing cycle when compared to FreeRTOS. [ABSTRACT FROM AUTHOR]

Improving traffic flow efficiency has become more important due to the growing number of vehicles in urban areas, and this requires optimizing traffic control systems. In order to reduce traffic, a smart traffic control system using infrared sharp sensors to count vehicles at intersections is proposed in this paper. The system uses sensors to measure distances to a fixed barrier, accurately counting vehicles while ignoring pedestrians. It was originally designed for four-way intersections but is adaptable to various junction types. Each lane's unique count is controlled by a separate Arduino Nano Board, and the data is saved in microcontrollers. Following the aggregation and processing of these counts, an Arduino Mega Board modifies the traffic light timings in response to actual vehicle flow. [ABSTRACT FROM AUTHOR]

Computer numerical control (CNC) machine tools mainly use transmission elements such as screws and gears as drive systems. To obtain better accuracy, equipment manufacturers apply pre-pressure to the screw to reduce the occurrence of backlash errors. Backlash errors are one of the important factors affecting positioning accuracy. When the pre-pressure fails, a backlash error occurs. Backlash error can cause abnormal vibration or drive delays in CNC drive systems, leading to reduced transmission efficiency and poor positioning accuracy. Therefore, in most research, vibration sensors are installed on the fixed end of the screw or the nut to detect abnormal phenomena and to estimate the backlash error using the algorithmic model. This traditional method has been established on the basis of the relationship between the amount of vibration and backlash error using an algorithmic model. The backlash can be estimated using this traditional method. However, this traditional method cannot directly sense backlash errors, and the accuracy of the measurement is limited by the algorithm model. Therefore, in this study, we attempted to use a photoelectric switch sensor combined with a microcontroller unit to detect the backlash errors of the CNC drive system. This system can detect a time change of 10 µs. After error corrections, the gain values of each backlash amount and delay time can be used to predict the backlash amount. Through the final verification with commercially available instruments, the system accuracy was found to reach 0.001 mm on the linear axis and 0.001° on the rotating axis. Owing to the streamlined sensing principle of the proposed system, in the future, the system can be integrated into the relevant rotary table components or within the CNC drive system. [ABSTRACT FROM AUTHOR]

In this work, we present a study on seat suspension technology that integrates pneumatic muscles, marking a significant advancement in active vibration control. This innovative approach addresses the limitations of traditional suspension systems, providing enhanced comfort and adaptability. A key achievement is the development of a mathematical model for controlling horizontal seat vibration, which serves as a valuable design tool for evaluating seat suspension under various conditions and control strategies. The creation of a custom microcontroller, benchmarked against a standard from National Instruments, highlights the practical applications of this research. Positive results suggest a promising future for this technology in industrial settings, where vibration reduction is critical. The system's scalability and user-adjustable signal levels further enhance its potential for widespread industrial adoption. [ABSTRACT FROM AUTHOR]

Electric mobility is pervasive and strongly affects everyone in everyday life. Motorbikes, bikes, cars, humanoid robots, etc., feature specific battery architectures composed of several lithium nickel oxide cells. Some of them are connected in series and others in parallel within custom architectures. They need to be controlled against over current, temperature, inner pressure and voltage, and their charge/discharge needs to be continuously monitored and balanced among the cells. Such a battery management system exhibits embarrassingly parallel computing, as hundreds of cells offer the opportunity for scalable and decentralized monitoring and control. In recent years, tiny machine learning has emerged as a data-driven black-box approach to address application problems at the edge by using very limited energy, computational and storage resources to achieve under mW power consumption. Examples of tiny devices at the edge include microcontrollers capable of 10–100 s MHz with 100 s KiB to few MB embedded memory. This study addressed battery management systems with a particular focus on state-of-charge prediction. Several machine learning workloads were studied by using IEEE open-source datasets to profile their accuracy. Moreover, their deployability on a range of microcontrollers was studied, and their memory footprints were reported in a very detailed manner. Finally, computational requirements were proposed with respect to the parallel nature of the battery system architecture, suggesting a per cell and per module tiny, decentralized artificial intelligence system architecture. [ABSTRACT FROM AUTHOR]

Simulation-based Fault Injection (FI) is crucial for validating system behaviour in safety-critical applications, such as the automotive industry. The ISO 26262 standard's Part 11 extension provides failure modes for digital components, driving the development of new fault models to assess software-implemented mechanisms against random hardware failures (RHF). This paper proposes a Fault Injection framework, QEFIRA, and shows its ability to achieve the failure modes proposed by Part 11 of the ISO 26262 standard and estimate relevant metrics for safety mechanisms. QEFIRA uses QEMU to inject permanent and transient faults during runtime, whilst logging the system state and providing automatic post-execution analysis. Complemented with a confusion matrix, it allows us to gather standard compliant metrics to characterise and evaluate different designs in the early stages of development. Comparatively to the native QEMU implementation, the tool only shows a slowdown of 1.4 × for real-time microcontroller-based applications. [ABSTRACT FROM AUTHOR]

Hybrid energy storage systems significantly impact the renewable energy sector due to their role in enhancing grid stability and managing its variability. However, implementing these systems requires advanced control strategies to ensure correct operation. This paper presents an algorithm for designing the power and control stages of a hybrid energy storage system formed by a battery, a supercapacitor, and a bidirectional Zeta converter. The control stage involves an adaptive sliding-mode controller co-designed with the power circuit parameters. The design algorithm ensures battery protection against high-frequency transients that reduce lifespan, and provides compatibility with low-cost microcontrollers. Moreover, the continuous output current of the Zeta converter does not introduce current harmonics to the battery, the microgrid, or the load. The proposed solution is validated through an application example using PSIM electrical simulation software (version 2024.0), demonstrating superior performance in comparison with a classical cascade PI structure. [ABSTRACT FROM AUTHOR]

The paper presents the essential theoretical elements related to the construction and operation of numerical control machines, starting from a study of the theoretical aspects related to the design of a CNC typewriter. The block diagrams of the machine, the interconnections between the component blocks and the operation of the whole system are highlighted. The paper also describes the implementation of the typewriter. It starts from a detailed diagram of the wiring and connections between the component elements, up to the presentation and commentary of how to create the program for the microcontroller used. Finally, the testing and operation of this CNC is detailed, from the design of the drawing to its actual realization, with the help of the designed and implemented assembly. CNC systems allow the repetitive production of the same parts, exactly the same and without deviations. Unlike a human operator who cannot execute two identical parts, the repeatability achieved by machines with numerical controls is clearly superior, so the reproducibility component is ensured. [ABSTRACT FROM AUTHOR]

Environmental sound classification (ESC) is one of the important research topics within the nonspeech audio classification field. While deep neural networks (DNNs) have achieved significant advances in ESC recently, their high computational and memory demands render them highly unsuitable for direct deployment on resource-constrained Internet of Things (IoT) devices based on microcontroller units (MCUs). To address this challenge, we propose a novel DNN compression framework specifically designed for such devices. On the one hand, we leverage pruning techniques to significantly compress the large number of model parameters in DNNs. To reduce the accuracy loss that follows pruning, we propose a knowledge distillation scheme based on feature information from multiple intermediate layers. On the other hand, we design a two-stage quantization-aware knowledge distillation scheme to mitigate the accuracy degradation of mandatory quantization required by MCU hardware. We evaluate our framework on benchmark ESC datasets (UrbanSound8K, ESC-50) using the STM32F746ZG device. The experimental results demonstrate that our framework can achieve compression rates up to 97% while maintaining competitive inference performance compared to the uncompressed baseline. [ABSTRACT FROM AUTHOR]

We propose an inhibitory control system for downhill turning by using a pre-installed friction brake mounted on a manual wheelchair. The braking force of the wheel is controlled by an added DC geared motor that pulls the brake wire in accordance with the ground angle. The proposed automatic braking system can reduce unexpected turns on downhill slopes. The proposed control system is also designed to be installed as an add-on device for manual wheelchairs. The effectiveness of the proposed system is verified using a wheelchair through a slope running experiments. [ABSTRACT FROM AUTHOR]

The integration of home automation systems has become increasingly prevalent, driven by advancements in sensor technologies and microcontroller capabilities. This paper presents the design, implementation, and evaluation of a comprehensive home automation system utilizing various sensors and control mechanisms. The system includes motion detectors, thermal sensors, presence sensors, light sensors, and devices such as fans and lighting systems. The effectiveness of the system in enhancing energy efficiency, comfort, and convenience is evaluated based on its real-world performance. [ABSTRACT FROM AUTHOR]

An Eggplant Fruit and Shoot Borer (EFSB) is a disease that affects the entirety of the eggplant fruit if not detected. Hence, a detector was proposed in the form of a handheld gun. It was designed and developed to non-invasively classify eggplant fruits that are noninfested and infested with EFSB. Using an Arduino Nano as its microcontroller and a near-infrared spectroscopy (NIRS) module, insect infestation is determined and displayed through its OLED display. Measured reflectance data through the NIRS module of the detector is then stored inside a MicroSD module for further use. Since the prototype was developed for online monitoring, portability was given of utmost importance, pattering the design in the form of a handheld gun, inside of which was powered by a 9V rechargeable battery. The 3D-printed chassis of the detector houses the aforementioned components and modules, alongside with switches for power and near-infrared detection. Through Support Vector Machine (SVM), the classifier model was trained and developed using Jupyter and was extracted as a C++ code for the Arduino Nano module. Compared with a farmer's traditional performance in terms of accuracy, precision, and speed, the prototype performed better with an accuracy of 84%, precision of 72.83%, and an average speed of 9.736 seconds [ABSTRACT FROM AUTHOR]

Running machine learning algorithms for image classification locally on small, cheap, and low-power microcontroller units (MCUs) has advantages in terms of bandwidth, inference time, energy, reliability, and privacy for different applications. Therefore, TinyML focuses on deploying neural networks on MCUs with random access memory sizes between 2 KB and 512 KB and read-only memory storage capacities between 32 KB and 2 MB. Models designed for high-end devices are usually ported to MCUs using model scaling factors provided by the model architecture's designers. However, our analysis shows that this naive approach of substantially scaling down convolutional neural networks (CNNs) for image classification using such default scaling factors results in suboptimal performance. Consequently, in this paper we present a systematic strategy for efficiently scaling down CNN model architectures to run on MCUs. Moreover, we present our CNN Analyzer, a dashboard-based tool for determining optimal CNN model architecture scaling factors for the downscaling strategy by gaining layer-wise insights into the model architecture scaling factors that drive model size, peak memory, and inference time. Using our strategy, we were able to introduce additional new model architecture scaling factors for MobileNet v1, MobileNet v2, MobileNet v3, and ShuffleNet v2 and to optimize these model architectures. Our best model variation outperforms the MobileNet v1 version provided in the MLPerf Tiny Benchmark on the Visual Wake Words image classification task, reducing the model size by 20.5% while increasing the accuracy by 4.0%. [ABSTRACT FROM AUTHOR]

Hand gesture recognition using a camera provides an intuitive and promising means of human-computer interaction and allows operators to execute commands and control machines with simple gestures. Research in hand gesture recognition-based control systems has garnered significant attention, yet the deploying of microcontrollers into this domain remains relatively insignificant. In this study, we propose a novel approach utilizing micro-hand gesture recognition built on micro-bottleneck Residual and micro-bottleneck Conv blocks. Our proposed model, comprises only 42K parameters, is optimized for size to facilitate seamless operation on resource-constrained hardware. Benchmarking conducted on STM32 microcontrollers showcases remarkable efficiency, with the model achieving an average prediction time of just 269ms, marking a 7× faster over the state-of-art model. Notably, despite its compact size and enhanced speed, our model maintains competitive performance result, achieving an accuracy of 99.6% on the ASL dataset and 92% on OUHANDS dataset. These findings underscore the potential for deploying advanced control methods on compact, costeffective devices, presenting promising avenues for future research and industrial applications. [ABSTRACT FROM AUTHOR]

The Trusted Execution Environment (TEE) is designed to establish a safe environment that prevents the execution of unauthenticated programs. The nature of TEE is a continuous verification process with hashing, signing, and verifying. Such a process is called the Chain-of-Trust, derived from the Root-of-Trust (RoT). Typically, the RoT is pre-programmed, hard-coded, or embedded in hardware, which is locally produced and checked before booting. The TEE employs various cryptographic processes throughout the boot process to verify the authenticity of the bootloader. It also validates other sensitive data and applications, such as software connected to the operating system. TEE is a self-contained environment and should not serve as the RoT or handle secure boot operations. Therefore, the issue of implementing hardware for RoT has become a challenge that requires further investigation and advancement. The main objective of this proposal is to introduce a secured RISC-V-based System-on-Chip (SoC) architecture capable of securely booting a TEE using a versatile boot program while maintaining complete isolation from the TEE processors. The suggested design has many cryptographic accelerators essential for the secure boot procedure. Furthermore, a separate 32-bit MicroController Unit (MCU) is concealed from the TEE side. This MCU manages sensitive information, such as the root key, and critical operations like the Zero Stage BootLoader (ZSBL) and key generation program. Once the RoT is integrated into the isolated sub-system, it becomes completely unavailable from the TEE side, even after booting, using any method. Besides providing a secured boot flow, the system is integrated with essential crypto-cores supporting Transport Layer Security (TLS) 1.3. The chip is finally fabricated using the Complementary Metal–Oxide–Semiconductor (CMOS) 180 nm process. [ABSTRACT FROM AUTHOR]

Currently, industrial engineers are witnessing a rapid development of innovation in modern industry and the integration of critical elements of Industry 4.0 into production processes in order to remain competitive. Such changes are characterized by a large amount of effort and financial resources. To successfully deploy these changes requires not only the purchase of hardware and software but also the training of employees and the modification of the company's organizational structure. The main objective of the article is to propose a framework for the modernization of SMEs to a level close to the Smart Factory by using the necessary attributes of Industry 4.0. The framework design is based on the initial state of a standard SME and consists of the design of fitting new IoT devices for efficient data collection, the design of a data warehouse for storing process data using Hadoop, and the integration of process- and operational-level data into the prepared data warehouse. The resulting design is developed in the form of a methodology and is generalized for use in manufacturing enterprises. The universal design is independent of the initial state of the enterprise. [ABSTRACT FROM AUTHOR]