检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Yizhang Zhou, Weiwei Li, Yanping Zhao, Shengjie School of Software Engineering Tongji University Shanghai China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Technology Tongji University Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

ISBN: (纸本)9798400706868

Correspondence pruning has recently drawn considerable attention as a crucial step in image matching. Existing methods typically achieve this by constructing neighborhoods for each feature point and imposing neighborhood consistency. However, the nearest-neighbor matching strategy often results in numerous many-to-one correspondences, thereby reducing the reliability of neighborhood information. Furthermore, the smoothness constraint fails in cases of large-scale rotations, leading to misjudgments. To address the above issues, this paper proposes a novel robust correspondence pruning method termed RoSe, which is based on rotation-invariant sequence-aware consensus. We formulate the correspondence pruning problem as a mathematical optimization problem and derive a closed-form solution. Specifically, we devise a rectified local neighborhood construction strategy that effectively enlarges the distribution between inliers and outliers. Meanwhile, to accommodate large-scale rotation, we propose a relative sequence-aware consistency as an alternative to existing smoothness constraints, which can better characterize the topological structure of inliers. Experimental results on image matching and registration tasks demonstrate the effectiveness of our method. Robustness analysis involving diverse feature descriptors and varying rotation degrees further showcases the efficacy of our method. © 2024 ACM.

关键词： correspondence pruning

来源：评论

学校读者我要写书评

暂无评论

Selective and Adaptive Incremental Transfer Learning with Multiple Datasets for Machine Fault Diagnosis

引用

computers, Materials & Continua 2024年第1期78卷 1363-1379页

作者： Kwok Tai Chui Brij B.Gupta Varsha Arya Miguel Torres-Ruiz School of Science and Technology Hong Kong Metropolitan UniversityHong Kong999077China Department of Computer Science and Information Engineering Asia UniversityTaichung41354Taiwan Center for Advanced Information Technology Kyung Hee UniversitySeoul02447Korea Symbiosis Centre for Information Technology Symbiosis International UniversityPuneMaharashtra411042India Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon School of Computing Skyline University CollegeSharjah1797United Arab Emirates Department of Business Administration Asia UniversityTaichung41354Taiwan Center for Interdisciplinary Research University of Petroleum and Energy StudiesDehradun248007India Department of Computer Science&Engineering Chandigarh UniversityChandigarh160036India Centro de Investigación en Computación Instituto Politécnico NacionalUPALM-ZacatencoMexico City07320Mexico

The visions of Industry 4.0 and 5.0 have reinforced the industrial *** have also made artificial intelligence incorporated as a major *** machine faults has become a solid foundation for automatically recognizing machine failure,and thus timely maintenance can ensure safe *** learning is a promising solution that can enhance the machine fault diagnosis model by borrowing pre-trained knowledge from the source model and applying it to the target model,which typically involves two *** response to the availability of multiple datasets,this paper proposes using selective and adaptive incremental transfer learning(SA-ITL),which fuses three algorithms,namely,the hybrid selective algorithm,the transferability enhancement algorithm,and the incremental transfer learning *** is a selective algorithm that enables selecting and ordering appropriate datasets for transfer learning and selecting useful knowledge to avoid negative *** algorithm also adaptively adjusts the portion of training data to balance the learning rate and training *** proposed algorithm is evaluated and analyzed using ten benchmark *** with other algorithms from existing works,SA-ITL improves the accuracy of all *** studies present the accuracy enhancements of the SA-ITL,including the hybrid selective algorithm(1.22%-3.82%),transferability enhancement algorithm(1.91%-4.15%),and incremental transfer learning algorithm(0.605%-2.68%).These also show the benefits of enhancing the target model with heterogeneous image datasets that widen the range of domain selection between source and target domains.

关键词： Deep learning incremental learning machine fault diagnosis negative transfer transfer learning

来源：评论

学校读者我要写书评

暂无评论

Efficiency and Precision: Control Systems Empowered by Smart Image Processing 3

Efficiency and Precision: Control Systems Empowered by Smart...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Sreenivasulu, Gunji Padmavathi, T. Nirisha, Anagandula Prakash, Dudi Bhanu Oudah, Mohammed Yousif Saikumar, K. Madanapalle Institute of Technology & Science Department of Computer Science & Engineering Madanapalle India Cvr College of Engineering Department of Ece India Mlr Institute of Technology Department of Computer Science and Information Technology Telangana Hyderabad India Cvr College of Engineering Department of Ece Hyderabad India Al-Ayen University Scientific Research Center Thi-Qar64001 Iraq School of Engineering Malla Reddy University Computer Science Telangana Hyderabad500100 India

ISBN: (纸本)9798350319125

The rapid increase in the population has resulted in traffic jams on the roads. There was a corresponding increase in the number of calls for emergency services, such as ambulances, police cars, and fire trucks. Maintaining rapid response times for emergency vehicles is critical right now. In this study, we present a smart traffic control system that integrates Internet of Things (IoT) chips into traffic signals and modifies their timing parameters. These chips will function in response to a road's estimated automobile count and the subsequent need for emergency vehicles along that route. The number of people in each automobile is going to be calculated using digital image analysis of the live camera feed. To make sure emergency vehicles get the help they require, GPS systems are going to be utilized to track the vehicles and update the chips with their current locations. It is envisioned that traffic lights on a road network will function by dynamically assigning weights for a particular node or the time among two consecutive lights. In order to maintain track of each node in the network, the weights assigned to each one must be updated in real-time. © 2023 IEEE.

关键词： Digital Image Processing Dijkstra's Algorithm Internet of things Smart Cities Transportation

来源：评论

学校读者我要写书评

暂无评论

Spectral period doubling and encoding of dissipative optical solitons via gain control

引用

PhotoniX 2024年第1期5卷 290-305页

作者： Kangwen Yang Yi Zhou Yuqing Ling Kevin K.Tsia Heping Zeng Kenneth K.Y.Wong Shanghai Key Laboratory of Modern Optical System and Engineering Research Center of Optical Instrument and SystemMinistry of EducationSchool of Optical Electrical and Computer EngineeringUniversity of Shanghai for Science and TechnologyShanghai 200093China Department of Electrical and Electronic Engineering The University of Hong KongHong KongChina Advanced Biomedical Instrumentation Centre Hong Kong Science ParkHong KongChina State Key Laboratory of Precision Spectroscopy East China Normal UniversityShanghai 200062China

Period-doubling bifurcation,as an intermediate state between order and chaos,is ubiquitous in all disciplines of nonlinear ***,previous experimental observations of period doubling in ultrafast fiber lasers are mainly restricted to self-sustained steady state,controllable manipulation and dynamic switching between period doubling and other intriguing dynamical states are still largely ***,we propose to expand the vision of dissipative soliton periodic doubling,which we illustrate experimentally by reporting original spontaneous,collisional,and controllable spectral period doubling in a polarization-maintaining ultrafast fiber ***,the spontaneous period doubling can be observed in both single-and *** mechanism of the switchable state and periodic doubling was revealed by numerical ***,state transformation of individual solitons can be resolved during the collision of triple solitons involving stationary,oscillating,and period ***,controllable deterministic switching between period doubling and other dynamical states,as well as exemplifying the application of period-doubling-based digital encoding,is achieved under programmable pump *** results open a new window for unveiling complex Hopf bifurcation in dissipative systems and bring useful insights into nonlinear science and applications.

关键词： Period doubling Mode locking Ultrafast fiber lasers

来源：评论

学校读者我要写书评

暂无评论

Characterizing Memory Access Patterns of Various Convolutional Neural Networks for Utilizing Processing-in-Memory

Characterizing Memory Access Patterns of Various Convolution...

引用

2023 International Conference on Electronics, Information, and Communication, ICEIC 2023

作者： Jang, Jihoon Kim, Hyun Lee, Hyokeun Research Center for Electrical and Information Technology Seoul National University of Science and Technology Department of Electrical and Information Engineering Seoul Korea Republic of Inter-University Semiconductor Research Center Seoul National University Department of Electrical and Computer Engineering Seoul Korea Republic of

ISBN: (纸本)9798350320213

Convolutional neural network (CNN) models require deeper networks and more training data for better performance, which in turn results in greater computational and memory requirements. In this paper, we analyze the memory access patterns that occur in main memory during the training processes of various CNN models. CNN training is a linear procedure consisting of a forward pass (FP) and a backward pass (BP). As a result of the analysis, we found that BP accounted for 83.4% of the total main memory accesses on average. Therefore, CNN training including FP and BP is much more memory-intensive than CNN inference using only FP. This demonstrates that CNN training is a suitable application for near-data processing to reduce memory bottlenecks and conserve computational resources. © 2023 IEEE.

关键词： Convolutional Neural Networks Memory access pattern Near data processing Network training Processing-in-Memory

来源：评论

学校读者我要写书评

暂无评论

Predictive modeling of MXene-based solar absorbers using a deep neural network

引用

Journal of the Optical Society of America B: Optical Physics 2025年第4期42卷 763-772页

作者： Waseer, Waleed Iqbal Baqir, Muhammad Abuzar Saqlain, Muhammad Mughal, Muhammad Junaid Khan, Shujaat School of Physics State Key Laboratory of Electronic Thin Films and Integrated Devices University of Electronic Science and Technology of China Chengdu China Department of Electrical Engineering COMSATS University Islamabad Sahiwal57000 Pakistan Department of Electrical and Computer Engineering COMSATS University Islamabad Islamabad45550 Pakistan Department of Computer Engineering College of Computing and Mathematics King Fahd University of Petroleum & Minerals Dhahran31261 Saudi Arabia SDAIA-KFUPM Joint Research Center for Artificial Intelligence King Fahd University of Petroleum & Minerals Dhahran31261 Saudi Arabia

Nanophotonic structures, such as photonic crystals, plasmonic nanostructures, and metamaterials, present transformative potential in advancing optical devices through innovative design capabilities. Among these, metamaterials—specifically metal–insulator–metal (MIM)-based absorbers—stand out for their ability to achieve high electromagnetic wave absorption across designated frequencies, proving valuable in applications ranging from solar cells to sensors. This study focuses on designing a high-efficiency MXene–SiO2–silver MIM metasurface absorber, leveraging deep learning techniques to streamline and enhance the simulation process traditionally reliant on finite-difference time-domain (FDTD) or finite-element methods (FEMs). By utilizing a deformable convolutional neural network (CNN), the proposed model predicts absorption spectra from metasurface geometries with superior accuracy and reduced computational demand while achieving dynamic spatial transformation handling. The model’s accuracy is further elucidated through Gradient-weighted Class Activation Mapping (Grad-CAM), which provides insights into the absorber’s most influential regions, supporting targeted optimization for specific applications. This deep learning approach demonstrates significant advantages over conventional methods in efficiency and adaptability, advancing the development of high-performance nanophotonic devices. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

UltraSegNet:A Hybrid Deep Learning Framework for Enhanced Breast Cancer Segmentation and Classification on Ultrasound Images

引用

computers, Materials & Continua 2025年第5期83卷 3303-3333页

作者： Suhaila Abuowaida Hamza Abu Owida Deema Mohammed Alsekait Nawaf Alshdaifat Diaa Salama Abd Elminaam Mohammad Alshinwan Department of Computer Science Faculty of Prince Al-Hussein Bin Abdallah II for Information TechnologyAl Al-Bayt UniversityMafraq25113Jordan Medical Engineering Department Faculty of EngineeringAl-Ahliyya Amman UniversityAmman19328Jordan Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Faculty of Computers Science Misr International UniversityCairo11800Egypt Jadara Research Center Jadara UniversityIrbid21110Jordan

Segmenting a breast ultrasound image is still challenging due to the presence of speckle noise,dependency on the operator,and the variation of image *** paper presents the UltraSegNet architecture that addresses these challenges through three key technical innovations:This work adds three things:(1)a changed ResNet-50 backbone with sequential 3×3 convolutions to keep fine anatomical details that are needed for finding lesion boundaries;(2)a computationally efficient regional attention mechanism that works on high-resolution features without using a transformer’s extra memory;and(3)an adaptive feature fusion strategy that changes local and global featuresbasedonhowthe image isbeing *** evaluation on two distinct datasets demonstrates UltraSegNet’s superior performance:On the BUSI dataset,it obtains a precision of 0.915,a recall of 0.908,and an F1 score of *** the UDAIT dataset,it achieves robust performance across the board,with a precision of 0.901 and recall of ***,these improvements are achieved at clinically feasible computation times,taking 235 ms per image on standard GPU ***,UltraSegNet does amazingly well on difficult small lesions(less than 10 mm),achieving a detection accuracy of *** is a huge improvement over traditional methods that have a hard time with small-scale features,as standard models can only achieve 0.63–0.71 *** improvement in small lesion detection is particularly crucial for early-stage breast cancer *** from this work demonstrate that UltraSegNet can be practically deployable in clinical workflows to improve breast cancer screening accuracy.

关键词： Breast cancer ultrasound image segmentation classification deep learning

来源：评论

学校读者我要写书评

暂无评论

UCR-SSL: Uncertainty-Based Consistency Regularization for Semi-Supervised Learning

UCR-SSL: Uncertainty-Based Consistency Regularization for Se...

引用

2023 International Conference on Electronics, Information, and Communication, ICEIC 2023

作者： Lee, Seungil Kim, Hyun Chun, Dayoung Seoul National University of Science and Technology Research Center for Electrical and Information Technology Department of Electrical and Information Engineering Seoul Korea Republic of Seoul National University Inter-University Semiconductor Research Center Department of Electrical and Computer Engineering Seoul Korea Republic of

ISBN: (纸本)9798350320213

Recently, semi-supervised learning methods are being actively developed to increase the performance of neural networks by using large amounts of unlabeled data. Among these techniques, pseudo-labeling methods have the advantage of low computational complexity, but are vulnerable to missing annotations. To solve this problem, we propose a method called uncertainty-based consistency regularization (UCR). UCR models a detection head to obtain different outputs for input images and computes a feature map of each. Subsequently, these feature maps are matched with the original and filtered ground truth (GT), and are classified as positive and negative samples, respectively. In this process, missing samples are generated by the filtered GT;therefore, we use a specialized loss function designed to reduce the logit difference of the samples for robustness against missing annotations. We also use the uncertainty extracted through Gaussian modeling as a criterion for annotation filtering to train the network to focus on reliable results. As a result of experiments with an SSD model on the Pascal VOC dataset, the proposed approach achieved an improvement of 0.7% in terms of mAP compared to a baseline method. © 2023 IEEE.

关键词： Consistency Regularization Convolutional Neural Network Semi-Supervised Object Detection Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Liveness Detection Using Handcrafted Feature Descriptors and Neural Network 11

Fingerprint Liveness Detection Using Handcrafted Feature Des...

引用

11th IEEE Global Conference on Consumer Electronics, GCCE 2022

作者： Chen, Zhi-Sheng Pulungan, Reza Li, Yung-Hui Raswa, Farchan Hakim Harjoko, Agus Wang, Jia-Ching Kinarta, Indra Yusuf Lee, Chung-Ting Providence University Department of Computer Science and Information Engineering Taiwan Universitas Gadjah Mada Department of Computer Science and Electronics Indonesia AI Research Center Hon Hai Research Institute Taiwan National Central University Department of Computer Science and Information Engineering Taiwan

ISBN: (纸本)9781665492324

Fingerprint recognition is commonly used to verify a user's identity. However, the fingerprint recognition systems in use today can be vulnerable to attacks. For example, some artificial fingerprints can spoof fingerprint recognition systems and use identity information to obtain personal information. For security reasons, fingerprint liveness detectors should be robust to attacks using various materials. As a result, we propose a fingerprint recognition method that uses multi-radius local binary pattern (Multi-radius LBP) and local phase quantization (LPQ) as local texture descriptors and wavelet transforms to remove noise. Classification results are obtained using a multi-layer perceptron (MLP) classifier. This study confirms that the proposed method is useful to improve the average fingerprint liveness detection tasks. On LivDet 2015 dataset, the proposed method achieves 6.73% Average Error Rate(AER). © 2022 IEEE.

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Security Analysis of IoT Networks using Diffusion Kernel Spike Attention Network with Atomic Optimization based Intrusion Detection System 5

Security Analysis of IoT Networks using Diffusion Kernel Spi...

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Sharma, Manju Sharma, Monika Lavanya Sharma, Pramod Gurpur, Shashikala Taqui, Syed Noeman University Institute of Engineering and Technology Maharshi Dayanand University Department of Computer Science and Engineering Haryana Rohtak124001 India The Technological Institute of Textile and Sciences Department of Computer Engineering Haryana Bhiwani127021 India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Viruthunagar626126 India University of Technology School of Engineering & Technology Rajasthan Jaipur303903 India Viman Nagar Maharashtra Pune411014 India Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Vlsi Microelectronics Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350389609

Recently, the most prominent study areas are Internet of Things (IoT) and its applications. The attributes of the Internet of Things (IoT) facilitate its practical uses in real life, but also leave it vulnerable to online attacks. Numerous IoT nodes gather, store, and handle personal data, making them a prime target for hackers. The main objective of a network intrusion detection system is to find network intrusions, which is essential to guaranteeing the Internet of Things' security. Numerous investigators have tackled this issue and have put out numerous intrusion detection methods. Cyberattack subcategories are hard to identify and performance improvement is a challenge for the existing system. This research project introduces a new method for security analysis in Internet of Things networks by creating the Diffusion Kernel Spike Attention Network with Atomic Optimization (DifK-SAN+AO). This research employs a Diffusion Kernel Spike Attention Network to counteract cyberthreats and provides an overall threat analysis of the Internet of Things. The classification of threat and normal patterns on an IoT network is the main topic of this research study. For every form of attack, the proposed model shows promising findings. We use empirically based, simulation-generated datasets (ToN-IoT, BoT-IoT, and CIC-IoT-23 datasets) to detect attacks directed on the IoT ecosystem. In order to perform a security analysis, the results can be compared using the security metrics that are calculated, including the accuracy, precision, recall, and F1-score factors. The experimental results are more reliable than current algorithms and show 99.2% accuracy in detecting a variety of threats. As it would be observed from the results of the simulations, this demonstrates how efficient our method is in assessing the impacts of the attacks in IoT networks and maintaining good performance values. © 2024 IEEE.

关键词： Network intrusion

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：