检索结果-内蒙古大学图书馆

Fast optical-writing recognition based on two-dimensional photothermoelectric effect assisted with deep learning

InfoMat 2023年第3期5卷 33-44页

作者： Yujia Zhong Haoyu Fang Yutong Ran Hongwei Zhu State Key Lab of New Ceramics and Fine Processing School of Materials Science and EngineeringTsinghua UniversityBeijingthe People's Republic of China Department of Electrical and Computer Engineering New York UniversityNew YorkNew YorkUSA

The photothermoelectric(PTE)effect enables a simple structure to construct a noncontact and self-powered writing *** detectors based on active materials and one-dimensional(1D)position-sensitive PTE effect have attracted considerable ***,there is no research on applying the 1D position-sensitive PTE effect to a two-dimensional(2D)***,flexible writing devices based on the PTE effect have not been ***,we demonstrate a self-powered flexible optical writing device based on the 2D position-sensitive PTE effect of SnSe thin *** positioning,tracking,and distinguishing of optically written characters have been realized by only measuring the bi-directional output voltages during the writing process.A deep convolutional neural network has been introduced to recognize optically written numbers and characters with high recognition accuracy(92%)and fast processing speed(8.6 ms).The flexible optical-writing device with a simple structure could rapidly and accurately recognize characters in a noncontact fashion using a small amount of training data.

关键词： deep neural network optical writing photothermoelectric effect tin selenide

来源：评论

学校读者我要写书评

暂无评论

Community-Based Multi-layer Analytics Architecture for Civic Violations 8

Community-Based Multi-layer Analytics Architecture for Civic...

引用

8th IEEE International Conference for Convergence in Technology, I2CT 2023

作者： Hernandez, Drixter V. Medina, Daryll John O. Salazar, Angelica Mhay C. Castillo, James Iñaki A. Austria, Yolanda D. Josh Domingo Lopez, Dylan Borq Technologies Inc. Manila Philippines Chung Yuan Christian University Department of Electrical Engineering and Computer Science Taoyuan Taiwan Adamson University Computer Engineering Department Manila Philippines

ISBN: (纸本)9798350334012

Civic violations such as public drinking and public smoking are common in the streets and have become a norm in the community. Recent efforts fail to automatically detect, alert, and make analytics for civic violations, specifically public smoking and alcohol drinking, for computing architectures adapted for local communities. This paper proposes a community-based multi-layer analytics architecture for civic violations. The multi-level civic violation recognition is implemented in a mist-fog-edge architecture. The architecture implements decentralization to support fault-tolerance in a community-based environment. The system implements a series of deep learning models for human clustering and scenario isolation using YOLOv5 with intersection of union (IoU) and non-maxima suppression (NMS) algorithms, and violation recognition using Vision Transformers with violation amplifiers. Experimental results show that the human clustering and scenario isolation has a mAP of 0.46 using IoU as 0.3 and the violation recognition with an accuracy score of 86.96 %. The overall architecture has a total latency of 3.06 seconds for end-to-end AI inference operation. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

NeighborTrack: Single Object Tracking by Bipartite Matching with Neighbor Tracklets and Its Applications to Sports

NeighborTrack: Single Object Tracking by Bipartite Matching ...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Chen, Yu-Hsi Wang, Chien-Yao Yang, Cheng-Yun Chang, Hung-Shuo Lin, Youn-Long Chuang, Yung-Yu Liao, Hong-Yuan Mark Institute of Information Science Academia Sinica Taiwan Purdue University Department of Electrical Engineering United States National Tsing Hua University Department of Computer Science Taiwan National Taiwan University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9798350302493

We propose a post-processor, called NeighborTrack, that leverages neighbor information of the tracking target to validate and improve single-object tracking (SOT) results. It requires no additional data or retraining. Instead, it uses the confidence score predicted by the backbone SOT network to automatically derive neighbor information and then uses this information to improve the tracking results. When tracking an occluded target, its appearance features are untrustworthy. However, a general siamese network often cannot tell whether the tracked object is occluded by reading the confidence score alone, because it could be misled by neighbors with high confidence scores. Our proposed NeighborTrack takes advantage of unoccluded neighbors' information to reconfirm the tracking target and reduces false tracking when the target is occluded. For the VOT challenge dataset commonly used in short-term object tracking, we improve three famous SOT networks, Ocean, TransT, and OSTrack, by an average of 1.92% EAO and 2.11% robustness. For the mid- and long-term tracking experiments based on OSTrack, we achieve state-of-the-art 72.25% AUC on LaSOT and 75.7% AO on GOT-10K. Most of the tracking examples we have used are related to sports. © 2023 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Comparison Between Jetson Nano and Jetson Xavier NX for Ag Data Security

Comparison Between Jetson Nano and Jetson Xavier NX for Ag D...

引用

2024 American Society of Agricultural and Biological Engineers Annual International Meeting, ASABE 2024

作者： Alahe, Mohammad Ashik Kemeshi, James Chang, Young Won, Kwanghee Department of Agricultural and Biosystems Engineering South Dakota State University United States Department of Electrical Engineering and Computer Science South Dakota State University United States

ISBN: (纸本)9798331302214

Smart Agriculture (SA) is a rapidly evolving technology that integrates Internet of Things (IoT) devices and computing systems to improve crop yields and reduce revenue losses. However, the rapid digitization and data-driven technologies present new security challenges. In addition, due to their low memory and power capabilities, many smart devices cannot be safeguarded using traditional cyber security protocols. Therefore, designing a robust and efficient secure framework for addressing the security challenges faced by the agriculture industry is essential to protect the industry and maintain food security. In this study, we propose a secure edge computing approach employing encryption algorithms on Jetson Nano and Jetson Xavier NX. Leveraging the Advanced Encryption Standard (AES), we successfully captured, encrypted, and decrypted real-time data using a Camera Serial Interface (CSI) camera mounted on an Unmanned Ground Vehicle (UGV). Our study compares the performance of Jetson Nano and Jetson Xavier NX, considering cost-effectiveness, processing time, and power consumption. Statistical analysis revealed that Jetson Xavier NX outperformed Jetson Nano in terms of average processing time (encryption and decryption) for both 29 fps and 30 fps data. Specifically, for Jetson Nano, the mean processing time was 19.625ms (8.629ms for encryption and 10.996ms for decryption) and standard deviation of encryption and decryption time was 1.122ms and 3.199ms to process 29 fps image data and the mean processing time was 22.31ms (10.025ms for encryption and 12.285ms for decryption) with standard deviation of 1.785ms and 1.542ms for encrypting and decrypting the 30 fps image data. In contrast, for Jetson Xavier NX, the mean processing time was 18.576ms (10.015ms for encryption and 8.56ms for decryption) and standard deviation of encryption and decryption time was 4.156ms and 1.645ms to process 29 fps image data and the mean processing time was 21.584ms (11.642ms for encryption an

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Fast Hybrid Far/Near-Field Beam Training For Extremely Large-Scale Millimeter Wave/Terahertz Systems

引用

IEEE Transactions on Communications 2024年第6期73卷 3956-3970页

作者： Wang, Hongwei Fang, Jun Duan, Huiping Li, Hongbin University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China University of Electronic Science and Technology of China School of Information and Communications Engineering Chengdu611731 China Stevens Institute of Technology Department of Electrical and Computer Engineering HobokenNJ07030 United States

In this paper, we consider the problem of downlink beam training for extremely large-scale millimeter wave (mmWave)/Terahertz (THz) systems, where the far-field assumption which treats wavefronts as planar waves may not hold valid. For such hybrid far/near-field channels, beam training needs to identify the best beam alignment on a two-dimensional angle-range domain. An exhaustive search scheme sequentially scanning the entire angle-range space incurs a high training overhead. To address this issue, in this paper, we propose an efficient hybrid far/near-field beam training method. By utilizing the approximate orthogonality of near-field steering vectors of the same effective distance, we devise a multi-directional beam training sequence which can more efficiently scan the entire angle-range space. Based on the devised beam training sequence, we develop a simple estimation method at the receiver that can simultaneously identify the angle and the range associated with the dominant path. Simulation results show that the proposed method achieves better performance than the exhaustive search scheme, while with a much lower overhead cost. The proposed method also presents a clear advantage over other existing state-of-the-art hybrid far/near-field beam training methods in terms of performance and generality. © 1972-2012 IEEE.

关键词： Wavefronts

来源：评论

学校读者我要写书评

暂无评论

Atmospheric Turbulence Correction via Variational Deep Diffusion 6

Atmospheric Turbulence Correction via Variational Deep Diffu...

引用

6th IEEE International Conference on Multimedia Information Processing and Retrieval, MIPR 2023

作者： Wang, Xijun Lopez-Tapia, Santiago Katsaggelos, Aggelos K. Northwestern University Dept. of Computer Science EvanstonIL United States Northwestern University Dept. of Electrical and Computer Engineering EvanstonIL United States

ISBN: (纸本)9798350307818

Atmospheric Turbulence (AT) correction is a challenging restoration task as it consists of two distortions: geometric distortion and spatially variant blur. If left unaddressed, these distortions can significantly impact downstream vision tasks. Diffusion models have shown impressive accomplishments in photo-realistic image synthesis and beyond. In this paper, we propose a novel deep conditional diffusion model under a variational inference framework to solve the AT correction problem. We use this framework to improve performance by learning latent prior information from the input and degradation processes. We use the learned information to further condition the diffusion model. Experiments are conducted in a comprehensive synthetic AT dataset. We show that the proposed framework achieves good quantitative and qualitative results. © 2023 IEEE.

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

Statistical Methods for Testing Equity of False Non Match Rates Across Multiple Demographic Groups 22

Statistical Methods for Testing Equity of False Non Match Ra...

引用

22nd International Conference of the Biometrics Special Interest Group, BIOSIG 2023

作者： Schuckers, Michael Fatima, Kaniz Purnapatra, Sandip Drahos, Joseph Hou, Daqing Schuckers, Stephanie St. Lawrence University Mathematics Computer Science and Statistics CantonNY United States Clarkson University Computer and Electrical Engineering PotsdamNY United States

ISBN: (纸本)9798350336559

Biometric recognition is used for a variety of applications including authentication, identity proofing, and border security. One recent focus of research and development has been methods to ensure fairness across demographic groups and metrics to evaluate fairness. However, there has been little work in this area incorporating statistical variation. This is important because differences among groups can be found by chance when no difference is present or may be due to an actual difference in system performance. We extend previous work to consider when individuals are members of one or more demographics (age, gender, race). Our methodology is meant to be more comprehendable by a non-technical audience and uses a robust bootstrap approach for estimation of variation in false non-match rates. After presenting our methodology, we present a simulation study and we apply our approach to MORPH-II data. © 2023 IEEE.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

DriSm_YNet: a breakthrough in real-time recognition of driver smoking behavior using YOLO-NAS

引用

Neural Computing and Applications 2024年第29期36卷 18413-18432页

作者： Pandey, Nageshwar Nath Pati, Avadh Maurya, Ritesh Department of Computer Science and Engineering ITER Siksha ‘O’ Anusandhan Odisha Bhubaneswar751030 India Department of Electrical Engineering National Institute of Technology Silchar Assam Silchar788010 India Amity Centre for Artificial Intelligence Amity University Noida201313 India

Driver smoking rates are rising day after day. This becomes more crucial when operating a vehicle because of the number of deadly traffic accidents caused by this careless behavior. Therefore, to overcome this problem, there is a need for a reliable system that can work in less time and with reasonable accuracy. Here, the motive of this study is to satisfy this demand. In this study, a vast video dataset named HMDB51 has been utilized. Further, this dataset is pre-processed with image enhancement techniques, i.e., histogram utilization and gamma correction. After that, computer vision techniques, i.e., Haar Cascade and YOLO-NAS, have been employed to capture the face, mouth, and eye regions of interest, respectively. Further, an occlusion condition is formulated based on eye parameters to discard the occluded frames at the initial processing stage. Afterward, the TransGAN-augmented technique was employed to avoid the possibility of underfitting that might occur due to the removal of occluded frames. Thereafter, spatio-temporal features were extracted from mouth ROI by the InceptionV3 and fed into LSTM to classify the smoking and non-smoking states of the driver. Thus, the proposed model has categorized the smoking and non-smoking conditions of the driver with a remarkable accuracy of 96.5% based on the AUC-ROC score and confusion metrics compared to existing models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Colonic Pressure Signal Analysis Method Based on Ensemble Support Vector Machine 4

Colonic Pressure Signal Analysis Method Based on Ensemble Su...

引用

4th International Conference on Electronic Information engineering and computer Technology, EIECT 2024

作者： Cui, Liu Si, Zhisen Zhao, Kai Wang, Shuangkui Shanghai Institute of Technology Department of Computer Science and Information Engineering Shanghai China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798331528850

Slow transit constipation is a common intestinal motility disorder. The colonic peristalsis can be well analyzed by the colonic pressure signal. However, medical physiological signal data are generally imbalanced, resulting in the low performance of traditional classification methods. To overcome this challenge, this paper proposes a Support Vector Machine classification method based on ensemble method. We extracted statistical features, nonlinear features and wavelet features from the colonic pressure signals, and integrated them as feature vectors to input the classifier. The experimental results show that, compared with the traditional support vector machine, the proposed method significantly improves the recognition effect of the minority class samples. Through grid search for model parameters optimization, ensemble support vector machine not only improves the recognition effect of minority class samples, but also maintains the recognition performance of majority class samples, which effectively alleviates the problem of biased toward the majority class in the classification process and improves the recognition accuracy of slow transit constipation patients. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Smooth Reference Command Generation and Control for Transition Flight of VTOL Aircraft Using Time-Varying Optimization

Smooth Reference Command Generation and Control for Transiti...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Kim, Jinrae Bullock, John L. Cheng, Sheng Hovakimyan, Naira Department of Mechanical Science and Engineering The Grainger College of Engineering University of Illinois Urbana-Champaign United States Department of Electrical and Computer Engineering The Grainger College of Engineering University of Illinois Urbana-Champaign United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

Vertical take-off and landing (VTOL) aircraft pose a challenge in generating reference commands during transition flight. While sparsity between hover and cruise flight modes can be promoted for effective transitions by formulating 1-norm minimization problems, solving these problems offline pointwise in time can lead to non-smooth reference commands, resulting in abrupt transitions. This study addresses this limitation by proposing a time-varying optimization method that explicitly considers time dependence. By leveraging a prediction-correction interior- point time-varying optimization framework, the proposed method solves an ordinary differential equation to update reference commands continuously over time, enabling smooth reference command generation in real time. Numerical simulations with a two-dimensional Lift+Cruise vehicle validate the effectiveness of the proposed method, demonstrating its ability to generate smooth reference commands online. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： VTOL/STOL aircraft

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：