Low-cost Single-board Computer Research Articles

Bare-Metal Redundant Multi-Threading on Multicore SoCs Under Neutron Irradiation

A software technique is presented to protect commercial multi-core microprocessors against radiation-induced soft errors. Important time overheads associated with conventional software redundancy techniques limit the feasibility of advanced critical electronic systems. In our approach, redundant bare-metal threads are used, so that critical computation is distributed over the different micro-processor cores. In doing so, software redundancy can be applied to Commercial Off-The-Shelf (COTS) micro-processors without incurring high-performance penalties. The proposed technique was evaluated using a low-cost single board computer (Raspberry Pi 4) under neutron irradiation. The results showed that the Redundant Multi-Threading versions detected and recovered all the Silent Data Corruption (SDC) events, and only increased HANG sensitivity with respect to the unhardened original versions. In addition, higher Mean Work to Failure (MWTF) estimations are achieved with our bare-metal technique than with the state-of-the-art bare-metal software-based techniques that only implement temporal redundancy.

Broken stitch detection system for industrial sewing machines using HSV color space and image processing techniques

Abstract Sewing defect detection is an essential step in garment production quality control. Although sewing defects significantly influence the quality of clothing, they are yet to be studied widely compared to fabric defects. In this study, to address sewing defect detection and develop an appropriate method for small and labor-intensive garment companies, an on-machine broken stitch detection system is proposed. In hardware, a versatile mounting kit, including clamping, display, and adjustable linkage for a camera, is presented for easy installation on a typical industrial sewing machine and for placing the camera close to the sewing position. Additionally, a prototype is implemented using a low-cost single-board computer, Raspberry Pi 4 B, its camera, and Python language. For automated broken stitch detection, a method is proposed that includes removing the texture of the background fabric, image processing in the HSV color space, and edge detection for robust broken detection under various fabric and thread colors and lighting conditions. The proposed system demonstrates reasonable real-time detection accuracy. The maximum accuracy obtained on a sewing stitch dataset with 880 images and on-site tests of various industrial sewing machines is 82.5%, which is 12.1–34.6% higher than that of the two existing methods.

Face Recognition Using Raspberry PI for Mentally Retarded Person

The face recognition system described in this paper focuses on addressing the needs of individuals with intellectual disabilities. Intellectual disabilities often affect an individual's cognitive and adaptive functioning, making it challenging for them to perform everyday tasks independently. This system utilizes the capabilities of Raspberry Pi , a low cost single-board computer, to create an accessible and user-friendly solution for face recognition. The main objective of this system is to assist mentally challenged individuals in recognizing and identifying familiar faces. By utilizing face recognition technology, the system aims to enhance their independence, social interactions, and overall quality of life. The Raspberry Pi platform provides a flexible and affordable hardware foundation for implementing this system. The system leverages a pre-trained deep learning model for face recognition, such as OpenCV or dlib, to perform face detection and identification tasks. The model is trained on a dataset containing facial images of familiar individuals to ensure accurate recognition. Raspberry Pi's computational capabilities enable real-time processing of the captured video feed, facilitating prompt recognition and response.

An Efficient Security Model for Industrial Internet of Things (IIoT) System Based on Machine Learning Principles

This paper presents a security paradigm for edge devices to defend against various internal and external threats. The first section of the manuscript proposes employing machine learning models to identify MQTT-based (Message Queue Telemetry Transport) attacks using the Intrusion Detection and Prevention System (IDPS) for edge nodes. Because the Machine Learning (ML) model cannot be trained directly on low-performance platforms (such as edge devices),a new methodology for updating ML models is proposed to provide a tradeoff between the model performance and the computational complexity. The proposed methodology involves training the model on a high-performance computing platform and then installing the trained model as a detection engine on low-performance platforms (such as the edge node of the edge layer) to identify new attacks. Multiple security techniques have been employed in the second half of the manuscript to verify that the exchanged trained model and the exchanged data files are valid and undiscoverable (information authenticity and privacy) and that the source (such as a fog node or edge device) is indeed what it it claimed to be (source authentication and message integrity). Finally, the proposed security paradigm is found to be effective against various internal and external threats and can be applied to a low-cost single-board computer (SBC).

Combining low-cost single board computers with open-source software to control noble gas extraction lines

Specialised mass spectrometers such as those used in noble gas geochemistry are often controlled by bespoke computer systems that get harder to maintain as, along with their expensive interface cards, they become obsolete. This work explains how bespoke interface cards and obsolete versions of software can be replaced with low-cost single board computers and open source software. Although tailored to an ultra-high vacuum helium extraction line the basic elements and microservices detailed in this paper provide a template for controlling a wider range of instruments.•Moving from obsolete computer hardware to current hardware.•Moving from licenced proprietary software to opensource software.•Automating processes to reduce process time and manual steps.

Heterogeneous hybrid extreme learning machine for temperature sensor accuracy improvement

High-accuracy temperature sensors usually come at a high cost, making them cost-ineffective solutions for mass-produced commercial products. The overall product cost can be one of the decisive factors for its success (e.g., commercial freezers). On the other hand, low-cost temperature sensors are viable options, but they suffer from accuracy issues. This paper presents a system aimed at improving the accuracy of a low-cost temperature sensor using a hybrid machine learning algorithm. The system utilizes a low-cost single-board computer connected to a series of sensors to collect data. These data are then used as an input vector to the proposed linear regression heterogeneous hybrid extreme learning machine (LR-HE-HyELM), a supervised learning algorithm responsible for increasing the sensors’ accuracy. The proposed linear regression heterogeneous extreme learning machine (LR-HE-HyELM) combines linear regression with the self-adaptive heterogeneous hybrid extreme learning machine (SA-He-HyELM) algorithm. SA-He-HyELM is an extreme learning machine (ELM) based algorithm that utilizes a genetic algorithm (GA) for the creation of an optimized single-layer neural network (SLNN) having different combinations of custom-created neurons at its hidden layer. The proposed training algorithm has all the advantages of SA-He-HyELM. These advantages include utilizing low-order and higher-order neurons in the same network while retaining ELM’s simplicity by making all GA parameters self-adaptive. The utilization of low-order and higher-order unit types in the same network resulted in optimized neural networks with better generalization ability than those with the same neuron types in their hidden layer. The creation of SA-He-HyELM was nature-inspired since the human brain contains different neuron types. The proposed system is tested with eight existing methods, with most of them having different neuron types in the hidden layer. The experimental results involved using a custom-created regression dataset having measurements taken from a commercial fridge. The proposed method managed to get the lowest mean square error (MSE) compared to the other eight methods.

A Mirror Environment to Produce Artificial Intelligence Training Data

With the increasing maturity of artificial intelligence (AI) technology, business automation technology has also become a trend. Particularly, network operation and maintenance (O<monospace>&#x0026;</monospace>M) is expected to soon become automated and more efficient. However, the automation of O<monospace>&#x0026;</monospace>M is hindered by the lack of network failure data and the cost of collecting data. We thus propose an approach to build a low-cost environment that can produce the same data as the actual production environment and use tools such as chaos engineering to generate training models for fault data. This paper attempts to build the underlying physical network layer using a low-cost single-board computer Raspberry Pi instead of an expensive PC server, while keeping the virtual network layer the same and performing fault simulation, data collection, and AI model training on the constructed virtual network layer. A comparison of the accuracy of the trained AI models verifies the feasibility of replacing the traditional PC server with an inexpensive Raspberry Pi device while keeping the structure and services of the virtual network layer unchanged. Also, a brief comparison with existing techniques is discussed. Our proposed approach solves the problem of insufficient data for AI training while reducing cost and risk.

Cognitive Accessibility and Support in Special Education.

This work describes an assistive technology development for cognitive support and training to be used by children of special education schools in Spain. Design is based on and guided by cognitive support findings coming from a long-term collaboration of a team of engineers (University of Zaragoza) and special education teachers (Alborada Special Education School, Zaragoza). The description starts by providing a structure of such findings in five cognitive-social areas (interface usability, virtual representations understanding, time orientation, self-awareness, and social interaction). Design requirements are extracted by applying those findings to four support services (home control, time orientation, behavior contention, and context anticipation). Technological system description follows, together with the degree of implementation and testing for each service. A major result is the benefit of using a services interface with the same structure and appearance as the alternative and augmentative communication system that children are already acquainted with. Based on regulatory conditions, the needed flexibility, and reduced available budgets, this support platform is built on mainstream technology and low-cost single-board computers with standard databases and free software packages. Results show evidence of benefit in children’s cognitive and social performance, in addition to offering a technological tool for deeper educational research.

Microfluidic System for In Vivo-Like Drug Permeation Studies with Dynamic Dilution Profiles.

Automated biomimetic systems for the preclinical testing of drugs are of great interest. Here, an in vitro testing platform for in vivo adapted drug absorption studies is presented. It has been designed with a focus on easy handling and the usability of established cell cultivation techniques in standard well plate inserts. The platform consists of a microfluidic device, which accommodates a well plate insert with pre-cultivated cells, and provides a fluid flow with dynamic drug dilution profiles. A low-cost single-board computer with a touchscreen was used as a control unit. This provides a graphical user interface, controls the syringe pump flow rates, and records the transepithelial electrical resistance. It thereby enables automated parallel testing in multiple devices at the same time. To demonstrate functionality, an MDCK cell layer was used as a model for an epithelial barrier for drug permeation testing. This confirms the possibility of performing absorption studies on barrier tissues under conditions close to those in vivo. Therefore, a further reduction in animal experiments can be expected.

THE WORLD DEVELOPMENT OF THE DIGITAL ECONOMY: THE MAIN DEVELOPMENT STRATAGEMS

The digital economy allows to compose the new business models, digital platforms and services, which create new types of economic activity, as well as the transformation of traditional industries. Due to the industries transformation to the digital economy there is the transformation of the world economy, or rather the economy itself is being digitized The purpose of the paper is to reveal the essence and features of the digital economy formation and to consider what significant transformations will take place in the world by the analysis of major trends in the near future. Accumulating all the concepts, we can say that the digital economy is the rather complex term, but we can assume that its development is based on the key components According to forecast estimates, the most advanced retail companies will begin implementing the service of virtual and voice search of goods by 2022. This will require from the company the better understanding of the consumers wishes, their interests and intentions. Consider the main technological development trends for 2020-2025 based on the data of the major consulting agencies and the consulting company "Cartner" Figure 2 shows the forecast curve of the new technologies development. Innovative development triggers that will actively influence the technology development include the following: the Authenticated Provenance, Low-Cost Single Board Computers at the Edge, Self-Supervised Learning, BMI (Brain Machine Interface), active development of "Packaged Business Capabilities" services, Digital Twin of the Person and Composible Enterprises. The peak of disappointments will be Social Distancing Technologies and Secure Access Service. The source of expectations will be the development of Carbon-Based transistors technology and Human digital Ontologies. The formation of a productivity platform will be based on trends in Self-Development and Self-Education. Digital IT trends grow, evolve and acquire new properties of social technologies that can influence the structure of the community, form dependencies and demand. Therefore, companies, large corporations and government need to move to more flexible composite business architectures. The modular business model is based on four basic principles: modularity, efficiency, continuous improvement and adaptive innovation. This business model allows to move from rigid traditional planning to a flexible response to rapidly changing business needs. In general, it creates opportunities for innovative approaches, reduces costs and improves partnerships. It is important to pay attention to the other technologies in the new business model such as bundled business services, data factories, private 5G networks and embedded artificial intelligence. Thus, as a result of the research it is proved that the digital world is a completely new order of life, which requires to change our thinking. The person should be always focused on the new technologies and methods in order the enterprises remain competitive and constantly developed, it will promote the economy development and the growth of well-being of the society. So, taking into account the global trends in technology development, Ukraine has to adapt to the new standards quickly and implement innovative solutions for the economic development. The digitalization of the economy, on the one hand, is the key to economic success, on the other hand, it is the driving force in the conditions of the conceptual understanding of the digital economy essence. The growth of the quality and innovation level of domestic goods and services should provide not only sustainable economic growth, but also competitive advantages with further integration into the EU. At the same time, there is the relevant need of the scientific and technological research, the formation of a certain business ("digital") culture, the implementation of smart city ideas in Ukraine based on the development of local communities and the emergence of new initiatives and proposals for innovative solutions.

An eight-camera fall detection system using human fall pattern recognition via machine learning by a low-cost android box

Falls are a leading cause of unintentional injuries and can result in devastating disabilities and fatalities when left undetected and not treated in time. Current detection methods have one or more of the following problems: frequent battery replacements, wearer discomfort, high costs, complicated setup, furniture occlusion, and intensive computation. In fact, all non-wearable methods fail to detect falls beyond ten meters. Here, we design a house-wide fall detection system capable of detecting stumbling, slipping, fainting, and various other types of falls at 60 m and beyond, including through transparent glasses, screens, and rain. By analyzing the fall pattern using machine learning and crafted rules via a local, low-cost single-board computer, true falls can be differentiated from daily activities and monitored through conventionally available surveillance systems. Either a multi-camera setup in one room or single cameras installed at high altitudes can avoid occlusion. This system’s flexibility enables a wide-coverage set-up, ensuring safety in senior homes, rehab centers, and nursing facilities. It can also be configured into high-precision and high-recall application to capture every single fall in high-risk zones.

A Wireless Instrumentation Control System Based on Low-Cost Single Board Computer Gateways

Nowadays, most of the automatized measurement processes are carried out by VISA (Virtual Instrument Software Architecture) compatible instruments, that execute the instructions provided by a host computer connected through wired standard buses, as USB (Universal Serial Bus), GPIB (General-Purpose Instrumentation Bus), PXI (PCI eXtensions for Instrumentation) or Ethernet. To overcome the intrinsic limitations associated to these wired systems, this work presents an instrumentation control system based on the IEEE 802.11 wireless communications standard. Intended for instruments having a USB control port, this port is connected to a gateway based on a compact Raspberry Single Board Computer (SBC) and thus the instrument can be connected to the host computer via Wireless Fidelity (WiFi), easily allowing the deployment of an ad-hoc instruments communication network in the working area or its connection to a previously deployed general purpose WiFi network. Developed under Python, the operation commands, wireless link protocol, and USB connection allow two modes of operation to provide system flexibility: a live mode, where commands are sent individually from the host computer to the selected instrument; and a standalone mode, where a full measurement process can be entirely downloaded in the gateway to be autonomously executed on the instrumentation. The system performance in both operation modes, distance of operation, time latencies, and operating lifetime in battery operation have been characterized.

A cost-effective redundant communication system for improving the reliability of a flood early warning system

Abstract All early flood warning systems (FEWS) work with gauges and communications systems to collect and distribute hydro-meteorological measurements in real-time. The objective is to allow the authorities to take action before the flood reaches critical places. The FEWS of the lower Salado River basin, Argentina, were established after the flood of Santa Fe city in 2003. Frequent loss of information due to communication problems with the repository site increases the operational vulnerability of the network. First, the document analyses the flood frequency of the region using known statistical distributions. Then, it offers a low-cost solution to the loss of information problem based on an interface that transmits in parallel the network data through an electronic bypass without interfering with the FEWS satellite communication system. The tests carried out along three stations show the interface proved efficient in transmitting data via WiFi or mobile communications in real-time. The results establish a one-to-one data correspondence when the satellite system and the redundant system are active. The interface is based on low-cost single-board computers and routers. The variety of commercial sensors tested makes the developed interface portable to similar situations, and the savings achieved – maintenance cost – are significant.

LW-RCP와 Odroid 기반의 Machine Vision을 이용한 Ball and Plate 시스템 구현에 관한 연구

In this paper, we propose the architecture of a ball-and-plate system as an educational platform that can help students comprehensively study control engineering, robotics, machine vision, and embedded systems. In addition, we describe how to implement the sub-systems and present an example of an education plan using the proposed system. In the proposed system, we use an LW-RCP(Light Weight-Rapid Control Prototyping) system, which is lab-built, to help students implement the control algorithm. An RCP system makes it easy for students who are not familiar with u-Controller or the C language to implement controllers. We also use Odroid, a low-cost SBC (single-board computer), and a single camera to calculate the position of ball using a machine vision algorithm. In this structure, the measurement subsystem is more durable compared with contact-based sensing systems and student can test their own machine vision algorithms for better measurements. We adopt the Stewart platform, a type of parallel robot, to generate roll-and-pitch actuation for the ball-and-plate system. By adopting the Stewart platform, we can handle more complicated control problems for movement that requires more than two degrees of freedom. Additionally, we implement an LQ controller, which is a typical model-based controller, and apply it to the ball-plate system. Finally, through experiments, we illustrate the usefulness of the proposed system.

Development and Testing of a Low-Cost Portable Apparent Soil Electrical Conductivity Sensor Using a Beaglebone Black

Abstract.The adoption of apparent soil electrical conductivity (soil ECa) sensors has increased in precision agricultural systems, especially in systems pulled by vehicles. This work developed a portable soil sensor for measuring soil ECa that could be used without vehicles in mountainous areas and small farms. The developed system was based on the electrical resistivity method. The system measured the electrical conductivity by applying a square wave signal at frequencies defined by the user. The acquired data were georeferenced using a low-cost global navigation satellite system (GNSS) receiver. The sensor system was developed using a BeagleBone Black, a low-cost single-board computer. A user interface was developed in C++, and a touch screen with a resolution of 800×480 pixels was used to display the results. This interface performed statistical analysis, and the results were used to guide the user to identify more field locations to be sampled to increase mapping accuracy. The system was tested in a coffee plantation located in a mountainous area and in a sugarcane plantation in Minas Gerais, Brazil. The system worked well in mapping the soil ECa. The apparent soil electrical conductivities measured using frequencies of 10, 20, 30, and 40 Hz were highly correlated. In the sugarcane field that had more variation in soil texture, a greater number of soil properties presented a significant correlation with the soil ECa. Keywords: Electrical conductivity, Geostatistics, Precision agriculture, Soil properties, Soil sensing, Spatial variability.

Cyber-physical framework for emulating distributed control systems in smart grids

This paper proposes a cyber-physical framework for investigating distributed control systems operating in the context of smart-grid applications. At the moment, the literature focuses almost exclusively on the theoretical aspects of distributed intelligence in the smart-grid, meanwhile, approaches for testing and validating such systems are either missing or are very limited in their scope. Three aspects need to be taken into account while considering these applications: (1) the physical system, (2) the distributed computation platform, and (3) the communication system. In most of the previous works either the communication system is neglected or oversimplified, either the distributed computation aspect is disregarded, either both elements are missing. In order to cover all these aspects, we propose a framework which is built around a fleet of low-cost single board computers coupled with a real-time simulator. Additionally, using traffic control and network emulation, the flow of data between different controllers is shaped so that it replicates various quality of service (QoS) conditions.The versatility of the proposed framework is shown on a study case in which 27 controllers self-coordinate in order to solve the distributed optimal power flow (OPF) algorithm in a dc network.

Internet of Energy Training through Remote Laboratory Demonstrator

In this paper, a new learning tool is proposed to train professional figures, such as entrepreneurs, engineers, and technicians, who need to improve their skills in the field of Internet of Energy. The proposed tool aims to cover the lack of experimental knowledge on new energy systems and to layer proper skills, which are useful to deal with challenges required by smart energy management in the new complex distributed configuration of the electric power systems, characterized by demand response services. This tool is based on a small-scale laboratory demonstrator, representative of a smart rural house, equipped with a measurement and control system. This demonstrator can be remotely accessed, through web server applications based on a low cost single-board computer. Trainers can have direct experience on the main concepts related to smart grids, renewable energy sources, electrochemical storage systems, and electric vehicles, through the use of the proposed tool managed by the web software interface.

Acquisition of Voltage and Current Signals using A Single Board Computer for Online Monitoring of Powers

During this time, Single Board Computers (SBCs) are widely used in monitoring and control applications. Many relatively low-cost SBCs are available. This paper explains the implementation of an SBC LattePanda for online monitoring of powers through Local Area Networks (LANs). The SBC was used as the main part of the monitoring system that mainly performed acquisition of voltage and current signals sent by some sensors. A program for the microcontroller on the SBC was written for the acquisition processes. Furthermore, a client/server application was developed using Delphi to perform online monitoring of the signals. Some experimentation was performed to mainly ensure that the microcontroller could capture the voltage and current signals with precise and constant sampling timing as well as send the data to the client/server application successfully. A PicoScope was utilized during the experimentation to gain the timing information performed by the microcontroller. For calibration of the voltage and current, a 4.5-digit digital multimeter was implemented. The final stage of the experimentation revealed that the intended signals could be sampled with a constant timing and in this case 128 samples per channel was chosen. The developed application could also show the expected parameters including the signal of powers using an additional remote computers connected to the LAN.

A Raspberry Pi-based, RFID-equipped birdfeeder for the remote monitoring of wild bird populations

ABSTRACT Radio-frequency identification (RFID) is an increasingly popular wireless technology that allows researchers to monitor wild bird populations from fixed locations in the field. I have developed an RFID-equipped birdfeeder based on the Raspberry Pi Zero W, a low-cost single-board computer, that collects continuous visitation data from birds marked with passive integrated transponder (PIT) tags. Each birdfeeder has a perch antenna connected to an RFID-reader board on a Raspberry Pi powered by a portable battery. When a tagged bird lands on the perch to eat from the feeder, its unique code is stored with the date and time on the Raspberry Pi. These birdfeeders require only basic soldering and coding skills to assemble, and can easily be outfitted with additional hardware like video cameras and microphones. I outline the process of assembling the hardware and setting up the operating system for the birdfeeders. Then, I describe an example implementation of the birdfeeders to track House Finches Haemorhous mexicanus on the campus of Queens College in New York City.

Performance and power consumption analysis of low-cost single board computers in educational robotics

This paper presents an overview of some of the most popular and cost effective single board computers in the scope of usage in the educational service robots. Data and analysis of the general performance and power consumption of the embedded systems is measured and presented. The aim is to study the available platforms and their optimal usage in the ROS enabled robots. Also an overview on the available peripherals of the different boards is presented.