A Computational Comparative Analysis Between Nvidia Jetson Nano and Raspberry Pi CM4 for the Classification of White Asparagus with SVM

Ruiz, Edgar; Ortiz, Manuel; Vinces, Leonardo

doi:10.1007/978-3-031-08545-1_49

Cited by 6 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The computing devices employed include Raspberry Pi models 4 and 3B, featuring ARM Cortex-A53 CPU1 with 1 GB and ARM Cortex BCM2711 at 1.5 GHz with 4 GB, respectively. Early tests also utilized Nvidia’s Jetson, which offers performance comparable to the Raspberry Pi 4 model [ 85 , 86 ].…”

Section: Methodsmentioning

confidence: 99%

Streamline Intelligent Crowd Monitoring with IoT Cloud Computing Middleware

Gazis,

Katsiri

2024

Sensors

View full text Add to dashboard Cite

This article introduces a novel middleware that utilizes cost-effective, low-power computing devices like Raspberry Pi to analyze data from wireless sensor networks (WSNs). It is designed for indoor settings like historical buildings and museums, tracking visitors and identifying points of interest. It serves as an evacuation aid by monitoring occupancy and gauging the popularity of specific areas, subjects, or art exhibitions. The middleware employs a basic form of the MapReduce algorithm to gather WSN data and distribute it across available computer nodes. Data collected by RFID sensors on visitor badges is stored on mini-computers placed in exhibition rooms and then transmitted to a remote database after a preset time frame. Utilizing MapReduce for data analysis and a leader election algorithm for fault tolerance, this middleware showcases its viability through metrics, demonstrating applications like swift prototyping and accurate validation of findings. Despite using simpler hardware, its performance matches resource-intensive methods involving audiovisual and AI techniques. This design’s innovation lies in its fault-tolerant, distributed setup using budget-friendly, low-power devices rather than resource-heavy hardware or methods. Successfully tested at a historical building in Greece (M. Hatzidakis’ residence), it is tailored for indoor spaces. This paper compares its algorithmic application layer with other implementations, highlighting its technical strengths and advantages. Particularly relevant in the wake of the COVID-19 pandemic and general monitoring middleware for indoor locations, this middleware holds promise in tracking visitor counts and overall building occupancy.

show abstract

Section: Methodsmentioning

confidence: 99%

Streamline Intelligent Crowd Monitoring with IoT Cloud Computing Middleware

Gazis,

Katsiri

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…In that study, only machine learning algorithms were compared. The complexity of the algorithms is relatively low and is not studied for more advanced and complex deep learning algorithms [10]. Gunawan Dewantoro used image processing and computer vision techniques to allow the patrol robot to identify objects and control robot motion.…”

Section: Related Workmentioning

confidence: 99%

The Performance Analysis of PSO-ResNet for the Fault Diagnosis of Vibration Signals Based on the Pipeline Robot

Zhang

Kim

2023

Sensors

View full text Add to dashboard Cite

In the context of pipeline robots, the timely detection of faults is crucial in preventing safety incidents. In order to ensure the reliability and safety of the entire application process, robots’ fault diagnosis techniques play a vital role. However, traditional diagnostic methods for motor drive end-bearing faults in pipeline robots are often ineffective when the operating conditions are variable. An efficient solution for fault diagnosis is the application of deep learning algorithms. This paper proposes a rolling bearing fault diagnosis method (PSO-ResNet) that combines a Particle Swarm Optimization algorithm (PSO) with a residual network. A number of vibration signal sensors are placed at different locations in the pipeline robot to obtain vibration signals from different parts. The input to the PSO-ResNet algorithm is a two-bit image obtained by continuous wavelet transform of the vibration signal. The accuracy of this fault diagnosis method is compared with different types of fault diagnosis algorithms, and the experimental analysis shows that PSO-ResNet has higher accuracy. The algorithm was also deployed on an Nvidia Jetson Nano and a Raspberry Pi 4B. Through comparative experimental analysis, the proposed fault diagnosis algorithm was chosen to be deployed on the Nvidia Jetson Nano and used as the core fault diagnosis control unit of the pipeline robot for practical scenarios. However, the PSO-ResNet model needs further improvement in terms of accuracy, which is the focus of future research work.

show abstract