检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Mo, Site Wang, Haoxin Li, Bixiong Fan, Songhai Wu, Yuankai Liu, Xianggen College of Electrical Engineering Sichuan University Chengdu610065 China College of Architecture and Environment Sichuan University Chengdu610065 China State Grid Sichuan Electric Power Research Institute Chengdu610041 China College of Computer Science Sichuan University Chengdu610065 China

Time series is a special type of sequence data, a sequence of real-valued random variables collected at even intervals of time. The real-world multivariate time series comes with noises and contains complicated local and global temporal dynamics, making it difficult to forecast the future time series given the historical observations. This work proposes a simple and effective framework, coined as TimeSQL, which leverages multi-scale patching and smooth quadratic loss (SQL) to tackle the above challenges. The multi-scale patching transforms the time series into two-dimensional patches with different length scales, facilitating the perception of both locality and long-term correlations in time series. SQL is derived from the rational quadratic kernel and can dynamically adjust the gradients to avoid overfitting to the noises and outliers. Theoretical analysis demonstrates that, under mild conditions, the effect of the noises on the model with SQL is always smaller than that with MSE. Based on the two modules, TimeSQL achieves new state-of-the-art performance on the eight real-world benchmark datasets. Further ablation studies indicate that the key modules in TimeSQL could also enhance the results of other models for multivariate time series forecasting, standing as plug-and-play techniques. Copyright © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Retraining and Regularization to Optimize Neural Networks for Stochastic Computing

Retraining and Regularization to Optimize Neural Networks fo...

引用

IEEE computer Society Annual Symposium on VLSI

作者： Junseok Oh Florian Neugebauer Ilia Polian John Hayes Institute of Computer Architecture and Computer Engineering University of Stuttgart Germany University of Michigan Ann Arbor MI USA

ISBN: (数字)9781728157757

ISBN: (纸本)9781728157764

Stochastic computing (SC) is a promising computation technique for applications with huge numbers of individually simple operations. One of the main application targets for SC is the design of convolutional neural networks (CNNs) due to their heavy reliance on multiply-accumulate operations that have compact and power-efficient SC realizations. We present a training optimization method that can improve the accuracy of SC-based CNNs significantly. Using regularization techniques in combination with a newly developed retraining algorithm, we enforce sparsity, reduce the number of required MUX-based additions, and thus minimize undesired downscaling. Our results show that the proposed regularized training procedure (RTP) can reduce the computation time of SC-based NNs by a factor of four without sacrificing classification accuracy while also reducing area in hardware implementations. These findings suggest that SC can be successfully applied to more powerful CNNs than previously thought possible, thus extending the range of potential uses of SC.

关键词： Artificial neural networks Training Optimization Logic gates Generators Convolution

来源：评论

学校读者我要写书评

暂无评论

Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention 32

Enhancing Local Feature Learning for 3D Point Cloud Processi...

引用

32nd British Machine Vision Conference, BMVC 2021

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science Tokyo Institute of Technology Tokyo Japan

We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA ensures query dependence via operating locally. Extensive experiments show that the UPA outperforms the SA consistently on various point cloud understanding tasks including shape classification, part segmentation, and scene segmentation. Moreover, simply equipping the popular PointNet++ method with the UPA even outperforms or is on par with the state-of-the-art attention-based approaches. In addition, the UPA systematically boosts the performance of both standard and modern networks when it is integrated into them as a compositional module. © 2021. The copyright of this document resides with its authors.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

WatchPlant: Networked Bio-hybrid Systems for Pollution Monitoring of Urban Areas

WatchPlant: Networked Bio-hybrid Systems for Pollution Monit...

引用

2021 Conference on Artificial Life, ALIFE 2021

作者： Hamann, Heiko Bogdan, Stjepan Diaz-Espejo, Antonio García-Carmona, Laura Hernandez-Santana, Virginia Kernbach, Serge Kernbach, Andreas Quijano-López, Alfredo Salamat, Babak Wahby, Mostafa Institute of Computer Engineering University of Lübeck Germany Faculty of Electrical Eng. and Comp. University of Zagreb Croatia Spain València Spain CYBRES GmbH Stuttgart Germany ITE Universitat Politècnica de València Spain

Growing cities are a world-wide phenomenon and simultaneously awareness about potential dangers due to air pollution, heat, and pathogens is increasing. Integrated and permanent monitoring of environmental features in cities can help to establish an early warning system and to provide data for policy makers. In our new project ‘WatchPlant,’ we propose a green approach for urban monitoring by a network of sensors tightly coupled with natural plants. We want to develop a sustainable, energy-efficient bio-hybrid system that harvests energy from living plants and utilizes methods of phytosensing, that is, using natural plants as sensors. We present our concept, here with focus on Alife-related methods operating on the gathered plant data and the bio-hybrid network. With a self-organizing network of sensors, that are alive, we hope to contribute to our future of livable green cities. © 2021 ALIFE. All Rights Reserved.

关键词： Biotic

来源：评论

学校读者我要写书评

暂无评论

Reliability-aware quantization for anti-aging NPUs

arXiv

引用

arXiv 2021年

作者： Salamin, Sami Zervakis, Georgios Spantidi, Ourania Anagnostopoulos, Iraklis Henkel, Jörg Amrouch, Hussam Karlsruhe Institute of Technology Karlsruhe Germany Department of Electrical and Computer Engineering Southern Illinois University Carbondale United States University of Stuttgart Stuttgart Germany

Transistor aging is one of the major concerns that challenges designers in advanced technologies. It profoundly degrades the reliability of circuits during its lifetime as it slows down transistors resulting in errors due to timing violations unless large guardbands are included, which leads to considerable performance losses. When it comes to Neural Processing Units (NPUs), where increasing the inference speed is the primary goal, such performance losses cannot be tolerated. In this work, we are the first to propose a reliability-aware quantization to eliminate aging effects in NPUs while completely removing guardbands. Our technique delivers a graceful inference accuracy degradation over time while compensating for the aging-induced delay increase of the NPU. Our evaluation, over ten state-of-the-art neural network architectures trained on the ImageNet dataset, demonstrates that for an entire lifetime of 10 years, the average accuracy loss is merely 3%. In the meantime, our technique achieves 23% higher performance due to the elimination of the aging guardband. Copyright © 2021, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

EPRD: Exploiting prior knowledge for evidence-providing automatic rumor detection

引用

Neurocomputing 2024年 563卷

作者： Li, Jiawen Li, Ronghui Ni, Shiwen Kao, Hung-Yu Naval Architecture and Shipping College Guangdong Ocean University Guangdong Zhanjiang524000 China Technical Research Center for Ship Intelligence and Safety Engineering of Guangdong Province Guangdong Zhanjiang524000 China Intelligent Knowledge Management Lab National Cheng Kung University Tainan Taiwan Department of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

With the prevalence of social media platforms, rumors have been a serious social problem. Notably, existing rumor detection methods simply provide detection labels while ignoring their explanation. However, illustrating the reasons why a suspicious statement is a rumor is essential. To address this realistic scenario, we propose a novel Evidence-Providing Rumor Detection model called EPRD. EPRD incorporates a wide variety of information from both prior knowledge sources and current comments. It also learns bilaterally friendly representations for interpretable rumor detection. EPRD first retrieves evidence from prior knowledge sources and checks the relationship between the given statement and its evidence. Our model then constructs two heterogeneous graph objects to simulate the propagation layout of the current comments and evidence relationships. Finally, EPRD integrates the GraphSAGE component and attention mechanism to detect rumors. To the best of our knowledge, we propose the first model that incorporates prior knowledge to verify rumors and boost credibility. Experiments on two real-world Twitter datasets demonstrate that EPRD consistently exhibits the best rumor detection performance. Moreover, EPRD outperforms other baselines in the early rumor detection task. © 2023

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Measuring Water Ponding Time, Location and Connectivity on Soil Surfaces Using Time-Lapse Images and Deep Learning

SSRN

引用

SSRN 2024年

作者： Pereira Zamboni, Pedro Alberto Blümlein, Mikesch Lenz, Jonas Gonçalves, Wesley Nunes Junior, Jose Marcato Wöhling, Thomas Eltner, Anette Institute of Photogrammetry and Remote Sensing Dresden University of Technology Dresden01069 Germany IPROconsult GmbH Dresden01069 Germany Faculty of Engineering Geography and Architecture Federal University of Mato Grosso do Sul Brazil Faculty of Computer Science Federal University of Mato Grosso do Sul Campo Grande79070-900 Brazil Institute of Hydrology and Meteorology Dresden University of Technology Dresden01069 Germany

Rainfall simulations are an established method to gain knowledge on small-scale hydrological processes like infiltration, ponding and the formation of surface runoff. Due to limitations in measuring methods, these processes must usually be understood to happen homogeneously within the bounded plot area while it is well known that they actually vary on a subplot scale. Within this study we took high resolution time-lapse images of several plots to observe and quantify the subplot processes of ponding and the formation of connectivity and surface *** investigated the potential of deep learning in the segmentation of water ponding areas in time-lapse images during rainfall simulations and to estimate the ponding time. We trained three different Convolutional Neural Networks (CNNs), considering classification uncertainty and imbalance of the ground-truth data (water pixels) as well as ensemble modeling and spatial correlation between samples. Our findings suggest that addressing ground-truth annotation uncertainty and imbalance was more important in our study than the choice of the CNNs itself, and ensemble models increase the model performance leading to more robust predictions. Overall, our results suggest that CNNs have a great potential to segment ponding areas, and thus it is possible to observe their spatio-temporal *** comparing the evolution of water ponding areas to runoff, different behaviors across the plots were observable, which could be related to differences in initial soil moisture and infiltration behaviors. Further, our image-based deep learning approach allows for direct measurement of the ponding time, and can be considered a first step to spatially and temporally resolved mapping of infiltration rates. © 2024, The Authors. All rights reserved.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Artificial pancreas under periodic MPC for trajectory tracking: handling circadian variability of insulin sensitivity

引用

IFAC-PapersOnLine 2022年第16期55卷 196-201页

作者： Pablo Abuin Antonio Ferramosca Chiara Toffanin Lalo Magni Alejandro H. Gonzalez Institute of Technological Development for the Chemical Industry (INTEC) CONICET-Universidad Nacional del Litoral (UNL) Santa Fe Argentina Department of Management Information and Production Engineering University of Bergamo Bergamo Italy Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy Department of Civil and Architecture Engineering University of Pavia Pavia Italy

Closed-loop glycemic control algorithms have demonstrated the ability to improve glucose regulation in patients with type 1 diabetes mellitus (T1D), both in silico and clinical trials. Many of the proposed control strategies have been developed, based on time-invariant linear models, without considering the parametric variations of T1DM subjects. In this work, a pulsatile Zone Model Predictive Control (pZMPC) is proposed, which explicitly considers patterns of intra-day insulin sensitivity ( S I ), according to the latest updates of the FDA-approved UVA/Padova simulator. Results show a significant improvement in the performance, which a-priori justifies the increment in the controller complexity.

关键词： Insulin sensitivity variations trajectory tracking MPC Artificial Pancreas

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Smart Health Monitoring System Using Wearable IoT Devices and Predictive Analytics

AI-Driven Smart Health Monitoring System Using Wearable IoT ...

引用

IoT, Communication and Automation Technology (ICICAT), International Conference on

作者： Bh. Prashanthi Ashish Sharma M. Mahima K. Navya Ramy Riad Al-Fatlawy Senthilnathan Chidambaranathan Department of CSE GRIET Bachupally Hyderabad Telangana India Department of Computer Engineering & Applications GLA University Mathura Department of IT New Prince Shri Bhavani College of Engineering and Technology Chennai Tamil Nadu India Department of ECE CMR Institute of Technology Hyderabad Telangana India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Architecture and Design Virtusa Corporation New Jersey USA

ISBN: (数字)9798350368109

ISBN: (纸本)9798350368116

The demonstrative realisation of this research is the smart health monitoring system, proposed and designed to employ wearable IoT technology and predictive analysis for constant health check. The system is intended to gather the physiological data; for example, pulse, blood pressure, and oxygen saturation and others via wearables and process it using sophisticated AI techniques and approaches, including deep learning based on CNN and LSTM. According to the systems, there are predictions that need to be offered by means of the programs and health risks that should be anticipated for timely intervention in order to increase chances for the patients’ recovery. Although the system is designed for home use, the writers applied a cloud-based solution that provides scalability and real-time data processing; data is securely transferred from the wearable devices to the cloud through Bluetooth and Wi-Fi. This physiological data is augmented by the other public datasets available in the healthcare domain such that the AI learning algorithms can learn from an extensive health record. From the above research, it manifests how the system was able to predict serious health precursors including; heart attack and respiratory failure with LSTM models having prediction rate of more than 96%. It also delivers on-time alarms to the clinical practitioners, with average response time of less than three seconds for critical states. A set of surveys concerning the usability and comfort of the wearable devices among the patients has been conducted and the results show high satisfaction levels reported by the patients about the accuracy as well as simplicity of the system. Despite the introduced effort of the system, there exist significant concerns involving data protection, compatibility, and AI ethic; therefore, the future study should overcome such shortcomings. With these advancements of an artificial intelligence driven health monitoring system, healthcare systems would shift to being

关键词： Smart healthcare Predictive models Real-time systems Internet of Things Biomedical monitoring Artificial intelligence Wearable devices Predictive analytics Monitoring Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Transforming the public transport sector in the Philippines through service contracts: A program evaluation study

引用

Transportation Research Procedia 2025年 82卷 890-907页

作者： Varsolo Sunio Wilhansen Li Joemier Pontawe Albert Dizon Alexis Fillone Science Engineering and Management Research Institute University of Asia and the Pacific Pasig City Metro Manila 1600 Philippines Toulan School of Urban Studies and Planning Portland State University Oregon 97201 United States Sakay Mobility Philippines Corporation Quezon City Metro Manila 1110 Philippines Department of Information Systems and Computer Science School of Science and Engineering Ateneo de Manila University Quezon City Metro Manila 1108 Philippines School of Architecture and Planning The University of Auckland New Zealand Civil Engineering Department De La Salle University Manila Metro Manila 1004 Philippines

We evaluate two schemes of service contracting (SC) program implemented for the first time in the Philippines: gross-cost and net-cost. Using an automatic vehicle location (AVL) dataset generated using a mobile application, we examine the supply and performance of jeepney, a form of paratransit, on 20 routes during the pandemic. Ten of these routes are under gross-cost, and the other ten are under net-cost. Our evaluation suggests that gross-cost SC has resulted in more kilometer-run travelled, more arrivals at the stop, shorter headway duration, which are indicative of increased supply, compared to net-cost. However, we obtain mixed results for metrics associated with performance (headway regularity, dwell time and route compliance) for gross- and net- cost. We recommend that for SC to maximize its impact and raise performance, the government should set standards on metrics associated with fleet management and enforce strict compliance. Since SC is typically applied for the management of formal public transport, our work represents a novel contribution on the application of SC on the management of paratransit in the Global South.

关键词： service contract public transport reform Global South paratransit

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：