检索结果-内蒙古大学图书馆

Triboelectric Sensor Based on NaCl/agar Hydrogel as Portable Implicit Alarm Cipher System

JOURNAL OF ELECTRONIC MATERIALS 2025年第6期54卷 4388-4400页

作者： Mou, Qirui Wei, Ouyang Qu, Bingbing Liu, Hongfu Xie, Yiyuan Chen, Bin Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuit & Intelligent Chongqing 400715 Peoples R China

Traditional locks exhibit vulnerabilities in emergency situations, as they lack alarm or response mechanisms and are unable to prevent brute force attacks. Amid the surge in IoT and biometric technology, smart locks are undergoing transformative improvements. Biometric locks, offering enhanced security and convenience, still face challenges such as irreversible data risks and high costs. To address these limitations, we proposed a green, safe triboelectric nanogenerator (AN-TENG) based on NaCl/agar hydrogel for a portable implicit alarm cipher system. By optimizing the concentration of agar solution and NaCl dopant, the sensor achieves a highest sensitivity of 3.61 V/kPa within the pressure range of 0-6 kPa and a low-pressure detection limit (33.32 mg). Then, a smart breath detector and a keyboard were fabricated by utilizing the proposed sensor, employed to design a portable implicit cipher system, where the keyboard enabled digital input unlocking, and the breath detector triggered implicit alarm. The system offers a hidden alarm function, and, by leveraging neural network algorithms, it achieves a recognition accuracy of 99% on identifying distinct respiratory patterns, and can provide high security in critical scenarios. This innovation leverages the strengths of TENGs to deliver a more secure and versatile smart lock alternative.

关键词： Self-powered triboelectric sensor NaCl/agar hydrogel deep learning algorithm implicit alarm

来源：评论

学校读者我要写书评

暂无评论

Middle- and Long-Term Runoff Forecast Model for Water Resource and Climate Security Based on Self-Attention Mechanism

引用

LAND DEGRADATION & DEVELOPMENT 2025年第8期36卷 2773-2785页

作者： Chen, Juan Liu, Mengchu Liu, Weifeng Chi, Dafeng Xie, Jianqing Liu, Jing Naushad, Mu. Zhang, Weiguo Hohai Univ Coll Hydrol & Water Resources Nanjing Peoples R China Hohai Univ Inst Water Transfer Engn Nanjing Peoples R China MWR Gen Inst Water Conservancy Resources & Hydropo Beijing Peoples R China Fuzhou Water Grp Ltd Fuzhou Peoples R China Water Resource & Hydropower Survey & Design Inst F Fuzhou Peoples R China China South to North Water Divers Eastern Route Co Beijing Peoples R China King Saud Univ Coll Sci Dept Chem Riyadh Saudi Arabia Ningbo Water Resources & Hydropower Planning & Des Ningbo Peoples R China

Reliable middle- and long-term streamflow forecasts are critical for ensuring water resources management and climate security. This study establishes a novel runoff forecasting model based on the self-attention (SA) mechanism and variational mode decomposition-gated recurrent unit (VMD-GRU) framework to improve monthly streamflow prediction accuracy. The maximal information coefficient (MIC) method is adopted to screen key drivers of runoff variability. The proposed model integrates VMD to decompose the runoff sequence into intrinsic components and applies GRU coupled with SA to predict each component. The whale optimization algorithm (WOA) is adopted for the optimization of VMD-SA-GRU model hyperparameters, and then monthly streamflow forecast results are obtained by superimposing the results of each component. Using 40 years of runoff data from the South-to-North Water Diversion Project in China, the VMD-SA-GRU model is evaluated against GRU and VMD-GRU benchmarks. Results demonstrate that the VMD-SA-GRU model leverages the strengths of its constituent algorithms, significantly improving forecast accuracy. Compared to the VMD-GRU model, the VMD-SA-GRU framework enhances the Nash-Sutcliff efficiency coefficient (NSE) by 6%-35%, reduces the root mean square error (RMSE) by 15%-30%, and decreases the mean absolute error (MAE) by 15%-33%. This robust forecasting framework provides a reliable tool for sustainable water resource management and addressing climate-related challenges.

关键词： deep learning algorithm gated recurrent unit model middle- and long-term runoff forecast self-attention mechanism variational mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Research on motion recognition based on multi-dimensional sensing data and deep learning algorithms

引用

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2023年第8期20卷 14578-14595页

作者： Qiu, Jia-Gang Li, Yi Liu, Hao-Qi Lin, Shuang Pang, Lei Sun, Gang Song, Ying-Zhe Capital Univ Phys Educ & Sports Inst Artificial Intelligence Sports Beijing 100191 Peoples R China

Motion recognition provides movement information for people with physical dysfunction, the elderly and motion-sensing games production, and is important for accurate recognition of human motion. We employed three classical machine learning algorithms and three deep learning algorithm models for motion recognition, namely Random Forests (RF), K-Nearest Neighbors (KNN) and Decision Tree (DT) and Dynamic Neural Network (DNN), Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). Compared with the Inertial Measurement Unit (IMU) worn on seven parts of body. Overall, the difference in performance among the three classical machine learning algorithms in this study was insignificant. The RF algorithm model performed best, having achieved a recognition rate of 96.67%, followed by the KNN algorithm model with an optimal recognition rate of 95.31% and the DT algorithm with an optimal recognition rate of 94.85%. The performance difference among deep learning algorithm models was significant. The DNN algorithm model performed best, having achieved a recognition rate of 97.71%. Our study validated the feasibility of using multidimensional data for motion recognition and demonstrated that the optimal wearing part for distinguishing daily activities based on multidimensional sensing data was the waist. In terms of algorithms, deep learning algorithms based on multi-dimensional sensors performed better, and tree structured models still have better performance in traditional machine learning algorithms. The results indicated that IMU combined with deep learning algorithms can effectively recognize actions and provided a promising basis for a wider range of applications in the field of motion recognition.

关键词： motion recognition IMU deep learning algorithm Classical machine learning algorithm daily actions

来源：评论

学校读者我要写书评

暂无评论

Improved performance for Alzheimer's disease earlier detection and diagnosis using deep learning algorithms

引用

INTERNATIONAL JOURNAL OF ENGINEERING SYSTEMS MODELLING AND SIMULATION 2024年第4期15卷 174-180页

作者： Deenadayalan, T. Shantharajah, S. P. Vellore Inst Technol Sch Informat Technol & Engn Vellore 632014 Tamil Nadu India

As our society ages, cognitive impairment and dementia in the elderly, particularly Alzheimer's disease (AD), have become more prevalent. After clinical symptoms arise, senile cognitive impairment will advance to irreversible dementia, finally leading to death as a multifactor, multistage, and clinical syndrome with concomitant disorders. Alzheimer's disease is currently irreversible, and scientific trials for effective treatments are lacking. The progression of a patient's condition will go through numerous stages, so early detection is critical. Early Alzheimer's disease treatments can effectively decrease disease development while also reducing the burden on patients' families and society. The research presents a deep learning-based strategy for early detection and screening of Alzheimer's disease. The method involves slicing a three-dimensional magnetic resonance picture of the human brain into a two-dimensional image, then using an object recognition network called faster region with convolutional neural networks (R-CNN) to detect shrinkage in the hippocampal region of the brain to make an AD diagnosis. To get feature maps and to get 100% high-precision detection of AD samples, a new network is constructed and optimised based on VGG16, which is the basic network of faster R-CNN. At the same time, the validation set achieves 97.67% of the detected picture correctness.

关键词： disease detection feature extraction CNN deep learning algorithm high-precision

来源：评论

学校读者我要写书评

暂无评论

deepLabV3+ Based Mask R-CNN for Crack Detection and Segmentation in Concrete Structures

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2025年第1期16卷 423-431页

作者： Liu, Yuewei Wenzhou Polytech Sch Civil Engn & Architecture Wenzhou Zhejiang Peoples R China

In order to solve the problem of concrete structure crack detection and segmentation and improve the efficiency of detection and segmentation, this paper proposes a crack detection and segmentation method for concrete structure based on deepLabV3+ and Mask R-CNN algorithm. Firstly, a crack detection and segmentation scheme is designed by analysing the crack detection and segmentation problem of concrete structure. Secondly, a crack detection method based on Mask R-CNN algorithm is proposed for the crack detection problem of concrete structure. Then, a crack segmentation method based on deepLabV3+ algorithm is proposed for the crack segmentation problem of concrete structure. Finally, bridge crack image data is used for the crack detection and segmentation of concrete structure. Finally, the concrete structure crack detection and segmentation method is validated and analysed using bridge crack image data. The results show that the Mask R-CNN model has better performance in the localisation and identification of cracks, and the deepLabV3+ model has higher accuracy and contour extraction integrity in solving the crack segmentation problem.

关键词： deepLabV3+ Mask R-CNN concrete structure crack detection and segmentation deep learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Text complexity analysis of college English textbooks based on blockchain and deep learning algorithms under the internet of things

引用

INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING 2023年第2-3期14卷 146-155页

作者： Shen, Bingjie Beijing Univ Civil Engn & Architecture Sch Humanities Xicheng Dist Beijing Peoples R China

College English textbooks are of great significance in college English teaching. In the context of the gradual development of the Internet of Things (IoT), this study introduces blockchain and deep learning to build a new college textbooks-oriented complexity analysis model. Three different college English textbooks are analysed from the perspectives of lexical complexity, grammatical difficulty, sentence coherence and sentence readability to ensure the comprehensiveness of the experiment. This study focuses on the text of the textbook, introduces vocabulary research into the system, and takes it as an indicator to judge the textbook. The results can provide suggestions and improvement directions for the subsequent editing and writing of college English textbooks.

关键词： IoT internet of things deep learning algorithm blockchain college English textbook text complexity

来源：评论

学校读者我要写书评

暂无评论

Computer-aided recognition of myopic tilted optic disc using deep learning algorithms in fundus photography

引用

BMC OPHTHALMOLOGY 2020年第1期20卷 407-407页

作者： Cho, Baek Hwan Lee, Young Park, Kyung-Ah Oh, Sei Yeul Moon, Jong Hak Lee, Ga-In Noh, Hoon Chung, Joon Kyo Kang, Min Chae Chung, Myung Jin Samsung Med Ctr Med AI Res Ctr Inst Smart Healthcare Seoul South Korea Sungkyunkwan Univ Dept Med Device Management & Res SAIHST Seoul South Korea Sungkyunkwan Univ Dept Digital Hlth SAIHST Seoul South Korea Sungkyunkwan Univ Samsung Med Ctr Dept Ophthalmol Sch Med 81 Irwon Ro Seoul 06351 South Korea Sungkyunkwan Univ Samsung Med Ctr Dept Radiol Sch Med Seoul South Korea

BackgroundIt is necessary to consider myopic optic disc tilt as it seriously impacts normal ocular parameters. However, ophthalmologic measurements are within inter-observer variability and time-consuming to get. This study aimed to develop and evaluate deep learning models that automatically recognize a myopic tilted optic disc in fundus *** study used 937 fundus photographs of patients with normal or myopic tilted disc, collected from Samsung Medical Center between April 2016 and December 2018. We developed an automated computer-aided recognition system for optic disc tilt on color fundus photographs via a deep learning algorithm. We preprocessed all images with two image resizing techniques. GoogleNet Inception-v3 architecture was implemented. The performances of the models were compared with the human examiner's results. Activation map visualization was qualitatively analyzed using the generalized visualization technique based on gradient-weighted class activation mapping (Grad-CAM++).ResultsNine hundred thirty-seven fundus images were collected and annotated from 509 subjects. In total, 397 images from eyes with tilted optic discs and 540 images from eyes with non-tilted optic discs were analyzed. We included both eye data of most included patients and analyzed them separately in this study. For comparison, we conducted training using two aspect ratios: the simple resized dataset and the original aspect ratio (AR) preserving dataset, and the impacts of the augmentations for both datasets were evaluated. The constructed deep learning models for myopic optic disc tilt achieved the best results when simple image-resizing and augmentation were used. The results were associated with an area under the receiver operating characteristic curve (AUC) of 0.9780.008, an accuracy of 0.960 +/- 0.010, sensitivity of 0.937 +/- 0.023, and specificity of 0.963 +/- 0.015. The heatmaps revealed that the model could effectively identify the locations of the opti

关键词： Fundus photographs Myopic tilted optic disc deep learning algorithm Automated computer-aided recognition

来源：评论

学校读者我要写书评

暂无评论

Research on Computer Network Intrusion Detection algorithm Based on deep learning

Research on Computer Network Intrusion Detection Algorithm B...

引用

2023 IEEE International Conference on Electrical, Automation and Computer Engineering, ICEACE 2023

作者： Huang, Xiaoyang Tianjin University of Technology Tianjin China

ISBN: (纸本)9798350309614

With the continuous popularization and deepening of the network, the problem of network security is becoming increasingly prominent. How to detect the network intrusion behavior timely and accurately plays a very important role in maintaining network security and improving information security. Traditional methods can not accurately judge the abnormal situation in computer network intrusion detection, and its detection speed is relatively slow, so this paper proposes a computer network intrusion detection method based on deep learning algorithm. Experiments show that the detection accuracy and false positive rate of computer network intrusion detection method based on deep learning algorithm are better than the traditional machine learning algorithm, and can be well applied to real-time network intrusion detection. © 2023 IEEE.

关键词： Artificial intelligence Computer network deep learning algorithm Network intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal deep learning for Raw Eye-Tracking Data 25

Spatial-Temporal Deep Learning for Raw Eye-Tracking Data

引用

Proceedings of the 2025 Symposium on Eye Tracking Research and Applications

作者： Yiting Wang Department of Clinical Neuroscience Karolinska Institutet Stockholm Sweden

来源：评论

学校读者我要写书评

暂无评论

Optimal control for quadrotors UAV based on deep neural network approximations of stable manifold of HJB equation

引用

AUTOMATIKA 2025年第2期66卷 201-216页

作者： Yue, Yuhuan Jiaxing Vocat & Tech Coll Jiaxing Zhejiang Peoples R China

This paper proposes a deep learning algorithm for solving the infinite-horizon optimal feedback control problem of a quadrotor unmanned aerial vehicle (UAV). The optimal control is represented by the stable manifold of the Hamilton-Jacobi-Bellman (HJB) equation in a 12-dimensional state space. Moreover, a deep learning algorithm is proposed to compute approximations of semiglobal stable manifold. The method is built on the geometric feature of the problem. The algorithm generates random data by solving the two-point boundary value problem of the characteristic Hamiltonian system of the HJB equation without discretizing the state space. The resulting data set lies on the stable manifold, and a deep neural network (NN) is trained to fit the data. The training process is conducted offline on a standard laptop without the use of a GPU. Generating feedback control for the quadrotor from the trained NN takes less than one millisecond, compared to several milliseconds required by existing methods for the same operation. The effectiveness of this approach is demonstrated by Monte Carlo tests and simulations in various scenarios.

关键词： Hamitlon-Jacobi-Bellman equation optimal control stable manifold quadrotor UAV deep learning algorithm real-time control

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：