检索结果-内蒙古大学图书馆

3rd ACM MobiCom Workshop on Integrated Sensing and Communication Systems, ISACom 2023

作者： Zhou, Fujia Zhu, Guangxu Li, Xiaoyang Li, Hang Shi, Qingjiang School of Software Engineering Tongji University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (纸本)9798400703645

Channel state information (CSI) and RGB (Red, Green, Blue) image are two fundamental modalities for accurate human activity recognition (HAR). CSI data is privacy preserving, independent of viewing angle and lighting, while RGB image data can provide useful information after processed by deep learning (DL) methods. However, both modalities have inherent disadvantages. CSI modality is with high environmental dependence, causing unstable fluctuations in wireless signals. RGB image modality is heavily restricted by camera facing angle and lighting condition. Hence, we propose a general multimodal fusion framework for HAR tasks based on both CSI and RGB image modalities. Distinct from other literatures on multimodal fusion mainly based on vision modalities, we utilized CSI modality from wireless domain along with RGB images to realize more comprehensive human activity sensing. Both early fusion and late fusion strategies are formulated and developed, with multiple models constructed from two modern unimodal frameworks to constitute corresponding fusion models. Experiments are conducted on a synchronous CSI and RGB image human activity dataset and validate the advantage of the proposed multimodal fusion design comparing with unimodal approaches. © 2023 ACM.

关键词： Channel state information

来源：评论

学校读者我要写书评

暂无评论

Alignment at Pre-training! Towards Native Alignment for Arabic LLMs 38

Alignment at Pre-training! Towards Native Alignment for Arab...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liang, Juhao Cai, Zhenyang Zhu, Jianqing Huang, Huang Zong, Kewei An, Bang Alharthi, Abdulmohsen He, Juncai Zhang, Lian Li, Haizhou Wang, Benyou Xu, Jinchao Shenzhen Research Institue of Big Data Shenzhen China The Chinese University of Hong Kong Shenzhen China King Abdullah University of Science and Technology Thuwal Saudi Arabia Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data China

The alignment of large language models (LLMs) is critical for developing effective and safe language models. Traditional approaches focus on aligning models during the instruction tuning or reinforcement learning stages, referred to in this paper as 'post alignment'. We argue that alignment during the pre-training phase, which we term 'native alignment', warrants investigation. Native alignment aims to prevent unaligned content from the beginning, rather than relying on posthoc processing. This approach leverages extensively aligned pre-training data to enhance the effectiveness and usability of pre-trained models. Our study specifically explores the application of native alignment in the context of Arabic LLMs. We conduct comprehensive experiments and ablation studies to evaluate the impact of native alignment on model performance and alignment stability. Additionally, we release open-source Arabic LLMs that demonstrate state-of-the-art performance on various benchmarks, providing significant benefits to the Arabic LLM community. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time Series data Cleaning under Expressive Constraints on Both Rows and Columns 40

Time Series Data Cleaning under Expressive Constraints on Bo...

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Ding, Xiaoou Li, Genglong Wang, Hongzhi Wang, Chen Song, Yichen School of Computer Science and Technology Harbin Institute of Technology China Tsinghua University National Engineering Laboratory for Big Data Software EIRI China

ISBN: (纸本)9798350317152

Time series data generated by thousands of sensors are suffering data quality problems. Traditional constraint-based techniques have greatly contributed to data cleaning applications. However, cleaning methods that support expressive constraints on time series data remain insufficient. Given the notable characteristics of time series data, existing cleaning approaches are challenged to provide good repair solutions. To address the challenges, we propose a novel data cleaning method for time series which incorporates expressive constraints that support arithmetic operations between attributes and time context. In the violation detection phase, we introduce specialized violation degree quantification functions and design a violation cell discovery algorithm to identify errors hidden in time series data. In the data repairing phase, we formalize the cleaning task as a constrained optimization problem and develop a novel repair objective function that considers both modification costs and conformance degrees of constraints. We effectively reduce the repair search space through the evaluation of time-context constraints and propose a bidirectional repairing algorithm. We also provide theoretical analysis of the proposed repairing method. Experimental results on three real-world IoT datasets across five metrics demonstrate that our proposed method outperforms seven state-of-the-art cleaning techniques specialized for time series data. Specifically, we achieve a 60% improvement in repairing effectiveness and a 70% reduction in time costs with our designed cleaning strategy. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Designing Group-Level Multi-User Precoding in Multi-Subcarrier Networks: Is EESM the Solution? 24

Designing Group-Level Multi-User Precoding in Multi-Subcarri...

引用

24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023

作者： Guan, Xin Shi, Qingjiang Tongji University School of Software Engineering Shanghai China Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (纸本)9781665496261

Existing researches on multi-subcarrie multi-antenna networks usually apply the subcarrier-level precoding, by which each tone is allocated with a dedicated precoder. Such kind of approaches are far from practical implementation due to unbearably high design complexity. By recognizing the fact that multiple subcarriers in a practical cellular network are assigned into one group and share one common precoder, we investigate a more realistic group-level precoding approach. Inspired by the commonly used link adaptation technique namely EESM (Exponential Effective SNR Mapping), a novel spectral efficiency (SE) evaluation scheme is proposed, from which a sumrate maximization of multiple users with group-level precoding is formulated. Via leveraging successive convex approximation (SCA) framework, we tackle the non-convex problem by solving a sequence of convex problems. Furthermore, we also develop a low-complexity solution using gradient projection which are free of any numerical solvers. Simulation results verify the superiority of our proposed novel SE model as well as the efficiency of the proposed algorithms. © 2023 IEEE.

关键词： Spectrum efficiency

来源：评论

学校读者我要写书评

暂无评论

The Mass Assembly History for Galaxies with MaNGA

引用

research in Astronomy and Astrophysics 2024年第3期24卷 58-69页

作者： Xue Ge Hong-Tao Wang Cheng-Long Lei Yun-Jun Guo Yi-Long Jiang Xiao-Xiao Cao School of Physics and Information Engineering Jiangsu Second Normal University Jiangsu Province Engineering Research Center of Basic Education Big Data Application Jiangsu Second Normal University Key Laboratory of Modern Astronomy and Astrophysics Nanjing UniversityMinistry of Education School of Science Langfang Normal University

How galaxies assemble masses through their own star formation or interaction with the external environment is still an important topic in the field of galaxy formation and *** use Value Added Catalogs with galaxy features that are spatially and temporally resolved from Sloan Digital Sky Survey data Release 17 to investigate the mass growth histories of early-type galaxies(ETGs)and late-type galaxies(LTGs).We find that the mass growth of ETGs is earlier than that of LTGs for massive galaxies(M_(*)>10^(10)M_⊙),while low-mass(M_(*)≤10^(10)M_⊙)ETGs have statistically similar mass assembly histories as low-mass *** stellar metallicity of all massive galaxies shows a negative gradient and basically does not change with ***,in low-mass galaxies,the stellar metallicity gradient of elliptical galaxies is negative,and the stellar metallicity gradient of lenticular and spiral galaxies evolves from positive to *** are not all in a high-density environment,but exhibit mass *** the tidal strength increases,the star formation rate of low-mass ETGs rapidly *** results support a picture where massive galaxies exhibit inside-out quenching mode,while low-mass galaxies show outside-in quenching *** effects play an important role in regulating the mass assembly histories of low-mass ETGs.

关键词： Galaxy evolution-galaxies star formation-Galaxy formation

来源：评论

学校读者我要写书评

暂无评论

Multicomponent Similarity Graphs for Cross-Network Node Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第3期5卷 1411-1424页

作者： Zhang, Yuhong Shi, Congmei Li, Xinzheng Zhang, Zan Hu, Xuegang School of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei230009 China

Cross-network node classification aims to train a classifier for an unlabeled target network using a source network with rich labels. In applications, the degree of nodes mostly conforms to the long-tail distribution, i.e., most nodes in the network are tail nodes with sparse neighborhoods. The established methods focus on either the discrepancy cross network or the long tail in a single network. As for the cross-network node classification under long tail, the coexistence of sparsity of tail nodes and the discrepancy cross-network challenges existing methods for long tail or methods for the cross-network node classification. To this end, a multicomponent similarity graphs for cross-network node classification (MS-CNC) is proposed in this article. Specifically, in order to address the sparsity of the tail nodes, multiple component similarity graphs, including attribute and structure similarity graphs, are constructed for each network to enrich the neighborhoods of the tail nodes and alleviate the long-tail phenomenon. Then, multiple representations are learned from the multiple similarity graphs separately. Based on the multicomponent representations, a two-level adversarial model is designed to address the distribution difference across networks. One level is used to learn the invariant representations cross network in view of structure and attribute components separately, and the other level is used to learn the invariant representations in view of the fused structure and attribute graphs. Extensive experimental results show that the MS-CNC outperforms the state-of-the-art methods. Impact Statement-Node classification is an important task in graph mining. With the unavailability of labels, some researchers propose cross-network node classification, using one labeled network to assist the node classification of another unlabeled network. However, the long-tail of nodes leads to unsatisfactory performance and challenges the recent cross-network node classification m

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Two efficient beamforming methods for hybrid IRS-aided AF relay wireless networks

引用

science China(Information sciences) 2025年第4期68卷 363-379页

作者： Xuehui WANG Qingbo LI Wen ZHU Feng SHU Mengxing HUANG Fuhui ZHOU Riqing CHEN Cunhua PAN Yongpeng WU Jiangzhou WANG School of Mathematics and Statistics Hainan Normal University Key Laboratory of Data Science and Smart Education Ministry of Education Hainan Normal University School of Information and Communication Engineering Hainan University Collaborative Innovation Center of Information Technology Hainan University School of Electronic and Optical Engineering Nanjing University of Science and Technology College of Electronic and Information Engineering Nanjing University of Aeronautics and Astronautics Digital Fujian Institute of Big Data for Agriculture Fujian Agriculture and Forestry University National Mobile Communications Research Laboratory Southeast University Shanghai Key Laboratory of Navigation and Location Based Services Shanghai Jiao Tong University School of Engineering University of Kent

Owing to its ability to mitigate the double-fading effect by amplifying the reflected signal, the active intelligent reflecting surface(IRS) has garnered significant attention. In this paper, an amplify-and-forward(AF) relay network assisted by a hybrid IRS consisting of both passive and active units is developed. A signal-to-noise ratio(SNR) maximization problem is formulated, where the AF relay beamforming matrix and the hybrid IRS reflecting coefficient matrices for two-time slots need to be optimized. To address the SNR maximization problem, this paper proposes both a high-performance(HP) method and a low-complexity(LC) method. The HP method is based on the semidefinite relaxation and fractional programming(SDR-FP)algorithm, with rank-1 solutions obtained through Gaussian randomization. For the LC method, the amplification coefficient of each active IRS element is assumed to be equal. The SNR maximization problem is then addressed using the whitening filter,generalized power iteration, and generalized Rayleigh-Ritz(WF-GPI-GRR) approach. Simulation results show that compared with the benchmarks, such as the passive IRS-aided AF relay network, the proposed HP-SDR-FP and WF-GPI-GRR methods achieve significant rate improvements. In particular, the HP-SDR-FP and WF-GPI-GRR methods yield more than a 135.0%rate gain when the transmit power Ps of the source is 10 dBm. Furthermore, the proposed HP-SDR-FP method outperforms the WF-GPI-GRR method in terms of rate performance.

关键词： double-fading intelligent reflecting surface active elements passive elements hybrid IRS AF relay

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning for Multiclass Classification of Wheat Leaf Diseases

Transfer Learning for Multiclass Classification of Wheat Lea...

引用

2024 International Conference on Advances in Computing research on science engineering and Technology, ACROSET 2024

作者： Verma, Riya Singh Rathore, Narendra Pal Sethi, Kamal Kumar Acropolis Institute of Technology and Research Artificial Intelligence and Data Science Indore India Acropolis Institute of Technology and Research Computer Science and Engineering Indore India

ISBN: (纸本)9798350388800

In the following paper, we explore a study focusing on the detection of wheat leaf diseases using transfer learning techniques combined with cutting-edge convolutional neural network (CNN) architectures, namely VGG16, ResNet152V2, and Inception. The aim is to enhance the accuracy of disease detection while minimizing computational resources and training time. We conducted experiments on a dataset consisting of wheat leaf images affected with several diseases. Through transfer learning, we fine-tuned pre-trained models on our dataset to leverage their learned features. Our results demonstrate that VGG16 consistently outperforms ResNet152V2 and Inception, achieving the highest accuracy of 98.66% in disease detection. This indicates the efficacy of VGG16 for wheat leaf disease classification tasks, highlighting its potential for agricultural applications requiring robust and accurate detection of plant diseases. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation Models with Attention-Based Dropout Layer

引用

Computers, Materials & Continua 2023年第5期75卷 2981-3009页

作者： Huma Israr Safdar Abbas Khan Muhammad Ali Tahir Muhammad Khuram Shahzad Muneer Ahmad Jasni Mohamad Zain School of Electrical Engineering and Computer Science(SEECS) National University of Science and TechnologyIslamabadPakistan Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Kompleks Al-KhawarizmiUniversiti Teknologi MARA40450Shah AlamSelangorMalaysia

In bilingual translation,attention-based Neural Machine Translation(NMT)models are used to achieve synchrony between input and output sequences and the notion of *** model has obtained state-of-the-art performance for several language ***,there has been little work exploring useful architectures for Urdu-to-English machine *** conducted extensive Urdu-to-English translation experiments using Long short-term memory(LSTM)/Bidirectional recurrent neural networks(Bi-RNN)/Statistical recurrent unit(SRU)/Gated recurrent unit(GRU)/Convolutional neural network(CNN)and *** results show that Bi-RNN and LSTM with attention mechanism trained iteratively,with a scalable data set,make precise predictions on unseen *** trained models yielded competitive results by achieving 62.6%and 61%accuracy and 49.67 and 47.14 BLEU scores,*** a qualitative perspective,the translation of the test sets was examined manually,and it was observed that trained models tend to produce repetitive output more *** attention score produced by Bi-RNN and LSTM produced clear alignment,while GRU showed incorrect translation for words,poor alignment and lack of a clear ***,we considered refining the attention-based models by defining an additional attention-based dropout *** dropout fixes alignment errors and minimizes translation errors at the word *** empirical demonstration and comparison with their counterparts,we found improvement in the quality of the resulting translation system and a decrease in the perplexity and over-translation *** ability of the proposed model was evaluated using Arabic-English and Persian-English datasets as *** empirically concluded that adding an attention-based dropout layer helps improve GRU,SRU,and Transformer translation and is considerably more efficient in translation quality and speed.

关键词： Natural language processing neural machine translation word embedding attention perplexity selective dropout regularization Urdu Persian Arabic BLEU

来源：评论

学校读者我要写书评

暂无评论

KubeSPT: Stateful Pod Teleportation for Service Resilience with Live Migration

引用

IEEE Transactions on Services Computing 2025年第03期18卷 1500-1514页

作者： Zhang, Hansheng Wu, Song Fan, Hao Huang, Zhuo Xue, Weibin Yu, Chen Ibrahim, Shadi Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong China

Container orchestration systems, such as Kubernetes, streamline containerized application deployment. As more and more applications are being deployed in Kubernetes, there is an increasing need for rescheduling - relocating a running pod to different nodes - due to system upgrades, node failures, and load-balancing optimizations. Live migration, which transfers services from source nodes to target nodes with minimal downtime, is the ideal support for rescheduling. However, implementing live migration for pods that run stateful services is challenging, because Kubernetes manages pods as stateless. First, the current pod's network namespace initialization process causes a mismatch in the network state between the migrated pod and internal containers. Second, migrating the memory state results in extended downtime. Third, Kubernetes operations on pods do not consider preserving the state of the pods. Therefore, we propose KubeSPT to achieve live migration of stateful pods in rescheduling scenarios. Firstly, we synchronize the network state of pods and internal containers by controlling packet flow and implement fast service redirection. Secondly, we introduce a Hot data and Lazy-Restore method for memory restoration to reduce migration downtime. Finally, we decouple pod migration operations from other Kubernetes operations to ensure compatibility with live migration. Experimental results show that KubeSPT reduces downtime by 86%-93% compared to current rescheduling methods. © 2008-2012 IEEE.

关键词： Restoration

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：