Embedded System Research Articles

AI and Cloud Computing in Healthcare: Transforming Patient Care with AWS and Java

A new era in healthcare is being ushered in by the convergence of artificial intelligence (AI) and cloud computing, which will significantly improve patient care through improved diagnosis, individualized treatment planning, and effective patient management. This article explores the potent combination of Java and Amazon Web Services (AWS) and how these technologies may be used to develop cutting-edge AI-driven healthcare solutions that optimize healthcare operations and dramatically enhance patient outcomes. Together with Java's robust and flexible programming environment, healthcare providers can leverage AWS's scalable infrastructure and advanced machine learning capabilities to create and implement sophisticated AI models that analyze massive amounts of medical data at a speed and accuracy never seen before. These developments are making it possible to make more accurate diagnoses, customized treatment plans, and proactive patient monitoring, which can result in better clinical judgment and possibly life-saving measures. But even as we consider the enormous positive effects these technologies have on society, we also have to face the ethical problems they raise, such as issues with data privacy, potential biases in algorithms, and unequal access to cutting-edge medical treatments. The goal of this thorough investigation is to present a fair assessment of the revolutionary potential of artificial intelligence (AI) and cloud computing in the healthcare industry, while also discussing the wider ramifications and obligations associated with incorporating these formidable technologies into our healthcare systems.

Artificial Intelligence for the Evaluation of Postures Using Radar Technology: A Case Study.

In the last few decades, major progress has been made in the medical field; in particular, new treatments and advanced health technologies allow for considerable improvements in life expectancy and, more broadly, in quality of life. As a consequence, the number of elderly people is expected to increase in the following years. This trend, along with the need to improve the independence of frail people, has led to the development of unobtrusive solutions to monitor daily activities and provide feedback in case of risky situations and falls. Monitoring devices based on radar sensors represent a possible approach to tackle postural analysis while preserving the person's privacy and are especially useful in domestic environments. This work presents an innovative solution that combines millimeter-wave radar technology with artificial intelligence (AI) to detect different types of postures: a series of algorithms and neural network methodologies are evaluated using experimental acquisitions with healthy subjects. All methods produce very good results according to the main parameters evaluating performance; the long short-term memory (LSTM) and GRU show the most consistent results while, at the same time, maintaining reduced computational complexity, thus providing a very good candidate to be implemented in a dedicated embedded system designed to monitor postures.

Energy-aware bio-inspired spiking reinforcement learning system architecture for real-time autonomous edge applications.

Mobile, low-cost, and energy-aware operation of Artificial Intelligence (AI) computations in smart circuits and autonomous robots will play an important role in the next industrial leap in intelligent automation and assistive devices. Neuromorphic hardware with spiking neural network (SNN) architecture utilizes insights from biological phenomena to offer encouraging solutions. Previous studies have proposed reinforcement learning (RL) models for SNN responses in the rat hippocampus to an environment where rewards depend on the context. The scale of these models matches the scope and capacity of small embedded systems in the framework of Internet-of-Bodies (IoB), autonomous sensor nodes, and other edge applications. Addressing energy-efficient artificial learning problems in such systems enables smart micro-systems with edge intelligence. A novel bio-inspired RL system architecture is presented in this work, leading to significant energy consumption benefits without foregoing real-time autonomous processing and accuracy requirements of the context-dependent task. The hardware architecture successfully models features analogous to synaptic tagging, changes in the exploration schemes, synapse saturation, and spatially localized task-based activation observed in the brain. The design has been synthesized, simulated, and tested on Intel MAX10 Field-Programmable Gate Array (FPGA). The problem-based bio-inspired approach to SNN edge architectural design results in 25X reduction in average power compared to the state-of-the-art for a test with real-time context learning and 30 trials. Furthermore, 940x lower energy consumption is achieved due to improvement in the execution time.

Design and implementation in power-efficient and thermal conductivity of vedic processor for embedded applications

An embedded system that handles critical applications requires power economy, performance and thermal management, and an efficient Vedic processor with highly efficienct thermal conductivity. The proposed contemporary processor architecture has been designed to use Vedic mathematics and elaborate power and thermal optimization approaches to formulate an Arithmetic Logic Unit (ALU). This ALU is based on Vedic Sutras to enable quick computation, high precision floating point operations, and low power consumption. Since thermal management leads to energy loss in the form of heat, the embedded processor’s thermal conductivity is enhanced using novel materials and unique ways of heat dissipation. This improves performance as well as power efficiency. The proposed approach uses extensive simulation thermal analysis by EDA tools to build an optimised embedded processor that consumes 35% less power, has 40% high thermal conductivity, is 25% faster, and utilizes 15% less area when compared to conventional embedded processors. This paper helps in furthering embedded systems research by showing how old mathematical ideas can be used in a new engineering approach to solve current technology issues. The suggested novel embedded system is more efficient and thermally resistant for IOT, mobile computing, and industrial control systems.

BUFIT: FINE-GRAINED DYNAMIC BURST FAULT INJECTION TOOL FOR EMBEDDED field programmable gate array TESTING

Fault injection (FI) is a well-known method to attack embedded systems, particularly advanced FPGAs and microcontrollers physically. The FPGA-based embedded system constitutes SRAM for configuration data storage. Multiple-bit upset is a main threat for FPGAs due to technology scaling and complex application bit files. Space environments additionally incur radiation threats to these devices. This paper proposes burst error modeling and a burst fault injection tool (BUFIT) to address these issues. BUFIT has been proposed with fine-grained and coarse-grained circuits. Built-in instrumented FPGA-based FI is proposed for effectively injecting MBUs in configuration memory with space adaptive rate for accurately estimating soft errors. Evaluation of proposed BUFIT on Kintex-7 target FPGA to various OR 1200-based workloads is given to analyze the speed up of the proposed technique. Results on the OR 1200 processor show that BUFIT is three and two orders of magnitude faster than existing DPR and SCFIT techniques. It uses only 0.4 % CLB overhead and has negligible impact on FFs of target SFPGAs.

A Machine Vision Method for Identifying Blade Tip Clearance in Wind Turbines.

This paper introduces a machine vision method for measuring the blade tip clearance in a wind turbine. An industrial personal computer (IPC) is installed in the nacelle of the wind turbine to continuously receive video data from a digital camera mounted at the bottom of the nacelle. Using the open-source computer vision (OpenCV) digital image processing library data base, the real-time trajectory of the turbine blades is determined from the video data. Furthermore, fast Fourier transform (FFT) analysis is performed for determining the operating frequency of the blades in the images. The amplitude analysis performed at this operating frequency reveals the pixel-based blade tip clearance, which is then used to calculate the actual clearance of the wind turbine. This value is subsequently transmitted to the main controller of the wind turbine. The main controller can enhance the operational safety of the wind turbine by implementing appropriate pitch control strategies to restrict and safeguard the blade tip clearance. The results obtained by conducting experiments on a 2.0 MW wind turbine unit validate the effectiveness of the proposed identification method. In this method, the blade tip clearance can be calculated effectively in real time, and both the video sampling rate and communication speed meet the requirements for controlling the blade pitch.

CANival: A multimodal approach to intrusion detection on the vehicle CAN bus

Vehicles of today are composed of over 100 electronic embedded devices known as Electronic Control Units (ECU), each of which controls a different component of the vehicle and communicates via the Controller Area Network (CAN) bus. However, unlike other network protocols, the CAN bus communication protocol lacks security features, which is a growing concern as more vehicles become connected to the Internet. To enable the detection of intrusions on the CAN bus, numerous intrusion detection systems (IDS) have been proposed. Although some are able to achieve high accuracy in detecting specific attacks, no IDS has been able to accurately detect all types of attacks against the CAN bus. To overcome the aforementioned issues, we propose a multimodal analysis framework named CANival, which consists of time interval-based and signal-based analyzers developed by designing a novel Time Interval Likelihood (TIL) model and optimizing an existing model CANet. Experimental results show that our multimodal IDS outperforms the base models and enhances the detection performance testing on two recent datasets, X-CANIDS Dataset and SynCAN, achieving average true positive rates of 0.960 and 0.912, and true negative rates of 0.997 and 0.996, respectively.

Advancements in TinyML: Applications, Limitations, and Impact on IoT Devices

Artificial Intelligence (AI) and Machine Learning (ML) have experienced rapid growth in both industry and academia. However, the current ML and AI models demand significant computing and processing power to achieve desired accuracy and results, often restricting their use to high-capability devices. With advancements in embedded system technology and the substantial development in the Internet of Things (IoT) industry, there is a growing desire to integrate ML techniques into resource-constrained embedded systems for ubiquitous intelligence. This aspiration has led to the emergence of TinyML, a specialized approach that enables the deployment of ML models on resource-constrained, power-efficient, and low-cost devices. Despite its potential, the implementation of ML on such devices presents challenges, including optimization, processing capacity, reliability, and maintenance. This article delves into the TinyML model, exploring its background, the tools that support it, and its applications in advanced technologies. By understanding these aspects, we can better appreciate how TinyML is transforming the landscape of AI and ML in embedded and IoT systems.

Markov-chain sampling for long-range systems without evaluating the energy.

In past decades, enormous effort has been expended to develop algorithms and even to construct special-purpose computers in order to efficiently evaluate total energies and forces for long-range-interacting particle systems, with the particle-mesh Ewald and the fast multipole methods as well as the "Anton" series of supercomputers serving as examples for biomolecular simulations. Cutoffs in the range of the interaction have also been used for large systems. All these methods require extrapolations. Within Markov-chain Monte Carlo, in thermal equilibrium, the Boltzmann distribution can, however, be sampled natively without evaluating the total energy. Using as an example the Lennard-Jones interaction, we review past attempts in this direction and then discuss in detail the class of cell-veto algorithms that allow for the fast, native sampling of the Boltzmann distribution without any approximation, extrapolation, or cutoff even for the slowly decaying Coulomb interaction. The computing effort per move remains constant with increasing system size, as we show explicitly. We provide worked-out illustrations and pseudocode representations of the discussed algorithms. Python scripts are made available in an associated open-source software repository.

TinyWolf — Efficient on-device TinyML training for IoT using enhanced Grey Wolf Optimization

Training a deep learning model generally requires a huge amount of memory and processing power. Once trained, the learned model can make predictions very fast with very little resource consumption. The learned weights can be fitted into a microcontroller to build affordable embedded intelligence systems which is also known as TinyML. Although few attempts have been made, the limits of the state-of-the-art training of a deep learning model within a microcontroller can be pushed further. Generally deep learning models are trained with gradient optimizers which predict with high accuracy but require a very high amount of resources. On the other hand, nature-inspired meta-heuristic optimizers can be used to build a fast approximation of the model’s optimal solution with low resources. After a rigorous test, we have found that Grey Wolf Optimizer can be modified for enhanced uses of main memory, paging and swap space among α,β,δ and ω wolves. This modification saved up to 71% memory requirements compared to gradient optimizers. We have used this modification to train the TinyML model within a microcontroller of 256KB RAM. The performances of the proposed framework have been meticulously benchmarked on 13 open-sourced datasets.

An Energy-Efficient Bayesian Neural Network Implementation Using Stochastic Computing Method.

The robustness of Bayesian neural networks (BNNs) to real-world uncertainties and incompleteness has led to their application in some safety-critical fields. However, evaluating uncertainty during BNN inference requires repeated sampling and feed-forward computing, making them challenging to deploy in low-power or embedded devices. This article proposes the use of stochastic computing (SC) to optimize the hardware performance of BNN inference in terms of energy consumption and hardware utilization. The proposed approach adopts bitstream to represent Gaussian random number and applies it in the inference phase. This allows for the omission of complex transformation computations in the central limit theorem-based Gaussian random number generating (CLT-based GRNG) method and the simplification of multipliers as AND operations. Furthermore, an asynchronous parallel pipeline calculation technique is proposed in computing block to enhance operation speed. Compared with conventional binary radix-based BNN, SC-based BNN (StocBNN) realized by FPGA with 128-bit bitstream consumes much less energy consumption and hardware resources with less than 0.1% accuracy decrease when dealing with MNIST/Fashion-MNIST datasets.

Design and Implementation of an Interactive Embedded System as a Low-Cost Remotely Operated Vehicle for Underwater Applications

The underwater environment is harsh and challenging for human life, prompting companies and researchers to develop advanced technologies for exploration. Building on previous work that applied a CNN-based method for underwater object classification, this paper focuses on the design and implementation of an interactive embedded system for a compact Remotely Operated Vehicle (ROV) with specific dimensions and weight. The primary goal is to capture real-time underwater video using remote control communication via Ethernet. The ROV is powered by five brushless motors controlled by a smart PID controller. Precise pulse-width modulation signals enhance stability during movements along three axes, enabling high-resolution video capture. The system utilizes the Raspberry Pi 3's computing power for motion control, positioning, temperature monitoring, and video acquisition. Experimental results demonstrate the system's capability to process 42 frames per second. A user-friendly graphical interface allows for remote ROV control across various operating systems. With a depth rating of 100 meters and speed of 0.148 m/s. This ROV surpasses human divers' limitations and holds significant potential for applications in surveillance, operations, maintenance, and measurement tasks underwater. The proposed ROV contributes to the advancement of underwater exploration technology by combining high performance with cost-effectiveness.

Design and implementation of a driving safety assistant system based on driver behavior

<p>These days, road accidents are one of Morocco's biggest problems. Fatigue, drowsiness, and driver behavior are among the primary causes.This research aims to develop an embedded system by image processing and computer vision to ensure driving safety by monitoring driver behavior and assist drivers to awaken from micro-sleep or fatigue due to long driving hours and various other reasons. Indeed, the driver inattention, drowsiness or driver fatigue can be detected. The suggested method is designed to support drivers if needed, based on the vehicle velocity. Once the driver crosses a certain speed limit, the program starts face detection and analyzing this data to determine whether the driver is tired, sleepy, or inattentive. This activates different alarm depending on the criticality level. It can sound a voice alert to help him wake up and drive more cautiously. The system is based on AI algorithms in image processing based on OpenCV libraries and the Python language to capture the movements of the driver's eyes and head when starting the automobile. Every algorithm is run on a Raspberry-Pi 4 card, and numerous experimentation series have demonstrated overall credible performance with success accuracy of over 93% in EAR and MAR calculations.</p>

A Lightweight Visual Understanding System for Enhanced Assistance to the Visually Impaired Using an Embedded Platform

Visually impaired individuals often face significant challenges in navigating their environments due to limited access to visual information. To address this issue, a portable, cost-effective assistive tool is proposed to operate on a low-power embedded system such as the Jetson Nano. The novelty of this research lies in developing an efficient, lightweight video captioning model within constrained resources to ensure its compatibility with embedded platforms. This research aims to enhance the autonomy and accessibility of visually impaired people by providing audio descriptions of their surroundings through the processing of live-streaming videos. The proposed system utilizes two distinct lightweight deep learning modules: an object detection module based on the state-of-the-art YOLOv7 model, and a video captioning module that utilizes both the Video Swin Transformer and 2D-CNN for feature extraction, along with the Transformer network for caption generation. The goal of the object detection module is for providing real-time multiple object identification in the surrounding environment of the blind while the video captioning module is to provide detailed descriptions of the entire visual scenes and activities including objects, actions, and relationships between them. The user interacts via a headphone with the proposed system using a specific audio command to trigger the corresponding module even object detection or video captioning and receiving an audio description output for the visual contents. The system demonstrates satisfactory results, achieving inference speeds between 0.11 to 1.1 seconds for object detection and 0.91 to 1.85 seconds for video captioning, evaluated through both quantitative metrics and subjective assessments.

Smart Car Parking System

In this fast-growing economy, the number of vehicle users is growing tremendously, wasting a significant amount of time and fuel while searching for an available parking space. This work highlights the optimum utilization of parking slots without the physical intervention of humans by making use of an IoT-integrated embedded system. This study aimed to create a mobile application for car parking that uses NodeMCU as the Microcontroller, which is further integrated with Radio-Frequency Identification (RFID) and the Internet of Things (IoT) to detect available parking slots, saving people’s time. When combined with an interactive mobile application, this technology provides an efficient solution by highlighting the availability and occupancy of parking spaces as green and red, respectively. It contributes to enhancing the quality of life of people living in congested metropolitan cities by digitizing the conventional parking system.

Vision-based trajectory generation and tracking algorithm for maneuvering of a paddy field robot

In this study, we propose a novel visual-based autonomous trajectory-tracking control method for steering a wheeled robot following the lines of crop row in paddy field. A rice crop rows detection method, based on the region growth sequential clustering − random sample consensus (RANSAC) algorithm, is developed to generate trajectory. Concurrently, a dynamics predictive controller is employed to compute the command for the desired steering angle. The controller leverages a model that incorporates slip dynamics and operates on a low power consumption industrial computer. Experimental results show that the developed algorithm can successfully obtain the correct trajectory in more than 96.25 % of the cases, with the angle error consistently below 3°. Furthermore, the single-image processing time is notably swift at 13.98 ms, underscoring the commendable adaptability and real-time performance of the proposed methodology. During movement in the paddy field, the robot exhibits maximum lateral deviations of 4.55 cm, 5.65 cm, and 6.41 cm at speeds of 0.3 m/s, 0.6 m/s, and 0.9 m/s, respectively, accompanied by corresponding heading angle errors of 4.59°, 5.63°, and 7.39°. Notably, while adeptly tracking rice crop rows at all three speeds, the robot consistently maintains a maximum lateral error below one-fourth of the inter-row spacing of rice planting. This study assumes significance in enhancing the stability of ground-traversing agricultural robots, serving as a valuable reference for advancing the research and development of intelligent and efficient agricultural robotic systems.

Polishing Machine Control System Based on B-Spline Curve Trajectory

In this study, a B-spline trajectory control algorithm is presented, showcasing its ability to achieve smooth trajectory control within an embedded motion control system. Traditional surface machining methods involve converting interpolated trajectories into G-code using numerical control (NC) software, which is then downloaded and executed on the numerical control system. This research introduces a specialized third-degree B-spline interpolation method tailored for curved surface trajectories, aiming to enhance machining efficiency. A significant strength of this project lies in the holistic design of an embedded system, encompassing both hardware circuitry and software logic. Utilizing the cost-effective STM32 architecture, a B-spline discrete velocity interpolation algorithm is implemented, validated through experiments conducted on a polishing machine system. The project involves MATLAB software for data simulations and experiments on a polishing machine using B-spline curve interpolation, confirming the practicality and effectiveness of the third-degree B-spline algorithm within an embedded system.

Detection of rice panicle density for unmanned harvesters via RP-YOLO

Rice panicle density is one of the essential bases for the automatic speed regulation of unmanned harvesters, making density detection crucial for intelligent upgrades. Currently, existing methods for detecting rice panicle density do not meet actual harvesting scenarios and struggle to meet real-time requirements. To address this, we developed a real-time rice panicle density detection method for unmanned harvesters. This method includes a panicle detection model based on YOLOv5n (RP-YOLO) and a rice panicle density calculation based on coordinate transformations. RP-YOLO was optimized through various techniques, such as enhancing the target detection head, reconfiguring the backbone network and downsampling module, introducing an attention mechanism, and refining the loss function. Based on coordinate conversion, we converted the world coordinates of the detection frame vertex to image coordinates and calculated the panicle density. We established the RP-1668 dataset for japonica rice and trained and tested the model. Compared to the original YOLOv5n model, our modifications reduced floating-point operations per second (FLOPs) by 33.33 %, decreased model size by 31.90 %, increased detection speed by 12.63 %, and improved accuracy (AP0.5) by 3.82 % (AP0.5:0.95, 6.96 %). RP-YOLO achieved superior accuracy and detection speed compared to both conventional lightweight and non-lightweight models. In field applications, the error in density detection was less than 10 % compared to manual counting, and the results clearly reflected changes in rice panicle density. For a 1.4 m × 1.0 m rice field imaging area (with a resolution of 2560 × 1280), the method detects at 15 fps on an on-board industrial computer, providing reliable data support for adjusting the operating speed of driverless harvesters.

Dual-Mode Embedded Impulse-Radio Ultra-Wideband Radar System for Biomedical Applications.

This paper presents a real-time and non-contact dual-mode embedded impulse-radio (IR) ultra-wideband (UWB) radar system designed for microwave imaging and vital sign applications. The system is fully customized and composed of three main components, an RF front-end transmission block, an analog signal processing (ASP) block, and a digital processing block, which are integrated in an embedded system. The ASP block enables dual-path receiving for image construction and vital sign detection, while the digital part deals with the inverse scattering and direct current (DC) offset issues. The self-calibration technique is also incorporated into the algorithm to adjust the DC level of each antenna for DC offset compensation. The experimental results demonstrate that the IR-UWB radar, based on the proposed algorithm, successfully detected the 2D image profile of the object as confirmed by numerical derivation. In addition, the radar can wirelessly monitor vital sign behavior such as respiration and heartbeat information.

Design of a High-Precision Self-Balancing Potential Transformer Calibrator

Potential transformers are vital for measuring and protecting the power grid. Their accuracy and reliability directly impact the stability and security of the power system. To address the issues with traditional high-precision potential transformer calibrators, such as cumbersome operation and low efficiency, a high-precision potential transformer calibrator has been developed. The calibrator is based on an embedded system architecture of FPGA and ARM. It uses a high-precision current comparator along with feedback control technology. By monitoring and adjusting the error feedback voltage, it can perform the automated calibration of potential transformers with an accuracy class of 0.0001. The measurement ranges from 0.00001% to 200.0%. This study can be adapted to meet the development needs of modern digital measurement systems.