检索结果-内蒙古大学图书馆

A Hybrid Deep Learning Method for Forecasting Reservoir Water Level from Sentinel-2 Satellite Images

computers, Materials and Continua 2025年第3期83卷 4915-4937页

作者： Hoang Thi Minh Chau Tran Thi Ngan Nguyen Long Giang Tran Manh Tuan Tran Kim Chau Graduate University of Science and Technology Vietnam Academy of Science and Technology Hanoi 100000 Vietnam Faculty of Information Technology University of Economics Technology for Industries Hanoi 100000 Vietnam Artificial Intelligence Research Center VNU Information Technology Institute Vietnam National University Hanoi 100000 Vietnam International School Vietnam National University Hanoi 100000 Vietnam Institute of Information Technology Vietnam Academy of Science and Technology Hanoi 100000 Vietnam Faculty of Computer Science and Engineering Thuyloi University Hanoi 100000 Vietnam Faculty of Water Resources Engineering Thuyloi University Hanoi 100000 Vietnam

Global climate change, along with the rapid increase of the population, has put significant pressure on water security. A water reservoir is an effective solution for adjusting and ensuring water supply. In particular, the reservoir water level is an essential physical indicator for the reservoirs. Forecasting the reservoir water level effectively assists the managers in making decisions and plans related to reservoir management policies. In recent years, deep learning models have been widely applied to solve forecasting problems. In this study, we propose a novel hybrid deep learning model namely the YOLOv9_ConvLSTM that integrates YOLOv9, ConvLSTM, and linear interpolation to predict reservoir water levels. It utilizes data from Sentinel-2 satellite images, generated from visible spectrum bands (Red-Blue-Green) to reconstruct true-color reservoir images. Adam is used as the optimization algorithm with the loss function being MSE (Mean Squared Error) to evaluate the model’s error during training. We implemented and validated the proposed model using Sentinel-2 satellite imagery for the An Khe reservoir in Vietnam. To assess its performance, we also conducted comparative experiments with other related models, including SegNet_ConvLSTM and UNet_ConvLSTM, on the same dataset. The model performances were validated using k-fold cross-validation and ANOVA analysis. The experimental results demonstrate that the YOLOv9_ConvLSTM model outperforms the compared models. It has been seen that the proposed approach serves as a valuable tool for reservoir water level forecasting using satellite imagery that contributes to effective water resource management.

关键词： YOLOv9 ConvLSTM reservoir water level forecasting satellite images

来源：评论

学校读者我要写书评

暂无评论

AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

来源：评论

学校读者我要写书评

暂无评论

In-Group Love, Out-Group Hate: A Framework to Measure Affective Polarization via Contentious Online Discussions 34

In-Group Love, Out-Group Hate: A Framework to Measure Affect...

引用

34th ACM Web Conference, WWW 2025

作者： Nettasinghe, Buddhika Rao, Ashwin Jiang, Bohan Percus, Allon G. Lerman, Kristina University of Iowa Tippie College of Business Iowa City IA United States USC Information Sciences Institute Department of Computer Science Marina del Rey CA United States Arizona State University School of Engineering Tempe AZ United States Claremont Graduate University Institute of Mathematical Sciences Claremont CA United States

ISBN: (纸本)9798400712746

Affective polarization, the emotional divide between ideological groups marked by in-group love and out-group hate, has intensified in the United States, driving contentious issues like masking and lockdowns during the COVID-19 pandemic. Despite its societal impact, existing models of opinion change fail to account for emotional dynamics nor offer methods to quantify affective polarization robustly and in real-time. In this paper, we introduce a discrete choice model that captures decision-making within affectively polarized social networks and propose a statistical inference method estimate key parameters—in-group love and out-group hate—from social media data. Through empirical validation from online discussions about the COVID-19 pandemic, we demonstrate that our approach accurately captures real-world polarization dynamics and explains the rapid emergence of a partisan gap in attitudes towards masking and lockdowns. This framework allows for tracking affective polarization across contentious issues has broad implications for fostering constructive online dialogues in digital spaces. © 2025 Copyright held by the owner/author(s).

关键词： COVID-19 Exposure Polarization Social Networks Twitter

来源：评论

学校读者我要写书评

暂无评论

Hadamard Attention Recurrent Transformer: A Strong Baseline for Stereo Matching Transformer

arXiv

引用

arXiv 2025年

作者： Chen, Ziyang Zhang, Yongjun Li, Wenting Wang, Bingshu Wu, Yabo Zhao, Yong Chen, C.L. Philip College of Computer Science The State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China School of Information Engineering Guizhou University of Commerce Guiyang550021 China School of Software Northwestern Polytechnical University Xi’an710129 China Key Laboratory of Integrated Microsystems Shenzhen Graduate School Peking University Shenzhen518055 China School of Computer Science and Engineering South China University of Technology Guangzhou510641 China

In light of the advancements in transformer technology, extant research posits the construction of stereo transformers as a potential solution to the binocular stereo matching challenge. However, constrained by the low-rank bottleneck and quadratic complexity of attention mechanisms, stereo transformers still fail to demonstrate sufficient nonlinear expressiveness within a reasonable inference time. The lack of focus on key homonymous points renders the representations of such methods vulnerable to challenging conditions, including reflections and weak textures. Furthermore, a slow computing speed is not conducive to the application. To overcome these difficulties, we present the Hadamard Attention Recurrent Stereo Transformer (HART) that incorporates the following components: 1) For faster inference, we present a Hadamard product paradigm for the attention mechanism, achieving linear computational complexity. 2) We designed a Dense Attention Kernel (DAK) to amplify the differences between relevant and irrelevant feature responses. This allows HART to focus on important details. DAK also converts zero elements to non-zero elements to mitigate the reduced expressiveness caused by the low-rank bottleneck. 3) To compensate for the spatial and channel interaction missing in the Hadamard product, we propose MKOI to capture both global and local information through the interleaving of large and small kernel convolutions. Experimental results demonstrate the effectiveness of our HART. In reflective area, HART ranked 1st on the KITTI 2012 benchmark among all published methods at the time of submission. Code is available at https://***/ ZYangChen/HART. Copyright © 2025, The Authors. All rights reserved.

关键词： Hadamard transforms

来源：评论

学校读者我要写书评

暂无评论

A Low Cost Triple-Node-Upset Self-Recoverable Latch Design for Nanoscale CMOS

引用

IEEE Transactions on Device and Materials Reliability 2025年

作者： Bai, Na Zhang, Pengshuai Xu, Yaohua Guo, Yunhui Li, Hang Wang, Yi Wen, Xiaoqing Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Hefei230601 China National University of Defense Technology College of Computers Hunan Changsha410073 China Kyushu Institute of Technology Graduate School of Computer Science and Systems Engineering Fukuoka8208502 Japan

Due to the constant reduction of semiconductor feature sizes, the charge sharing effect is getting worse. The occurrence probability of triple-node upset (TNU), which has a significant impact on the circuit’s reliability, is rising in nanoscale digital circuits. This paper proposes a low overhead and TNU self-recovery latch (TNU-SR) based on the 28 nm CMOS technology to efficiently tolerate TNU and reduce the power dissipation and latency of the latch. The latch design proposed in this article adopts stacked transistors to reduce sensitive nodes and area overhead. The TNU-SR latch uses clock gating and high-speed transfer path technology, resulting in low power dissipation and low delay. For simulation results, compared with existing latches, it can be known that the TNU-SR latch performs well in terms of delay, power consumption, and area, so it is a good choice for radiation-hardened design for space applications. In addition, compared with the latest TNU self-recovery latch (HLTNURL), the TNU-SR latch proposed in this paper reduces the Power-Area-Delay Product (PADP) metric by 111.13%. © 2001-2011 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Supplemental information

arXiv

引用

arXiv 2025年

作者： Sunada, Satoshi Niiyama, Tomoaki Kanno, Kazutaka Nogami, Rin Röhm, André Awano, Takato Uchida, Atsushi Faculty of Mechanical Engineering Institute of Science and Engineering Kanazawa University Kakuma-machi Kanazawa Ishikawa920-1192 Japan Department of Information and Computer Sciences Saitama University 255 Shimo-Okubo Sakura-ku Saitama338-8570 Japan Department of Information Physics and Computing Graduate School of Information Science and Technology The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan

The rapidly increasing computational demands for artificial intelligence (AI) have spurred the exploration of computing principles beyond conventional digital computers. Physical neural networks (PNNs) offer efficient neuromorphic information processing by harnessing the innate computational power of physical processes;however, training their weight parameters is computationally expensive. We propose a training approach for substantially reducing this training cost. Our training approach merges an optimal control method for continuous-time dynamical systems with a biologically plausible training method—direct feedback alignment. In addition to the reduction of training time, this approach achieves robust processing even under measurement errors and noise without requiring detailed system information. The effectiveness was numerically and experimentally verified in an optoelectronic delay system. Our approach significantly extends the range of physical systems practically usable as PNNs. Copyright © 2025, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Musculoskeletal Load Generated when a Small Dog Walks on a Slippery Floor*

Analysis of the Musculoskeletal Load Generated when a Small ...

引用

IEEE/SICE International Symposium on System Integration

作者： Shijian Li Daisuke Chugo Satoshi Muramatsu Sho Yokota Jin-Hua She Hiroshi Hashimoto Uemura Takashi Hiroaki Kamishina Yoshiharu Hata Takayuki Yamada Takahiro Uchida Graduate School of Science and Technology Kwansei Gakuin University Sanda Japan School of Information Science and Technology Tokai University Hiratsuka Japan Faculty of Science and Engineering Toyo University Kawagoe Japan School of Engineering Tokyo University of Technology Tokyo Japan Master Program of Innovation for Design and Engineering Advanced Institute of Industrial Technology Tokyo Japan KyotoAR Animal Advanced Medical Center Kyoto Japan Rinrei Co. Ltd. Tokyo Japan

ISBN: (数字)9798331531614

ISBN: (纸本)9798331531621

The objective of this paper is to identify the stresses placed on the musculoskeletal system when small dogs walk on floors with low friction coefficients. In many households, and small dogs in particular are often kept indoors. According to veterinary experience, it is known that small dogs kept indoors that walk with their lower limbs slipping cause a great deal of stress on the musculoskeletal system, and that the incidence of joint disease in the lower limbs of such small dogs is high. In this study, we measured the body movements of small dogs walking on slippery floors using a three-dimensional motion capture system and force plate system. Furthermore, by inputting these measurements into the musculoskeletal simulation model we have developed to simulate the musculoskeletal system of dogs, we derived the load on the musculoskeletal system of small dogs on slippery and non-slippery floors. As a result, it was identified that walking on a slippery floor causes a strong load on the lower limb muscles of small dogs.

关键词： Legged locomotion Limbs Friction Dogs System integration Muscles Object recognition Floors Stress Paints

来源：评论

学校读者我要写书评

暂无评论

Twenty Years of Personality Computing: Threats, Challenges and Future Directions

arXiv

引用

arXiv 2025年

作者： Celli, Fabio Kartelj, Aleksandar Ðorðević, Miljan Suhartono, Derwin Filipović, Vladimir Milutinović, Veljko Spathoulas, Georgios Vinciarelli, Alessandro Kosinski, Michal Lepri, Bruno Maggioli SpA Italy Faculty of Mathematics University of Belgrade Serbia School of Electrical Engineering University of Belgrade Serbia School of Computer Science Bina Nusantara University Indonesia Dept. of Information Security Norwegian University of Science and Technology Norway School of Computing Science University of Glasgow United Kingdom Graduate School of Business Stanford University United States Center for Augmented Intelligence Fondazione Bruno Kessler Italy

Personality Computing is a field at the intersection of Personality Psychology and computer science. Started in 2005, research in the field utilizes computational methods to understand and predict human personality traits. The expansion of the field has been very rapid and, by analyzing digital footprints (text, images, social media, etc.), it helped to develop systems that recognize and even replicate human personality. While offering promising applications in talent recruiting, marketing and healthcare, the ethical implications of Personality Computing are significant. Concerns include data privacy, algorithmic bias, and the potential for manipulation by personality-aware Artificial Intelligence. This paper provides an overview of the field, explores key methodologies, discusses the challenges and threats, and outlines potential future directions for responsible development and deployment of Personality Computing technologies. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User-Centric Data Management in Decentralized Internet of Behaviors System

arXiv

引用

arXiv 2025年

作者： Zhang, Shiqi Wu, Dapeng Wang, Honggang Wang, Ruyan School of Communications and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China Chongqing Key Laboratory of Ubiquitous Sensing and Networking China Department of Graduate Computer Science and Engineering Katz School of Science and Health Yeshiva University in New York City United States

The Internet of Behaviors (IoB) is an emerging concept that utilizes devices to collect human behavior and provide intelligent services. Although some research has focused on human behavior analysis and data collection within IoB, the associated security and privacy challenges remain insufficiently explored. This paper analyzes the security and privacy risks at different stages of behavioral data generating, uploading, and using, while also considering the dynamic characteristics of user activity areas. Then, we propose a blockchain-based distributed IoB data storage and sharing framework, which is categorized into sensing, processing, and management layers based on these stages. To accommodate both identity authentication and behavioral privacy, zero-knowledge proofs are used in the sensing layer to separate the correlation between behavior and identity, which is further extended to a distributed architecture for cross-domain authentication. In the processing layer, an improved consensus protocol is proposed to enhance the decision-making efficiency of distributed IoB by analyzing the geographical and computational capability of the servers. In the management layer, user permission differences and the privacy of access targets are considered. Different types of behavior are modeled as corresponding relationships between keys, and fine-grained secure access is achieved through function secret sharing. Simulation results demonstrate the effectiveness of the proposed framework in multi-scenario IoB, with average consensus and authentication times reduced by 74% and 56%, respectively. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Novel intelligent exogenous neuro-architecture–driven machine learning approach for nonlinear fractional breast cancer risk system

引用

Communications in Nonlinear science and Numerical Simulation 2025年 149卷

作者： Fida, Afshan Raja, Muhammad Asif Zahoor Chang, Chuan-Yu Raja, Muhammad Junaid Ali Asif Khan, Zeshan Aslam Shoaib, Muhammad of Engineering Science and Technology National Yunlin University of Science and Technology Yunlin 64002 Taiwan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin 64002 Taiwan International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan AI center Yuan Ze University Taoyuan 320 Taiwan

Breast cancer remains one of the most prevalent and life-threatening diseases worldwide, necessitating mathematical modelling frameworks to capture the complexity of its progression and risk factors. This research endeavor uncovers the novel machine learning expedition using an Adaptive Nonlinear AutoRegressive eXogenous (ANARX) neural network on a Fractional Order Breast Cancer Risk (FO-BCR) model. A novel Caputo fractional operator-based breast cancer risk model is presented using a five compartmental system reflected by healthy, tumor, immune, estrogen, and fatty cells. A modified fractional Adams PECE method is opted to generate solutions of the five fractional order variants on the four diverse BCR scenarios. These temporal sequences are parsed as ground truth for the adept ANARX network, which is iteratively refined using the Levenberg-Marquardt (LM) algorithm. The performance evaluation of the temporal feature learning of the ANARX-LM algorithm is comprehensively evaluated against reference numerical outcomes using mean square error (MSE) performance graphics, input-error cross correlation, error autocorrelation, error histogram analysis, sequential response and comparative error analysis charts. Low disparity between reference solutions is observed for all FO-BCR systems, with MSE errors in the range of 10−8 to 10−11. Finally, the ANARX-LM's predictive prowess is evaluated using the single and multistep configurations. Minute errors in the range of 10−9 to 10−11, 10−8 to 10−10 suggest accurate anticipation of the FO-BCR system enabling preventive and prognostic measures for breast cancer models. These empirical findings underscore the potential of advanced machine-learning-driven neuro-architecture for next-generation predictive-oncology solutions that may facilitate treatment strategies. © 2025 Elsevier B.V.

关键词： Risk assessment

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：