检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Jahin, Md Abrar Shovon, Md Sakib Hossain Mridha, M.F. Islam, Md rashedul Watanobe, Yutaka Khulna9203 Bangladesh Department of Computer Science American International University-Bangladesh Dhaka1229 Bangladesh Lab Dhaka1229 Bangladesh Offshore AI Development Group Department of R&D Chowagiken Corp. Hokkaido Japan Department of Computer Science and Engineering University of Asia Pacific Dhaka1216 Bangladesh Department of Computer Science and Engineering University of Aizu Aizu-Wakamatsu965-8580 Japan

Sentiment analysis is a pivotal tool in understanding public opinion, consumer behavior, and social trends, underpinning applications ranging from market research to political analysis. However, existing sentiment analysis models frequently encounter challenges related to linguistic diversity, model generalizability, explainability, and limited availability of labeled datasets. To address these shortcomings, we propose the Transformer and Attention-based Bidirectional LSTM for Sentiment Analysis (TrABSA) model, a novel hybrid sentiment analysis framework that integrates transformer-based architecture, attention mechanism, and recurrent neural network like BiLSTM. The TrABSA model leverages the powerful roBErTa-based transformer model for initial feature extraction, capturing complex linguistic nuances from a vast corpus of tweets. This is followed by an attention mechanism that highlights the most informative parts of the text, enhancing the model's focus on critical sentiment-bearing elements. Finally, the BiLSTM networks process these refined features, capturing temporal dependencies and improving the overall sentiment classification into positive, neutral, and negative classes. Leveraging the latest roBErTa-based transformer model trained on a vast corpus of 124M tweets, our research bridges existing gaps in sentiment analysis benchmarks, ensuring state-of-the-art accuracy and relevance. Furthermore, we contribute to data diversity by augmenting existing datasets with 411,885 tweets from 32 English-speaking countries and 7,500 tweets from various US states. This study also compares six word-embedding techniques, identifying the most robust preprocessing and embedding methodologies crucial for accurate sentiment analysis and model performance. We meticulously label tweets into positive, neutral, and negative classes using three distinct lexicon-based approaches and select the best one, ensuring optimal sentiment analysis outcomes and model efficacy. Here, we demon

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

An eco-friendly method to prepare superwetting composites by modifying cotton with TA/FeIII/PddA coatings for highly effective separations of emulsions

引用

Progress in Organic Coatings 2023年 178卷

作者： Udomsin, Jittrakorn Lin, Ching-Hsuan Wang, Chih-Feng Chen, Jem-Kun Tsai, Hsieh-Chih Hung, Wei-Song Hu, Chien-Chieh Lai, Juin-Yih Graduate Institute of Applied Science and Technology Advanced Membrane Materials Research Center National Taiwan University of Science and Technology Taipei106 Taiwan Department of Chemical Engineering National Chung Hsing University Taichung402 Taiwan Institute of Advanced Semiconductor Packaging and Testing National Sun Yat-sen University Kaohsiung804 Taiwan Department of Materials Science and Engineering National Taiwan University of Science and Technology Taipei106 Taiwan R&D Center for Membrane Technology Chung Yuan Christian University Chungli Taoyuan320 Taiwan Department of Chemical Engineering and Materials Science Yuan Ze University Taoyuan320 Taiwan

Separating oil/water mixtures and emulsions is an important global topic. Accordingly, it is imperative to prepare superwetting materials for the efficient separation of oily wastewater. Herein, we report an eco-friendly method for preparing multifunctional superwetting cotton-based materials without using organic solvents. Pristine cotton was modified with tannic acid (TA)/ferric ion (FeIII)/poly(diallyldimethylammonium chloride) (PddA) coatings to form TA/FeIII/PddA@cotton. The as-prepared TA/FeIII/PddA@cotton exhibited superhydrophilicity (both in air and underoil), underwater superoleophobicity, and underoil water sorption property, and could be applied for both surfactant-stabilized oil-in-water (SOW) and water-in-oil (SWO) emulsion separations possessing excellent separation performance. The separation fluxes of the SOW and SWO emulsions were 38,600 and 246,000 L m−2 h−1 bar−1, respectively. The oil content in all SOW emulsion filtrates was 99.96 wt%. In addition, our TA/FeIII/PddA@cotton could be successfully used for the separation of dye-containing aqueous solutions and dye-spiked emulsions. Because of the outstanding separation performance of the oil/water mixtures and emulsions, the as-prepared TA/FeIII/PddA@cotton exhibited remarkable potential for practical applications. © 2023 Elsevier B.V.

关键词： Cotton

来源：评论

学校读者我要写书评

暂无评论

Generic and scalable multi-layered architecture for digital Twin implementation in industrial processes: Mineral Processing case study 23

Generic and scalable multi-layered architecture for Digital ...

引用

Proceedings of the 2023 7th International Conference on Advances in Artificial Intelligence

作者： Oussama Hasidi El Hassan Abdelwahed Aimad Qazdar Moulay Abdellah El Alaoui-Chrifi Intissar Benzakour rachida Chahid Ahmed Bendaouia François Bourzeix Computer Science Departement Computer Systems Engineering Laboratory Cadi Ayyad University Morocco and Analytics Lab Mohammed VI Polytechnic University Morocco Computer Science Departement Computer Systems Engineering Laboratory Cadi Ayyad University Morocco ESTIDMA Laboratory Ibn Zohr University Morocco R&D and Engineering center Reminex Managem Group Morocco Computer Science Departement Computer Systems Engineering Laboratory Cadi Ayyad University Morocco and SEIA Departement MAScIR Morocco Analytics Lab Mohammed VI Polytechnic University Morocco

ISBN: (纸本)9798400708985

digitalization is crucial for achieving product quality, cost reduction, and timely delivery in manufacturing. With the rise of Industry 4.0, digital Twin technology has gained popularity, enabling real-time monitoring, predictive maintenance, process optimization, and assumption testing. Manufacturing digital Twins utilize digital models to represent physical processes, facilitating continuous simulation, interaction, correction, and optimization for autonomous control. However, implementing digital Twins can be challenging due to diverse data requirements and multiple services. This paper proposes a scalable, service-oriented multi-layered architecture for developing digital Twins in mineral processing, which can be adapted to other manufacturing systems. The paper provides an overview of digital Twins, their data-centric workflow, and industrial applications. Additionally, a case study on implementing a digital Twin for the froth flotation process in the mining industry is presented based on the proposed architecture.

关键词： digital Twin Implementation Industry 4.0 Multi-layered Architecture Optimisation Predictive model real time control and monitoring

来源：评论

学校读者我要写书评

暂无评论

AirVO: An Illumination-robust Point-Line Visual Odometry

AirVO: An Illumination-Robust Point-Line Visual Odometry

引用

IEEE/rSJ International Conference on Intelligent robots and Systems (IrOS)

作者： Kuan Xu Yuefan Hao Shenghai Yuan Chen Wang Lihua Xie School of Electrical and Electronic Engineering Nanyang Technological University Singapore Robot R&D Department Geekplus Corp. Beijing China Spatial AI & Robotics Lab at The Department of Computer Science & Engineering State University of New York at Buffalo Buffalo NY USA

This paper proposes an illumination-robust visual odometry (VO) system that incorporates both accelerated learning-based corner point algorithms and an extended line feature algorithm. To be robust to dynamic illumination, the proposed system employs the convolutional neural network (CNN) and graph neural network (GNN) to detect and match reliable and informative corner points. Then point feature matching results and the distribution of point and line features are utilized to match and triangulate lines. By accelerating CNN and GNN parts and optimizing the pipeline, the proposed system is able to run in real-time on low-power embedded platforms. The proposed VO was evaluated on several datasets with varying illumination conditions, and the results show that it outperforms other state-of-the-art VO systems in terms of accuracy and robustness. The open-source nature of the proposed system allows for easy implementation and customization by the research community, enabling further development and improvement of VO for various applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shenqi Fuzheng injection alleviates chemotherapy-induced cachexia by restoring glucocorticoid signaling in hypothalamus

引用

Journal of Pharmaceutical Analysis 2024年第3期14卷 431-434页

作者： Entezar Berik Zijia Zhang Wei Li Yawen Liu Sihan Chen Wenyong Wu Zhaojun Wang Xinqin Kong Wenqiang Pei Huiqing dong Huali Long Min Lei Jennifer Yiyang Wang Liangfeng Liu Jinjun Hou Jing Feng Zhaoxia Li Wanying Wu de-an Guo Beijing Key Lab of TCM Collateral Disease Theory Research School of Traditional Chinese MedicineCapital Medical UniversityBeijing100069China National Engineering Research Center of TCM Standardization Technology Shanghai Institute of Materia MedicaChinese Academy of SciencesShanghai201203China University of Chinese Academy of Sciences Beijing100049China School of Chinese Materia Medica Nanjing University of Chinese MedicineNanjing210029China Limin Pharmaceutical Factory Livzon Group LimitedShaoguanGuangdong512028China Guangdong Corporate Key Laboratory of High-End Liquid Medicine R&D IndustrilizationShaoguanGuangdong512028China Center for Neurological and Psychiatric Research and Drug Discovery Shanghai Institute of Materia MedicaChinese Academy of ScienceShanghai201203China

Chemotherapy-induced cachexia(CIC)is a debilitating condition characterized by weight loss,muscle atrophy,and anorexia[1].While peripheral mechanisms of cachexia have been extensively studied,the involvement of the central nervous system(CNS)in CIC is often *** drugs cause stress responses and inflammation,which may impact the hypothalamus and disrupt systemic energy and neuroendocrine *** hypothalamic roles in regulating these processes can provide insights into CIC's mechanisms and aid in developing novel therapies.

关键词： injection drugs glucocorticoid chemotherapy

来源：评论

学校读者我要写书评

暂无评论

dVI-SLAM: A dual Visual Inertial SLAM Network

arXiv

引用

arXiv 2023年

作者： Peng, Xiongfeng Liu, Zhihua Li, Weiming Tan, Ping Cho, SoonYong Wang, Qiang SAIT-China Lab Samsung R&D Institute China-Beijing China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology China Multimedia System TU Samsung Advanced Institute of Technology Korea Republic of

recent deep learning based visual simultaneous localization and mapping (SLAM) methods have made significant progress. However, how to make full use of visual information as well as better integrate with inertial measurement unit (IMU) in visual SLAM has potential research value. This paper proposes a novel deep SLAM network with dual visual factors. The basic idea is to integrate both photometric factor and re-projection factor into the end-to-end differentiable structure through multi-factor data association module. We show that the proposed network dynamically learns and adjusts the confidence maps of both visual factors and it can be further extended to include the IMU factors as well. Extensive experiments validate that our proposed method significantly outperforms the state-of-the-art methods on several public datasets, including TartanAir, EuroC and ETH3d-SLAM. Specifically, when dynamically fusing the three factors together, the absolute trajectory error for both monocular and stereo configurations on EuroC dataset has reduced by 45.3% and 36.2% respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Fluorine-Free Paraffin Binder-Based dry Thick Electrodes Toward Sustainable and Efficient Battery Manufacturing

SSRN

引用

SSrN 2024年

作者： Kim, Min Kyung Yu, Taegyun Jang, Sungbin Lee, Juho Jang, Min Oh, Hyeseong Cha, Hyungyeon Lee, Huiyeol Kang, Joonhee Lee, Seung Min Shim, Hyeongseok Lee, Kwon-Hyung Song, Gyujin Jin, Wooyoung Kim, Tae-Hee Jeong, Kyeong-Min Han, Joong Tark Yoo, Jung-Keun Song, Sanghyun Park, Myoungkeon Seong, Jinwoo Kim, dongoh Choi, Hyunwoo Seong, Minjong Lim, Min Jin Hwang, Wook ryol Nam, Jieun Jo, Sanghoon Kim, Jinsoo Ulsan Advanced Energy Technology R&D Center Korea Institute of Energy Research Ulsan Korea Republic of Department of Nano Fusion Technology Pusan National University Busan Korea Republic of Department of Organic Material Science and Engineering Pusan National University Busan Korea Republic of Ulsan Korea Republic of Changwon Korea Republic of Changwon Korea Republic of Seoul Korea Republic of R&D Center Rechargeable Battery Division Hanwha Momentum Seongnam Korea Republic of School of Mechanical Engineering Gyeongsang National University Jinju Korea Republic of R&D Center Yunsung F&C Co. Ltd. Anseong Korea Republic of Multiphysics Digital Twin Lab Trinity Engineering Seoul Korea Republic of

dry electrodes are being actively developed for sustainable and efficient battery manufacturing. Currently, polytetrafluoroethylene (PTFE) binders dominate dry processes, yet their production contributes to significant CO2 emissions, and concerns persist regarding their high fluorine content, especially considering evolving per- and polyfluorinated substances (PFAS) restrictions. Moreover, the poor adhesion of bare current collectors necessitates a wet coating-based primer layer with this binder. In this study, we introduce an alternative dry processing concept based on a thermoplastic fluorine-free binder with low environmental impact and high productivity. Paraffin, a short-chain family of saturated hydrocarbons known as an n-alkane, is the most stable chemical species owing to its C-H covalent bonds and the wide gap between highest occupied molecular orbital (HOMO) and lowest unoccupied molecular orbital (LUMO) energies. It also has a low melting temperature, allowing facile cohesion of the active materials to be interconnected by mild pressing activation. This novel dry electrode binder provides substantial electrochemical properties based on both NCM811 cathodes over 5 mAh cm−2 for 500 cycles. Furthermore, it implements true solvent-free adhesion without the wet-coating of primers on the current collector. This unique characteristic of paraffin can enable a powder-to-electrode manufacturing strategy with pattern coating, which alters the well-known PTFE-based freestanding electrode concept. This integrated approach bridges the gap between materials and processes, paving the way for sustainable advancements in battery electrode technology. © 2024, The Authors. All rights reserved.

关键词： Binders

来源：评论

学校读者我要写书评

暂无评论

Wearable-based behaviour interpolation for semi-supervised human activity recognition

arXiv

引用

arXiv 2024年

作者： duan, Haoran Wang, Shidong Ojha, Varun Wang, Shizheng Huang, Yawen Long, Yang ranjan, rajiv Zheng, Yefeng Department of Computer Science Durham University United Kingdom School of Engineering Newcastle University United Kingdom School of Computing Newcastle University United Kingdom Jarvis Research Center Tencent YouTu Lab China Chinese Academy of Sciences R&D Center for Internet of Things China

While traditional feature engineering for Human Activity recognition (HAr) involves a trial-and-error process, deep learning has emerged as a preferred method for high-level representations of sensor-based human activities. However, most deep learning-based HAr requires a large amount of labelled data and extracting HAr features from unlabelled data for effective deep learning training remains challenging. We, therefore, introduce a deep semi-supervised HAr approach, MixHAr, which concurrently uses labelled and unlabelled activities. Our MixHAr employs a linear interpolation mechanism to blend labelled and unlabelled activities while addressing both inter- and intra-activity variability. A unique challenge identified is the activity-intrusion problem during mixing, for which we propose a mixing calibration mechanism to mitigate it in the feature embedding space. Additionally, we rigorously explored and evaluated the five conventional/popular deep semi-supervised technologies on HAr, acting as the benchmark of deep semi-supervised HAr. Our results demonstrate that MixHAr significantly improves performance, underscoring the potential of deep semi-supervised techniques in HAr. © 2024, CC BY.

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

decoupling of Four Closely Spaced PIFAs Using Parasitic Elements and Bridge Lines

Decoupling of Four Closely Spaced PIFAs Using Parasitic Elem...

引用

2022 International Symposium on Antennas and Propagation (ISAP)

作者： Quang Quan Phung Naobumi Michishita Hiroshi Sato Yoshio Koyanagi Hisashi Morishita Graduate School of Science and Engineering National Defense Academy Yokosuka Kanagawa Japan Panasonic System Networks R&D Lab. Tuzuki Yokohama Kanagawa Japan

ISBN: (数字)9781665479622

ISBN: (纸本)9781665479639

This study proposed a simple decoupling method for four planar inverted-F antennas (PIFAs) operating at 2.0 GHz (f 0 ) using parasitic elements (PEs) and bridge lines (BLs). The edge-to-edge spacings of the adjacent PIFAs is extremely small, resulting in strong mutual coupling among them. The simulated results showed that loading the proposed PEs and BLs onto the four PIFAs could reduce as well as maintain all mutual coupling for less than -10dB, which are acceptable levels for MIMO antennas, and simultaneously improve impedance matching. Therefore, the total antenna efficiency at 2.0 GHz could be significantly improved from 64.2% to 84.8% for PIFAI and PIFA4 and from 35.9% to 74.2% for PIFA2 and PIFA3.

关键词： Bridges Mutual coupling Impedance matching Loading Bandwidth MIMO communication Loaded antennas

来源：评论

学校读者我要写书评

暂无评论

Orthogonal Polarized Omnidirectional Antenna Composed of Halo Antenna with Parasitic Elements and dipole Antenna

Orthogonal Polarized Omnidirectional Antenna Composed of Hal...

引用

2022 International Symposium on Antennas and Propagation (ISAP)

作者： Tomokazu Mizutani Naobumi Michishita Hiroshi Sato Yoshio Koyanagi Hisashi Morishita Graduate School of Science and Engineering National Defense Academy Yokosuka Kanagawa Japan Panasonic System Networks R&D Lab. Tuzuki Yokohama Kanagawa Japan

ISBN: (数字)9781665479622

ISBN: (纸本)9781665479639

This paper proposes a small-diameter, low-profile and an omnidirectional orthogonally polarized antenna composed of a Halo antenna and a dipole antenna. As a result of the simulation, the characteristics of the proposed antenna are that the relative bandwidth is 8.8%, and the antenna height and diameter are $0.45\lambda_r$ and $0.13\lambda_r(\lambda 0$ the wavelength of the center operational frequency), respectively.

关键词： Antenna measurements Coaxial cables dipole antennas Simulation Omnidirectional antennas Bandwidth Loaded antennas

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：