Design Space Exploration of a Multi-Model AI-Based Indoor Localization System

In this paper, we present the results of a performance evaluation and optimization process of an indoor positioning system (IPS) designed to operate on portable as well as miniaturized embedded systems. The proposed method uses the Received Signal Strength Indicator (RSSI) values from multiple Bluetooth Low-Energy (BLE) beacons scattered around interior spaces. The beacon signals were received from the user devices and processed through an RSSI filter and a group of machine learning (ML) models, in an arrangement of one model per detected node. Finally, a multilateration problem was solved using as an input the inferred distances from the advertising nodes and returning the final position approximation. In this work, we first presented the evaluation of different ML models for inferring the distance between the devices and the installed beacons by applying different optimization algorithms. Then, we presented model reduction methods to implement the optimized algorithm on the embedded system by appropriately adapting it to its constraint resources and compared the results, demonstrating the efficiency of the proposed method.

Green House Smart Farming Echosystem

The future of farming has been one of the most talked-about issues on world forums, with the world population increasing yearly there is a special need to develop more efficient ways to grow food and distribute them effectively. This work discusses the design and implementation of a greenhouse smart farming echo system for the cultivation and distribution of plants using mushrooms as a focused product, linking a farm environment to a business market (cultivation processes and supply chain). A greenhouse farm smartly monitored with embedded devices, a control interface for these devices, and a web platform for product distribution and consumer management platform was developed to create a unified smart agricultural echo system. The embedded system has sensors that monitor the levels of light, temperature, soil moisture and humidity and automatically open the tap to water the farm. In addition, the supply chain was designed for the distribution of farm products. The prototype was fabricated and tested. The results showed that both the electronic part and the supply chain are working as proposed.

ESQuMo an Embedded Software Quality Model

Embedded systems are increasingly used in our daily life due to their importance. They are computer platforms consisting of hardware and software. They run specific tasks to realize functional and non functional requirements. Several specific quality attributes were identified as relevant to the embedded system domain. However, the existent general quality models do not address clearly these specific quality attributes. Hence, the proposition of quality models which address the relevant quality attributes of embedded systems needs more attention and investigation. The major goal of this paper is to propose a new quality model (called ESQuMo for Embedded Software Quality Model) which provides a better understanding of quality in the context of embedded software. Besides, it focuses the light on the relevant attributes of the embedded software and addresses clearly the importance of these attributes. In fact, ESQuMo is based on the well-established ISO/IEC 25010 standard quality model.

Development of a smart clothing product using an Arduino platform

This paper presents a "smart" clothing product implemented as a jacket that contains sensors, a processing unit for display and interaction. The system has the ability to remotely read the data provided by the sensors, ensuring the monitoring of several parameters of the wearer. The following characteristics have been considered: body temperature and humidity, atmospheric temperature, pressure and altitude, the heart beat and number of steps converted into the number of calories consumed and traveled distance. The data is acquired and processed by an Arduino AT Mega 2560, via the I2C bus, digital ports and analog to digital converters, depending on the type of sensors. The processed information is printed on a 128x64 pixel display. To be able to view more pages of information, one can interact with the 4-key keyboard that has been connected to the digital input ports or through a proximity sensor, which will function as a gesture sensor. The processed information can also be accessed from a web server, built on the ESP8266 Wi-Fi module, connected to Arduino's TX/RX lines. A mobile phone or another device can connect to the Access Point and open a web page which displays the values of all sensors, as well as other information. The embedded system was inserted on a jacket and wired according to the sensors and modules usage.

Detection and Classification System for Rail Surface Defects Based on Eddy Current

The prospect of growth of a railway system impacts both the network size and its occupation. Due to the overloaded infrastructure, it is necessary to increase reliability by adopting fast maintenance services to reach economic and security conditions. In this context, one major problem is the excessive friction caused by the wheels. This contingency may cause ruptures with severe consequences. While eddy’s current approaches are adequate to detect superficial damages in metal structures, there are still open challenges concerning automatic identification of rail defects. Herein, we propose an embedded system for online detection and location of rails defects based on eddy current. Moreover, we propose a new method to interpret eddy current signals by analyzing their wavelet transforms through a convolutional neural network. With this approach, the embedded system locates and classifies different types of anomalies, enabling an optimization of the railway maintenance plan. Field tests were performed, in which the rail anomalies were grouped in three classes: squids, weld and joints. The results showed a classification efficiency of ~98%, surpassing the most commonly used methods found in the literature.

Design and Research of Optical Fiber Signal Analyzer in Embedded System Based on Big Data

With the advent of the era of big data, substation automation technology has reached a certain level after more than ten years of application development. In recent years, in the transformation and construction of the transmission and distribution network, a large number of substations have adopted modern technology, which has greatly improved the technological modernization of transmission and distribution and transformer construction, enhanced the reliability of transmission and distribution and transformer scheduling, and reduced the substation. The total cost of construction and the application of electronic transformers have effectively promoted the research on digital substations. In order to complete the real-time monitoring and testing of the substation system, so as to more quickly grasp the working status of the substation equipment, this paper proposes a research and design of an optical fiber signal analyzer for substation system testing. By analyzing the IEC 61850 protocol, the characteristics of the embedded system and the embedded operating system, the software modular design of the sampling value module of the signal analyzer is carried out, and the analysis of the substation configuration file SCD is designed and realized. The research results show that in practical applications, it is necessary to parse the CID files one by one, which will cause cumbersome work and easy omissions. Based on the above considerations, the SCD configuration file containing the entire site information was finally selected.

System for Remote Collaborative Embedded Development

This paper explores the challenges and devised solutions for embedded development which arose during the COVID-19 pandemic. While software development, nowadays with modern tools and services such as git, virtual machines and commu-nication suits, is relatively una˙ected by resource location. That is not the case for firmware and embedded systems, which relies on physical hard-ware for design, development, and testing. To overcome the limitations of remote work and ob-structed access to actual hardware, two ideas were implemented and tested. First, based on inte-grated circuit emulation using QEMU to emulate an ARM core and custom software to facilitate communication with the embedded system. Sec-ond, remote programming and debugging over the internet with a dedicated computer system acting as a middle man between a development environ-ment and physical hardware using OpenOCD de-bugger.

Simulator Proses Pengisian dan Pemasangan Tutup Botol Terkendali PLC Berbantuan Miniatur Konveyor

A miniature conveyor machine assisted by embedded systems and controlled by a programmable logic controller (PLC) has been fabricated with the operating mechanism is based on the detection of two different colors. The objectives of this research are to obtain a miniature machine is controlled by the PLC system, create a ladder diagram-based program structure, and measure the performance of the embedded system. Obtaining the machine is carried out through assembly of the conveyor frame, installation of all devices, and integrated wiring. The programming for the Omron PLC system is based on providing the CX-Programmer 64 bits, establishing algorithms and compiling ladder diagrams, and compiling and uploading processes. The performance measurement includes synchronization conditions between the simulator and the control system, observations of the readings of installed sensors for activating all devices on the output side, and observing the measurement of the filling process time and the installation of bottle caps assisted by the pneumatic system. The results of the performance during the process of filling and installing the lid obtained a success rate of 75%, based on four trials, three successes, and one failure. The general conclusion is that the embedded system that has been built can be used as a simulator for the mechanism of filling liquid into bottles and installing bottle caps, and it is as an implementation of instrumentation and automation processes.