NSTL国家科技图书文献中心

1. Enhancing Agricultural Internet of Things Data Accuracy: Evaluating Kalman Filter-Based Sensor Denoising Techniques NSTL国家科技图书文献中心

Armando, Egas Jose | Hanyurwimfura, Damie...... - 《Journal of Biosystems Engineering》 - 2025,50(1) - 47～58 - 共12页

摘要： filter models on a Raspberry* Pi 4.MethodsA sensor node* | PurposeWith the rapid adoption of the Internet | of Things (IoT) in agriculture, monitoring | ecological parameters has become increasingly important for | farmers aiming to optimize crop yields. However, sensor

关键词： Real-time state prediction | Raspberry Pi 4 | Sensor denoising

2. Virtually Contiguous Memory Allocation in Embedded Systems: A Performance Analysis NSTL国家科技图书文献中心

Yacine Hadjadj | Chakib Mustapha Anou...... - 《IEEE embedded systems letters》 - 2025,17(1) - 26～29 - 共4页

摘要： Raspberry Pi 4 platform. Through a series of meticulously | In an era dominated by embedded systems, where | efficient memory management is crucial, this study delves | into the effectiveness of VCMalloc, a novel memory | allocator that ensures virtual contiguity, on the

关键词： Memory management | Resource management | Embedded systems | Dynamic scheduling | Task analysis | Distance measurement | Bars

3. Implementation of a License Plate Recognition System in Vietnam Using Embedding Devices NSTL国家科技图书文献中心

Vanha Tran | Thiloan Bui - 《Multi-disciplinary Trends in Artificial Intelligence,Part II》 - International Conference on Multi-disciplinary Trends in Artificial Intelligence - 2025, - 231～243 - 共13页

摘要： set, using Raspberry* Pi 4 hardware and Raspberry Pi* | Technology trend 4.0 has created a revolution | in devices integrating artificial intelligence (AI | ) to solve everyday problems, including license plate | recognition technology. Currently, many organizations in the

关键词： Automatic license plate recognition | Embedded devices | Single shot multibox detector | YOLOv8 | Vietnamese license plate

4. Catalysing assistive solutions by deploying light-weight deep learning model on edge devices NSTL国家科技图书文献中心

Kanak Manjari | Madhushi Verma ... - 《Journal of experimental and theoretical artificial intelligence》 - 2025,37(3) - 465～486 - 共22页

摘要：), Raspberry* Pi 4 (RPi4), Intel Neural Compute Stick 2 (NCS2* | models for real-time applications. Raspberry* Pi 3 (RPi3* | Nowadays, real-time object detection, which is | a crucial task, is being performed through image | processing and deep learning techniques. As there are

关键词： Assistive technology | edge devices | raspberry | neural compute stick | jetson NANO

5. Time-Lapse Imaging Identifies Key Indicators of Brown Planthopper Damage Progression in Rice Varieties NSTL国家科技图书文献中心

Choi, Nak Jung | Ku, Kibon ... - 《Entomological Research》 - 2025,55(3) - 共11页

摘要： acquisition with 12 Raspberry* Pi 4 Model B units and* | Raspberry Pi NoIR cameras fitted with blue filters for | Improving complex agronomic traits such as | yield, plant height, and disease resistance in rice | (Oryza sativa L.) is challenging due to their polygenic

关键词： collective parameter | image analysis | individual parameter | phenomics | phenotype

6. Development of a resource-efficient real-time vibration-based tool condition monitoring system using PVDF accelerometers NSTL国家科技图书文献中心

Kodric, Miha | Korbar, Jure ... - 《Measurement》 - 2025,251 - 117183.1～117183.8 - 共8页

摘要： Pi 4, and a data acquisition card. A multi-level | system integrates a PVDF-based accelerometer, Raspberry | Sustainable machining demands efficient tool | condition monitoring (TCM) to maximize tool utilization | and reduce environmental impact. Existing TCM

关键词： Tool condition monitoring | Surface roughness | Tool vibration | Turning | Tool used life

7. Leveraging Fog Computing for Security-Aware Resource Allocation in Narrowband Internet of Things NSTL国家科技图书文献中心

Mohan, Vamshi Sunku | Sankaran, Sriram ... - 《Software》 - 2025,55(4) - 683～713 - 共31页

摘要： prototype protocols on iFogSim2 and Raspberry* Pi 4* | Narrowband Internet of Things (NB-IoT) is | LPWAN operating using narrowband spectrum in IoTs | , requiring low data rates and long battery life. Since NB | -IoT does not support handover, the requirement to

关键词： deep learning | fog computing | narrowband internet of things (NB-IoT) | performance analysis | resource allocation | EFFICIENT

8. Structured PruningとQuantizationを用いた軽量化CNNによるコーヒー生豆の良否判定とその高速化 NSTL国家科技图书文献中心

内田雅人 | 橋本恭輔 ... - 《日本食品科学工学会誌》 - 2025,72(1) - 11～17 - 共7页

摘要：,モデルの実行速度を汎用デバイス(ここでは Raspberry* Pi 4B と Jetson Orin* | 本研究ではCNNを用いたコーヒー生豆の良否判定においてStructured Pruning | とQuantization によってモデルの軽量化および高速化しその有効性を検証した. 実験では | まず基準となるCNNのモデルを構築した. ここでは10層の畳み込み層と1層の全結合層を用いたモデルを | 作成した.基準となるCNNはテストデー夕を84.9%の精度で良否判定が可能なモデルとなった.次に

关键词：コーヒー豆 | 異常検知 | 深層学習 | 枝刈り | 量子化 | Coffee beans | Anomaly detection | Deep learning | Pruning | Quantization

9. Low Latency Visual Inertial Odometry With On-Sensor Accelerated Optical Flow for Resource-Constrained UAVs NSTL国家科技图书文献中心

Kuhne, Jonas | Magno, Michele ... - 《IEEE sensors journal》 - 2025,25(5) - 7838～7847 - 共10页

摘要： ARM Cortex-A72 processor of a Raspberry* Pi Compute* | Module 4. | Visual inertial odometry (VIO) is the task of | estimating the movement trajectory of an agent from an | onboard camera stream fused with additional inertial

关键词： Hardware acceleration | optical flow (OF) | visual odometry

10. Benchmarking Deep Learning Models for Object Detection on Edge Computing Devices NSTL国家科技图书文献中心

Daghash K. Alqahtani | Muhammad Aamir Cheem...... - 《Service-Oriented Computing,Part I》 - International Conference on Service-Oriented Computing - 2025, - 142～150 - 共9页

摘要： popular edge devices such as the Raspberry* Pi 3, 4, and* | Modern applications, such as autonomous | vehicles, require deploying deep learning algorithms on | resource-constrained edge devices for real-time image and | video processing. However, there is limited

摘要： filter models on a Raspberry* Pi 4.MethodsA sensor node* | PurposeWith the rapid adoption of the Internet | of Things (IoT) in agriculture, monitoring | ecological parameters has become increasingly important for | farmers aiming to optimize crop yields. However, sensor

关键词： Real-time state prediction | Raspberry Pi 4 | Sensor denoising

摘要： Raspberry Pi 4 platform. Through a series of meticulously | In an era dominated by embedded systems, where | efficient memory management is crucial, this study delves | into the effectiveness of VCMalloc, a novel memory | allocator that ensures virtual contiguity, on the

关键词： Memory management | Resource management | Embedded systems | Dynamic scheduling | Task analysis | Distance measurement | Bars

摘要： set, using Raspberry* Pi 4 hardware and Raspberry Pi* | Technology trend 4.0 has created a revolution | in devices integrating artificial intelligence (AI | ) to solve everyday problems, including license plate | recognition technology. Currently, many organizations in the

关键词： Automatic license plate recognition | Embedded devices | Single shot multibox detector | YOLOv8 | Vietnamese license plate

摘要：), Raspberry* Pi 4 (RPi4), Intel Neural Compute Stick 2 (NCS2* | models for real-time applications. Raspberry* Pi 3 (RPi3* | Nowadays, real-time object detection, which is | a crucial task, is being performed through image | processing and deep learning techniques. As there are

关键词： Assistive technology | edge devices | raspberry | neural compute stick | jetson NANO

摘要： acquisition with 12 Raspberry* Pi 4 Model B units and* | Raspberry Pi NoIR cameras fitted with blue filters for | Improving complex agronomic traits such as | yield, plant height, and disease resistance in rice | (Oryza sativa L.) is challenging due to their polygenic

关键词： collective parameter | image analysis | individual parameter | phenomics | phenotype

摘要： Pi 4, and a data acquisition card. A multi-level | system integrates a PVDF-based accelerometer, Raspberry | Sustainable machining demands efficient tool | condition monitoring (TCM) to maximize tool utilization | and reduce environmental impact. Existing TCM

关键词： Tool condition monitoring | Surface roughness | Tool vibration | Turning | Tool used life

摘要： prototype protocols on iFogSim2 and Raspberry* Pi 4* | Narrowband Internet of Things (NB-IoT) is | LPWAN operating using narrowband spectrum in IoTs | , requiring low data rates and long battery life. Since NB | -IoT does not support handover, the requirement to

关键词： deep learning | fog computing | narrowband internet of things (NB-IoT) | performance analysis | resource allocation | EFFICIENT

关键词：コーヒー豆 | 異常検知 | 深層学習 | 枝刈り | 量子化 | Coffee beans | Anomaly detection | Deep learning | Pruning | Quantization

摘要： ARM Cortex-A72 processor of a Raspberry* Pi Compute* | Module 4. | Visual inertial odometry (VIO) is the task of | estimating the movement trajectory of an agent from an | onboard camera stream fused with additional inertial

关键词： Hardware acceleration | optical flow (OF) | visual odometry

摘要： popular edge devices such as the Raspberry* Pi 3, 4, and* | Modern applications, such as autonomous | vehicles, require deploying deep learning algorithms on | resource-constrained edge devices for real-time image and | video processing. However, there is limited

关键词： Deep learning | Object detection models | Performance evaluation | Inference time | Energy efficiency | Accuracy | Edge

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： filter models on a Raspberry Pi 4.MethodsA sensor node | PurposeWith the rapid adoption of the Internet | of Things (IoT) in agriculture, monitoring | ecological parameters has become increasingly important for | farmers aiming to optimize crop yields. However, sensor

关键词： Real-time state prediction | Raspberry Pi 4 | Sensor denoising

摘要： Raspberry Pi 4 platform. Through a series of meticulously | In an era dominated by embedded systems, where | efficient memory management is crucial, this study delves | into the effectiveness of VCMalloc, a novel memory | allocator that ensures virtual contiguity, on the

关键词： Memory management | Resource management | Embedded systems | Dynamic scheduling | Task analysis | Distance measurement | Bars

摘要： set, using Raspberry Pi 4 hardware and Raspberry Pi | Technology trend 4.0 has created a revolution | in devices integrating artificial intelligence (AI | ) to solve everyday problems, including license plate | recognition technology. Currently, many organizations in the

关键词： Automatic license plate recognition | Embedded devices | Single shot multibox detector | YOLOv8 | Vietnamese license plate

摘要：), Raspberry Pi 4 (RPi4), Intel Neural Compute Stick 2 (NCS2 | models for real-time applications. Raspberry Pi 3 (RPi3 | Nowadays, real-time object detection, which is | a crucial task, is being performed through image | processing and deep learning techniques. As there are

关键词： Assistive technology | edge devices | raspberry | neural compute stick | jetson NANO

摘要： acquisition with 12 Raspberry Pi 4 Model B units and | Raspberry Pi NoIR cameras fitted with blue filters for | Improving complex agronomic traits such as | yield, plant height, and disease resistance in rice | (Oryza sativa L.) is challenging due to their polygenic

关键词： collective parameter | image analysis | individual parameter | phenomics | phenotype

摘要： Pi 4, and a data acquisition card. A multi-level | system integrates a PVDF-based accelerometer, Raspberry | Sustainable machining demands efficient tool | condition monitoring (TCM) to maximize tool utilization | and reduce environmental impact. Existing TCM

关键词： Tool condition monitoring | Surface roughness | Tool vibration | Turning | Tool used life

摘要： prototype protocols on iFogSim2 and Raspberry Pi 4 | Narrowband Internet of Things (NB-IoT) is | LPWAN operating using narrowband spectrum in IoTs | , requiring low data rates and long battery life. Since NB | -IoT does not support handover, the requirement to

关键词： deep learning | fog computing | narrowband internet of things (NB-IoT) | performance analysis | resource allocation | EFFICIENT

关键词： コーヒー豆 | 異常検知 | 深層学習 | 枝刈り | 量子化 | Coffee beans | Anomaly detection | Deep learning | Pruning | Quantization

摘要： ARM Cortex-A72 processor of a Raspberry Pi Compute | Module 4. | Visual inertial odometry (VIO) is the task of | estimating the movement trajectory of an agent from an | onboard camera stream fused with additional inertial

关键词： Hardware acceleration | optical flow (OF) | visual odometry

摘要： popular edge devices such as the Raspberry Pi 3, 4, and | Modern applications, such as autonomous | vehicles, require deploying deep learning algorithms on | resource-constrained edge devices for real-time image and | video processing. However, there is limited

关键词： Deep learning | Object detection models | Performance evaluation | Inference time | Energy efficiency | Accuracy | Edge

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： filter models on a Raspberry* Pi 4.MethodsA sensor node* | PurposeWith the rapid adoption of the Internet | of Things (IoT) in agriculture, monitoring | ecological parameters has become increasingly important for | farmers aiming to optimize crop yields. However, sensor

摘要： set, using Raspberry* Pi 4 hardware and Raspberry Pi* | Technology trend 4.0 has created a revolution | in devices integrating artificial intelligence (AI | ) to solve everyday problems, including license plate | recognition technology. Currently, many organizations in the

摘要：), Raspberry* Pi 4 (RPi4), Intel Neural Compute Stick 2 (NCS2* | models for real-time applications. Raspberry* Pi 3 (RPi3* | Nowadays, real-time object detection, which is | a crucial task, is being performed through image | processing and deep learning techniques. As there are

摘要： acquisition with 12 Raspberry* Pi 4 Model B units and* | Raspberry Pi NoIR cameras fitted with blue filters for | Improving complex agronomic traits such as | yield, plant height, and disease resistance in rice | (Oryza sativa L.) is challenging due to their polygenic

摘要： prototype protocols on iFogSim2 and Raspberry* Pi 4* | Narrowband Internet of Things (NB-IoT) is | LPWAN operating using narrowband spectrum in IoTs | , requiring low data rates and long battery life. Since NB | -IoT does not support handover, the requirement to

关键词：コーヒー豆 | 異常検知 | 深層学習 | 枝刈り | 量子化 | Coffee beans | Anomaly detection | Deep learning | Pruning | Quantization

摘要： ARM Cortex-A72 processor of a Raspberry* Pi Compute* | Module 4. | Visual inertial odometry (VIO) is the task of | estimating the movement trajectory of an agent from an | onboard camera stream fused with additional inertial

摘要： popular edge devices such as the Raspberry* Pi 3, 4, and* | Modern applications, such as autonomous | vehicles, require deploying deep learning algorithms on | resource-constrained edge devices for real-time image and | video processing. However, there is limited