检索结果-内蒙古大学图书馆

AFuNet: an attention-based fusion network to classify texts in a resource-constrained language

Neural Computing and Applications 2025年第9期37卷 6725-6748页

作者： Hossain, Md. Rajib Hoque, Mohammed Moshiul Dewan, M. Ali Akber Hoque, Enamul Siddique, Nazmul Department of Computer Science & Engineering Chittagong University of Engineering & Technology Chittagong4349 Bangladesh School of Computing and Information Systems Faculty of Science and Technology Athabasca University AthabascaABT9S 3A3 Canada School of Information Technology York University TorontoONM3J 1P3 Canada School of Computing Engineering and Intelligent Systems Ulster University Coleraine United Kingdom

In the era of widespread Internet use and extensive social media interaction, the digital realm is accumulating vast amounts of unstructured text data. This unstructured data often contain undesirable information, necessitating time-consuming manual classification efforts. An intelligent text classification system capable of automatically categorizing digitized texts based on semantic meaning is crucial. However, this task is particularly challenging for low-resource languages like Bengali due to a shortage of annotated corpora, issues with out-of-vocabulary words, lack of domain-specific hyperparameter tuning, limited ability to extract generalized text features, and class imbalances within the corpus. AFuNet: an attention-based fusion network to classify texts in a resource-constrained language. AFuNet undergoes a comprehensive four-phase experimental process, including baseline model evaluation and hyperparameter tuning, late fusion and model selection, attention-based early fusion and model identification, and an ablation study with impact analysis. Fine-tuned based on five Bengali text classification corpora, AFuNet achieves impressive accuracies: 96.60 ± 0.2 (BTCC11), 85.37 ± 0.2 (OSBC), 97.35 ± 0.2 (BARD), 93.74 ± 0.2 (IndicNLP), and 96.51 ± 0.2 (ProthomAlo). In comparison with previous state-of-the-art models on these corpora, AFuNet demonstrates significant accuracy improvements ranging from 0.54% to 4.49%, showcasing its effectiveness in advancing text classification capabilities for the Bengali language. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Deep Learning Techniques on Cyber Attacks on Cyber Physical systems

引用

SN Computer science 2024年第7期5卷 891页

作者： Sagar, Maloth Vanmathi, C. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore 632014 India

Cyber-Physical systems (CPSs), which integrate control, computing, and communication, are considered as next-generation intelligent systems.A major concern in CPS is to ensure security. If security is not ensured, then it leads to both property damage and *** CPS is closely associated with real life, it is a hot research area in present security research. Nevertheless, cyber security issues are also raised. More efforts are still required for understanding CPS security from a more comprehensive perspective even though there are several studies on CPS *** identify and detect cyber security in CPS, numerous methods have been applied. The majority of recently published studies focused on Machine Learning (ML) techniques, with little attention paid to the development of Deep Learning (DL). Hence, the analysis of cyber security on CPS utilizing several algorithms of DL techniques is systematically *** appropriate cyber security risk levels and their corresponding detection and mitigation processesare determined. This study could augment the adaptability of the system of CPS data. Also, it could increase the generalization of the models of security attacks in CPS. Using DL algorithms is strongly recommended by most authors as a means to identify cyber security issues in *** CNN-centric LSTM, Deep Multi-architectural Approach, and DL-Meta classifier attained the highest accuracy in the detection rate of cyber security attacks in CPS when analogized with the other algorithms in DL techniques. Hence, for several critical systems in CPSs, the result renders clear guidelines to apply other regularization on DL techniques. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： CPS Cyber security Cyber-attack Cyber-attack detection Deep learning Risk analysis Security threats

来源：评论

学校读者我要写书评

暂无评论

Differential-geometry-based multi-dimensional joint position-velocity estimation using Crab pulsar profile distortion

引用

Chinese Journal of Aeronautics 2025年第1期38卷 551-567页

作者： Jin LIU Huanzi ZHANG Xiaolin NING Xin MA School of Electronic Information Wuhan University of Science and TechnologyWuhan 430081China School of Instrumentation and Optoelectronic Engineering Beihang UniversityBeijing 100191China Hefei National Laboratory Hefei 230088China

The traditional orbit determination method based on pulsar profile distortion can determine the six elements of the ***,the estimation accuracies of these methods are limited and the computational load of a six-dimensional search is *** solve this problem,the differential-geometry-based Multi-dimensional Joint Position-Velocity Estimation(MJPVE)using Crab pulsar profile distortion is proposed in this ***,through theoretical analysis,it is found that the pulsar profile distortion caused by the initial state error in some joint positionvelocity directions is very *** other words,the accuracies of estimation in these directions are very ***,the search dimension can be reduced,which in turn greatly reduces the computational ***,we construct the chi-squared function of the pulsar profile with respect to the estimation error in joint position-velocity direction and use differential geometry to find the joint position-velocity directions corresponding to different degrees of ***,we utilize the grid search based on directory folding in these joint position-velocity directions corresponding to large degrees of distortion to obtain the joint position-velocity *** experimental results show that compared with the grouping bi-chi-squared inversion method,MJPVE has high precision and extensive navigation information.

关键词： Joint Position-Velocity Estimation Pulsars Profile Distortion Orbit Determination Differential Geometry

来源：评论

学校读者我要写书评

暂无评论

High-Speed PAM8 Silicon Photonics IM/DD System with Artificial Neural Network Equalization 13

High-Speed PAM8 Silicon Photonics IM/DD System with Artifici...

引用

Optoelectronic Devices and Integration XIII 2024

作者： Lu, Junde Sun, Yu Qin, Jun Tan, Junxiong Wang, Qian Li, Yueqin Sun, Jian Li, Zhensong Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing100192 China Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing Information Science and Technology University Beijing100192 China

ISBN: (纸本)9781510682009

The intensity modulation direct detection (IM/DD) system based on silicon photonic devices stands out as a leading contender for the next generation of short-reach optical communication due to its cost-effectiveness, low power consumption, and compact physical footprint. Nonetheless, its direct representation of digital information through amplitude variations renders them acutely susceptible to transmission impairments. To improve the signal quality at the receiver, digital signal processing (DSP) based equalization plays a pivotal role due to its programmability, flexibility and stability. Among different kinds of equalization methods, neural network (NN)-based equalization algorithms have attracted considerable attention, surpassing traditional algorithms such as feed-forward equalization (FFE), decision feedback equalization (DFE) and Volterra series-based nonlinear equalization (VNLE) et al. This increased attention is attributed to their robust capability for modeling both linear and nonlinear systems. In this paper, by employing a novel NN-based equalization with eight saturation regions activation function, we successfully transmit a 60 GBaud 8-ary pulse amplitude modulation (PAM8) signal with the bit error rate (BER) below high-definition forward error correction (HD-FEC) threshold of 3.8×10-3 and a 70 GBaud PAM8 signal with BER below soft-decision forward error correction (SD-FEC) threshold 2×10-2 using a 4-layer network architecture. Compared to the traditional activation function such as sigmoid and tanh, 1∼3 orders of magnitude of BER can be decreased. The results show that the proposed innovative NNbased equalization has the potential to significantly enhance the performance of the next generation silicon photonics based short-range optical communication systems. © 2024 SPIE. All rights reserved.

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Pedestrian airbag folding patterns on airbag deployment and head injuries based on corpuscular particle method

引用

International Journal of Vehicle Safety 2023年第3-4期12卷 226-252页

作者： Deabae, Reza Marzbanrad, Javad Vehicle Dynamical Systems Research Laboratory School of Automotive Engineering Iran University of Science and Technology Tehran Iran

An earlier study by authors implemented Corpuscular Particle Method (CPM) for simulations of Pedestrian Protection Airbags (PPA). Present study utilised the CPM to investigate the effect of gas flow on the airbag’s unfolding procedure. A PPA was designed to cover bottom of windshield and A-pillars where pedestrian head is more likely to hit and stiffness is high. This paper aims to investigate the effect of six folding patterns on PPA deployment behaviour and pedestrian head injuries. For each folding pattern, headform impact on nine points was simulated. Head acceleration curves, HIC values, PPA pressure and friction curves were exported. Results show that a PPA can reduce pedestrian head injuries by up to 90%. Across six patterns studied in this research, the folding-rolling as the best pattern generates lowest HIC values and the rolling-folding and rolling-stochastic as the weakest patterns generate high HIC values as they have higher friction. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Pedestrian safety

来源：评论

学校读者我要写书评

暂无评论

Low dielectric loss in vanadium-based zircon ceramics via high-entropy strategy

引用

Journal of Advanced Ceramics 2025年第1期14卷 151-161页

作者： Yuheng Zhang Huaicheng Xiang Xiaoyu Wu Yang Zhou Ying Tang Liang Fang College of Physics and Electronic Information Engineering Guilin University of TechnologyGuilin 541004China Guangxi Universities Key Laboratory of Non-Ferrous Metal Oxide Electronic Functional Materials and Devices Guangxi Key Laboratory of Optical and Electronic Materials and DevicesCollege of Materials Science and EngineeringGuilin University of TechnologyGuilin 541004China

Zircon ceramics have potential applications in next-generation wireless communication because of their low permittivity and adjustable temperature coefficient at microwave ***,the vast challenge of realizing ultralow dielectric loss still ***,we propose a high-entropy strategy to enhance the bonding of the A-site dodecahedron in zircon and design(Nd_(0.2)Eu_(0.2)Y_(0.2)Ho_(0.2)Yb_(0.2))VO_(4) ceramics with a high quality factor(high Q×f,that is,low dielectric loss).The(Nd_(0.2)Eu_(0.2)Y_(0.2)Ho_(0.2)Yb_(0.2))VO_(4) high-entropy ceramics,which belong to the tetragonal zircon structure with the I4_(1)/amd space group,exhibit a low relative permittivity(ε_(r)=11.55),a negative temperature coefficient of resonant frequency(τ_(f)=−37.3 ppm/℃),and a high Q×f of 76,400 GHz(at 12.31 GHz).The high Q×f value can be attributed to the high chemical bond strength and structural ***,the relationship between the crystal structure and the microwave dielectric properties of(Nd_(0.2)Eu_(0.2)Y_(0.2)Ho_(0.2)Yb_(0.2))VO_(4) high-entropy ceramics was analyzed through high resolution transmission electron microscopy(HRTEM),Raman spectroscopy,far-infrared reflection spectroscopy,and chemical bond *** work provides an effective avenue for designing microwave dielectric materials with low loss to meet the demands of passive components.

关键词： high-entropy ceramics vanadium-based zircon microwave dielectric properties low dielectric loss chemical bond characteristics

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Informed Renewable Energy Scheduling: A Scalable Bilevel Framework

IEEE Transactions on Energy Markets, Policy and Regulation

引用

IEEE Transactions on Energy Markets, Policy and Regulation 2024年第1期2卷 132-145页

作者： Zhao, Dongwei Dvorkin, Vladimir Delikaraoglou, Stefanos Lamadrid L, Alberto J. Botterud, Audun Massachusetts Institute of Technology Energy Initiative and Laboratory for Information and Decision Systems CambridgeMA02139 United States Massachusetts Institute of Technology Laboratory for Information and Decision Systems CambridgeMA02139 United States Lehigh University Department of Economics Department of Industrial and Systems Engineering BethlehemPA18015 United States

This work proposes an uncertainty-informed bid adjustment framework for integrating variable renewable energy sources (VRES) into electricity markets. This framework adopts a bilevel model to compute the optimal VRES day-ahead bids. It aims to minimize the expected system cost across day-ahead and real-time stages and approximate the cost efficiency of the stochastic market design. However, solving the bilevel optimization problem is computationally challenging for large-scale systems. To overcome this challenge, we introduce a novel technique based on strong duality and McCormick envelopes, which relaxes the problem to a linear program, enabling large-scale applications. The proposed bilevel framework is applied to the 1576-bus NYISO system and benchmarked against a myopic strategy, where the VRES bid is the mean value of the probabilistic power forecast. Results demonstrate that, under high VRES penetration levels (e.g., 40%), our framework can significantly reduce system costs and market-price volatility, by optimizing VRES quantities efficiently in the day-ahead market. Furthermore, we find that when transmission capacity increases, the proposed bilevel model will still reduce the system cost, whereas the myopic strategy may incur a much higher cost due to over-scheduling of VRES in the day-ahead market and the lack of flexible conventional generators in real time. © 2023 IEEE.

关键词： Power markets

来源：评论

学校读者我要写书评

暂无评论

Layered double hydroxide-derived Mg_(2)Ni/TiH_(1.5)composite catalysts for enhancing hydrogen storage performance of MgH_(2)

引用

Journal of Magnesium and Alloys 2024年第12期12卷 4966-4975页

作者： Gang Huang Yao Lu Xiaofang Liu Wukui Tang Xinyu Li Feng Wang Jianglan Shui Ronghai Yu School of Materials Science and Engineering Beihang UniversityNo.37 Xueyuan RoadBeijing 100191PR China School of Materials Science and Engineering&Guangxi Key Laboratory of Information Materials Guilin University of Electronic TechnologyGuilin 541004PR China

Developing efficient catalysts is of great significance in improving the sluggish kinetics and high desorption temperature of Mg H_(2)hydrogen storage ***,ultrathin Ni Ti-layered double hydroxide(Ni Ti-LDH)nanosheets are used as precursors to prepare Mg_(2)Ni/TiH_(1.5)composite catalysts to improve the hydrogen storage properties of MgH_(2).The variation of Ni/Ti ratio in LDH plays an important role in regulating the composition,morphology and distribution of Mg_(2)Ni/Ti H_(1.5)catalysts,which significantly affect their synergistic catalytic ***_(2)Ni/TiH_(1.5)composite catalyst exhibits significantly improved catalytic performance compared with conventional Ni-,Ti-and Ni/Ti-based *** optimal Mg H_(2)/Mg_(2)Ni/TiH_(1.5)system shows a significantly reduced desorption temperature of 212℃which is 133℃lower than that of pure MgH_(2)(345℃),and can release 5.97 wt%hydrogen within 300s at 300℃.Further mechanism analysis reveals that the unique flaky morphology and suitable composition of Ni/Ti LDH can significantly enhance the synergistic effect of Mg_(2)Ni and TiH_(1.5),which promotes the fracture of the H–H and Mg-H bonds.

关键词： Hydrogen storage materials MgH_(2) Layered double hydroxides Nanocatalysts

来源：评论

学校读者我要写书评

暂无评论

A Novel Three-layer GRU Equalizer for High-speed PAM-4 Transmission beyond 300Gbps

A Novel Three-layer GRU Equalizer for High-speed PAM-4 Trans...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on information Photonics and Optical Communications, IPOC 2024

作者： Sun, Yu Lu, Junde Qin, Jun Tan, Junxiong Wang, Qian Shi, Jie Chen, Lanling Li, Yueqin Sun, Jian Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing100192 China Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument Beijing Information Science and Technology University Beijing100192 China

ISBN: (纸本)9798350379266

A novel three-layer gated recurrent unit neural network (TL-GRU) equalizer for high-speed intensity modulation direct-detection (IM/DD) PAM-4 systems is *** on this novel equalization scheme, the BER performance of the 200 Gbaud (400 Gbps) PAM-4 can be decreased into hard-decision forward error correction (HD-FEC) threshold 3.8× 10−3, which is much better than least mean squares (LMS), polynomial nonlinear equalization (PNE) and gated recurrent unit (GRU) *** TL-GRU highlights its potential as a promising signal equalization solution for 1.6T and 3.2T short-reach optical interconnect systems. © 2024 IEEE.

关键词： Forward error correction

来源：评论

学校读者我要写书评

暂无评论

Investigation of erythrocyte aggregation parameters of blood with low levels of fibrinogen by syllectometry

引用

Journal of Biorheology 2023年第1期37卷 2-8页

作者： Higuchi, Makoto Tanaka, Masayoshi Watanabe, Nobuo Functional Control Systems Course Graduate School of Engineering and Science Shibaura Institute of Technology Saitama Japan Ogino Memorial Laboratory Nihon Kohden Corporation Tokyo Japan Systems Engineering and Science Graduate School of Engineering and Science Shibaura Institute of Technology Saitama Japan

An increase in fibrinogen, a coagulation factor in blood, enhances erythrocyte aggregation. However, no pre-vious studies have fully investigated erythrocyte aggregation at low plasma fibrinogen concentrations (1/2) increased with decreasing fibrinogen concentration (r = –0.827), similar to previously reported results for normal to high fibrinogen concentrations. Relax-ation time (t0) increased exponentially with decreasing fibrinogen concentration (r = –0.608). These results suggest that erythrocyte aggregability decreases with decreasing fibrinogen concentration even at low fibrinogen levels that can cause coagulopathy, and that syllectometry can be used to detect decreases in fibrinogen. © Japanese Society of Biorheology 2023.

关键词： Rheology

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：