Robotics, IoT and AI Technologies in Bioengineering DOI Creative Commons
Luigi Bibbò, Alessia Bramanti

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(9), P. 5070 - 5070

Published: May 2, 2025

Bioengineering is a discipline that integrates aspects of traditional engineering with health-related issues [...]

Language: Английский

Classifying Storage Temperature for Mandarin (Citrus reticulata L.) Using Bioimpedance and Diameter Measurements with Machine Learning DOI Creative Commons

Daesik Son,

S. D. Lee, S. Jeon

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(8), P. 2627 - 2627

Published: April 21, 2025

Mandarin (Citrus reticulata L.) is consumed worldwide. Improper storage temperatures cause flavor loss and shorten shelf lives, reducing marketability. Mandarins’ quality difficult to assess visually, as they show no apparent changes during storage. Therefore, a simple, non-destructive method needed their freshness affected by temperature. This work utilized non-invasive bioimpedance spectroscopy (BIS) on mandarins stored at different temperatures. Eight machine learning (ML) models were trained with data classify Also, we confirmed whether integrating diameter time-series into the could improve ML models’ accuracies minimizing sample variations. Additionally, evaluated effectiveness of equivalent circuit (EC) parameters derived from for training. Although slightly less accurate than using raw data, EC can efficiently reduce dimensionality. Among all models, SVM model in integrated achieved highest accuracy 0.92. It was significant improvement compared 0.76 when only data. Thus, this study suggests novel temperature mandarins. approach also be applied other fruits utilizing BIS.

Language: Английский

Citations

0

A Physiological Evaluation of Driver Workload in the Lead Vehicle of an Autonomous Truck Platoon Using Bio-Signal Analysis DOI Open Access
Emi Yuda, Junichiro Hayano, Makoto Takahashi

et al.

Electronics, Journal Year: 2025, Volume and Issue: 14(8), P. 1681 - 1681

Published: April 21, 2025

The evaluation of driver workload in the lead vehicle a driver-following autonomous truck platoon was conducted using bio-signal analysis. In this study, single operated while second and third trucks followed autonomously. Three professional drivers (38 ± 4 years old, male) participated experiment. During driving, wearable sensors measured heart-rate variability indices, body acceleration, skin temperature. heart rate acceleration were sampled at 128 Hz (7.8 ms intervals), temperature recorded 1 Hz. Each participant underwent three measurement sessions on different days, with each session lasting approximately 30–40 min. Statistical analysis performed repeated-measures ANOVA to determine significant differences across conditions days. results indicated that compared solo driving significantly increased (p < 0.001), suggesting higher physiological workload. This study provides insight into impact platooning lead-vehicle drivers, which is crucial for developing strategies mitigate such systems.

Language: Английский

Citations

0

Differential Phase Coupler Using Balun-Type Power Divider DOI Creative Commons
Chatrpol Pakasiri,

Chung-Yu Chang,

Sen Wang

et al.

Micromachines, Journal Year: 2025, Volume and Issue: 16(5), P. 496 - 496

Published: April 24, 2025

This paper presents a differential phase coupler design methodology in the IPD process. The consists of balun and two phase-shifter circuits. compact was designed with lumped components common inductor. Each output circuit connected to shifter an opposite make desired phase. In example, three-port 90-degree hybrid implemented on process operate at 6 GHz WIFI frequency. post-simulation showed that all reflection coefficients were below −19 dB, insertion loss 1.76 dB isolation 20 dB. core chip size only 0.02λ0 × 0.018λ0.

Language: Английский

Citations

0

Neural Network Implementation for Fire Detection in Critical Infrastructures: A Comparative Analysis on Embedded Edge Devices DOI Open Access
Jon Aramendia, Andrea Cabrera, Jon Martín

et al.

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1809 - 1809

Published: April 29, 2025

This paper explores the application of artificial intelligence on edge devices to enhance security in critical infrastructures, with a specific focus use case battery-powered mobile system for fire detection tunnels. The study leverages YOLOv5 convolutional neural network (CNN) real-time detection, focusing comparative analysis across three low-power platforms, NXP i.MX93, Xilinx Kria KV260, and NVIDIA Jetson Orin Nano, evaluating their performance terms accuracy (mAP), inference time, energy consumption. also presents methodology implementing networks various aiming provide scalable approach (AI) deployment. findings offer valuable insights into trade-offs between computational efficiency power consumption, guiding selection computing solutions security-critical applications.

Language: Английский

Citations

0

VRBiom: A New Periocular Dataset for Biometric Applications of Head-Mounted Display DOI Open Access
Ketan Kotwal, Ibrahim Ulucan, Gökhan Özbulak

et al.

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1835 - 1835

Published: April 30, 2025

With advancements in hardware, high-quality head-mounted display (HMD) devices are being developed by numerous companies, driving increased consumer interest AR, VR, and MR applications. This proliferation of HMD opens up possibilities for a wide range applications beyond entertainment. Most commercially available equipped with internal inward-facing cameras to record the periocular areas. Given nature these captured data, many such as biometric authentication gaze analysis become feasible. To effectively explore potential HMDs diverse use-cases enhance corresponding techniques, it is essential have an dataset that captures realistic scenarios. In this work, we present new videos acquired using virtual reality headset called VRBiom. The VRBiom, targeted at applications, consists 900 short from 25 individuals recorded NIR spectrum. These 10 s long been tracking Meta Quest Pro 72 FPS. encompass real-world variations, includes recordings under three conditions: steady, moving, partially closed eyes. We also ensured equal split without glasses facilitate eye-wear. videos, characterized non-frontal views eye relatively low spatial resolutions (400×400), can be instrumental advancing state-of-the-art research across various VRBiom utilized evaluate, train, or adapt models iris and/or recognition associated sub-tasks detection semantic segmentation. addition data real individuals, included around 1100 presentation attacks constructed 92 PA instruments. PAIs fall into six categories through combinations print (real synthetic identities), fake 3D eyeballs, plastic eyes, types masks mannequins. combined genuine (bona fide) address concerns related spoofing, which significant threat if used authentication. publicly purposes only.

Language: Английский

Citations

0

Robotics, IoT and AI Technologies in Bioengineering DOI Creative Commons
Luigi Bibbò, Alessia Bramanti

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(9), P. 5070 - 5070

Published: May 2, 2025

Bioengineering is a discipline that integrates aspects of traditional engineering with health-related issues [...]

Language: Английский

Citations

0