检索结果-内蒙古大学图书馆

A Lightweight Convolutional Neural Network with Representation Self-challenge for Fingerprint Liveness Detection

computers, Materials & Continua 2022年第10期73卷 719-733页

作者： Jie Chen Chengsheng Yuan Chen Cui Zhihua Xia Xingming Sun Thangarajah Akilan School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityZhejiang Police CollegeHangzhou310053China Jiangsu Yuchi Blockchain Research Institute Nanjing210044China Department of Software Engineering Lakehead UniversityThunder BayON P7B 5E1Canada

Fingerprint identification systems have been widely deployed in many occasions of our daily ***,together with many advantages,they are still vulnerable to the presentation attack(PA)by some counterfeit *** address challenges from PA,fingerprint liveness detection(FLD)technology has been proposed and gradually attracted people’s *** vast majority of the FLD methods directly employ convolutional neural network(CNN),and rarely pay attention to the problem of overparameterization and over-fitting of models,resulting in large calculation force of model deployment and poor model *** at filling this gap,this paper designs a lightweight multi-scale convolutional neural network method,and further proposes a novel hybrid spatial pyramid pooling block to extract abundant features,so that the number of model parameters is greatly reduced,and support multi-scale true/fake fingerprint ***,the representation self-challenge(RSC)method is used to train the model,and the attention mechanism is also adopted for optimization during execution,which alleviates the problem of model over-fitting and enhances generalization of detection ***,experimental results on two publicly benchmarks:LivDet2011 and LivDet2013 sets,show that our method achieves outstanding detection results for blind materials and *** size of the model parameters is only 548 KB,and the average detection error of cross-sensors and cross-materials are 15.22 and 1 respectively,reaching the highest level currently available.

关键词： FLD lightweight multi-scale RSC blind materials

来源：评论

学校读者我要写书评

暂无评论

LACC:a hardware and software co-design accelerator for deep neural networks

引用

High Technology Letters 2021年第1期27卷 62-67页

作者： Yu Yong Zhi Tian Zhou Shengyuan State Key Laboratory of Computer Architecture Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190P.R.China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049P.R.China Cambricon Technologies Ltd Beijing 100190P.R.China

With the increasing of data size and model size,deep neural networks(DNNs)show outstanding performance in many artificial intelligence(AI)*** the big model size makes it a challenge for high-performance and low-power running DNN on processors,such as central processing unit(CPU),graphics processing unit(GPU),and tensor processing unit(TPU).This paper proposes a LOGNN data representation of 8 bits and a hardware and software co-design deep neural network accelerator LACC to meet the *** data representation replaces multiply operations to add and shift operations in running *** accelerator achieves higher efficiency than the state-of-the-art DNN accelerators by domain specific arithmetic computing ***,LACC speeds up the performance per watt by 1.5 times,compared to the state-of-the-art DNN accelerators on average.

关键词： deep neural network(DNN) domain specific accelerator domain specific data type

来源：评论

学校读者我要写书评

暂无评论

AutoQNN: An End-to-End Framework for Automatically Quantizing Neural Networks

arXiv

引用

arXiv 2023年

作者： Gong, Cheng Lu, Ye Dai, Surong Qian, Deng Du, Chenkun Li, Tao College of Software Nankai University Tianjin300350 China College of Computer Science Nankai University Tianjin300350 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

Exploring the expected quantizing scheme with suitable mixed-precision policy is the key point to compress deep neural networks (DNNs) in high efficiency and accuracy. This exploration implies heavy workloads for domain experts, and an automatic compression method is needed. However, the huge search space of the automatic method introduces plenty of computing budgets that make the automatic process challenging to be applied in real scenarios. In this paper, we propose an end-to-end framework named AutoQNN, for automatically quantizing different layers utilizing different schemes and bitwidths without any human labor. AutoQNN can seek desirable quantizing schemes and mixed-precision policies for mainstream DNN models efficiently by involving three techniques: quantizing scheme search (QSS), quantizing precision learning (QPL), and quantized architecture generation (QAG). QSS introduces five quantizing schemes and defines three new schemes as a candidate set for scheme search, and then uses the differentiable neural architecture search (DNAS) algorithm to seek the layer- or model-desired scheme from the set. QPL is the first method to learn mixed-precision policies by reparameterizing the bitwidths of quantizing schemes, to the best of our knowledge. QPL optimizes both classification loss and precision loss of DNNs efficiently and obtains the relatively optimal mixed-precision model within limited model size and memory footprint. QAG is designed to convert arbitrary architectures into corresponding quantized ones without manual intervention, to facilitate end-to-end neural network quantization. We have implemented AutoQNN and integrated it into Keras. Extensive experiments demonstrate that AutoQNN can consistently outperform state-of-the-art quantization. For 2-bit weight and activation of AlexNet and ResNet18, AutoQNN can achieve the accuracy results of 59.75% and 68.86%, respectively, and obtain accuracy improvements by up to 1.65% and 1.74%, respectively, compared

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

TAPEMAN: Towards an Optimal Data Gathering Mechanism in Wireless Sensor Networks

引用

Chinese Journal of Electronics 2023年第4期19卷 594-598页

作者： Yu Gu Yusheng Ji Hongyang Chen Baohua Zhao Department of Computer Science University of Science and Technology of China Hefei China State Key Laboratory of Networking and Switching Technology Beijing China Information Systems Architecture Science Research Division NII Tokyo Japan Institute of Industrial Science University of Tokyo Tokyo Japan

In this paper, we study the lifetime optimization problem using a mobile sink node in a storage-constrained wireless sensor network, and propose an optimal data gathering mechanism named (TAPEMAN) which runs in three steps: first a tight upper bound of the network lifetime is derived through analysis of energy consumption, then we generate a Traveling salesman problem (TSP) solution based on a 2-approximation $O(n^{2})$ algorithm. A judgment will be made about whether this solution is optimal. If the answer is yes, TAPEMAN terminates. If not, a novel data diffusion scheme is used to distribute data to neighboring nodes, in order to avoid data leaking. We prove that under some reasonable assumptions, our algorithm can achieve this upperbound. Simulation results demonstrate the efficiency of our proposed solution and substantiate the importance of using sink mobility for energy-constrained sensor networks.

关键词： Wireless communication Wireless sensor networks Energy consumption Upper bound Simulation Traveling salesman problems Delays

来源：评论

学校读者我要写书评

暂无评论

Using Mobile Sinks in WSN: Computational Complexity and a Theoretical Bound

引用

Chinese Journal of Electronics 2023年第1期20卷 147-150页

In this paper, we study the lifetime optimization problem in wireless sensor networks using mobile sink nodes. This problem is inherently difficult since we need to consider both sink scheduling and data routing. Through a simple case study we develop a novel notation named the Placement pattern (PP) to bound traffic patterns with candidate locations. This significantly decreases the number of elements needed to be scheduled. Based on the PP, we mathematically formulate this optimization problem as a Mixed-integer non-linear programming (MINLP), which is very tough and time consuming to solve. By proving that the problem is NP-complete, we point out that instead of seeking an optimal algorithm, heuristic algorithms, especially those with performance guarantee, would be much more desirable to develop. Furthermore, in order to help identify performance gains of heuristic algorithms proposed in the future, we develop a Linear programming (LP) formulation which serves as an upper bound by adopting a reformulation and relaxation technique.

关键词： Wireless sensor networks Upper bound Heuristic algorithms Traffic control Programming Performance gain Routing

来源：评论

学校读者我要写书评

暂无评论

Investigation of Circular Patch Antenna for Wi-Fi and Bluetooth Applications 3

Investigation of Circular Patch Antenna for Wi-Fi and Blueto...

引用

3rd International Conference on Advancement in Electronics and Communication Engineering, AECE 2023

作者： Ghassan Majeed, Maryam Qasim, Haitham Bashar Kosimova, Shakhlokhon Diame, Hussein Alaa Lafta, Alaa M. Alchilibi, Haider Al-Kunooze University College Computer Engineer Department Basra Iraq Al-Esraa University College Forensic Sciences Department Baghdad Iraq Fergana Polytechnic Institute Department of Architecture Fergana Uzbekistan National University of Science and Technology Dhi Qar Iraq Al-Farahidi University Medical Laboratory Techniques Department Baghdad10022 Iraq

ISBN: (纸本)9798350330724

The purpose of this paper is to examine and contrast the Novel Circular Patch Antenna employing FR4 and RT Droid (CPA). Resonant frequency of 2.5 GHz in a static medium. To create the antenna, we use the HFSS and two different sample sets. Ten samples are taken from each antenna at 80% G-Power. Assume that the members of Group 1 are all CPAs that use the FR4 substrate. The Novel circular patch antenna (CPA) on RT roger's substrate is in the second group under consideration. This antenna operates at 2.5 GHz to measure reflectance at both ends. A VSWR of 2.1786 dB was measured at 2.4 GHz for a circular CPA designed for RT rogers, while the measured value for a CPA with FR4 was 0.7088 dB. The significance level in SPSS was 0.038 (p 0.05). The findings of this study show that RT rogers is approximately as effective as the FR4 substrate. © 2023 IEEE.

关键词： Natural frequencies

来源：评论

学校读者我要写书评

暂无评论

What Dense Graph Do You Need for Self-Attention?

arXiv

引用

arXiv 2022年

作者： Wang, Yuxin Lee, Chu-Tak Guo, Qipeng Yin, Zhangyue Zhou, Yunhua Huang, Xuanjing Qiu, Xipeng School of Computer Science Fudan University China Institute of Modern Languages and Linguistics Fudan University China Peng Cheng Laboratory China

Transformers have made progress in miscellaneous tasks, but suffer from quadratic computational and memory complexities. Recent works propose sparse Transformers with attention on sparse graphs to reduce complexity and remain strong performance. While effective, the crucial parts of how dense a graph needs to be to perform well are not fully explored. In this paper, we propose Normalized Information Payload (NIP), a graph scoring function measuring information transfer on graph, which provides an analysis tool for trade-offs between performance and complexity. Guided by this theoretical analysis, we present Hypercube Transformer, a sparse Transformer that models token interactions in a hypercube and shows comparable or even better results with vanilla Transformer while yielding O(N log N) complexity with sequence length N. Experiments on tasks requiring various sequence lengths lay validation for our graph function well. Copyright © 2022, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Beyond Boundaries: Learning a Universal Entity Taxonomy across Datasets and languages for Open Named Entity Recognition

arXiv

引用

arXiv 2024年

作者： Yang, Yuming Zhao, Wantong Huang, Caishuang Ye, Junjie Wang, Xiao Zheng, Huiyuan Nan, Yang Wang, Yuran Xu, Xueying Huang, Kaixin Zhang, Yunke Gui, Tao Zhang, Qi Huang, Xuanjing School of Computer Science Fudan University China Honor Device Co. Ltd China Institute of Modern Languages and Linguistics Fudan University China Pengcheng Laboratory China Research Institute of Intelligent Complex Systems Fudan University China Shanghai Key Laboratory of Intelligent Information Processing China

Open Named Entity Recognition (NER), which involves identifying arbitrary types of entities from arbitrary domains, remains challenging for Large Language Models (LLMs). Recent studies suggest that fine-tuning LLMs on extensive NER data can boost their performance. However, training directly on existing datasets neglects their inconsistent entity definitions and redundant data, limiting LLMs to dataset-specific learning and hindering out-of-domain adaptation. To address this, we present B2NERD, a compact dataset designed to guide LLMs’ generalization in Open NER under a universal entity taxonomy. B2NERD is refined from 54 existing English and Chinese datasets using a two-step process. First, we detect inconsistent entity definitions across datasets and clarify them by distinguishable label names to construct a universal taxonomy of 400+ entity types. Second, we address redundancy using a data pruning strategy that selects fewer samples with greater category and semantic diversity. Comprehensive evaluation shows that B2NERD significantly enhances LLMs’ Open NER capabilities. Our B2NER models, trained on B2NERD, outperform GPT-4 by 6.8-12.0 F1 points and surpass previous methods in 3 out-of-domain benchmarks across 15 datasets and 6 languages. The data, models, and code are publicly available at https://***/UmeanNever/B2NER. Copyright © 2024, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

F3D: Accelerating 3D Convolutional Neural Networks in Frequency Space Using ReRAM 21

F3D: Accelerating 3D Convolutional Neural Networks in Freque...

引用

Proceedings of the 58th Annual ACM/IEEE Design Automation Conference

作者： Bosheng Liu Zhuoshen Jiang Wu Jigang Xiaoming Chen Yinhe Han Peng Liu School of Computer Science and Technology Guangdong University of Technology China and State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology Guangdong University of Technology China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9781665432740

3D convolutional neural networks (CNNs) are widely deployed in video analysis. Fast algorithms such as fast Fourier transforms (FFTs) are gaining popularity in reducing computation complexity for their superior capability of replacing convolutions with simpler element-wise multiplications. Conventional frequency-domain dedicated accelerators employ memory hierarchy organization for high throughput but at the expensive costs of a significant amount of data movements and energy consumptions. This paper presents F3D, a processing-in-memory frequency-domain accelerator using resistive random access memory (ReRAM). F3D supports frequency-domain complex number multiplications directly in ReRAM-based crossbar architecture. We alleviate the overheads of redundant data movements in ReRAM-based complex number multiplications by data reuse and the inherent symmetry of inputs in the frequency space. Evaluation results demonstrate that F3D outperforms state-of-the-art accelerators with significant improvements in performance and energy efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient Vectorization Scheme for Stencil Computation

An Efficient Vectorization Scheme for Stencil Computation

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Kun Li Liang Yuan Yunquan Zhang Yue Yue Hang Cao State Key Laboratory of Computer Architecture Chinese Academy of Sciences Institute of Computing Technology Beijing School of Computer Science and Technology University of Chinese Academy of Sciences Beijing

Stencil computation is one of the most important kernels in various scientific and engineering applications. A variety of work has focused on vectorization and tiling techniques, aiming at exploiting the in-core data parallelism and data locality respectively. In this paper, the downsides of existing vectorization schemes are analyzed. Briefly, they either incur data alignment conflicts or hurt the data locality when integrated with tiling. Then we propose a novel transpose layout to preserve the data locality for tiling and reduce the data reorganization overhead for vectorization simultaneously. To further improve the data reuse at the register level, a time loop unroll-and-jam strategy is designed to perform multistep stencil computation along the time dimension. Experimental results on the AVX2 and AVX-S12 CPUs show that our approach obtains a competitive performance with the classic vectorization methods (Auto Vectorization and Data Reorganization), state-of-the-art compilers (Pluto and SDSL), and highly-optimized work (DLT and Tessellation).

关键词： Concurrent computing Distributed processing Layout Parallel processing Registers Computational efficiency Kernel

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：