检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4026-4041页

作者： Zhu, Kun Zhang, Nana Ding, Weiping Jiang, Changjun the Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China Collaborative Innovation Center for Financial Network Security Tongji University Shanghai201804 China the School of Computer Science and Technology Donghua University Shanghai201620 China the School of Information Science and Technology Nantong University Nantong226019 China

Heterogeneous fraud detection is an important means of credit card security assurance, which can utilize historical transaction records in a source and target domain to build an effective fraud detection model. Nevertheless, large feature distribution differences between source and target transaction instances and the complex intrinsic structure hidden behind transaction data make it difficult for existing credit card fraud detection (CCFD) models to capture and transfer the most informative feature representations and seriously hinder detection performance. In this work, we propose a novel adaptive heterogeneous CCFD model named adaptive heterogeneous credit card fraud detection model based on deep reinforcement training subset selection (RTAHC) based on deep reinforcement training subset selection, which mainly contains two components: selection distribution generator (SDG) and transaction fraud detector (TFD, including feature extractor with an attention mechanism and classifier). The SDG can generate the selection probability distribution vector via the reinforcement reward mechanism, and then transaction instances in the source domain relevant to the target domain are selected. The feature extractor with an attention mechanism can learn the abstract deep semantic feature representations of selected source transaction instances and the target domain. The joint training of SDG and TFD can provide more real-time and accurate transaction feature representations to reduce the distribution discrepancy between the two domains. We verify the detection performance of RTAHC across a large real-world credit card transaction dataset and four public datasets. Experimental results demonstrate that the RTAHC model can exhibit competitive CCFD performance. Impact Statement—With the rise of artificial intelligence (AI)generated models, credit card fraud has become increasingly rampant, which also causes tens of billions of U.S. dollars in credit card losses worldwide every year

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

HWD-YOLO:A New Vision-Based Helmet Wearing Detection Method

引用

Computers, Materials & Continua 2024年第9期80卷 4543-4560页

作者： Licheng Sun Heping Li Liang Wang College of Information Science and Technology Beijing University of TechnologyBeijing100124China Chinese Institute of Coal Science Beijing100013China State Key Laboratory for Intelligent Coal Mining and Strata Control Beijing100013China Engineering Research Center of Digital Community of Ministry of Education Beijing100124China

It is crucial to ensure workers wear safety helmets when working at a workplace with a high risk of safety accidents,such as construction sites and mine *** existing methods can achieve helmet detection in images,their accuracy and speed still need improvements since complex,cluttered,and large-scale scenes of real workplaces cause server occlusion,illumination change,scale variation,and perspective ***,a new safety helmet-wearing detection method based on deep learning is ***,a new multi-scale contextual aggregation module is proposed to aggregate multi-scale feature information globally and highlight the details of concerned objects in the backbone part of the deep neural ***,a new detection block combining the dilate convolution and attention mechanism is proposed and introduced into the prediction *** block can effectively extract deep featureswhile retaining information on fine-grained details,such as edges and small ***,some newly emerged modules are incorporated into the proposed network to improve safety helmetwearing detection performance *** experiments on open dataset validate the proposed *** reaches better performance on helmet-wearing detection and even outperforms the state-of-the-art *** be more specific,the mAP increases by 3.4%,and the speed increases from17 to 33 fps in comparison with the baseline,You Only Look Once(YOLO)version 5X,and themean average precision increases by 1.0%and the speed increases by 7 fps in comparison with the YOLO version *** generalization ability and portability experiment results show that the proposed improvements could serve as a springboard for deep neural network design to improve object detection performance in complex scenarios.

关键词： Object detection deep learning safety helmet wearing detection feature extraction attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Deep learning enhanced quantum holography with undetected photons

引用

PhotoniX 2024年第1期5卷 54-66页

作者： Weiru Fan Gewei Qian Yutong Wang Chen-Ran Xu Ziyang Chen Xun Liu Wei Li Xu Liu Feng Liu Xingqi Xu Da-Wei Wang Vladislav V.Yakovlev Zhejiang Province Key Laboratory of Quantum Technology and Device School of Physicsand State Key Laboratory for Extreme Photonics and InstrumentationZhejiang UniversityHangzhou 310027Zhejiang ProvinceChina College of Information Science and Electronic Engineering Zhejiang UniversityHangzhou 310027Zhejiang ProvinceChina College of Information Science and Engineering Fujian Key Laboratory of Light Propagation and TransformationHuaqiao UniversityXiamen 361021Fujian ProvinceChina Beijing Institute of Space and Electricity China Academy of Space TechnologyBeijing 100094China College of Optical Science and Engineering Zhejiang UniversityHangzhou 310027Zhejiang ProvinceChina Hefei National Laboratory Hefei 230088Anhui provinceChina Department of Biomedical Engineering Texas A&M UniversityCollege Station 77843TXUSA

Holography is an essential technique of generating three-dimensional ***,quantum holography with undetected photons(QHUP)has emerged as a groundbreaking method capable of capturing complex amplitude *** its potential,the practical application of QHUP has been limited by susceptibility to phase disturbances,low interference visibility,and limited spatial *** learning,recognized for its ability in processing complex data,holds significant promise in addressing these *** this report,we present an ample advancement in QHUP achieved by harnessing the power of deep learning to extract images from single-shot holograms,resulting in vastly reduced noise and distortion,alongside a notable enhancement in spatial *** proposed and demonstrated deep learning QHUP(DL-QHUP)methodology offers a transformative solution by delivering high-speed imaging,improved spatial resolution,and superior noise resilience,making it suitable for diverse applications across an array of research fields stretching from biomedical imaging to remote ***-QHUP signifies a crucial leap forward in the realm of holography,demonstrating its immense potential to revolutionize imaging capabilities and pave the way for advancements in various scientific *** integration of DL-QHUP promises to unlock new possibilities in imaging applications,transcending existing limitations and offering unparalleled performance in challenging environments.

关键词： Quantum holography Computational imaging Undetected photons Deep learning

来源：评论

学校读者我要写书评

暂无评论

Effect of mouse skin autofluorescence on the measurement of photosensitizer fluorescence 14

Effect of mouse skin autofluorescence on the measurement of ...

引用

Optics in Health Care and Biomedical Optics XIV 2024

作者： Guo, Xingran Peng, Weijin Wei, Zhe Cui, Shengdong Zhan, Huiqi Ke, Cheng Huang, Zheng MOE Key Laboratory of Medical Optoelectronics Science and Technology Key Laboratory of Photonics Technology of Fujian Province School of Optoelectronics and Information Engineering Fujian Normal University Fuzhou China

ISBN: (纸本)9781510682122

Background: Mouse model is a unique tool for preclinical evaluation of photosensitizing drugs for their potential applications in photodynamic therapy (PDT). The fluorescent property of photosensitizer provides a useful means for in situ measurement of photosensitizer distribution. However, the autofluorescence of mouse tissues might potentially affect in situ photosensitizer fluorescence measurement. Objectives: The aim of this study was to evaluate the autofluorescence in lab mice and its influence on the in situ measurement of photosensitizer fluorescence. Materials and Materials and methods: ICR mice, commonly used lab animal model, were used. Mice were fed with regular diet and clean water. Domestically produced photosensitizing drug Hemoporfin® was used as a model sensitizer. Costume-built fluorescence imaging and spectroscope systems were used for fluorescence examination under the excitation wavelength of 400 ±5 nm, generated from a laser or LED panel. In situ fluorescence was examined before and after i.v. injection of Hemoporfin®. Results: Epifluorescence imaging examination showed yellowish and reddish autofluorescence fluorescence in the mouth, nose, paws and tail areas. The absorption and emission spectra of mouse tissue overlaid to some degrees with that of Hemoporfin®. In situ fluorescence examination of ICR mice showed significant influence of autofluorescence on the spectral and intensity measurement of Hemoporfin® fluorescence. Such influence might be eliminated by post-measurement spectral correction algorithms. Conclusions: The autofluorescence in mouse tissues poses a significant influence on the in situ measurement of fluorescence emission of Hemoporfin®. Careful post-measurement spectral correction is needed for accurately measuring photosensitizer fluorescence. © 2024 SPIE.

关键词： Tissue

来源：评论

学校读者我要写书评

暂无评论

Embedding Data in Bitcoin Transaction Values with Restricted Boltzmann Machine 2nd

Embedding Data in Bitcoin Transaction Values with Restrict...

引用

2nd International Conference on Data Security and Privacy Protection, DSPP 2024

作者： An, Jiayi Tian, Haibo Guangdong Province Key Laboratory of Information Security Technology School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (纸本)9789819785391

Constructing covert channels on blockchains has recently become a significant research focus. A major challenge lies in embedding data into blockchain transactions, while maintaining strong concealment. This study focuses on utilizing blockchain transaction values as a carrier, exploring methods to ensure that the distribution of values with embedded data mimics that of standard transactions. Initially, we gathered authentic blockchain transaction data, conducted a frequency analysis on the transaction values, and filtered out abnormal values to establish a baseline normal value dataset. Subsequently, we employed a Restricted Boltzmann Machine (RBM) to generate a simulated value dataset that mirrors the distribution of the normal dataset, facilitating the embedding of data within the simulated value dataset. By fine-tuning the number of bits embedded in the values, we achieved a value dataset with embedded data that closely resembles the normal distribution. We have calculated the Kullback-Leibler Divergence and the Kolmogorov-Smirnov Test between the value dataset with embedded data and the normal value dataset under various embedding scenarios, revealing that the changes to the original dataset are minimal. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Improving hole transfer of boron nitride quantum dots modified PDI for efficient photodegradation

引用

Frontiers of Chemical science and engineering 2023年第11期17卷 1718-1727页

作者： Shiqing Ma Chundong Peng Zeyu Jia Yanmei Feng Kai Chen Hao Ding Daimei Chen Zhong-Yong Yuan Engineering Research Center of Ministry of Education for Geological Carbon Storage and Low Carbon Utilization of Resources Beijing Key Laboratory of Materials Utilization of Nonmetallic Minerals and Solid WastesNational Laboratory of Mineral MaterialsSchool of Material Sciences and TechnologyChina University of GeosciencesBeijing 100083China School of Materials Science and Engineering Nankai UniversityTianjin 300350China Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Jiangsu Key Laboratory of Atmospheric Environment Monitoringand Pollution Control School of Environmental Science and EngineeringNanjing University of Information Science and TechnologyNanjing 210044China

In recent years,organic photocatalyst under visible-light absorption has shown significant potential for solving environmental ***,it is still a great challenge for constructing a highly active organic photocatalyst due to the low separation efficiency of photogenerated ***,an effective and robust photocatalyst perylene-3,4,9,10-tetracarboxylic diamide/boron nitride quantum dots(PDI/BNQDs),consisting of selfassemble PDI withπ–πstacking structure and BNQDs,has been constructed and researched under visible light *** PDI/BNQDs composite gradually increases organic pollutant photodegradation with the loading amount of *** 10 mL of BNQDs solution added(PDI/BNQDs-10),the organic pollutant photodegradation performance reaches a maximum,about 6.16 times higher with methylene blue and 1.68 times higher with ciprofloxacin than that of pure PDI *** enhancement is attributed to improved separation of photogenerated carriers from self-assembled PDI by BNQDs due to their preeminent ability to extract *** work is significant for the supplement of PDI supramolecular composite *** believe that this photocatalytic design is capable of expanding organic semiconductors’potential for their applications in photocatalysis.

关键词： PDI boron nitride quantum dots photocatalysis hole transfer

来源：评论

学校读者我要写书评

暂无评论

Self-supervised graph learning with target-adaptive masking for session-based recommendation

引用

Frontiers of information technology & Electronic engineering 2023年第1期24卷 73-87页

作者： Yitong WANG Fei CAI Zhiqiang PAN Chengyu SONG Science and Technology on Information Systems Engineering Laboratory National University of Defense TechnologyChangsha 410073China

Session-based recommendation aims to predict the next item based on a user’s limited interactions within a short *** approaches use mainly recurrent neural networks(RNNs)or graph neural networks(GNNs)to model the sequential patterns or the transition relationships between ***,such models either ignore the over-smoothing issue of GNNs,or directly use cross-entropy loss with a softmax layer for model optimization,which easily results in the over-fitting *** tackle the above issues,we propose a self-supervised graph learning with target-adaptive masking(SGL-TM)***,we first construct a global graph based on all involved sessions and subsequently capture the self-supervised signals from the global connections between items,which helps supervise the model in generating accurate representations of items in the ongoing *** that,we calculate the main supervised loss by comparing the ground truth with the predicted scores of items adjusted by our designed target-adaptive masking ***,we combine the main supervised component with the auxiliary self-supervision module to obtain the final loss for optimizing the model *** experimental results from two benchmark datasets,Gowalla and Diginetica,indicate that SGL-TM can outperform state-of-the-art baselines in terms of Recall@20 and MRR@20,especially in short sessions.

关键词： Session-based recommendation Self-supervised learning Graph neural networks Target-adaptive

来源：评论

学校读者我要写书评

暂无评论

A Flexible-Integrated Multimodal Hydrogel-Based Sensing Patch

引用

纳微快报（英文版） 2025年第7期17卷 107-125页

作者： Peng Wang Guoqing Wang Guifen Sun Chenchen Bao Yang Li Chuizhou Meng Zhao Yao School of Mechanical Engineering University of JinanJinan 250022People's Republic of China School of Information Science and Engineering University of JinanJinan 250022People's Republic of China State Key Laboratory for Reliability and Intelligence of Electrical Equipment Engineering Research Center of Ministry of Education for Intelligent Rehabilitation Device and Detection TechnologyHebei Key Laboratory of Smart Sensing and Human-Robot InteractionSchool of Mechanical EngineeringHebei University of TechnologyTianjin 300401People's Republic of China School of Information Science and Engineering University of JinanJinan 250022People's Republic of China School of Integrated Circuits Shandong UniversityJinan 250101People's Republic of China State Key Laboratory of Integrated Chips and Systems Fudan UniversityShanghai 200433People's Republic of China College of Electronics and Information Qingdao UniversityQingdao 266071People's Republic of China

Sleep monitoring is an impor-tant part of health management because sleep quality is crucial for restoration of human ***,current commercial prod-ucts of polysomnography are cumbersome with connecting wires and state-of-the-art flexible sensors are still interferential for being attached to the ***,we develop a flexible-integrated multimodal sensing patch based on hydrogel and its application in unconstraint sleep *** patch comprises a bottom hydrogel-based dual-mode pressure-temperature sensing layer and a top electrospun nanofiber-based non-contact detection layer as one integrated *** hydrogel as core substrate exhibits strong toughness and water retention,and the multimodal sensing of temperature,pressure,and non-contact proximity is realized based on different sensing mechanisms with no crosstalk *** multimodal sensing function is verified in a simulated real-world scenario by a robotic hand grasping objects to validate its *** multimodal sensing patches integrated on different locations of a pillow are assembled for intelligent sleep *** human-pillow interaction information as well as their evolution over time are acquired and analyzed by a one-dimensional convolutional neural *** of head movement and recognition of bad patterns that may lead to poor sleep are achieved,which provides a promising approach for sleep monitoring.

关键词： Multimodal sensing Proximity sensor Pressure sensor Temperature sensor Electrospun nanofibers

来源：评论

学校读者我要写书评

暂无评论

Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-Identification

引用

IEEE Internet of Things Journal 2025年第12期12卷 22381-22392页

作者： Pei, Jiangbo Jiang, Zhuqing Men, Aidong Wang, Haiying Luo, Haiyong Wen, Shiping Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing100876 China Beijing Key Laboratory of Network System and Network Culture China Chinese Academy of Sciences Institute of Computing Technology Beijing100190 China University of Technology Australian AI Institute Faculty of Engineering and Information Technology SydneyNSW2007 Australia

Single-camera-training person re-identification (SCT re-ID) aims to train a re-ID model using SCT datasets where each person appears in only one camera. The main challenge of SCT re-ID is to learn camera-invariant feature representations without cross-camera same-person (CCSP) data as supervision. Previous methods address it by assuming that the most similar person should be found in another camera. However, this assumption is not guaranteed to be correct. In this paper, we propose a novel solution: the Camera-Invariant Meta-Learning Network (CIMN) for SCT re-ID. CIMN operates under the premise that camera-invariant feature representations should remain robust despite changes in camera settings. To achieve this, we partition the training data into a meta-train set and a meta-test set based on camera IDs. We then conduct a cross-camera simulation using a meta-learning strategy, aiming to enforce the feature representations learned from the meta-train set to be robust when applied to the meta-test set. We further introduce three specific loss functions to leverage potential identity relations between the meta-train set and the meta-test set. Through the cross-camera simulation and the introduced loss functions, CIMN can extract feature representations that are both camera-invariant and identity-discriminative even in the absence of CCSP data. Our experimental results demonstrate that CIMN can extract feature representations that are both camera-invariant and identity-discriminative, even in the absence of CCSP data. our method achieves comparable performance with and without the use of CCSP data, and outperforms state-of-the-art methods on three SCT re-ID benchmarks. © 2014 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Laser polishing of a high-entropy alloy manufactured by selective laser melting

引用

Frontiers of Mechanical engineering 2024年第5期19卷 73-86页

作者： Xiaojun TAN Haibing XIAO Zihong WANG Wei ZHANG Zhijuan SUN Xuyun PENG Zhongmin LIU Liang GUO Qingmao ZHANG Intelligent Manufacturing and Equipment School Shenzhen Institute of Information TechnologyShenzhen 518172China Sino-German Intelligent Manufacturing School Shenzhen City PolytechnicShenzhen 518116China Guangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices School of Information and Optoelectronic Science and EngineeringSouth China Normal UniversityGuangzhou 510006China Guangdong Provincial Key Laboratory of Industrial Ultrashort Pulse Laser Technology Shenzhen 518055China College of Materials Science and Engineering Chongqing UniversityChongqing 400045China

The selective laser melting(SLM)technique applied to high-entropy alloys(HEAs)has attracted considerable attention in recent ***,its practical application has been restricted by poor surface *** this study,the capability of laser polishing on the rough surface of a Co-free HEA fabricated using SLM was *** show that the initial SLM-manufactured(as-SLMed)surface of the Co-free HEA,with a roughness exceeding 3.0μm,could be refined to less than 0.5μm by laser ***,the microstructure,microhardness,and wear resistance of the laser-polished(LP-ed)zone were *** indicate that compared with the microhardness and wear resistance of the as-SLMed layer,those of the LP-ed layer decreased by 4%and 11%,respectively,because of the increase in grain size and reduction of the BCC *** study shows that laser polishing has an excellent application prospect in surface improvement of HEAs manufactured by SLM.

关键词： laser polishing selective laser melting high-entropy alloy surface roughness mechanical performance

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：