检索结果-内蒙古大学图书馆

Nanodiamond-Based Sensing: A revolution for biosensors in capturing elusive bio-signals in living cells

advanced DRUG DELIVERY REVIEWS 2025年 221卷 115590页

作者： Zhang, Jiahua Ma, Linjie Hou, Yong Ouyang, Haoyi Hong, Hyunsik Kim, Kanghyeon Kang, Heemin Chu, Zhiqin Univ Hong Kong Dept Elect & Elect Engn Hong Kong Peoples R China Korea Univ Dept Mat Sci & Engn Seoul 02841 South Korea Korea Univ Coll Med Seoul 02841 South Korea Univ Hong Kong Sch Biomed Sci Hong Kong Peoples R China Adv Biomed Instrumentat Ctr Hong Kong Sci Pk Hong Kong Peoples R China

Cells constantly produce elusive bio-signals, such as cellular forces, free radicals, and molecular interactions, that are important for understanding diseases and treatment effects. However, detecting these signals is challenging because of issues with sensitivity, specificity, and the complexity of biological systems. Owing to their unique properties, nanodiamonds have emerged as a promising platform for detecting such elusive bio-signals, providing enhanced precision and effectiveness in diagnostics and therapies. In this review, we explore the detection of intracellular elusive bio-signals using nitrogen-vacancy (NV) centers in nanodiamonds, presenting case studies on their applications in cell force, free radicals, molecular interactions, and nanoscale thermometry. Moreover, we explore the design and applications of nanodiamonds as nanocarriers in quantum sensors and drug delivery systems.

关键词： Nanodiamond Quantum sensor Elusive bio-signal Nanocarrier Drug delivery

来源：评论

学校读者我要写书评

暂无评论

Survey of Multimodal Federated Learning: Exploring Data Integration, Challenges, and Future Directions

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY

引用

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY 2025年 6卷 2510-2538页

作者： Adam, Mumin Albaseer, Abdullatif Baroudi, Uthman Abdallah, Mohamed King Fahd Univ Petr & Minerals Dept Comp Engn Dhahran 31261 Saudi Arabia King Fahd Univ Petr & Minerals IRC ISS Dhahran 31261 Saudi Arabia Hamad Bin Khalifa Univ Coll Sci & Engn Div Informat & Comp Technol Doha Qatar

The rapidly expanding demand for intelligent wireless applications and the Internet of Things (IoT) requires advanced system designs to handle multimodal data effectively while ensuring user privacy and data security. Traditional machine learning (ML) models rely on centralized architectures, which, while powerful, often present significant privacy risks due to the centralization of sensitive data. Federated Learning (FL) is a promising decentralized alternative for addressing these issues. However, FL predominantly handles unimodal data, which limits its applicability in environments where devices collect and process various data types such as text, images, and sensor output. To address this limitation, Multimodal FL (MMFL) integrates multiple data modalities, enabling a richer and more holistic understanding of data. In this survey, we explore the challenges and advancements in MMFL, including data representation, fusion techniques, and cross-modal learning strategies. We present a comprehensive taxonomy of MMFL, outlining critical challenges such as modality imbalance, fusion complexity, and security concerns. Additionally, we highlight the role of transformers in MMFL by leveraging their powerful attention mechanisms to process multimodal data in a federated setting. Finally, we discuss various applications of MMFL, including healthcare, human activity recognition, and emotion recognition, and propose future research directions for improving the scalability and robustness of MMFL systems in real-world scenarios.

关键词： Data models Surveys Transformers Data privacy Computational modeling Internet of Things Accuracy Scalability Federated learning Distributed databases Multimodal FL data fusion cross-modal multimodal federated transformer learning multimodal FL communication intelligent IoT applications

来源：评论

学校读者我要写书评

暂无评论

Unified Deep Learning for Real-Time Pedestrian Detection, Pose Estimation, and Tracking Towards Safe and Robust sensor-Perception System of Autonomous Vehicle Research

引用

INTERNATIONAL JOURNAL OF advanced COMPUTER SCIENCE AND applications 2025年第3期16卷 192-203页

作者： De Guia, Joseph Deveraj, Madhavi Mapua Univ Sch Informat Technol SOIT Manila Philippines Nanyang Technol Univ Energy Res Inst ERI N Singapore Singapore

This study introduces a novel unified deep learning framework for real-time pedestrian and Vulnerable Road User (VRU) detection, pose estimation, and tracking using YOLOv8. Unlike traditional approaches that separately handle these tasks, our integrated multi-task model leverages YOLOv8's advanced multi-scale feature extraction and optimized architecture to efficiently perform simultaneous detection, pose estimation, and tracking. Experimental evaluations demonstrate superior performance compared to baseline YOLOv8 configurations, achieving an mAP@0.5 of 57.2%, OKS of 76.1% (COCO dataset), MOTA of 67.1%, and IDF1 of 64.3%. The framework's robust performance is validated through comprehensive testing under realistic urban scenarios and challenging conditions. By effectively addressing limitations in current autonomous vehicle (AV) perception systems, such as handling occlusions, varying lighting, and dense pedestrian environments, this integrated approach significantly enhances AV safety and navigation reliability at critical junctions and pedestrian crossings.

关键词： Pedestrian detection pose estimation tracking YOLOv8 deep learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Passive RFID sensor for Crack Monitoring of Metallic Structures 16

A Novel Passive RFID Sensor for Crack Monitoring of Metallic...

引用

16th International conference on Signal Processing systems, ICSPS 2024

作者： Li, Chenxi Liu, Haichao Ni, Yubo Meng, Zhaozong Gao, Nan Zhang, Zonghua School of Mechanical Engineering Hebei University of Technology Tianjin China

ISBN: (纸本)9781510689251

Structural Health Monitoring (SHM) is essential for maintaining the safety and integrity of many large-scale buildings and infrastructure. In the scope of the Internet of Things (IoT), Radio Frequency Identification (RFID) introduces an innovative approach to SHM. This investigation presents a cost-effective passive RFID crack sensor solution tailored for IoT applications. An RFID tag sensor with a Planar Inverted-F Antenna (PIFA) structure specifically is designed to detect and characterize surface cracks on metallic structures. In addition, a low-cost detection method optimized for large-scale mechanical systems is proposed. Traditional SHM techniques often face challenges in adapting to IoT environments due to their complex measurement processes and a high cost. The RFID tag sensor, featuring anti-metal properties, compact size, high data capacity, and high sensitivity, could potentially overcome these challenges. To enhance the sensing precision, a Defected Ground Structure (DGS) is integrated into the sensor design, which allows the sensor to accurately determine the direction of cracks. The sensing data is collected and transmitted to a host PC using a commercial RFID reader, and Principal Component Analysis (PCA) algorithm is employed to improve the detection accuracy. The proposed RFID sensor solution provides an efficient solution for safety assessment and damage detection in large infrastructure structures. © 2025 SPIE.

关键词： Structural health monitoring

来源：评论

学校读者我要写书评

暂无评论

Adaptive Vision sensor Based on Nonlinear Negative Photoconductivity Behavior

引用

advanced FUNCTIONAL MATERIALS 2025年

作者： Jin, Chenxing Wang, Jingwen Liu, Wanrong xu, Yunchao Shi, xiaofang Li, Ruihan Sun, Jia Yang, Junliang Cent South Univ Sch Phys Hunan Key Lab Super Microstruct & Ultrafast Proc Changsha 410083 Hunan Peoples R China Cent South Univ Sch Elect & Informat Changsha 410083 Hunan Peoples R China Cent South Univ Coll Mech & Elect Engn State Key Lab Precis Mfg Extreme Serv Performance Changsha 410083 Hunan Peoples R China Shanghai Inst Microsyst & Informat Technol State Key Lab Transducer Technol 865 Changning Rd Shanghai 200050 Peoples R China

In-sensor adaptive visual systems represent a promising technology applicable across various fields. This method significantly enhances image quality while reducing system complexity, thereby holding substantial scientific significance and practical applications. This study emulates a light-triggered depolarization neuromorphic response utilizing an In2O3/C8-BTBT heterojunction transistor device equipped with ion-gel gating. When the heterojunction device is exposed to UV light, electrons in the In2O3 layer recombine with holes in the C8-BTBT layer, leading to a rapid decrease in photocurrent and resulting in a significant negative photoresponse. The device is capable of simulating spike-dependent inhibitory currents and multilevel storage capabilities. Moreover, the proposed device is employed in constructing a UV-adaptive retina, facilitating in-sensor adaptive computational imaging by leveraging its unique dependence on UV intensity and temporal characteristics, thereby significantly enhancing the visualization of image details.

关键词： adaptive computational imaging negative photoresponse optical stimulation depolarization

来源：评论

学校读者我要写书评

暂无评论

Flexible Thermoelectric BiSbTe/Carbon Paper/BiSbTe Sandwiches for Bimode Temperature-Pressure sensors

引用

advanced FUNCTIONAL MATERIALS 2025年第5期35卷

作者： Shu, Min He, Zhengxi Zhu, Junjie Ji, Yuru Zhang, xuefei Zhang, Chuanrui Chen, Mengran Zong, Peng-an Nanjing Tech Univ Coll Mat Sci & Engn Nanjing 211800 Peoples R China Nucl Power Inst China Sci & Technol Reactor Syst Design Technol Lab Chengdu 610213 Peoples R China Tsinghua Univ Sch Mat Sci & Engn State Key Lab New Ceram & Fine Proc Beijing 100084 Peoples R China

Bimode temperature-pressure sensors hold significant promise in personal health monitoring, wearables and robotic signal detection. Traditional bimode sensors typically combine two independent sensors, leading to fabrication complexity. This study develops a bimode temperature-pressure sensor by using a facile electrodeposition method to create sandwiched BiSbTe/Carbon Paper/BiSbTe thin films and stacking them to a vertical structure. It demonstrates high sensitivity for temperature sensing, capable of detecting temperature difference as low as 1 K, and a rapid response time of 0.92 s due to a vertical structure. Utilizing its thermoelectric mechanism, the sensor achieves self-powered sensing for finger touch and respiration states. Furthermore, its island-like contact surface ensures high sensitivity with an extremely fast response time of 0.17 s, by rapidly changing contact resistance under pressure, allowing it to detect various human behaviors, including body movements and micro-expressions. Beyond its sensing capabilities, the film excels in flexibility, electromagnetic interference shielding, and stability, presenting significant potential for integration into self-powered electronic skin systems for health monitoring, wearables, artificial intelligence, and other electronic skin applications.

关键词： bimode bismuth telluride carbon flexible sandwich temperature-pressure sensor thermoelectric

来源：评论

学校读者我要写书评

暂无评论

A Predictive Maintenance Platform for a Conveyor Motor sensor System Using Recurrent Neural Networks 5th

A Predictive Maintenance Platform for a Conveyor Motor Senso...

引用

5th International conference on Neural Computing for advanced applications (NCAA)

作者： Kiangala, Kahiomba Sonia Wang, Zenghui Univ South Africa UNISA Dept Elect & Smart Syst Engn ZA-1709 Johannesburg Gauteng South Africa

ISBN: (纸本)9789819770007;9789819770014

Since the effusion of Industry 4.0 (I40) and smart manufacturing, predictive maintenance (PdM) has become critical to prevent severe system breakdowns and costly production downtime in various industries. Several state-of-the-art Artificial Intelligence (AI) approaches, such as machine learning models (ML), empower the PdM design concept to produce more accurate outcomes. In this study, we propose the development of a PdM platform that effectively detects future possible warnings and failures in the vibration speed sensor of a conveyor motor. We build the platform backend using recurrent neural networks (RNN) regression ML models to predict vibration speed values and their trends. We train our RNN models using univariate time-series historical vibration sensor data recorded over the years. The experimental results demonstrate the robustness of our platform built on RNN models compared to other traditional regression machine learning models such as Extreme Gradient Boosting (xGboost). We compare the effectiveness of the PdM platform with two RNN models: a basic RNN model and a long short-term memory (LSTM) model. Unlike other regression PdM systems focusing on predicting devices Remaining Useful Life (RUL), our PdM platform forecasts and generates new vibration sensor data based on the desired future time range. It also pinpoints set warning and failure values and indicates when these faults are more likely to occur. Factories can utilize this feature for analytics purposes.

关键词： Conveyor Motor sensor Predictive Maintenance (PdM) Recurrent Neural Networks (RNN) Regression Models time-series data

来源：评论

学校读者我要写书评

暂无评论

A SERS-Fluorescence dual-mode fiber sensor for monitoring in FRET system

引用

MICROCHEMICAL JOURNAL 2025年 212卷

作者： Zheng, Zhihan Liu, Yan Li, Minglu Chen, Huifang Chen, Shen Lin, Chengqi Jiang, xiaowei Lin, Huihuang Hong, Simin Broderick, Neil G. R. xu, Ben Kang, Juan Zhao, Chunliu Wang, Yi China Jiliang Univ Coll Opt & Elect Technol Hangzhou 310018 Peoples R China Zhejiang Univ Coll Pharmaceut Sci Hangzhou 310058 Peoples R China Univ Auckland Dept Phys Auckland New Zealand Univ Auckland Dodd Walls Ctr Excellence Photon & Quantum Technol Auckland New Zealand

In a complex Forster resonance energy transfer (FRET) system, it is necessary to monitor the composition change, chemical structural construction or intermolecular interactions. The fluorescence detecting method is not sufficient to supply such information. In this paper, a dual-mode fiber sensor for monitoring in FRET system is proposed. SERS and fluorescence detection can be realized with only one fiber probe. The sensor was designed on separated regions for each mode detections. The sensing capacities was tested, the lowest LOD was calculated to be 1.38 x 10-14 M in SERS detections. A FRET system was simulated with Rhodamine 6G (R6G) and Rhodamine B (RhB). There are FRET, spectra overlap, and competition on substrate between the two dyes, which makes the mixture a typical and complex FRET system. With the proposed sensor, the fluorescence intensity change was monitored, at the same time, a small portion of R6G (1/500 in high concentration and 1/105 in low concentration) in the mixture be recognized with SERS detection. We further detected the illegal addition of Rhodamine in commercially available 100 % orange juice. Even when fluorescence could not detect it, R6G could still be effectively detected by SERS method at a concentration of 10-10 M. By the help of this dual-mode sensing device, the process of chemical reaction in FRET system could be monitored, and more widely applications of FRET technique could be realized.

关键词： Forster Resonance Energy Transfer Surface Enhanced Raman Scattering Dual-mode sensor In Situ Chemical Reaction Monitoring Low LOD

来源：评论

学校读者我要写书评

暂无评论

3D Successive Nanoscale Interactions-Driven Mechanoreceptors with Broad Linear Range and Ultra-High Sensitivity for Efficient Gesture Recognition

引用

advanced FUNCTIONAL MATERIALS 2025年

作者： Wu, Chenling Zhang, Sen Wang, Yi Wang, Fangjun Wang, Taihong Zhang, Ming Hunan Univ Engn Res Ctr Adv Semicond Technol & Applicat Natl Key Lab Power Semicond & Integrat Technol Minist EducColl SemicondColl Integrated Circuits Changsha 410082 Peoples R China Hunan Univ Sch Phys & Elect Changsha 410082 Peoples R China Southern Univ Sci & Technol Dept Elect & Elect Engn Shenzhen 518055 Guangdong Peoples R China

Wearable biosensing systems for monitoring daily human activities have been extensively investigated by researchers of human-machine interactions. However, the transmission of biomechanical signals is degraded owing to limitations arising from the non-ideal characteristics of hardware, which obstructs the precise recognition of human motions by sensing systems and practical applications. In this study, we demonstrates, for the first time, 3D successive nanoscale interaction-driven artificial slow-adapting (SA) mechanoreceptors to develop a biosensing system integrated with sensing, learning, and computational functionalities for efficient sign-language detection and translation. Specifically, nanocellular graphene (GN) with a high conductivity of 1.26 x 104 S m-1 is constructed via submicron porous template-assisted synthesis. More importantly, by leveraging unique conductive networks driven by 3D successive nanoscale interactions of artificial SA mechanoreceptors, co-optimization of the sensitivity (gauge factor = 242) and linear operating range is achieved, unlike the case of foam GN sensors. An artificial biosensing system (ABSS) based on sensing arrays operating via machine-learning algorithms achieves real-time gesture detection and recognition with 98.8% recognition accuracy. This 3D successive nanoscale template-assisted design strategy may provide a new path toward high-performance ABSS fabrication, thus enabling potential applications in fields such as human-computer interaction, virtual reality, and healthcare.

关键词： artificial biosensing system machine learning nanocellular graphene slow-adapting mechanoreceptor strain sensor

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for sensor-Based Handwritten Character Recognition: A Brief Survey 21st

Machine Learning for Sensor-Based Handwritten Character Reco...

引用

21st International conference on Distributed Computing and Intelligent Technology

作者： Singh, Shashank Kumar Chaturvedi, Amrita IIT BHU Dept Comp Sci & Engn Varanasi 221005 Uttar Pradesh India

ISBN: (纸本)9783031814037;9783031814044

Handwriting recognition technologies have evolved significantly, with recent advancements incorporating wearable devices such as smartpens, smartwatches, and smartphones to capture motion and gesture data. This paper reviews various efficient handwriting recognition models that utilize inertial sensors, visual sensors, EMG sensors, and acoustic and Wi-Fi signals. Inertial sensor-based approaches often use accelerometers and gyroscopes to collect three-dimensional data during handwriting, with models achieving high accuracy in recognizing digits and alphabets. Visual sensor-based techniques, leveraging cameras and image processing, have been fundamental in developing Optical Character Recognition (OCR), further enhanced by deep learning algorithms. EMG sensors have been explored for their potential to capture muscle activity for gesture recognition. At the same time, acoustic and WiFi signal-based methods offer innovative ways to recognize handwriting through sound and signal variation. Despite the progress, challenges such as sensor drift, data generalization, and computational requirements persist. Integrating multi-modal sensors and advanced machine learning techniques holds promise for overcoming these limitations and improving the accuracy and usability of handwriting recognition systems across diverse applications.

关键词： Inertial sensor Machine Learning Visual sensors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：