Embedded System Hardware Research Articles

Smart Handling of Biomedical Waste using Intelligent Deep Learning and IOT

Hospitals create an enormous volume of potentially hazardous trash. Currently, bandages, plastic papers, wasted pus, syringes, glucose drip bottles, other dangerous medical wastes, and containers are separated by hand, resulting in long-term health consequences such as tuberculosis, cancer, and infectious diseases. Rag pickers are currently responsible for the majority of waste separation. Efficient management of medical waste demands not only precise segregation but also real-time monitoring and notification systems to ensure timely intervention and optimized waste handling. This project proposes an integrated solution combining deep learning, image processing, Embedded Systems hardware and Internet of Things (IoT) technologies. Medical waste will be detected using the Deep Learning technique; A deep learning model is trained on a diverse dataset to classify medical waste items, and image processing techniques are utilized to enhance the accuracy of the classification process. This holistic approach offers an efficient and automated system for medical waste management integrating waste segregation, waste level monitoring, and timely notifications, thereby ensuring a sustainable and responsible waste management process in healthcare facilities.

An Ultralow-Power Real-Time Machine Learning Based fNIRS Motion Artifacts Detection.

Due to iterative matrix multiplications or gradient computations, machine learning modules often require a large amount of processing power and memory. As a result, they are often not feasible for use in wearable devices, which have limited processing power and memory. In this study, we propose an ultralow-power and real-time machine learning-based motion artifact detection module for functional near-infrared spectroscopy (fNIRS) systems. We achieved a high classification accuracy of 97.42%, low field-programmable gate array (FPGA) resource utilization of 38354 lookup tables and 6024 flip-flops, as well as low power consumption of 0.021 W in dynamic power. These results outperform conventional CPU support vector machine (SVM) methods and other state-of-the-art SVM implementations. This study has demonstrated that an FPGA-based fNIRS motion artifact classifier can be exploited while meeting low power and resource constraints, which are crucial in embedded hardware systems while keeping high classification accuracy.

The Application of Embedded Hardware System and Blockchain in Rural Financial Management Cloud Platform

With the rapid development of information technology, rural financial management is facing the great challenge of digitalization and intelligentization. This study aims to explore the application of embedded systems combined with blockchain technology in rural financial management to provide more efficient and secure solutions. Firstly, the main problems in rural financial management are analyzed, including low data processing efficiency and poor data security. It then explores the potential applications of embedded systems in financial management, as well as the main characteristics and classifications of blockchain technology. Based on this, a model integrating embedded systems and blockchain technology is designed, and the effectiveness of the model is verified by experiments. The experimental results show that the system not only significantly improves the data processing speed, but also enhances the data security and improves the user satisfaction. In general, this study provides theoretical and practical support for the technical innovation of rural financial management and shows a broad prospect in practical application.

Research and Design of a Decentralized Edge-Computing-Assisted LoRa Gateway

As a narrowband communication technology, long-range (LoRa) contributes to the long development of Internet of Things (IoT) applications. The LoRa gateway plays an important role in the IoT transport layer, and security and efficiency are the key issues of the current research. In the centralized working model of IoT systems built by traditional LoRa gateways, all the data generated and reported by end devices are processed and stored in cloud servers, which are susceptible to security issues such as data loss and data falsification. Edge computing (EC), as an innovative approach that brings data processing and storage closer to the endpoints, can create a decentralized security infrastructure for LoRa gateway systems, resulting in an EC-assisted IoT working model. Although this paradigm delivers unique features and an improved quality of service (QoS), installing IoT applications at LoRa gateways with limited computing and memory capabilities presents considerable obstacles. This article proposes the design and implementation of an “EC-assisted LoRa gateway” using edge computing. Our proposed latency-aware algorithm (LAA) can greatly improve the reliability of the network system by using a distributed edge computing network technology that can achieve maintenance operations, such as detection, repair, and replacement of failures of edge nodes in the network. Then, an EC-assisted LoRa gateway prototype was developed on an embedded hardware system. Finally, experiments were conducted to evaluate the performance of the proposed EC-assisted LoRa gateway. Compared with the conventional LoRa gateway, the proposed edge intelligent LoRa gateway had 41.1% lower bandwidth utilization and handled more end devices, ensuring system availability and IoT network reliability more effectively.

Exploring Artificial Intelligence in Smart Education: Real-Time Classroom Behavior Analysis with Embedded Devices

Modern education has undergone tremendous progress, and a large number of advanced devices and technologies have been introduced into the teaching process. We explore the application of artificial intelligence to education, using AI devices for classroom behavior analysis. Embedded systems are special-purpose computer systems tailored to an application. Embedded system hardware for wearable devices is often characterized by low computing power and small storage, and it cannot run complex models. We apply lightweight models to embedded devices to achieve real-time emotion recognition. When teachers teach in the classroom, embedded portable devices can collect images in real-time and identify and count students’ emotions. Teachers can adjust teaching methods and obtain better teaching results through feedback on students’ learning status. Our optimized lightweight model PIDM runs on low-computing embedded devices with fast response times and reliable accuracy, which can be effectively used in the classroom. Compared with traditional post-class analysis, our method is real-time and gives teachers timely feedback during teaching. The experiments in the control group showed that after using smart devices, the classroom teaching effect increased by 9.44%. Intelligent embedded devices can help teachers keep abreast of students’ learning status and promote the improvement of classroom teaching quality.

Human Postures Recognition by Accelerometer Sensor and ML Architecture Integrated in Embedded Platforms: Benchmarking and Performance Evaluation

Embedded hardware systems, such as wearable devices, are widely used for health status monitoring of ageing people to improve their well-being. In this context, it becomes increasingly important to develop portable, easy-to-use, compact, and energy-efficient hardware-software platforms, to enhance the level of usability and promote their deployment. With this purpose an automatic tri-axial accelerometer-based system for postural recognition has been developed, useful in detecting potential inappropriate behavioral habits for the elderly. Systems in the literature and on the market for this type of analysis mostly use personal computers with high computing resources, which are not easily portable and have high power consumption. To overcome these limitations, a real-time posture recognition Machine Learning algorithm was developed and optimized that could perform highly on platforms with low computational capacity and power consumption. The software was integrated and tested on two low-cost embedded platform (Raspberry Pi 4 and Odroid N2+). The experimentation stage was performed on various Machine Learning pre-trained classifiers using data of seven elderly users. The preliminary results showed an activity classification accuracy of about 98% for the four analyzed postures (Standing, Sitting, Bending, and Lying down), with similar accuracy and a computational load as the state-of-the-art classifiers running on personal computers.

High-level power estimation techniques in embedded systems hardware: an overview

High-level power estimation techniques in embedded systems hardware: an overview

Demonstration and verification experiment in deep space optical communications

In deep space optical communications, pointing, acquisition and tracking (PAT) system need to locate the position of the beacon, precisely. The way of employing the natural celestial body as the beacon come to draw attention, in contrast to regarding the laser as the beacon which has a series of problems of limited power, serious attenuation, high cost and difficult design realization. In this paper, the primary goal is to study the problem of precise positioning for the beacon by taking the natural celestial body as the beacon. Given the long distance, with small target and large uncertain region in deep space optical communications, the location of the beacon can be realized by the combination of rough and precise positioning based on the image feature of the beacon. Firstly, it performs the rough positioning according to the image characteristic information of the beacon’s edge, then in the uncertain region, the processing scope has been narrowed according the results of the rough positioning, finally the beacon is precisely located based on its minutiae feature by the way of feature point matching to achieve the position of the beacon. The impact due to the autorotation of celestial body on the image transform has been also discussed and analyzed with the mapping relationship of coordinate and geometric transform. The feasibility of the algorithm is verified by a long distance far-field Earth–Moon experiment. The design of system implementation on embedded hardware system can provide a reference for the real-time positioning system in deep space optical communications.

WITHDRAWN: Embedded Hardware System and Sensor Robot Used In Goal Tracking Technology Of Sports Football Goalkeeper

ABSTRACT The purpose of the software-only system built into the hardware of the design is called embedded systems. The system is maybe a stand-alone system or a larger system. Software is usually built into the memory module. It does not require any auxiliary storage device in the computer. Telecommunications, smart cards, missiles, computer networks, digital consumer electronics, and satellites are part of the sensor's robot used in embedded systems. In embedded systems, hardware platforms need to interact with various real-time input and output or variable. In the previous method Principal Component Analysis (PCA) Algorithm and Independent Component Analysis (ICA), several countries encourage football practice for rehabilitation and social inclusion purposes. For visually impaired people, football is purely sound-based, where the ball and the players are constantly emitting sounds for localization purposes in the field. The proposed Support Vector Machine (SVM) algorithm Embedded Hardware System and Sensor Robot Used in Goal Tracking Technology of Sports Football Goalkeeper Functions The electronics' goal, the position and the ball is by returning the feedback based on the sound that are affecting the location. It is to design the four functions for training. The system has confirmed the volunteers from the Chilean national football team.

Implementasi Master-slave pada Embedded system menggunakan komunikasi RS485

The use of multiprocessor methods in robotics systems has a significant impact on overall robot performance. The Master-slave method is a model of a multiprocessor system where there are several processors that communicate with each other to carry out the robot's overall function. RS-485 can be used as a communication model in the master-slave method. RS-485 is a development of RS-232 which has the ability to communicate with several nodes. In this research, an experiment will be conducted to implement RS-485 to support the master-slave processor communication. Stages of research began with making system design, which includes the design of embedded hardware systems, the design of data communication protocols on RS-485 networks, software design, followed by implementation and testing. The test is carried out to measure the time response of the device to three data transmission models, namely broadcast, addressing slaves without responding and addressing slaves with responses. The test results carried out on three slaves with a communication speed of 9600 bps. Measured response time on broadcast data transmission is 8ms, and address slave without response is 7ms. Whereas delivery by addressing slaves with responses, shows that the measurement method cannot be applied.

Embedded Real-Time System for Traffic Sign Recognition on ARM Processor

This article proposes the design of a novel hardware embedded system used for automatic real-time road sign recognition. The algorithm used was implemented in two main steps. The first step, which detects the road signs, is performed by the maximally stable extremal region method on HSV color space. The second step enables the recognition of the detected signs by using the oriented fast and rotated brief features method. The novelty of the embedded hardware system, on an ARM processor, leads to a real-time implementation of the ADAS applications. The proposed system was tested on the Belgium Traffic Sign Detection and Recognition Benchmark and on the German Traffic Signs Datasets. The proposed approach attained a high detection and recognition rate with real-world situations. The achieved results are acceptable when compared to state-of-the-art systems.

An Efficient Data Transmission with GSM-MPAPM Modulation for an Indoor VLC System

As an emerging wireless communication technique, visible light communication is experiencing a boom in the global communication field, and the dream of accessing to the Internet with light is fast becoming a reality. The objective of this study was to put forward an efficient and theoretical scheme that is based on generalized spatial modulation to reduce the bit error ratio in indoor short-distance visible light communication. The scheme was implemented while using two steps in parallel: (1) The multi-pulse amplitude and the position modulation signal were generated by combining multi-pulse amplitude modulation with multi-pulse position modulation using transmitted information, and (2) certain light-emitting diodes were activated by employing the idea of generalized spatial modulation to convey the generated multi-pulse amplitude and position modulation optical signals. Furthermore, pulse width modulation was introduced to achieve dimming control in order to improve anti-interference ability to the ambient light of the system. The two steps above involved the information theory of communication. An embedded hardware system, which was based on the C8051F330 microcomputer and included a transmitter and a receiver, was designed to verify the performance of this new scheme. Subsequently, the verifiability experiment was carried out. The results of this experiment demonstrated that the proposed theoretical scheme of transmission was feasible and could lower the bit error ratio (BER) in indoor short-distance visible light communication while guaranteeing indoor light quality.

Deep Learning-Based Real-Time Multiple-Object Detection and Tracking from Aerial Imagery via a Flying Robot with GPU-Based Embedded Devices.

In recent years, demand has been increasing for target detection and tracking from aerial imagery via drones using onboard powered sensors and devices. We propose a very effective method for this application based on a deep learning framework. A state-of-the-art embedded hardware system empowers small flying robots to carry out the real-time onboard computation necessary for object tracking. Two types of embedded modules were developed: one was designed using a Jetson TX or AGX Xavier, and the other was based on an Intel Neural Compute Stick. These are suitable for real-time onboard computing power on small flying drones with limited space. A comparative analysis of current state-of-the-art deep learning-based multi-object detection algorithms was carried out utilizing the designated GPU-based embedded computing modules to obtain detailed metric data about frame rates, as well as the computation power. We also introduce an effective target tracking approach for moving objects. The algorithm for tracking moving objects is based on the extension of simple online and real-time tracking. It was developed by integrating a deep learning-based association metric approach with simple online and real-time tracking (Deep SORT), which uses a hypothesis tracking methodology with Kalman filtering and a deep learning-based association metric. In addition, a guidance system that tracks the target position using a GPU-based algorithm is introduced. Finally, we demonstrate the effectiveness of the proposed algorithms by real-time experiments with a small multi-rotor drone.

Fast High-Fidelity Readout of a Single Trapped-Ion Qubit via Machine-Learning Methods

In this work, we introduce machine learning methods to implement readout of a single qubit on $^{171}\mathrm{Yb^{+}}$ trapped-ion system. Different machine learning methods including convolutional neural networks and fully-connected neural networks are compared with traditional methods in the tests. The results show that machine learning methods have higher fidelity, more robust readout results in relatively short time. To obtain a 99% readout fidelity, neural networks only take half of the detection time needed by traditional threshold or maximum likelihood methods. Furthermore, we implement the machine learning algorithms on hardware-based field-programmable gate arrays and an ARM processor. An average readout fidelity of 99.5% (with $10^5$ magnitude trials) within 171 $\mu$s is demonstrated on the embedded hardware system for $^{171}\mathrm{Yb^{+}}$ ion trap.

An Urban Based Smart IOT Farming System

Recent technological developments have led to the emergence of new trends in agriculture to ensure increased production through sustainable utilization of resources. One of the new trends is Precision Agriculture (PA). However, like many new emerging trends, PA is faced with a number of uncertainties and hurdles. One of the major issues and hurdles in precision agriculture is the uncertainty of optimum application of resources necessary for optimum yield production while minimizing resource wastage for sustainable agricultural production. Therefore, this paper presents a fuzzy based Decision Support System (DSS) to intelligently allocate water and fertilizer used in crop production based on the age of the plant and data collected from the soil and surrounding environment with the aid of a network of sensors. An embedded hardware system consisting of a Cartesian robot has also been implemented to ensure effective application of the fuzzy derived decisions. Two Fuzzy Inference Systems (FIS) consisting of linear, non-linear Membership Functions and a 149-rule base for the PA system have been developed in MATLAB, implemented using Arduino microcontrollers and tested on spinach plants whereby results show that the linear FIS is able to achieve more accurate results in terms of the quality of yield realized and resource utilllisation. Resource utilllisation comparison with other systems in literature reviewed is also done whereby the DSS is able to save up to 2031 ml and 524 ml of water and fertilizer respectively.

Design and Development Based on Embedded System

The demand for equipment has been unable to meet the current and future high performance application anddevelopment needs with the rapid development of electronic technology and upgrading of traditional industries inChina. At the same time, intense market competition and technical competition require that the development cycle ofthe product to be as short as possible. Obviously, the software and hardware of embedded system are becoming moreimportant foundation of technological innovation in various fi elds. The embedded system is a combination of advancedcomputer technology, semiconductor technology, electronic technology and the specific application of variousindustries. This determines that it must be a technology-intensive, capital-intensive, highly fragmented and innovativeknowledge integration system. The embedded type is based on the application of computer technology-based hardwareand software can be tailored to adapt to the application system on the function, reliability, cost, size, power and otherstrict requirements of the special computer system. The emergence of consumer appliances and cheap microprocessorsembedded systems will form larger application areas in daily life to as the embedded system usually has low powerconsumption, small size and high integration. Embedded employment is widely embedded in the social needs of largetalent. The content of the paper is clear in the embedded control system overview - development - application writingideas in three chapters gradually. Chapter 1 introduces the defi nition, frame, characteristic, development history, currentsituation and prospect of the embedded control system in detail. The development of the embedded control systemmainly discusses the development steps and methods. The third chapter embedded control system. This paper discussesthe practical application of embedded control system in public life. As the application of these research results in thefi nal summary of the various aspects of the system capacity and analysis of the existing problems for further research toprovide a direction and valuable experience.

Surveying the Hardware Trojan Threat Landscape for the Internet-of-Things

The Internet-of-Things (IoT) has emerged as one of the most innovative multidisciplinary paradigms combining heterogeneous sensors, software architectures, embedded hardware systems, and data analytics. With the growth in deployment of IoT systems, security of the sensors and trustworthiness of the data exchanged is of paramount significance. IoT security approaches are derived from the vulnerabilities existing in cyber-physical systems (CPS) and the countermeasures designed against them. This paper surveys the vulnerabilities posed due to the presence of hardware Trojans in such IoT-based CPS. The threats, trigger points, detection methods, and countermeasures for targeting hardware Trojans are discussed in detail. Finally, some of the new emerging security challenges and countermeasures are addressed.

Design and Analysis of Multiple OS Implementation on a Single ARM-Based Embedded Platform

Recently, with the development of embedded system hardware technology, there is a need to support various kinds of operating system (OS) operation in embedded systems. In mobile processors, ARM started to provide the virtualization extension support technology which was intended for processors in PC processors. Virtualization technology has the advantage of using hardware resources effectively. If the real-time operating system (RTOS) is operated on a hypervisor, there is a problem that RTOS performance is degraded due to overhead. Thus, we need to compare the performance between a single execution of the RTOS and simultaneous execution of multiple OS (RTOS + Linux). Therefore, in this paper, we measure the performance when the RTOS operates independently on the NVidia Jetson TK-1 embedded board supporting virtualization technology. Then, we measure the performance when the RTOS and Linux are operating simultaneously on top of a hypervisor. For this purpose, we implemented and ported such a RTOS, especially FreeRTOS and uC/OS, onto two embedded boards, such as the Arndale board (SAMSUNG, Seoul, South Korea) and the NVidia TK1 board (NVIDIA, Santa Clara, CA, USA).

An Introductory Embedded Systems Teaching Using Open-Source Hardware and Software Platforms

Embedded systems are used everywhere in human lives. They are in alarm clocks, automobiles, mobile phones, personal digital assistants, home appliances and etc. The Faculty of Electronic Engineering and Technologies at Technical University of Sofia decided after many iterations and discussions with the partners companies and employers organizations to accept a new curriculum for Bachelor degree in Electronics. In order to prepare the students for the challenges of their future job in the new curriculum it was emphasized on the practice and especially on obtaining skills in embedded systems programming. The laboratory classes in “Practice on open source platforms programming” are intended to give the students basic knowledge and skills in this field. The open source hardware and software platforms—Arduino development board and the software IDE, which are globally recognized as tools for introductory education, are chosen for this purpose. In this paper it is proposed a practical approach for teaching the basics of embedded systems hardware and software. The stress is on the program control of inputs and outputs to convince the students in the flexibility and universality of the programmable devices. Also there are introduced the principles of the sensors and their application. Some examples are presented.

Research on Real-Time Monitoring System for Traction Motor of EMUs

A multi-function, easily extensible and portable tracking and monitoring system is designed for traction and drive system to meet the growing requirements of high-speed EMUs, which is increasingly complex for real-time monitoring system. The design principle of the embedded hardware system based on the modular structure of CPCI bus is presented in details, and the realization of software functions such as on-line real-time data processing, offline data analysis, and human-machine interaction is put forward on the basis of LabVIEW development platform. Furthermore, the VI design and scheduling mechanism based on state-machine are elaborated, and the measurement algorithm and its implementation of the traction motors input power and constantly changing signal frequency of the monitoring system is also analyzed. The system has been applied in certain models of the high-speed EMUs, and its stable operation, flexible settings, high accuracy and good application effect makes it provide a scientific guarantee for the safe operation of the high-speed EMUs.