检索结果-内蒙古大学图书馆

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Yan Jin Haoyu Fan Yaojie Liu School of Geographic and Biologic Information Nanjing University of Posts and Telecommunications China Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province China School of Geographic Sciences Nanjing University of Information Science and Technology China

This paper proposes a hybrid downscaling method, named random forest area-to-area regression kriging (RFATARK), to improve the resolution of the Global Ozone Monitoring Experiment (GOME) solar-induced chlorophyll fluorescence (SIF) product over East Asia during 1995-2003. The RFATARK method effectively captures the nonlinear relationships between variables and incorporates spatial variability through residual prediction. Comparative analyses with two alternative downscaling methods demonstrate the superior performance of RFATARK in enhancing the spatial patterns of the downscaled SIF data. The reconstructed 0.5-degree SIF product offers a more detailed representation of the vegetation dynamics and carbon cycle in East Asia. The proposed methodological framework can also be applied to other coarse-resolution SIF products obtained from different satellite sensors, providing valuable datasets for regional vegetation monitoring and carbon cycle modeling.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Simulation of Multi-tiered Heterogeneous Memory Architecture

Design and Simulation of Multi-tiered Heterogeneous Memory A...

引用

International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems (MASCOTS)

作者： Jinyuan Hu Haikun Liu Hai Jin Xiaofei Liao 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 University of Science and Technology Wuhan China

Heterogeneous memory systems have become increasingly popular in recent years. Because heterogeneous storage media often show significantly different characteristics in terms of bandwidth, latency, capacity, and energy consumption, it is still challenging to best utilize them for cost-efficient and energy-efficient heterogeneous memory systems. In this paper, we propose a simulation framework for multi-tiered heterogeneous memory architectures based on GEM5 and DRAMsim3 simulators. We design a heterogeneous memory controller to architect Non-Volatile Memory (NVM) as main memory, and architect both Dynamic Random Access Memory (DRAM) and High-Bandwidth Memory (HBM) as a hybrid cache of NVM. Specifically, HBM, DRAM, and NVM are managed in a single (flat) address space. However, we use an address remapping table to maintain the mappings between NVM pages and HBM/DRAM pages, and logically manage HBM/DRAM/NVM as a three-tiered hybrid memory system. We also design a hardware-supported hot page monitor based on Majority Element Algorithm (MEA) to identify the hottest pages in the DRAM, and a dynamic threshold adjustment scheme for hot page migration to balance the memory bandwidth between DRAM and HBM. Our multi-tiered heterogeneous memory architecture can take advantage of the large capacity of NVM, the low latency of DRAM, and the high bandwidth of HBM concurrently. Experimental results show that our tiered memory architecture can improve application performance by an average of $2.5\times$ compared with an NVM-only architecture, and up to 57.4% compared with a DRAM-only architecture. Moreover, the performance gap between our HBM/DRAM/NVM architecture and a HBM-only architecture is less than 10%.

关键词： Analytical models Nonvolatile memory Heuristic algorithms Computational modeling Memory architecture Random access memory Computer architecture

来源：评论

学校读者我要写书评

暂无评论

General Two-Stage Network Systems Based on Stackelberg Game

SSRN

引用

SSRN 2023年

作者： Zhang, Linyan Zhang, Jian Guo, Chuanyin School of Economics and Management Beijing Information Science & Technology University Beijing100192 China Research Center for Knowledge Management Beijing100192 China Beijing Key Lab of Green Development Decision Based on Big Data Beijing100192 China

Noncooperative approach is a key technique for modeling network systems. In general, there are two types of noncooperative network models in the literature. One is the bilevel model based on Stackelberg game, which is often transformed into a parametric linear program. The other is the leader-follower model, which uses only Stackelberg game concept, which may yield an infeasible solution. The current study shows that the bilevel model can be solved by using two linear models, without having to resort to solving heuristic parametric linear models. Furthermore, the global optimal solution is guaranteed for the nonlinear bilevel model. We prove the equivalence between the bilevel technique and our two linear-model approach. We further improve the existing leader-follower models, and as well the newly developed approaches are extended to general two-stage structures. The newly developed approaches are illustrated with a numerical data set and a real-world case. © 2023, The Authors. All rights reserved.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

Attenuated niacin-induced skin flush response in individuals with clinical high risk for psychosis

引用

General Psychiatry 2022年第2期35卷 92-100页

作者： Ranpiao Gan Yanyan Wei Guisen Wu Jiahui Zeng Yegang Hu Lihua Xu Xiaochen Tang Xiaohua Liu Haichun Liu Tao Chen Jijun Wang Tianhong Zhang Shanghai Intelligent Psychological Evaluation and Intervention Engineering Technology Research Center Shanghai Key Laboratory of Psychotic DisordersShanghai Mental Health CenterShanghai Jiao Tong University School of MedicineShanghaiChina Department of Automation Shanghai Jiao Tong UniversityShanghaiChina Big Data Research Lab University of WaterlooWaterlooOntarioCanada Center for Excellence in Brain Science and Itelligence Technology(CEBSIT) Chinese Academy of ScienceShanghaiChina Brain Science and Technology Research Center Shanghai Jiao Tong UniversityShanghaiChina

Background Im paired sesitwity of he soin Mlush response bo miacin is one of the most rpicated findngs in patents with schizoprenia *** studies have usaly focused on postonset psychusis,and ll is knowm about the dinical high-risk(CHR)phase of niacin senstity in psychosis Aims To proftle and compare the miacin flush responsge among CHR individuals(converters and non-coverters)patients with frstepso schinophrenia(FES)and healty controls(HCs).Methods Sensivily 1o ftour concentralions (0.1-0001M)of aqueous methylnicotinate was tested in 105 CHR individuals,57 patients with FES and 52 *** individuals were further grouped as converters and non converters according to the 2-year follow-up *** flush response scores were rated on a 4-point *** Of the 105 CHR individuals,21 individuals were lost during the study,leaving 84 CHR individuals;16(19.0%)converted to full psychosis at 2 years of *** response scores identifed in the CHR samples were characterised as modest degree levels,intermediate between those of HC individuals and patients with *** flush responses in the CHR group mimicked the responses observed in the FES group at higher concentrations(0.01 M,0.1 M)and longer time points(15 min,20min);however,these became comparable vith the responses in the HC group at the shorter time points and at lower concentr *** converters exhibited lower mean flush response scores than the *** Attenuated niacin-induced flushing emerged during the early phase of *** devices should be developed and verified for objective quantification of skin responses in the CHR population.

关键词： Skin high shorter

来源：评论

学校读者我要写书评

暂无评论

DISENTANGLING THE PROSODY AND SEMANTIC INFORMATION WITH PRE-TRAINED MODEL FOR IN-CONTEXT LEARNING BASED ZERO-SHOT VOICE CONVERSION

arXiv

引用

arXiv 2024年

作者： Chen, Zhengyang Wang, Shuai Zhang, Mingyang Liu, Xuechen Yamagishi, Junichi Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China Chinese University of Hong Kong Shenzhen China National Institute of Informatics Tokyo Japan

Voice conversion (VC) aims to modify the speaker's timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic tokens, our experiments on the LibriTTS dataset demonstrate that ICL-VC improves speaker similarity. Additionally, we find that k-means is a versatile tokenization method applicable to various pre-trained models. However, the ICL-VC system faces challenges in preserving the prosody of the source speech. To mitigate this issue, we propose incorporating prosody embeddings extracted from a pre-trained emotion recognition model into our system. Integration of prosody embeddings notably enhances the system's capability to preserve source speech prosody, as validated on the Emotional Speech database. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Disentangling The Prosody And Semantic Information With Pre-Trained Model For In-Context Learning Based Zero-Shot Voice Conversion

Disentangling The Prosody And Semantic Information With Pre-...

引用

IEEE Spoken Language Technology Workshop

作者： Zhengyang Chen Shuai Wang Mingyang Zhang Xuechen Liu Junichi Yamagishi Yanmin Qian Department of Computer Science and Engineering Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai China Shenzhen Research Institute of Big Data Shenzhen China Chinese University of Hong Kong Shenzhen China National Institute of Informatics Tokyo Japan

ISBN: (数字)9798350392258

ISBN: (纸本)9798350392265

Voice conversion (VC) aims to modify the speaker’s timbre while retaining speech content. Previous approaches have tokenized the outputs from self-supervised into semantic tokens, facilitating disentanglement of speech content information. Recently, in-context learning (ICL) has emerged in text-to-speech (TTS) systems for effectively modeling specific characteristics such as timbre through context conditioning. This paper proposes an ICL capability enhanced VC system (ICL-VC) employing a mask and reconstruction training strategy based on flow-matching generative models. Augmented with semantic tokens, our experiments on the LibriTTS dataset demonstrate that ICL-VC improves speaker similarity. Additionally, we find that k-means is a versatile tokenization method applicable to various pre-trained models. However, the ICL-VC system faces challenges in preserving the prosody of the source speech. To mitigate this issue, we propose incorporating prosody embeddings extracted from a pre-trained emotion recognition model into our system. Integration of prosody embeddings notably enhances the system’s capability to preserve source speech prosody, as validated on the Emotional Speech database.

关键词： Training Emotion recognition databases Semantics Self-supervised learning Speech enhancement Tokenization Text to speech Multilingual Timbre

来源：评论

学校读者我要写书评

暂无评论

From Mimicking to Integrating: Knowledge Integration for Pre-Trained Language Models

From Mimicking to Integrating: Knowledge Integration for Pre...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Li, Lei Lin, Yankai Ren, Xuancheng Zhao, Guangxiang Li, Peng Zhou, Jie Sun, Xu MOE Key Lab of Computational Linguistics School of Computer Science Peking University China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tsinghua University China Pattern Recognition Center WeChat AI Tencent Inc. China

Investigating better ways to reuse the released pre-trained language models (PLMs) can significantly reduce the computational cost and the potential environmental side-effects. This paper explores a novel PLM reuse paradigm, Knowledge Integration (KI). Without human annotations available, KI aims to merge the knowledge from different teacher-PLMs, each of which specializes in a different classification problem, into a versatile student model. To achieve this, we first derive the correlation between virtual golden supervision and teacher predictions. We then design a Model Uncertainty-aware Knowledge Integration (MUKI) framework to recover the golden supervision for the student. Specifically, MUKI adopts Monte-Carlo Dropout to estimate model uncertainty for the supervision integration. An instance-wise re-weighting mechanism based on the margin of uncertainty scores is further incorporated, to deal with the potential conflicting supervision from teachers. Experimental results demonstrate that MUKI achieves substantial improvements over baselines on benchmark datasets. Further analysis shows that MUKI can generalize well for merging teacher models with heterogeneous architectures, and even teachers major in cross-lingual datasets. © 2022 Association for Computational Linguistics.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

SMS Spam Detection Using BERT and Multi-Graph Convolutional Networks

SSRN

引用

SSRN 2025年

作者： Shen, Linjie Wang, Yanbin Li, Zhao Ma, Wenrui School of Computer Science and Technology Zhejiang Gongshang University Zhejiang Hangzhou China Department of Engineering Shenzhen MSU-BIT University Guangdong Shenzhen518172 China Zhejiang Lab Zhejiang Hangzhou China Department of Big Data and Future E-Commerce Technology Zhejiang Key Laboratory Zhejiang Hangzhou China

The surge in smartphone usage has significantly increased SMS traffic and, consequently, SMS spam, posing risks such as phishing, financial losses, and privacy breaches. Traditional rule-based and blacklist methods fail against evolving spamming techniques, prompting the adoption of machine learning and deep learning approaches. However, models like CNNs and RNNs struggle to capture global co-occurrence patterns and complex semantics, while transformer-based models like BERT lack explicit syntactic and co-occurrence modeling. To address these limitations, we propose the BERT with Triple-Graph Convolutional Networks (BERT-G3CN) model, the first framework to integrate BERT word embeddings with graph embeddings from Cooccurrence, Heterogeneous, and Integrated Syntactic Graphs. This multi-graph approach captures diverse features and models both global and local structures using tailored Graph Convolutional Networks (GCNs). Experiments on two benchmark datasets demonstrate that BERT-G3CN achieves superior accuracy of 99.28% and 93.78%. © 2025, The Authors. All rights reserved.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

CPSAA: Accelerating Sparse Attention using Crossbar-based Processing-In-Memory Architecture

arXiv

引用

arXiv 2022年

作者： Li, Huize Jin, Hai Zheng, Long Liao, Xiaofei Huang, Yu Liu, Cong Xu, Jiahong Duan, Zhuohui Chen, Dan Gui, Chuangyi 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 University of Science and Technology Wuhan China

The attention-based neural network attracts great interest due to its excellent accuracy enhancement. However, the attention mechanism requires huge computational efforts to process unnecessary calculations, significantly limiting the system’s performance. To reduce the unnecessary calculations, researchers propose sparse attention to convert some dense-dense matrices multiplication (DDMM) operations to sampled dense-dense matrix multiplication (SDDMM) and sparse matrix multiplication (SpMM) operations. However, current sparse attention solutions introduce massive off-chip random memory access since the sparse attention matrix is generally unstructured. We propose CPSAA, a novel crossbar-based processing-in-memory (PIM)-featured sparse attention accelerator to eliminate off-chip data transmissions. First, we present a novel attention calculation mode to balance the crossbar writing and crossbar processing latency. Second, we design a novel PIM-based sparsity pruning architecture to eliminate the pruning phase’s off-chip data transfers. Finally, we present novel crossbar-based SDDMM and SpMM methods to process unstructured sparse attention matrices by coupling two types of crossbar arrays. Experimental results show that CPSAA has an average of 89.6×, 32.2×, 17.8×, 3.39×, and 3.84× performance improvement and 755.6×, 55.3×, 21.3×, 5.7×, and 4.9× energy-saving when compare with GPU, FPGA, SANGER, ReBERT, and ReTransformer. Copyright © 2022, The Authors. All rights reserved.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Random noise defense against query-based black-box attacks

arXiv

引用

arXiv 2021年

作者： Qin, Zeyu Fan, Yanbo Zha, Hongyuan Wu, Baoyuan School of Data Science Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China Tencent AI Lab United States

The query-based black-box attacks have raised serious threats to machine learning models in many real applications. In this work, we study a lightweight defense method, dubbed Random Noise Defense (RND), which adds proper Gaussian noise to each query. We conduct the theoretical analysis about the effectiveness of RND against query-based black-box attacks and the corresponding adaptive attacks. Our theoretical results reveal that the defense performance of RND is determined by the magnitude ratio between the noise induced by RND and the noise added by the attackers for gradient estimation or local search. The large magnitude ratio leads to the stronger defense performance of RND, and it’s also critical for mitigating adaptive attacks. Based on our analysis, we further propose to combine RND with a plausible Gaussian augmentation Fine-tuning (RND-GF). It enables RND to add larger noise to each query while maintaining the clean accuracy to obtain a better trade-off between clean accuracy and defense performance. Additionally, RND can be flexibly combined with the existing defense methods to further boost the adversarial robustness, such as adversarial training (AT). Extensive experiments on CIFAR-10 and ImageNet verify our theoretical findings and the effectiveness of RND and RND-GF. © 2021, CC BY.

关键词： Network security

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：