Raspberry Pi Research Articles

Construction Jobsite Image Classification Using an Edge Computing Framework

Image classification is increasingly being utilized on construction sites to automate project monitoring, driven by advancements in reality-capture technologies and artificial intelligence (AI). Deploying real-time applications remains a challenge due to the limited computing resources available on-site, particularly on remote construction sites that have limited telecommunication support or access due to high signal attenuation within a structure. To address this issue, this research proposes an efficient edge-computing-enabled image classification framework for support of real-time construction AI applications. A lightweight binary image classifier was developed using MobileNet transfer learning, followed by a quantization process to reduce model size while maintaining accuracy. A complete edge computing hardware module, including components like Raspberry Pi, Edge TPU, and battery, was assembled, and a multimodal software module (incorporating visual, textual, and audio data) was integrated into the edge computing environment to enable an intelligent image classification system. Two practical case studies involving material classification and safety detection were deployed to demonstrate the effectiveness of the proposed framework. The results demonstrated the developed prototype successfully synchronized multimodal mechanisms and achieved zero latency in differentiating materials and identifying hazardous nails without any internet connectivity. Construction managers can leverage the developed prototype to facilitate centralized management efforts without compromising accuracy or extra investment in computing resources. This research paves the way for edge “intelligence” to be enabled for future construction job sites and promote real-time human-technology interactions without the need for high-speed internet.

Development of an intelligent-based telemetry hexapod robotic system for surveillance of power system components

A robot is an artificial system that performs specific programmed tasks to aid day-to-day human activities. Robot finds applications in industries for large-scale production, healthcare for computer-aided surgeries, security for surveillance of electrical power system equipment, and the military for carrying out dangerous reconnaissance. Most robotic systems employed for different operations use a wheeled mode of locomotion which has limitations over rough terrains and the issue of communication setup of the system. This work developed a hexapod, a six-legged robotic system, to overcome these identified challenges. The robot was developed in tandem with a telemetry system for surveillance. Although, automating the surveillance process using robotic systems has been in the works for some time. However, this work developed a telemetry hexapod robotic system for enhanced surveillance for the security of power systems equipment and other critical infrastructures using a Raspberry Pi for fast, secure data transmission, and precise system synchronization. An inverse kinematics approach was used to determine joint configurations for better positions of each endpoint. A digital camera was integrated into the robot to relay real-time images of adversaries of power system components intelligently. In addition, the system incorporates data processing capability. In the result obtained, the developed telemetry hexapod robotic system receives instructions over a distance slightly above 300 m. It establishes effective control of the telemetry system without any hindrance of a limited range as observed in Bluetooth-controlled systems. The system's performance includes an average efficiency of 98.2 %, latency of 0.48 s at the peak distance, and an endurance of 4 h. Further analysis of the system shows that the corresponding increase in the latency with the distance is negligible. The system performed better than other related systems considered in the literature. The correct implementation of the developed telemetry hexapod robotic system further enhances mobility, stability in rough terrain, reliable communication system. Also, it brings about a notable reduction in component theft in electrical power systems.

ECG signal analysis and detection system based on deep learning

In view of the problems of large workload and easy error in traditional manual recognition of ECG signals, and the existing ECG monitoring equipment still has few ECG signal recognition types, low diagnostic accuracy, and excessive reliance on network services, in order to improve the performance of ECG monitoring equipment, an ECG (Electrocardiogram Signals) analysis and detection system is designed based on deep learning technology. The SENet-LSTM (Squeeze-and-Excitation Networks Long Short Term Memory) network model is built to realize automatic diagnosis of 7 categories of ECG signals. The model is built on an intelligent hardware platform that uses ADS1292R as ECG acquisition module, STM32F103 as data processing module, and Raspberry Pi as central processing module. The system uses the integrated high- performance microcomputer Raspberry Pi for calculation and analysis, providing users with offline artificial intelligence (AI: Artificial Intelligence) services. At the same time, the accuracy and precision of the model are and respectively 98.44%, 90.00%thereby realizing real-time detection and accurate classification of ECG, providing patients with accurate disease diagnosis.

Analysis and comparison of encryption and verification algorithms applied to a Fog Computing Architecture

ABSTRACT Due to the Internet of Things (IoT) widespread adoption, data traffic to cloud servers for analysis has surged, impacting IoT system latency. Fog Computing emerged as a solution, bringing processing capabilities closer to data generation points, reducing data sent to the cloud, and improving response times. However, it intensifies security concerns due to the proximity of sensitive data to users and limited node computational resources. This research aims to study encryption and data verification algorithms using various datasets and the cryptography software OpenSSL. Testing is performed on Raspberry Pi hardware, facilitating the implementation of Fog nodes. Metrics such as CPU, memory, and energy consumption are evaluated using scripts. Results show that data type does not influence algorithm choice, and patterns related to data size behaviour are identified, aiding in defining security strategies.

The collapse of modern exposures in the recording of X-RAY images in medicine

This article reviewed the methods and algorithms for processing and diagnosing X-ray images that are widely used in medicine today. In order to improve the implementation of deep learning in modern medicine and further improve the widespread use of HMLs, the method, algorithm and model of X-ray image processing using the Raspberry Pi device were analyzed.

Zigbee-Based Wireless Sensor Network of MEMS Accelerometers for Pavement Monitoring

In this paper, we propose a wireless sensor network for pavement health monitoring exploiting the Zigbee technology. Accelerometers are adopted to measure local accelerations linked to pavement vibrations, which are then converted into displacements by a signal processing algorithm. Each device consists of an on-board unit buried in the roadway and a roadside unit. The on-board unit comprises a microcontroller, an accelerometer and a Zigbee module that transfers acceleration data wirelessly to the roadside unit. The roadside unit consists of a Raspberry Pi, a Zigbee module and a USB Zigbee adapter. Laboratory tests were conducted using a vibration table and with three different accelerometers, to assess the system capability. A typical displacement signal from a five-axle truck was applied to the vibration table with two different displacement peaks, allowing for two different vehicle speeds. The prototyped system was then encapsulated in PVC packaging, deployed and tested in a real-life road situation with a fatigue carousel featuring rotating truck axles. The laboratory and on-road measurements show that displacements can be estimated with an accuracy equivalent to that of a reference sensor.

The Design of Multi-Connector IoT Central Gateway Based on Raspberry Pi and Docker

With the vigorous development of Internet of Things (IoT) technology, the demand for communication and data exchange between different types of IoT devices is increasing day by day. To solve the problems of diversity and complexity of communication protocols between devices, this paper proposes a design scheme of a multi-connector IoT central gateway based on Raspberry Pi and Docker. Through the research and application of related technologies, by integrating multiple communication interfaces and utilizing containerization technology, an efficient, flexible, and scalable IoT central gateway has been realized, which can support the connection and data interaction of multiple communication protocols and provide strong support for the stable operation and development of the IoT system.

Real-Time Forward Head Posture Detection and Correction System Utilizing an Inertial Measurement Unit Sensor

Forward head posture (FHP) has become a prevailing health issue in modern society as people spend more time on computers and smartphones. FHP is a posture where the head is forward and the anterior and posterior curvatures of the lower cervical and upper thoracic spines are both, respectively, exaggerated. FHP is often associated with neck pain, bad static balance, and hunched shoulders or back. To prevent this, consciously maintaining good posture is important. Therefore, in this study, we propose a system that gives users real-time, accurate information about their neck posture, and it also encourages them to maintain a good posture. This inexpensive system utilizes a single inertial measurement unit sensor and a Raspberry Pi system to detect the changes in state that can progress to an FHP. It retrieves data from the sensor attached to the user’s cervical spine to indicate their real-time posture. In a real-world office environment experiment with ten male participants, the system accurately detected the transition to the FHP state for more than 10 s, with a delay of less than 0.5 s, and it also provided personalized feedback to encourage them to maintain good posture. All ten participants recognized that their average craniovertebral angle had to be increased after receiving visual alerts regarding their poor postures in real time. The results indicate that the system has potential for widespread applications.

ISETECH-Analysis Detection of Real-Time Metallic Surface Defect using MobileNetv2 and YOLOv3 on Raspberry Pi

This work presents an innovative solution utilizing a Raspberry Pi detection system to identify any defects on metallic surfaces in real-time. Manual inspection has several limitations, including time-consuming, subjective assessments, and a higher probability of human error could compromise product quality, lead to potential failures, and result in substantial costs for manufacturers. The primary focus of this endeavour is to enhance manufacturing efficiency and reduce labour expenses by automating the defect identification process. This objective is realized by employing the YOLOv3-tiny and MobileNetv2 algorithms which are subsequently deployed on a Raspberry Pi to enable precise and swift defect detection on metallic surfaces. The implementation process involves training and testing the models on a computer, followed by their deployment onto the Raspberry Pi. Upon proper setup, the trained models are employed for real-time inferences, effectively identifying defects. Notably, while the MobileNetv2 exhibits impressive accuracy in classifying defect types above 0.9, it is found to be less efficient for real-time detection on the Raspberry Pi. In contrast, the YOLO model proves to be well-suited for real-time detection on this platform with above probability of 0.8 for selected types of defects. The successful integration of this model significantly transforms quality control and inspection procedures across various industries.

IoT-Based Smart Parking System

the research is about parking management using iot devices like raspberry pi, sensorand LCD. it will navigate drivers to the vacant parking spot and also display how many spots are empty

Leveraging Digital Twins and Intrusion Detection Systems for Enhanced Security in IoT-Based Smart City Infrastructures

In this research, we investigate the integration of an Intrusion Detection System (IDS) with a Digital Twin (DT) to enhance the cybersecurity of physical devices in cyber–physical systems. Using Eclipse Ditto as the DT platform and Snort as the IDS, we developed a near-realistic test environment that included a Raspberry Pi as the physical device and a Kali Linux virtual machine to perform common cyberattacks such as Hping3 flood attacks and NMAP reconnaissance scans. The results demonstrated that the IDS effectively detected Hping3-based flood attacks but showed limitations in identifying NMAP scans, suggesting areas for IDS configuration improvements. Furthermore, the study uncovered significant system resource impacts, including high Central Processing Unit (CPU) usage during SYN and ACK flood attacks and persistent memory usage after Network Mapper (NMAP) scans, highlighting the need for enhanced recovery mechanisms. This research presents a novel approach by coupling a Digital Twin with an IDS, enabling real-time monitoring and providing a dual perspective on both system performance and security. The integration offers a holistic method for identifying vulnerabilities and understanding resource impacts during cyberattacks. The work contributes new insights into the use of Digital Twins for cybersecurity and paves the way for further research into automated defense mechanisms, real-world validation of the proposed model, and the incorporation of additional attack scenarios. The results suggest that this combined approach holds significant promise for enhancing the security and resilience of IoT devices and other cyber–physical systems.

THE TRAINING OF TEMPERATURE MONITORING SYSTEM WITH LM35 SENSOR BASED ON RESBEERY PI

Abstract. This community service activity aims to train the community on developing and implementing a temperature monitoring system using the LM35 sensor integrated with Raspberry Pi. This training was carried out to improve people's understanding and skills, especially in utilizing microcontroller-based technology and IoT (Internet of Things) in daily life, especially in the field of room temperature or environmental monitoring. This activity involves targets, for example, teachers, students, and technicians, at SMA AL-IRSYAD TEGAL, with training methods that include basic theories about temperature sensors, introduction to Raspberry Pi, and hands-on practice in assembling and programming temperature monitoring systems. The results of this training showed that participants could understand the basic concepts of temperature monitoring systems and could apply the knowledge gained in making simple devices that can measure and display temperature in real time. The activity evaluation showed that most of the participants felt helped by this training and showed high interest in further developing the system that had been studied. In the future, it is hoped that similar activities can continue to be carried out to empower the community to utilize technology for daily needs. Keywords: Community service, temperature monitoring system, LM35, Raspberry Pi, technology training.

Environmental sound classification on an embedded hardware platform

Convolutional neural networks (CNNs) have exhibited state-of-the-art performance in various audio classification tasks. However, their real-time deployment remains a challenge on resource constrained devices such as embedded systems. In this paper, we analyze how the performance of large-scale pre-trained audio neural networks designed for audio pattern recognition changes when deployed on a hardware such as a Raspberry Pi. We empirically study the role of CPU temperature, microphone quality and audio signal volume on performance. Our experiments reveal that the continuous CPU usage results in an increased temperature that can trigger an automated slowdown mechanism in the Raspberry Pi, impacting inference latency. The quality of a microphone, specifically with affordable devices such as the Google AIY Voice Kit, and audio signal volume, all affect the system performance. In the course of our investigation, we encounter substantial complications linked to library compatibility and the unique processor architecture requirements of the Raspberry Pi, making the process less straightforward compared to conventional computers (PCs). Our observations, while presenting challenges, pave the way for future researchers to develop more compact machine learning models, design heat-dissipative hardware, and select appropriate microphones when AI models are deployed for real-time applications on edge devices.

Beyond loudness: development of a holistic solar-powered urban soundscape sensor

Low-cost sensor networks have increasingly been used to monitor noise pollution as an alternative to certified sound level meters. Existing sensor networks monitor loudness and, in some cases, classify sound sources. Most sensors do not capture metrics that are more representative of the human perception of sound, require a permanent power supply, or are relatively expensive. We develop an energy-efficient soundscape sensor with the goal of recording metrics complementary to loudness. We have implemented metrics from psychoacoustics and metrics inspired by biodiversity research, such as sharpness, intermittency, and acoustic entropy. Furthermore, the sensor predicts the source of sound events. For privacy-preservation, all audio is processed directly on the sensor. The sensor is based on a low-power microcontroller (ESP32-S3), available for a fraction of the cost of a Raspberry Pi, which is often used for sound source prediction. Finally, the sensor is solar-powered and therefore easy to install for research purposes at places without direct access to the power grid. A temporary deployment of several sensors in Amsterdam, the Netherlands, is planned

Improved yolov5 algorithm combined with depth camera and embedded system for blind indoor visual assistance

To assist the visually impaired in their daily lives and solve the problems associated with poor portability, high hardware costs, and environmental susceptibility of indoor object-finding aids for the visually impaired, an improved YOLOv5 algorithm was proposed. It was combined with a RealSense D435i depth camera and a voice system to realise an indoor object-finding device for the visually impaired using a Raspberry Pi 4 B device as its core. The algorithm uses GhostNet instead of the YOLOv5s backbone network to reduce the number of parameters and computation of the model, incorporates an attention mechanism (coordinate attention), and replaces the YOLOv5 neck network with a bidirectional feature pyramid network to enhance feature extraction. Compared to the YOLOv5 model, the model size was reduced by 42.4%, number of parameters was reduced by 47.9%, and recall rate increased by 1.2% with the same precision. This study applied the improved YOLOv5 algorithm to an indoor object-finding device for the visually impaired, where the searched object was input by voice, and the RealSense D435i was used to acquire RGB and depth images to realize the detection and ranging of the object, broadcast the specific distance of the target object by voice, and assist the visually impaired in finding the object.

Convolutional Neural Networks for Real Time Classification of Beehive Acoustic Patterns on Constrained Devices.

Recent research has demonstrated the effectiveness of convolutional neural networks (CNN) in assessing the health status of bee colonies by classifying acoustic patterns. However, developing a monitoring system using CNNs compared to conventional machine learning models can result in higher computation costs, greater energy demand, and longer inference times. This study examines the potential of CNN architectures in developing a monitoring system based on constrained hardware. The experimentation involved testing ten CNN architectures from the PyTorch and Torchvision libraries on single-board computers: an Nvidia Jetson Nano (NJN), a Raspberry Pi 5 (RPi5), and an Orange Pi 5 (OPi5). The CNN architectures were trained using four datasets containing spectrograms of acoustic samples of different durations (30, 10, 5, or 1 s) to analyze their impact on performance. The hyperparameter search was conducted using the Optuna framework, and the CNN models were validated using k-fold cross-validation. The inference time and power consumption were measured to compare the performance of the CNN models and the SBCs. The aim is to provide a basis for developing a monitoring system for precision applications in apiculture based on constrained devices and CNNs.

The Development of Remotely Operated Underwater Vehicle for Plastic Waste Detection with Raspberry Pi

Abstract Underwater Plastic waste has had a serious impact on the environment. Unfortunately, Detecting and collecting underwater plastic waste is still a challenge, especially in Indonesia because of its position in the water, and the water turbidity. In previous research, a computer algorithm for detecting underwater plastic waste has been developed with Yolov3. To improve the research, we developed a Remotely Operated Underwater Vehicle (ROUV) with Raspberry Pi through the Research and Development (R&D) method. This ROUV is like a submarine that operates in the water and is integrated with a camera and computer algorithm to detect plastic waste. To get close to the real condition, we created an artificial water environment in a pond with various turbidity (from 20 to 200 Nephelometric Turbidity Unit). We use 30 pieces of plastic waste in several colors: white, red, black, and transparent. The plastic waste dipped in the water and was then detected by the ROUV camera. The result shows that the effective threshold for object detection is around 100 Nephelometric Turbidity Unit (NTU). Below 100 NTU, although the number of detected plastic images decreases as the turbidity increases, the visibility and contrast still allow for reasonably good object detection. The average confidence value for detection at turbidity levels below 100 NTU is 77%. At high turbidity conditions, the detection model may require adjustment or retraining with data that reflects those turbidity conditions.

Design of a Portable Spectrophotometer Based on Raspberry Pi for Tea Type Classification Using Machine Learning

Abstract The use of spectrophotometers in food and beverage quality analysis has become common. However, portability and high cost have long been a problem for food industry players and small-scale laboratories. In this study, a more compact and low-cost spectrophotometer has been developed using raspberry pi. To validate its performance, the prototype was used to classify green tea, black tea, and oolong tea types. The research started with designing and assembling the hardware using a raspberry pi camera with Complementary Metal Oxide Semiconductor (CMOS) sensor, Digital Versatile Disk (DVD) as diffraction grating, white LED as light source and 3D printer as casing. The prototype was then used to acquire data from green tea, black tea and oolong tea solutions. In the tea type identification process, Principal Component Analysis (PCA) was applied to the data obtained. The experiment involved 30 solution samples of each of the three types of tea. The light source was directed past the sample towards the slit and DVD, then the spectrum image of the light source was displayed through a user interface built using python programming. This research resulted in a spectrophotometer with dimensions of 260 mm x 120 mm x 63 mm that is capable of capturing light spectra in the range of 400 - 700 nm. Based on the experimental results, the classification accuracy of the three types of tea using CNN and Decision Tree reached 100%.

The use of digital twin for mobile robot swarm task allocation

Cyber-physical systems, with the advent of the Internet of Things (IoT), have paved the way for the rise of the Industrial Internet of Things (IIoT) in industrial environments. A significant manifestation of this synergy is the Digital Twin—a virtual representation of industrial entities, including robots. This paper examines the fusion of digital twins in swarm robotics, emphasizing communication, and task allocation among robots. This study employs several mobile robots interconnected via a wireless network, each equipped with a Raspberry Pi and specific sensors. A centralized server, acting as both a Docker host and a Docker registry, facilitates task allocation. The results indicate effective communication among robots, with the digital twin playing an instrumental role in safety assessment and task allocation, as well as deploying Docker containers using Portainer and GitLab APIs. Unity3D aids in visualizing IMU motion and orientation. The motivation behind this study stems from the need to enhance efficiency and safety in industrial settings through advanced automation and coordination in swarm robotics. This research not only demonstrates the feasibility of integrating digital twins with IoT-enabled robots but also sets the stage for future investigations into more complex task allocation and safety protocols in industrial environments. By leveraging digital twins in swarm robotics, we open new pathways for research into more adaptive, responsive, and efficient industrial systems.

Imaging pollen using a Raspberry Pi and LED with deep learning

The production of low-cost, small footprint imaging sensor would be invaluable for airborne global monitoring of pollen, which could allow for mitigation of hay fever symptoms. We demonstrate the use of a white light LED (light emitting diode) to illuminate pollen grains and capture their scattering pattern using a Raspberry Pi camera. The scattering patterns are transformed into 20× microscope magnification equivalent images using deep learning. We show the ability to produce images of pollen from plant species previously unseen by the neural network in training. Such a technique could be applied to imaging airborne particulates that contribute to air pollution, and could be used in the field of environmental science, health science and agriculture.