检索结果-内蒙古大学图书馆

Enhancing Sentiment Analysis of Corruption-Related Comments on Social Networks in Ecuador Using Techniques of Machine Learning: LSTM, Linear Regression, and Support Vector Machine

Enhancing Sentiment Analysis of Corruption-Related Comments...

引用

International Conference on Information Technology and Systems, ICITS 2024

作者： Idrovo-Berrezueta, Paul S. Dutan-Sanchez, Denys A. León-Paredes, Gabriel A. Research Group in Cloud Computing Smart Cities and High Performance Computing Universidad Politécnica Salesiana Cuenca Ecuador

ISBN: (纸本)9783031542343

This research focuses on obtaining effective models that can predict a person’s sentiments from written messages. While the initially proposed models were within acceptable ranges as classifiers, applying quality metrics revealed a new perspective. For this research a dataset from comments from Facebook were collected and these comments were processed in two manners. the text was first processed as a normal bag of words and the second process was a TF-IDF. Both methods were used to train 3 different models the first model is a support vector machine, the second model is a linear regression, and the third model was long-short term memory model. Upon processing our dataset with the best model, the LSTM, which achieved an accuracy of 92% and obtained the highest scores in quality metrics. Although the model was not perfect, an interesting phenomenon emerged regarding sentiment classification. A considerable percentage of comments were classified as positive concerning the search hashtag, suggesting possible support for political actors. However, the vast majority of classified comments expressed negative sentiments. This leads to a significant conclusion that evaluating sentiment in social media comments is a complex challenge due to the presence of emojis and informal writing with spelling errors and inconsistencies, which impact model results. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Web Approach for the Extraction, Analysis, and Visualization of Sentiments in Social Networks Regarding the Public Opinion on Politicians in Ecuador Using Natural Language Processing and high-performance computing Tools

A Web Approach for the Extraction, Analysis, and Visualiz...

引用

International Conference on Information Technology and Systems, ICITS 2024

作者： Parra-Zambrano, Bryam E. León-Paredes, Gabriel A. Research Group in Cloud Computing Smart Cities and High Performance Computing Universidad Politécnica Salesiana Cuenca Ecuador

ISBN: (纸本)9783031542343

In a constantly evolving technological world, the presence of state-of-the-art computer-based methods such as Machine Learning (ML), Deep Learning (DL), and Natural Language Processing (NLP), among others has leveraged to develop systems for information extraction and sentiment analysis in raw text. Hence, the integration of these methods with the social network data is crucial to analyze posts, comments, or tweets on various subjects to capture social humor or sentiment around specific issues like the political arena as addressed in this paper. Hence, this research introduces a web application that enables interaction with web components and facilitates the extraction of posts and comments from Facebook related to political representatives using novelties technologies such as Selenium and ChatGPT. The latter has demonstrated an accuracy of 95%, a significantly high mark for a text processing-focused machine learning model. Hence, we have successfully categorized sentiments of social network data into positive, neutral, and negative. Also, we have found outstanding results by using an architectural parallel computing approach such as multiprocessing, where notable accelerations of 2.28× for extraction, and 2.69× for analysis have been achieved. As the digital environment continues to evolve, tools like these become fundamental for analyzing and comprehending social perceptions in an increasingly interconnected world. Therefore, the web application presented here represents a step forward in obtaining valuable information quickly and accurately, contributing to the understanding of public opinion regarding political and social matters, and not only limited to those issues but also to any subject addressed in society. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Transforming desalination brine into highly reactive magnesium oxide and life cycle analysis

引用

Watershed Ecology and the Environment 2025年 7卷 36-46页

作者： Senevirathna, Hasanthi L. Lee, W.P. Cathie Wu, Shunnian Bai, Kewu Wu, Ping Entropic Interface Group Engineering Product Development Singapore University of Technology and Design 8 Somapah Road 487372 Singapore Institute of High-Performance Computing Agency for Science Technology and Research Fusionopolis Way #16-16 Connexis 138632 Singapore

The sustainable production of magnesium oxide (MgO) from reject brine at a desalination facility in Singapore presents a promising alternative to traditional building materials. This study investigates the properties and extraction methods of MgO derived from reject brine, focusing on environmental sustainability and resource efficiency. By utilizing a combination of thermodynamic modelling of concentrated salt aqueous solutions and experimental validation, we optimized the recovery process for Mg²⁺ from reject brine, achieving an impressive 99 % recovery rate to produce MgO with ∼ 98 % purity. The MgO produced, calcined at 700 °C, exhibits high reactivity and a large surface area of 58.01 m²/g, making it a highly viable option for various industrial applications. This approach addresses reject brine disposal challenges and emphasizes brine valorization, aligning with strict environmental regulations by treating both freshwater and concentrated brine as valuable products. The technology enables cost-effective reject brine treatment by recycling Mg²⁺ to produce sustainable Mg-based materials. A comprehensive Life Cycle Assessment (LCA) was conducted to evaluate the environmental impact of MgO production from reject brine. This analysis provides a thorough examination of the transformation process, assessing the sustainability of employing MgO in commercial applications. The findings of this study offer valuable insights for enhancing sustainability in various sectors, underscoring the promise of MgO as an environmentally friendly and cost-effective material. © 2025 The Authors

关键词： CO2 emission MgO Reactivity Reject brine Solution model

来源：评论

学校读者我要写书评

暂无评论

An Attention Model Based Approach for Leakage Detection in Water Distribution Networks Using Normal Pressure Data 21st

An Attention Model Based Approach for Leakage Detection in...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Luo, Juan Zhou, Du Wang, Chongxiao Yang, Jielong Zhong, Xionghu Hunan University Changsha China Hunan Construction Investment Group Co. Ltd. Changsha China Institute of High Performance Computing Agency for Science Technology and Research Singapore Singapore Jiangnan University Wuxi China

ISBN: (纸本)9789819601271

In the past, machine learning methods such as Convolutional Neural Networks (CNN) and Autoencoder (AE) have been employed for leakage detection in water distribution networks (WDNs). However, these methods primarily rely on local pressure information and often fail to capture long-term dependencies in pressure series. In this paper, we propose a transformer based model to detect leakages in WDNs. This model incorporates an attention mechanism to learn data distributions and account for correlations between historical and daily interval pressures, thereby emphasizing long-term dependencies in the pressure series. The performance of the proposed method is evaluated using detection accuracy and F1-score. Experimental studies conducted on simulated pressure datasets from two different WDNs demonstrate that the transformer based model significantly outperforms traditional CNN methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Data-driven identification of port-Hamiltonian DAE systems by Gaussian processes

arXiv

引用

arXiv 2024年

作者： Zaspel, Peter Günther, Michael IMACM School of Mathematics and Natural Sciences University of Wuppertal Germany Research Group Scientific Computing and High Performance Computing Research Group Applied and Computational Mathematics

Port-Hamiltonian systems (pHS) allow for a structure-preserving modeling of dynamical systems. Coupling pHS via linear relations between input and output defines an overall pHS, which is structure preserving. However, in multiphysics applications, some subsystems do not allow for a physical pHS description, as (a) this is not available or (b) too expensive. Here, data-driven approaches can be used to deliver a pHS for such subsystems, which can then be coupled to the other subsystems in a structure-preserving way. In this work, we derive a data-driven identification approach for port-Hamiltonian differential algebraic equation (DAE) systems. The approach uses input and state space data to estimate nonlinear effort functions of pH-DAEs. As underlying technique, we us (multi-task) Gaussian processes. This work thereby extends over the current state of the art, in which only port-Hamiltonian ordinary differential equation systems could be identified via Gaussian processes. We apply this approach successfully to two applications from network design and constrained multibody system dynamics, based on pH-DAE system of index one and three, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Towards Green HPC Job Outsourcing: Energy Models for Molecular Dynamics Simulations on Three Clusters

Towards Green HPC Job Outsourcing: Energy Models for Molecul...

引用

International Symposium on Parallel and Distributed computing

作者： Ruben Horn Philipp Neumann Chair for High Performance Computing Helmut Schmidt University Hamburg Germany Research Group High Performance Computing and Data Science Universitä Hamburg Deutsches Elektronen-Synchroton Hamburg Germany

ISBN: (数字)9798350369199

ISBN: (纸本)9798350369205

In order to facilitate outsourcing of HPC jobs to remote computing resources powered directly by renewable energy, we aim to model the energy requirement of MD simulations on a single node. First, three different clusters are compared using an example simulation scenario with varying volume using a simple linear model. Then we investigate the impact of the density and simulated substance (number of LJ sites) and confirm their linear effect on the energy consumption of the simulation. Combining these insights with direct energy measurements could allow the prediction of the total energy required for a given job. Other simulation parameters, such as the temperature, and hardware parameters like FLOPS and cache size, should be added to such a model in the future to improve its generalizability.

关键词： Temperature measurement Solid modeling Energy consumption Renewable energy sources Computational modeling Green products Energy measurement Hardware Outsourcing Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Medical image registration and its application in retinal images:a review

引用

Visual computing for Industry,Biomedicine,and Art 2024年第1期7卷 142-164页

作者： Qiushi Nie Xiaoqing Zhang Yan Hu Mingdao Gong Jiang Liu Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Singapore Eye Research Institute Singapore 169856Singapore State Key Laboratory of Ophthalmology Optometry and Visual ScienceEye HospitalWenzhou Medical UniversityWenzhou 325027China

Medical image registration is vital for disease diagnosis and treatment with its ability to merge diverse informa-tion of images,which may be captured under different times,angles,or *** several surveys have reviewed the development of medical image registration,they have not systematically summarized the existing med-ical image registration *** this end,a comprehensive review of these methods is provided from traditional and deep-learning-based perspectives,aiming to help audiences quickly understand the development of medical image *** particular,we review recent advances in retinal image registration,which has not attracted much *** addition,current challenges in retinal image registration are discussed and insights and prospects for future research provided.

关键词： Computer-aided diagnosis Medical image registration Deep learning Generative model Transformer Retina

来源：评论

学校读者我要写书评

暂无评论

On the use of BLAS libraries in modern scientific codes at scale 17th

On the use of BLAS libraries in modern scientific codes at s...

引用

17th Smoky Mountains Computational Sciences and Engineering Conference, SMC 2020

作者： Waugh, Harry McIntosh-Smith, Simon High Performance Computing Research Group University of Bristol Bristol United Kingdom

ISBN: (纸本)9783030633929

As we approach the Exascale era, computer architectures are evolving ever-greater vector and matrix acceleration units—NVIDIA’s Ampere Tensor Cores, Intel’s AMX, and Arm’s SVE vector instruction set developments are just three recent examples [1,2,10]. To exploit these, it is expected that optimised math libraries such as those for dense and sparse linear algebra, will play an increasing role in achieving optimal performance. It is therefore useful to understand which of these functions dominate an application’s runtime, and in particular how this changes with increasing scale. This work aims to provide a contemporary dataset regarding how much dense linear algebra (BLAS) is used in HPC codes at scale. We have analysed several science codes widely used on the UK HPC service, ARCHER (https://***), including CASTEP, CP2K, QuantumESPRESSO, and Nektar++. To capture demands from the AI community, we have additionally traced the training stage of the Convolutional Neural Network (CNN), AlexNet [7]. HPLinpack is also included as a reference, as it exhibits a well-understood BLAS usage pattern. Results from across all the codes show that, unlike HPLinpack, BLAS usage is never more than 25% of the total runtime, even when running at a modest scale (32 nodes of the Arm-based supercomputer, Isambard). This presents limited speedup opportunity when considering Amdahl’s law, and suggests that application developers may need to adjust their algorithms to spend more time in optimised BLAS libraries to capitalise on new architectures and accelerators. © Springer Nature Switzerland AG 2020.

关键词： Supercomputers

来源：评论

学校读者我要写书评

暂无评论

The Impact of Thermal Aging on Mechanical and Electrical Properties of Epoxy/Amine Resin

The Impact of Thermal Aging on Mechanical and Electrical Pro...

引用

2023 International Symposium on Electrical Insulating Materials, ISEIM 2023

作者： Deng, Yuheng Wang, Qi Ma, Jielin Yang, Yan Yap, Malvern Chern, Wen Kwang Oh, Joo Tien Chen, Zhong School of Material Science and Engineering Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore Singapore Power Group Singapore

ISBN: (纸本)9784886864376

Epoxy resin is widely employed as a polymeric insulation material. Epoxy/amine resin is a type of resin that is crosslinked by amine groups, exhibiting improved mechanical properties, better durability, and easier curing process. However thermal degradation is a concern as the polymeric insulation material is prone to heat accumulation during long-term use. Thus, this study aims to investigate the effects of thermal aging on the mechanical and dielectric properties of epoxy/amine resin, along with the associated molecule change. Specimens were prepared and thermally aged at 105 ℃ for durations ranging from 0 hours to 1000 hours. Tensile strength, electrical tree growth, dielectric constant and loss were measured to assess the impact of thermal aging. ATR-FTIR (Attenuated total reflectance Fourier-transform infrared) and UV-Vis (Ultraviolet-visible) spectrometers were utilized to analyze the relationship between property changes and chemical structure. With increased aging time, tensile strength initially rose and then fell, which can be attributed to the formation and subsequent degradation of ether bonds in the surface layer of epoxy/amine resin. The consistent chain scission and oxidation were also observed in the specimen surface. Notably, a heterogeneous degradation was found to appear from the sample surface to the core, with nearly no degradation in the core of the specimen After almost 1000 hours of aging. Moreover, a higher crosslinking degree was observed inside the aged specimen than the unaged one, leading to a higher electrical tree initiation voltage. This spatial inhomogeneity of thermal degradation provides a compelling explanation to the diverse effects of thermal aging on mechanical and electrical properties. © 2023 The Institute of Electrical Engineers of Japan.

关键词： Thermal aging

来源：评论

学校读者我要写书评

暂无评论

Modeling the dielectric breakdown of nanocomposites using a novel phase-field model

Modeling the dielectric breakdown of nanocomposites using a ...

引用

2023 International Symposium on Electrical Insulating Materials, ISEIM 2023

作者： Wang, Qi Deng, Yuheng Ma, Jielin Yap, Malvern Yang, Yan Chern, Wen Kwang Chen, Zhong School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Materials Science and Engineering Nanyang Technological University Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore Singapore Power Group Singapore

ISBN: (纸本)9784886864376

With the development of nanotechnology, nanocomposites have gained more attention for their increased dielectric breakdown strength and the potential to improve the reliability of electrical equipment. However, there is still a lack of physics-based numerical methods to study dielectric breakdown mechanism of nanocomposite. In this paper, we present a novel phase-field model that utilizes the similarity between fracture and dielectric breakdown. The model employs a phase-field variable, ranging from 0 to 1, to characterize the breakdown damage driven by the competition between surface energy and stored elastic energy. The phase-field variable evolves in accordance with the laws of thermodynamics, which dictates a minimization of the energy of the system. With the setup of the phase-field model, the influences of SiO2 and TiO2 fillers on the electric field, breakdown strength and thermal conductivity of nanocomposites are further discussed. The results highlight that the electric field distortion in TiO2/epoxy (EP) is more severe than that of SiO2/EP, resulting in an earlier initiation of breakdown damage and lower breakdown strength. However, the stored energy density of TiO2/EP is about five times higher than the SiO2/EP, while the effective thermal conductivities of the two composites are almost the same. © 2023 The Institute of Electrical Engineers of Japan.

关键词： Nanocomposites

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：