检索结果-内蒙古大学图书馆

Preface to Special Issue on Optoelectronic Neuromorphic Devices

Journal of Semiconductors 2025年第2期46卷 2-4页

作者： Zhenyi Ni Zhongqiang Wang Jia Huang Xiaodong Pi State key Laboratory of Silicon and Advanced Semiconductor Materials&School of Materials Science and Engineering Zhejiang UniversityHangzhou 310027China Shangyu Institute of Semiconductor Materials Shaoxing 312300China Key Laboratory of UV-Emitting Materials and Technology of Ministry of Education Northeast Normal UniversityChangchun 130024China School of Materials Science and Engineering&National Key Laboratory of Autonomous Intelligent Unmanned Systems Tongji UniversityShanghai 201804China Institute of Advanced Semiconductors&Zhejiang Provincial Key Laboratory of Power Semiconductor Materials and Devices ZJ-UHangzhou Global Scientific and Technological Innovation CenterZhejiang UniversityHangzhou 311200China

The rapid advancement of artificial intelligence(AI),recognized with Nobel Prizes in both Physics and Chemistry in 2024,has been revolutionizing countless aspects of modern life,driving innovations across diverse fields and reshaping how people interact with *** its great advances,the computing of AI systems is now approaching the limit of traditional computing based on the von Neumann architecture,which is characterized by separated memory and process units-a challenge known as the"von Neumann bottleneck".

关键词： approaching separated Neumann

来源：评论

学校读者我要写书评

暂无评论

Self-Adaptive Fine-grained Multi-modal Data Augmentation for Semi-supervised Muti-modal Coreference Resolution 24

Self-Adaptive Fine-grained Multi-modal Data Augmentation for...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zheng, Li Chen, Boyu Fei, Hao Li, Fei Wu, Shengqiong Liao, Lizi Ji, Donghong Teng, Chong School of Cyber Science and Engineering Wuhan University Wuhan China School of Computing National University of Singapore Singapore Singapore SCIS Singapore Management University Singapore Singapore Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education China

ISBN: (纸本)9798400706868

Coreference resolution, an essential task in natural language processing, is particularly challenging in multi-modal scenarios where data comes in various forms and modalities. Despite advancements, limitations due to scarce labeled data and underleveraged unlabeled data persist. We address these issues with a self-adaptive fine-grained multi-modal data augmentation framework for semi-supervised MCR, focusing on enriching training data from labeled datasets and tapping into the untapped potential of unlabeled data. Regarding the former issue, we first leverage text coreference resolution datasets and diffusion models,to perform fine-grained text-to-image generation with aligned text entities and image bounding boxes. We then introduce a self-adaptive selection strategy, meticulously curating the augmented data to enhance the diversity and volume of the training set without compromising its quality. For the latter issue, we design a self-adaptive threshold strategy that dynamically adjusts the confidence threshold based on the model's learning status and performance, enabling effective utilization of valuable information from unlabeled data. Additionally, we incorporate a distance smoothing term, which smooths distances between positive and negative samples, enhancing discriminative power of the model?s feature representations and addressing noise and uncertainty in the unlabeled data. Our experiments on the widely-used CIN dataset show that our framework significantly outperforms state-of-the-art baselines by at least 9.57% on MUC F1 score and 4.92% on CoNLL F1 score. Remarkably, against weakly-supervised baselines, our framework achieves a staggering 22.24% enhancement in MUC F1 score. These results, underpinned by in-depth analyses, underscore the effectiveness and potential of our approach for advancing MCR tasks. © 2024 ACM.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Altered spatiotemporal consistency of local neural activities in Parkinson’s disease 3

Altered spatiotemporal consistency of local neural activitie...

引用

3rd International Conference on Optics and Image Processing, ICOIP 2023

作者： Jin, Chaoyang Yang, Lei Qi, Shouliang College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China

ISBN: (纸本)9781510667426

The present study aims to explore the local spatiotemporal consistency of brain connectivity in PD patients. In total, 30 PD patients and 20 health controls (HC) were collected from the Parkinson’s progression markers initiative (PPMI) and their resting state functional MRI images are acquired. FOur-dimensional Consistency of local neural Activities (FOCA) was employed for the first time to explore local brain activity differences between the two groups. To explore the relationship between FOCA values and neuropsychological indices, the Pearson correlation analysis was performed. And receiver operating characteristic (ROC) analysis was carried out to distinguish PD from HC. Compared with HC, PD patients demonstrated decreased FOCA values in the right inferior temporal gyrus (ITG.R), right middle temporal gyrus (MTG.R), right middle occipital gyrus (MOG.R), right superior occipital gyrus, right inferior occipital gyrus, left precentral gyrus (PreCG.L), left postcentral gyrus (PoCG.L) and left rolandic operculum. The FOCA values in MTG.R and ITG.R were positively related to Montreal Cognitive Assessment (MoCA) values. Negative relationships had been found in FOCA values of PreCG.L and MOG.R and Unified Parkinson’s Disease Rating Scale (UPDRS) III scores. What’s more, the ROC analysis showed that the FOCA values of altered brain regions can be used to distinguish PD patients from HC with high performance. PD patients demonstrated disrupted local brain activity in several brain regions. These brain regions are mainly involved in motor, cognitive and emotional functions. The current study provides important insights into understanding the pathophysiological mechanism of PD symptoms. © 2023 SPIE. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Adversarial Network Pruning by Filter Robustness Estimation 48

Adversarial Network Pruning by Filter Robustness Estimation

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Zhuang, Xinlu Ge, Yunjie Zheng, Baolin Wang, Qian Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Hubei China Alibaba Group Beijing China

ISBN: (纸本)9781728163277

Network pruning has been extensively studied in model compression to reduce neural networks' memory, latency, and computation cost. However, the pruned networks still suffer from the threat posed by adversarial examples, limiting the broader application of the pruned networks in safety-critical applications. Previous studies maintain the robustness of the pruned networks by combining adversarial training and network pruning but ignore preserving the robustness at a high sparsity ratio in structured pruning. To address such a problem, we propose an effective filter importance criterion, Filter Robustness Estimation (FRE), to evaluate the importance of filters by estimating their contribution to the adversarial training loss. Empirical results show that our FRE-based Robustness-aware Filter Pruning (FRFP) outperforms the state-of-the-art methods by 12.19%∼37.01% of empirical robust accuracy on the CIFAR10 dataset with the VGG16 network at an extreme pruning ratio of 90%. © 2023 IEEE.

关键词： adversarial example adversarial training Neural network pruning structured pruning

来源：评论

学校读者我要写书评

暂无评论

Principled Design of Translation, Scale, and Rotation Invariant Variation Operators for Metaheuristics

引用

Chinese Journal of Electronics 2023年第1期32卷 111-129页

作者： TIAN Ye ZHANG Xingyi HE Cheng TAN Kay Chen JIN Yaochu Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Anhui University School of Artificial Intelligence Anhui University School of Electrical and Electronic Engineering Huazhong University of Science and Technology Department of Computing The Hong Kong Polytechnic University Faculty of Technology Bielefeld University

A large number of metaheuristics have been proposed and shown high performance in solving complex optimization problems. While most variation operators in existing metaheuristics are empirically designed,new operators are automatically designed in this work,which are expected to be search space independent and thus exhibit robust performance on different *** work first investigates the influence of translation invariance, scale invariance, and rotation invariance on the search behavior and performance of some representative operators. This work then deduces the generic form of translation, scale, and rotation invariant operators, and proposes a principled approach for the automated design of operators, which searches for high-performance operators based on the deduced generic form. The experimental results demonstrate that the operators generated by the proposed approach outperform state-of-the-art ones on a variety of problems with complex landscapes and up to 1000decision variables.

关键词： Deep learning Metaheuristics Reinforcement learning Benchmark testing Search problems Robustness Behavioral sciences

来源：评论

学校读者我要写书评

暂无评论

A RIS-Assisted Multiuser MIMO Communication Method Based on Deep Reinforcement Learning 7

A RIS-Assisted Multiuser MIMO Communication Method Based on ...

引用

7th International Conference on Communication and Information Systems, ICCIS 2023

作者： Tian, Changlin Zhi, Hui Tie, Kui Anhui University School of Electronic and Information Engineering Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Hefei China CO. Ltd Bengbu China

ISBN: (纸本)9798350330540

In this paper, a RIS-assisted multiuser MIMO communication method based on deep reinforcement learning (RMMC-DRL) is proposed for multiuser scenarios. Our objective is to find the optimal transmit beamforming matrix of BS and optimal phase shift matrix of reflective intelligent surface (RIS) to maximize the sum rate of multiuser, this problem is reduced into a constrained optimization problem. It is a non-convex optimization problem, so we solve it through deep reinforcement learning (DRL) and then use the results for communication. In the DRL, a deep deterministic policy gradient (DDPG) framework that can handle continuous states and actions is designed, reward is set as optimization goal, and the transmit beamforming matrix and the phase shift matrix of RIS are obtained through the interaction with environment. Unlike the alternating optimization (AO) method, which solve the transmit beamforming matrix and the RIS phase shift matrix alternatively, the RMMC-DRL can obtain both transmit beamforming matrix and RIS phase shift matrix simultaneously as the output of DRL. Simulation results show that RMMC-DRL can learn and improve its behavior by interacting with the environment. Compared with AO method, RMMC-DRL can obtain higher sum rate and lower computational complexity. © 2023 IEEE.

关键词： beamforming matrix deep reinforcement learning phase shift matrix reconfigurable intelligent surface

来源：评论

学校读者我要写书评

暂无评论

An epidermal electrode based triboelectric walking energy harvester for wearable wireless sensing applications

引用

Science China(Technological Sciences) 2024年第3期67卷 949-957页

作者： CHANG ShiYuan LIU FuHai CHEN JinKai XIA LianBin ZHOU Hao JIANG JingYang DONG Kang ZHANG ChenHao WU Yun CHEN Jin XUAN Weipeng SUN LingLing JIN Hao DONG ShuRong LUO JiKui Ministry of Education Key Laboratory of RF Circuits and Systems Hangzhou Dianzi UniversityHangzhou 310018China Special Equipment College Hangzhou Vocational&Technical CollegeHangzhou 310018China College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 330027China ZJU-Hangzhou Global Scientific and Technological Innovation Center Zhejiang UniversityHangzhou 311200China

Harvesting bio-kinetic energy using a triboelectric nanogenerator(TENG) is one of the promising routes to solve the sustainable energy supply problem for wearable electronics. However, additional materials, complex fabricating processes or specific mechanical structures are needed for existing TENGs to harvest bio-kinetic energy. Besides, they need to be tightly attached to the human body, which may result in detachment and malfunction under tense human motion. Herein, an intrinsic epidermal electrode-based TENG(E-TENG) is proposed to harvest human walking energy. The wearing shoes and ground are used as tribo-materials, and the human epidermis is used as the back electrode of the E-TENG. Compared with the traditional TENGs,the E-TENG does not need any additional tribo-materials and complex mechanical structures. Under optimal conditions, the voltage output of E-TENG can reach 914 V. E-TENG has been used as a self-powered warning sensor and pedometer sensor for demonstration. Furthermore, E-TENG based self-powered wireless sensor system has been developed using a newly designed micro energy electronic switch(MEES). Ambient ultraviolet intensity, temperature and humidity information can be monitored and then transmitted to mobile phone every 3.5 min, demonstrating great potential for widespread wearable applications.

关键词： triboelectric nanogenerator wearable wireless sensing self-powered

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Motion Feature Integration for Action Recognition 9

Multi-scale Motion Feature Integration for Action Recognitio...

引用

9th International Conference on Computer and Communications, ICCC 2023

作者： Lai, Jinming Zheng, Huicheng Dang, Jisheng Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing China Guangdong Province Key Laboratory of Information Security Technology China

ISBN: (纸本)9798350317251

Analyzing video data with intricate temporal structures and extracting comprehensive motion information remains a significant challenge. In this work, we introduce the multi-scale motion feature integration (MMFI) network, which leverages two key modules for motion analysis: the progressive local context aggregation (PLCA) module and the multi-scale motion excitation (MSME) module. The PLCA module captures frame-level motion details by incrementally processing frame-wise differences near the input frame in the early stages of the network. The MSME module provides motion-attentive channel weights in deeper layers with higher dimensions, incorporating short- and long-range segment-level motion information. These modules synergistically capture motion details across various scales. Our approach is evaluated on the large-scale video dataset Something-Something V1, yielding state-of-the-art performance with minimal computational overhead. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep Instruction Tuning for Segment Anything Model 24

Deep Instruction Tuning for Segment Anything Model

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Huang, Xiaorui Luo, Gen Zhu, Chaoyang Tong, Bo Zhou, Yiyi Sun, Xiaoshuai Ji, Rongrong Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Xiamen University Fujian Xiamen China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)9798400706868

Recently, Segment Anything Model (SAM) has become a research hotspot in the fields of multimedia and computer vision, which exhibits powerful yet versatile capabilities on various (un) conditional image segmentation tasks. Although SAM can support different types of segmentation prompts, we note that, compared to point- and box-guided segmentations, it performs much worse on text-instructed tasks, e.g., referring image segmentation (RIS). In this paper, we argue that deep text instruction tuning is key to mitigate such shortcoming caused by the shallow fusion scheme in its default light-weight mask decoder. To address this issue, we propose two simple yet effective deep instruction tuning (DIT) methods for SAM, one is end-to-end and the other is layer-wise. With minimal modifications, DITs can directly transform the image encoder of SAM as a stand-alone vision-language learner in contrast to building another deep fusion branch, maximizing the benefit of its superior segmentation capability. Extensive experiments on three highly competitive benchmark datasets of RIS show that a simple end-to-end DIT can improve SAM by a large margin, while the layer-wise DIT can further boost the performance to state-of-the-art with much less data and training expenditures. Our code is released at: https://***/wysnzzzz/DIT. © 2024 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Characteristics of catalytic destruction of dichloromethane and ethyl acetate mixture over H_(x)PO_(4)-RuO_(x)/CeO_(2) catalyst

引用

Journal of Environmental Sciences 2025年第2期148卷 336-349页

作者： Jiawen Chen Qingjie Meng Feng Bi Jingkun Chen Xiaole Weng Zhongbiao Wu Key Laboratory of Environment Remediation and Ecological Health Ministry of EducationCollege of Environmental and Resource SciencesZhejiang UniversityHangzhou 310058China School of Civil&Environmental Engineering and Geography Science Ningbo UniversityNingbo 315211China ZJU-Hangzhou Global Scientific and Technological Innovation Center Hangzhou 311200China Zhejiang Provincial Engineering Research Centre of Industrial Boiler&Furnace Flue Gas Pollution Control Hangzhou 310058China

Catalytic destruction is an ascendant technology for the abatement of volatile organic compounds(VOCs)originating fromsolvent-based industrial *** varied composition tends to influence each VOC’s catalytic behavior in the reaction *** investigated the catalytic destruction of multi-component VOCs including dichloromethane(DCM)and ethyl acetate(EA),as representatives from pharmaceutical waste gases,over co-supported HxPO_(4)-RuOx/CeO_(2) catalyst.A mutual inhibitory effect relating to concentrations because of competitive adsorption was verified in the binary VOCs oxidation and EA posed a more negative effect on DCM oxidation owing to EA’s superior adsorption *** adsorption of EA on acidic sites(HxPO_(4)/CeO_(2))promoted DCM activation on basic sites(O^(2−))and the dominating EA oxidation blocked DCM’s access to oxidation centers(RuOx/CeO_(2)),resulting in boosted monochloromethane yield and increased chlorine deposition for DCM *** impaired redox ability of Ru species owing to chlorine deposition in turn jeopardized deep oxidation of EA and its by-products,leading to increased gaseous by-products such as acetic acid originating fromEA ***,DCM at low concentration slightly promoted EA conversion at low temperatures with or without water,consistent with the enhanced EA adsorption in co-adsorption *** was mainly due to that DCM impeded the shielding effect of hydrolysate deposition from rapid EA hydrolysis depending on the decreased ***,water benefited EA hydrolysis but decreased CO_(2) selectivity while the generated water derived from EA was likely to affect DCM *** work may provide theoretical guidance for the promotion of applied catalysts toward industrial applications.

关键词： Catalytic destruction Multi-component VOCs Mixture effect Interaction mechanism

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：