检索结果-内蒙古大学图书馆

IEEE International Workshop on Measurements and Networking Proceedings (M&N)

作者： Ivan Zyrianoff Mattia Forlesi Lorenzo Gigli Soroosh Kamali Nicola Testoni Canio Mennuti Giuseppe Augugliaro Luca De Marchi Alessandro Marzani Luciano Bononi Marco Di Felice Department of Computer Science and Engineering University of Bologna Italy Advanced Research Center on Electronic Systems “Ercole De Castro” University of Bologna Italy Technological Innovations Department INAIL Roma Italy Department of Civil Chemical Environmental and Materials Engineering University of Bologna Bologna Italy

ISBN: (数字)9798350370539

ISBN: (纸本)9798350370546

Real-time monitoring of civil infrastructures is of great importance to ensure their integrity and safety. Achieving these goals requires a strong synergy between multiple tools, disciplines, and approaches, which can be realized through a joint hardware-software co-design of the different components based on the Internet of Things (IoT) paradigm. Deploying IoT-based systems for bridge monitoring presents many challenges, including difficulties in deploying sensors in real-world testbeds, the lack of reliability of IoT devices, constant network disconnections, power outages, and challenges in rapid on-site maintenance. To address these challenges, we propose an IoT-SHM architecture that incorporates mechanisms to ensure robustness across system infrastructure, software components, data flow, and data quality. Our system was deployed on the Volto Santo bridge in Naples, where it successfully collected data for over six months, capturing more than 3000 acoustic emission events and more than 250 million accelerometer data points. Despite several interruptions due to environmental hazards, the system was able to automatically restart data collection. Additionally, we present the specifics of the testbed and a processing of the collected data based on operational modal analysis (OMA).

关键词： Accelerometers Data integrity Bridge circuits Acoustic emission Software Robustness Sensors

来源：评论

学校读者我要写书评

暂无评论

Neural P3M: a long-range interaction modeling enhancer for geometric GNNs 24

Neural P3M: a long-range interaction modeling enhancer for g...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yusong Wang Chaoran Cheng Shaoning Li Yuxuan Ren Bin Shao Ge Liu Pheng-Ann Heng Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University University of Illinois Urbana-Champaign Department of Computer Science and Engineering The Chinese University of Hong Kong University of Science and Technology of China Microsoft Research AI4Science

ISBN: (纸本)9798331314385

Geometric graph neural networks (GNNs) have emerged as powerful tools for modeling molecular geometry. However, they encounter limitations in effectively capturing long-range interactions in large molecular systems due to the localization assumption of GNN. To address this challenge, we introduce Neural P3M, a versatile enhancer of geometric GNNs to expand the scope of their capabilities by incorporating mesh points alongside atoms and reimaging traditional mathematical operations in a trainable manner. Neural P3M exhibits flexibility across a wide range of molecular systems and demonstrates remarkable accuracy in predicting energies and forces, outperforming on benchmarks such as the MD22 dataset. It also achieves an average improvement of 22% on the OE62 dataset while integrating with various architectures. Codes are available at https://***/OnlyLoveKFC/Neural_P3M.

关键词：

来源：评论

学校读者我要写书评

暂无评论

28-4: Positive Aging Resulted in Highly Efficient Blue Quantum Rod Light Emitting Diodes

引用

SID Symposium Digest of Technical Papers 2024年第1期55卷 360-363页

作者： Kumar Mallem Zebing Liao Maksym F. Prodanov Jianxin Song Debjyoti Bhadra Roja Ramani Gavara Abhishek K. Srivastava State Key Laboratory on Advanced Displays and Optoelectronics Technologies and Centre for Display Research Department of Electronics and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong China 999077 IAS Center for Quantum Technologies The Hong Kong University of Science and Technology Hong Kong China

The synthesis of blue quantum rods (QRs) is challenging due to fast kinetics and a significant shift in color during the synthesis of w-CdSe seeds. Herein, we synthesized highly bright CdSe/ZnxCd1-xS/ZnS core/shell blue QRs with an emission wavelength of 480 nm and fabricated blue QRLEDs. We found that the aging process of the QRLEDs significantly improved their performance by slowly reacting Al with ZnMgO and forming an AlOx interlayer among the ZnMgO/Al, which increased electron injection by over 3x times. The AlOx layer minimized the electron injection barrier and produced highly conductive ZnMgO by forming oxidation deficiency. Additionally, the exciton quenching suppressed at the QRs/ZnMgO/Al interface, and film morphology also changed among the QRs/ZnMgO stacks with the time. As a result, the aged QRLEDs showed an EQE of 9.4% and luminance of 61500 cd/m 2 , which is 2.6x and 3x times higher than the freshly made QRLEDs. These are the highest reported numbers in EQE and luminance of blue QRLEDs. Additionally, the durability of the blue QRLEDs significantly improved from 50 to 300 hours at 100 cd/m 2 initial luminance. Overall, the use of QRs in LEDs greatly improves device efficiency and brightness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Gradient Regularization Method

arXiv

引用

arXiv 2024年

作者： Yang, Ling Jiang, Huixiu Bao, Yu Si, Rutong Department of Computer Science Illinois Institute of Technology Chicago United States Bioinformatics Center Institute for Chemical Research Kyoto University Japan The Abdus Salam International Centre for Theoretical Physics Strada Costiera 11 Trieste34151 Italy

Optimizer plays an important role in neural network training with high efficiency and performance. Weight update based on its gradient is the central part of the optimizer. It has been shown that normalization and standardization operation on weight and gradient can accelerate the training process and improve performance such as Weight Standardization (WS), weight normalization (WN) and gradient normalization (GN);there is also gradient centralization (GC). In this work, we introduce a new optimization technique based on the gradient magnitude in a gradient vector named adaptive gradient regularization (AGR), which normalizes the gradient vector in all dimensions as a coefficient vector and subtracts the product of the gradient and its coefficient vector by the vanilla gradient. It can be viewed as an adaptive gradient clipping method. We show that the AGR can improve the loss function Lipschitzness with a more stable training process and better generalization performance. AGR is very simple to be embedded into vanilla optimizers such as Adan and AdamW with only three lines of code. Our experiments are conducted in image generation, image classification and language representation, which shows that our AGR improves the training result. Copyright © 2024, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Intra-operative tumour margin evaluation in breast-conserving surgery with deep learning

arXiv

引用

arXiv 2024年

作者： Shia, Wei-Chung Huang, Yu-Len Chen, Yi-Chun Wu, Hwa-Koon Chen, Dar-Ren Molecular Medicine Laboratory Department of Research Changhua Christian Hospital Changhua Taiwan Department of Computer Science Tunghai University Taichung Taiwan Department of Medical Imaging Changhua Christian Hospital Changhua Taiwan Comprehensive Breast Cancer Center Changhua Christian Hospital Changhua Taiwan

Background A positive margin may result in an increased risk of local recurrences after breast retention surgery for any malignant tumour. In order to reduce the number of positive margins would offer surgeon real-time intra-operative information on the presence of positive resection margins. This study aims to design an intra-operative tumour margin evaluation scheme by using specimen mammography in breast-conserving surgery. Method Total of 30 cases were evaluated and compared with the manually determined contours by experienced physicians and pathology report. The proposed method utilizes image thresholding to extract regions of interest and then performs a deep learning model, i.e. SegNet, to segment tumour tissue. The margin width of normal tissues surrounding it is evaluated as the result. Results The desired size of margin around the tumor was set for 10 mm. The smallest average difference to manual sketched margin (6.53 mm ± 5.84). In the all case, the SegNet architecture was utilized to obtain tissue specimen boundary and tumor contour, respectively. The simulation results indicated that this technology is helpful in discriminating positive from negative margins in the intra-operative setting. Conclusions The aim of proposed scheme was a potential procedure in the intra-operative measurement system. The experimental results reveal that deep learning techniques can draw results that are consistent with pathology *** Codes 68U10 © 2024, CC BY-NC-ND.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Soliton-M-lump wave formation and other interacting propagation for the nonlinear Geng equation

引用

The European Physical Journal Plus 2025年第6期140卷 1-8页

作者： Ali, Karmina K. Yusuf, Abdullahi Salahshour, Soheil Department of Mathematics College of Science University of Zakho Zakho Iraq Department of Computer Science College of Science Knowledge University Erbil Iraq Department of Mathematics Firat University Elazig Turkey Department of Mathematics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Faculty of Engineering and Natural Sciences Istanbul Okan University Istanbul Turkey Faculty of Engineering and Natural Sciences Bahcesehir University Istanbul Turkey Research Center of Applied Mathematics Khazar University Baku Azerbaijan

In this work, we obtain various kind of lump interaction solutions for the (3 + 1)-dimensional nonlinear Geng equation, which was derived in relation to Hamiltonian flows on nonlinear subvarieties of hyperelliptic Jacobian. The well-known technique namely Hirota bilinear is used to accomplish the task. A lump solution is a real analytical rational function solution that decays in all directions of the space variables. The governing equation describes wave dynamical behaviors in more complex applications related to shallow water wave or other similar fluids. Numerical simulations using the three-dimensional and contour profiles are carried out with careful consideration for the values of the involved parameters in order to shed more light on the properties of the acquired solutions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dementia Assessment Using Mandarin Speech with an Attention-Based Speech Recognition Encoder

Dementia Assessment Using Mandarin Speech with an Attention-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zih-Jyun Lin Yi-Ju Chen Po-Chih Kuo Likai Huang Chaur-Jong Hu Cheng-Yu Chen Department of Computer Science National Tsing Hua University Hsinchu Taiwan Dementia Center and Department of Neurology Shuang-Ho Hospital New Taipei City Taiwan Research Center for Artificial Intelligence in Medicine Taipei Medical University Taipei Taiwan Department of Medical Imaging Taipei Medical University Hospital Taipei Taiwan

Dementia diagnosis requires a series of different testing methods, which is complex and time-consuming. Early detection of dementia is crucial as it can prevent further deterioration of the condition. This paper utilizes a speech recognition model to construct a dementia assessment system tailored for Mandarin speakers during the picture description task. By training an attention-based speech recognition model on voice data closely resembling real-world scenarios, we have significantly enhanced the model’s recognition capabilities. Subsequently, we extracted the encoder from the speech recognition model and added a linear layer for dementia assessment. We collected Mandarin speech data from 99 subjects and acquired their clinical assessments from a local hospital. We achieved an accuracy of 92.04% in Alzheimer’s disease detection and a mean absolute error of 9% in clinical dementia rating score prediction. 1

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Neural Function Approximation: The XNet Outperforming KAN

arXiv

引用

arXiv 2025年

作者： Li, Xin Zheng, Xiaotao Xia, Zhihong Oxford Suzhou Centre for Advanced Research Suzhou China Department of Computer Science Northwestern University EvanstonIL United States Center for Financial Engineering Soochow University Suzhou China School of Natural Science Great Bay University Guangdong China Department of Mathematics Northwestern University EvanstonIL United States

XNet is a single-layer neural network architecture that leverages Cauchy integral-based activation functions for high-order function approximation. Through theoretical analysis, we show that the Cauchy activation functions used in XNet can achieve arbitrary-order polynomial convergence, fundamentally outperforming traditional MLPs and Kolmogorov-Arnold Networks (KANs) that rely on increased depth or B-spline activations. Our extensive experiments on function approximation, PDE solving, and reinforcement learning demonstrate XNet’s superior performance - reducing approximation error by up to 50000 times and accelerating training by up to 10 times compared to existing approaches. These results establish XNet as a highly efficient architecture for both scientific computing and AI applications. © 2025, CC BY.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Gaze Behavior During a Long-Term, In-Home, Social Robot Intervention for Children with ASD

arXiv

引用

arXiv 2025年

作者： Ramnauth, Rebecca F., Shic B., Scassellati Department of Computer Science Yale University New HavenCT United States Center for Child Health Behavior and Development Seattle Children’s Research Institute SeattleWA United States Department of Pediatrics University of Washington School of Medicine SeattleWA United States

Atypical gaze behavior is a diagnostic hallmark of Autism Spectrum Disorder (ASD), playing a substantial role in the social and communicative challenges that individuals with ASD face. This study explores the impacts of a month-long, in-home intervention designed to promote triadic interactions between a social robot, a child with ASD, and their caregiver. Our results indicate that the intervention successfully promoted appropriate gaze behavior, encouraging children with ASD to follow the robot’s gaze, resulting in more frequent and prolonged instances of spontaneous eye contact and joint attention with their caregivers. Additionally, we observed specific timelines for behavioral variability and novelty effects among users. Furthermore, diagnostic measures for ASD emerged as strong predictors of gaze patterns for both caregivers and children. These results deepen our understanding of ASD gaze patterns and highlight the potential for clinical relevance of robot-assisted interventions. © 2025, CC BY-NC-SA.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

Provably Secure and Efficient Identity-Based Medical Data Sharing Framework Using Cloud-Assisted Blockchain

SSRN

引用

SSRN 2025年

作者： Ghosh, Sudeep Islam, S.K. Hafizul Vasilakos, Athanasios V. Department of Information Technology Guru Nanak Institute of Technology Kolkata700114 India Department of Computer Science and Engineering Indian Institute of Information Technology West Bengal Kalyani741235 India Center for AI Research University of Agder Grimstad4879 Norway Fuzhou University China

Cloud computing has become a popular paradigm in healthcare industries for ubiquitously sharing and accessing patient's electronic medical records (EMRs). However, for security reasons, all EMRs are stored in an encrypted format on a cloud server. However, searching encrypted EMR using the traditional plaintext search method is computationally infeasible. Public key encryption with keywords (PEKS) is used to search encrypted EMRs over an extensive database. The current EMR storage systems have problems with data leakage, improper user authorization, untrustworthy service providers, etc. Blockchain has exciting features like decentralization, transparency, and immutability. We design a blockchain-assisted identity-based medical data-sharing (BCT-IMDS) scheme to share EMRs among the cloud servers maintained at different hospitals. BCT-IMDS uses private and consortium blockchains to share and access the EMRs of patients. All participating hospitals keep the encrypted keywords and verification index in the consortium blockchain. BCT-IMDS scheme provides ciphertext, trapdoor indistinguishability, and designated-server testability in the random oracle model. We verified BCT-IMDS using Scyther verification tools and implemented it using the Python programming language, PBC, and the Charm crypto library. We considered 80, 112, 128, 192, and 256-bit security, estimated the computation, communication, and storage overheads of BCT-IMDS, and compared them with the existing PEKS schemes. © 2025, The Authors. All rights reserved.

关键词： Authorization

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：