检索结果-内蒙古大学图书馆

5th International Conference on Data-Driven Optimization of Complex Systems, DOCS 2023

作者： Xiao, Kaiwen Cai, Xiaodong Xu, Ke School of Artificial Intelligence Anhui University Hefei China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China

ISBN: (纸本)9798350393521

Most of existing studies on neural network pruning only consider memory-based pruning strategies. However pruning for computational workload is often more important in hardware deployments due to a greater focus on model computation reductions. In addition, most pruning schemes restore model accuracy during pruning at the expense of adding hyperparameters, extending training time and training complexity. This work proposes a statistical-based globally soft iterative pruning scheme. With little extra calculation, an extremely sparse model can be obtained without additional hyperparameters and extended training time. Moreover, this work proposes the concept of computational intensity to balance model memory and computational workload during pruning. Focusing on memory orientated pruning, we can achieve 303×, 100× and 25× parameter compression on LeNet-5 (MNIST), VGG (CIFAR-10) and AlexNet (ImageNet) models, respectively. In particular, combined with cluster quantization, the LeNet-5 model parameters can be compressed to 3232×. Focusing on workload orientated pruning, we can reduce the computation by 7}.6× on the AlexNet model, without accuracy loss, significantly higher than prior work. In addition, in order to verify the versatility of the pruning method, we also migrate the pruning task to the object detection and implement 10× parameter compression and 2.8× computation compression for YOLOv2 with reduced mAP within 1%. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Community Evolution Tracking Based on Core Node Extension and Edge Variation Discerning 17th

Community Evolution Tracking Based on Core Node Extension a...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social computing, ChineseCSCW 2022

作者： Zhuang, Qifeng Yu, Zhiyong Guo, Kun College of Computer and Data Science Fuzhou University Fuzhou350108 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350108 China Key Laboratory of Spatial Data Mining and Information Sharing Ministry of Education Fuzhou350108 China

ISBN: (纸本)9789819923557

Communities exist anywhere in various complex networks, and community evolution tracking is one of the most well-liked areas of inquiry in the study of dynamic complex networks. Community evolution tracking has many applications in daily life, such as predicting social network behaviors or analyzing the spread of infectious illnesses. However, the majority of existing evolution tracking algorithms obtain community detection results before matching the community in tracking evolution events, making it difficult to trace the whole evolution of communities because of community matching errors. In addition, the majority of evolution tracking algorithms do not adequately account for the potential scenarios in community evolution, resulting in erroneous detection of evolution events. In this research, a community evolution tracking algorithm based on edge variation discerning and core node extension is proposed. First, we detect communities based on the core node extension strategy, which avoids the problem of community matching errors. Second, we track community evolution based on the edge variation discerning strategy, which fully considers various situations that may occur during the community evolution process. According to the outputs of our experiments, our system can effectively track the evolution of communities in synthetic dynamic networks. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Real-time pricing method through market auction based on multi-agent reinforcement learning 8

Real-time pricing method through market auction based on mul...

引用

8th International Conference on Power and Renewable Energy, ICPRE 2023

作者： Hong, Peng He, Shuping Fang, Xiaohan Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Hefei230601 China

ISBN: (纸本)9798350328813

With the development of distributed energy systems, pricing different energy sources in microgrids has become a significant challenge. To solve this problem, this paper proposes an real-time pricing method through market auction based on multi-agent reinforcement learning. The energy supply side provides different energy production and quotations, while consumers on the energy demand side freely quote and purchase the required energy in the energy market based on their own needs. The final transaction price of different energy sources is determined by the quotes of the buyer and seller who have reached the transaction. The simulation results indicate that the proposed pricing method have a good performance. © 2023 IEEE.

关键词： Market auction Multi-agent reinforcement learning Real-time pricing

来源：评论

学校读者我要写书评

暂无评论

Phase unwrapping method for 3D measurement based on multi-frequency asynchronous phase shift 2

Phase unwrapping method for 3D measurement based on multi-fr...

引用

2nd International Conference on Electronic information Engineering and Computer Communication, EIECC 2022

作者： Cao, Chunyang Deng, Chengzhi Wu, Zhaoming Zhang, Xiaoxiao Hu, Cheng Jiangxi Province Key laboratory of Water Information Cooperative Sensing and Intelligent Processing School of Information Engineering Nanchang Institute of Technology 330099 China

ISBN: (纸本)9781510663121

Aiming at the problems that 3D optical measurement is easy to be affected by peripheral noise, difficult to calculate relative height and low measurement accuracy, a multi-frequency asynchronous phase shift algorithm based on time series changes was proposed. In order to improve the measurement accuracy and anti-interference ability of the system, five kinds of frequency grating projections were adopted. In order to improve the efficiency of phase undoing, the asynchronous phase shift method was used to extract the phase principal value. In view of the multi-frequency heterodyne phase solution method is prone to produce phase jump error, a phase jump error correction method based on threshold discrimination is proposed. The experimental results show that the improved algorithm has better measurement accuracy than the original algorithm, and compared with the traditional multi-frequency heterodyne method, it has strong anti-interference ability and higher measurement accuracy. © 2023 SPIE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Non-negative Matrix Factorization Method Based on Mixed Gaussian Kernels 1

引用

3rd International Conference on Artificial Intelligence Logic and Applications, AILA 2023

作者： Yang, Zhenting Pei, Jihong Ye, Sicong College of Electronics and Information Engineering Shenzhen University Guangdong Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Guangdong Shenzhen China

ISBN: (数字)9789819978694

ISBN: (纸本)9789819978687

Non-negative Matrix Factorization (NMF) is a data dimensionality reduction method, which can process large scale and high dimensional data more efficiently. Among them, kernel-based non-negative matrix factorization maps data to high-dimensional space, which is a nonlinear NMF method and is mainly used to extract high-order features of image data. The feature information obtained by different kernel functions has different characteristics and makes different contributions to image classification. However, most of the researches only consider single-kernel NMF, and some multi-kernel NMF methods also have some problems such as uneven weight distribution, which loses the feature information of some kernel functions. Therefore, it is necessary to study the NMF method of multi-kernel fusion with adaptive weights. In this paper, a non-negative matrix factorization method based on mixed Gaussian kernels is proposed. By fusing multiple Gaussian kernels with different weights and updating weights adaptively, the feature information of different Gaussian kernels can complement each other, which has good performance on public datasets FERET, ORL and Yale Face, indicating that the algorithm can effectively improve the classification performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Human Activity Classification Based-On Micro-Doppler Simulations with DNNs and Transfer Learning

Human Activity Classification Based-On Micro-Doppler Simulat...

引用

International Conference on Internet of Things, Communication and intelligent Technology, IoTCIT 2022

作者： Lai, Jialei Chu, Ping Yang, Zhaocheng Shenzhen University Guangdong Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Guangdong China

ISBN: (纸本)9789819904150

Deep convolution neural networks (DCNN) have been an excellent classifier in various fields such as radar images classification. However, the number of training samples deeply influences the performance of networks and radar samples are not easy to be obtained. In this paper, we utilize micro-Doppler simulated data from Kinect sensor and online dataset to train networks and figure out the differences. In order to enhance the reliability of Kinect simulation, a filter for Kinect data is proposed. Later, transfer learning is used to improve the performance. Moreover, bistatic deep convolutional neural networks (bistatic-DCNN) are proposed. After transfer learning, experimental results show that the performances of both 7-class and 13-class motion classification reach over 98%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Flexible TiO_(2)-WO_(3−x) hybrid memristorwith enhanced linearity and synaptic plasticity for precise weight tuning in neuromorphic computing

引用

npj Flexible Electronics 2024年第1期8卷 180-191页

作者： Jianyong Pan Hao Kan Zhaorui Liu Song Gao Enxiu Wu Yang Li Chunwei Zhang Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and EngineeringUniversity of JinanJinanChina State Key Lab of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghaiChina School of Integrated Circuits Shandong UniversityJinanChina

Tungsten oxide(WO_(3))-based memristors show promising applications in neuromorphic ***,single-layer WO_(3) memristors suffer from issues such as weak memory performance and nonlinear conductance *** this work,a functional layer based on the hybrids of WO_(3−x) and TiO_(2) is proposed for constructing flexible memristors featuring outstanding synaptic *** diverse electrical stimulations to the memristor enables a range of synaptic functions,elucidating its conduction mechanism through the conductive filament *** incorporation of TiO_(2) not only enhances the memristor’s memory characteristics but makes its conductance more linear,symmetrical and uniform during the long-term ***,in view of the enhanced device performance by TiO_(2) doping,the potential of this device for simple behavioral simulation and processing of complex computing problems is ***“learning-forgetting-relearning”characteristics and device integrability are visually *** the device to a convolutional neural network,the recognition accuracy of MNIST handwritten digits reaches 98.7%.

关键词： computing tuning precise

来源：评论

学校读者我要写书评

暂无评论

A Transformer-Assisted Cascade Learning Network for Choroidal Vessel Segmentation

引用

Journal of Computer Science & Technology 2024年第2期39卷 286-304页

作者：温阳吴依林毕磊石武祯刘潇骁许毓鹏许迅曹文明冯大淦 Guangdong Provincial Key Laboratory of Intelligent Information Processing School of Electronics and Information EngineeringShenzhen UniversityShenzhen 518060China Institute of Translational Medicine Shanghai Jiao Tong UniversityShanghai 200240China Department of Ophthalmology Shanghai General HospitalShanghai Jiao Tong University School of MedicineShanghai 200080China School of Information Technologies The University of SydneySydney 2006Australia

As a highly vascular eye part,the choroid is crucial in various eye disease ***,limited research has focused on the inner structure of the choroid due to the challenges in obtaining sufficient accurate label data,particularly for the choroidal ***,the existing direct choroidal vessel segmentation methods for the intelligent diagnosis of vascular assisted ophthalmic diseases are still unsatisfactory due to noise data,while the synergistic segmentation methods compromise vessel segmentation performance for the choroid layer segmentation *** cascaded structures grapple with error propagation during *** address these challenges,we propose a cascade learning segmentation method for the inner vessel structures of the choroid in this ***,we propose TransformerAssisted Cascade Learning Network(TACLNet)for choroidal vessel segmentation,which comprises a two-stage training strategy:pre-training for choroid layer segmentation and joint training for choroid layer and choroidal vessel *** also enhance the skip connection structures by introducing a multi-scale subtraction connection module designated as MSC,capturing differential and detailed information ***,we implement an auxiliary Transformer branch named ATB to integrate global features into the segmentation *** results exhibit that our method achieves the state-of-the-art performance for choroidal vessel ***,we further validate the significant superiority of the proposed method for retinal fluid segmentation in optical coherence tomography(OCT)scans on a publicly available *** these fully prove that our TACLNet contributes to the advancement of choroidal vessel segmentation and is of great significance for ophthalmic research and clinical application.

关键词： choroidal vessel segmentation optical coherence tomography(OCT) Transformer-assisted cascade learning retinal fluid segmentation multi-scale feature extraction

来源：评论

学校读者我要写书评

暂无评论

Strong Co-Location Pattern Mining Incorporating Multi-Path and Distance Decay Effects 7

Strong Co-Location Pattern Mining Incorporating Multi-Path a...

引用

7th International Conference on Algorithms, computing and Artificial Intelligence, ACAI 2024

作者： He, Yonggui Yang, Peizhong Wang, Lizhen Chen, Hongmei Yunnan University School of Information Science and Engineering Kunming China Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing School of Information Science and Engineering Kunming China

ISBN: (纸本)9798331529314

Spatial co-location pattern mining (SCPM) is a sub-field of data mining, which aims to discover the subset of spatial features whose instances are frequently located in proximate areas. SCPM has broad prospects in many applications, such as ecology, public health, smart cities, etc. In recent years, improving and applying SCPM technology with the constraints of road networks has emerged as a prominent research focus. However, existing studies solely focus on the shortest path between instances when assessing the proximity relationships, neglecting other proximity paths, and thus may overlook co-location patterns with strong associations. To address this issue, this paper introduces a novel metric called Strong Proximity Score, which integrates both multi-path proximity and distance decay effects to measure the strength of proximity relationships. Additionally, the Minimum First Search (MFS) algorithm is presented, which utilizes the strategy of minimum instance pair search to accelerate the calculation of Strong Proximity Score. Extensive experiments conducted on real datasets of points of interest demonstrate the superiority of the method based on Strong Proximity Score over traditional SCPM methods and confirm the efficiency of MFS algorithm. © 2024 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

A Novel Wide-Band High-Gain Microstrip Quasi-Yagi Antenna Design for X-Band Applications 5

A Novel Wide-Band High-Gain Microstrip Quasi-Yagi Antenna De...

引用

5th International Conference on Advances in Electrical, Electronics and computing Technology, EECT 2025

作者： Wang, Xinju Wang, Sentao Chen, Zhuo Gan, Zongsheng Zhang, Haowei Yin, Yutong Liu, Lu Chen, Peng School of Ocean Information Engineering Jimei University Xiamen China School of Transportation and Civil Engineering Nantong University Nantong China School of Ocean Information Engineering Jimei University Fujian Provincial Key Laboratory of Maritime Communication and Intelligent Electronic Systems Fujian Provincial Key Laboratory of Oceanic Information Perception and Intelligent Processing Xiamen China

ISBN: (纸本)9798331541545

A new broadband high-gain microstrip quasi-yagi antenna is proposed. With the aim of designing an end-firing antenna for X-band by utilizing the good directivity of yagi antennas. The main radiating dipole patches of this antenna adopts an additional tapered trapezoidal-like structure to optimize its radiation characteristics. In addition, the operating bandwidth and main beam gain of the antenna are effectively adjusted by placing four identical microstrip metal strip patches on the bottom surface of the dielectric substrate to act as the reflector and the guide, respectively. Simulation results show that the designed antenna operates in the frequency bands of 8.33-13.07 GHz and 13.57-13.95 GHz with relative bandwidths of 44.3% and 2.76%, respectively, and achieves a peak gain of 8.9 dBi. The antenna has a simple structural design and is suitable for X-band wireless communication systems with a wide range of applications. © 2025 IEEE.

关键词： Microstrip 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：