检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yan, Qingsen Hu, Tao Sun, Yuan Tang, Hao Zhu, Yu Dong, Wei Van Gool, Luc Zhang, Yanning School of Computer Science Northwestern Polytechnical University China School of Computer Science Xi’an University of Architecture and Technology China School of Computer Science ETH Zurich Switzerland

High Dynamic Range (HDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. Despite the remarkable progress, DNN-based methods still generate ghosting artifacts when LDR images have saturation and large motion, which hinders potential applications in real-world scenarios. To address this challenge, we formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model’s condition, consisting of the feature condition generator and the noise predictor. Feature condition generator employs attention and Domain Feature Alignment (DFA) layer to transform the intermediate features to avoid ghosting artifacts. With the learned features as conditions, the noise predictor leverages a stochastic iterative denoising process for diffusion models to generate an HDR image by steering the sampling process. Furthermore, to mitigate semantic confusion caused by the saturation problem of LDR images, we design a sliding window noise estimator to sample smooth noise in a patch-based manner. In addition, an image space loss is proposed to avoid the color distortion of the estimated HDR results. We empirically evaluate our model on benchmark datasets for HDR imaging. The results demonstrate that our approach achieves state-of-the-art performances and well generalization to real-world images. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Affine-NoC: Multi-ring NoCs exploiting long physical links

Affine-NoC: Multi-ring NoCs exploiting long physical links

引用

International Workshop on Network on Chip architectures, NoCArc

作者： Enrique Vallejo Evangelos Mageiropoulos Nikolaos Chrysos Manolis G.H. Katevenis Computer Science Dept. Universidad de Cantabria Spain Santander Spain Computer Architecture and VLSI Systems (CARV) Laboratory Foundation for Research and Technology – Hellas (FORTH) Heraklion Greece

ISBN: (数字)9798331506421

ISBN: (纸本)9798331506438

Routerless multi-ring proposals are low-cost NoCs that employ multiple independent rings, avoiding any crossbars or arbitration mechanisms. Their complexity lies on the selection of the set of rings to connect all the nodes. Previous proposals result in unbalanced designs with high hop *** work introduces Affine-NoC, a balanced routerless NoC based on a novel arrangement of rings derived from the Affine Plane. Affine-NoC exploits express channels to connect distant processing elements, allowing for a completely balanced layout of the set of rings and a reduction in average distance and diameter without sacrificing bisection *** shows that Affine-NoC presents a balanced design with a low number of rings per node and reduced complexity, similar cost to previous proposals in terms of aggregated link length, while it simplifies the multiplex units and reduces the hop count. Simulation results show that Affine-NoC reduces hop count and average latency by 76% and 20.5% respectively compared to previous designs, it reduces deflections by 27% and avoids unfairness, making it a feasible alternative for multi-ring routerless NoCs.

关键词： Multiplexing Network topology Flow production systems Simulation Layout computer architecture Complexity theory Topology Proposals Logic

来源：评论

学校读者我要写书评

暂无评论

Tunable Multicolor Fluorescence of Perovskite-Based Composites for Optical Steganography and Light-Emitting Devices

引用

Research 2023年第1期2022卷 185-195页

作者： Kewei Ma Qingfeng Gui Cihui Liu Yunyi Yang Fangjian Xing Yunsong Di Xiaoming Wen Baohua Jia Zhixing Gan Center for Future Optoelectronic Functional Materials School of Computer and Electronic Information/School of Artificial IntelligenceNanjing Normal UniversityNanjing 210023China College of Naval Architecture and Ocean Engineering Jiangsu Maritime InstituteNanjing 211170China Centrefor Translational Atomaterials Schoolof ScienceSwinburne University of TechnologyJohn Street Hawthon VIC3122Australia School of Science RMIT UniversityMelbourne3000 VICAustralia College of Materials Science and Engineering Qingdao University of Science and TechnologyQingdao 266042China

Multicolor fluorescence of mixed halide perovskites enormously enables their applications in photonics and ***,it remains an arduous task to obtain multicolor emissions from perovskites containing single halogen to avoid phase ***,a fluorescent composite containing Eu-based metal-organic frameworks(MOFs),OD Cs PbBre,and 3D CsPbBrs is *** excitations at 365 nm and 254nm,the pristine composite emits blue(B)and red(R)fluorescence,which are ascribed to radiative defects within CsPbBr and 5Do→7F,transitions of Eu^(3+),***,after light soaking in the ambient environment,the blue fluorescence gradually converts into green(G)emission due to the defect repairing and 0D-3D phase *** permanent and unique photochromic effect enables anticounterfeiting and microsteganography with increased security through a micropatterning ***,the RGB luminescence is highly stable after encapsulation by a transparent polymer ***,trichromatic light-emitting modules are fabricated by using the fluorescent composites as color-converting layers,which almost fully cover the standard color ***,this work innovates a strategy for construction of tunable multicolor luminescence by manipulating the radiative defects and structural dimensionality.

关键词： composite composites perovskite

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based vehicle image detection using Yolo V5 with Region-Based Convolutional Neural Network 3

Deep Learning based vehicle image detection using Yolo V5 wi...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Rani, S. Swapna Mudigonda, Aditya Hemanth, S.V. Sundararajan Reddy, G. Vinoda Amirthayogam, G. Engineering College Department of Electronics and Communication Engineering Hyderabad India JNIAS School of Planning and Architecture Telangana Hyderabad500034 India Hyderabad Institute of Technology and Management Department of Computer Science and Engineering Telangana Hyderabad501401 India PSNA College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Dindigul624622 India Telangana Hyderabad501401 India Hindustan Institute of Technology and Science Department of Information Technology Tamilnadu Chennai603103 India

ISBN: (纸本)9798350372120

Detecting and classifying vehicles is a modern technology with numerous uses. Administration and regulation of traffic is one of the primary uses. Projects utilizing image processing to prevent traffic accidents heavily rely on vehicle monitoring and detection. Monitoring and recording human movement in surveillance situations require the ability to follow moving objects. Considering its significance, it provides a valuable image processing-based vehicle detection technique - a vehicle tracking and detection system based on images. The recently released high-resolution road vehicle dataset supports deep learning-based vehicle detection and monitoring on the Python platform. It includes over 100 well-defined pictures taken from movies from various locations. This data is produced using a range of image processing methods. The most recent iteration of the YOLO model, the v5 model, was employed for detection. R-CNN is additionally utilized for model detection. The four stages in the Region-Based Convolutional Neural Network (RCNN) process are preprocessing, segmentation, feature selection, and classification. The first step is identifying moving vehicles accurately. Preprocessing the original image is necessary. This enhances the image's quality, valuable information extracted, or unwanted areas cropped out. Segmentation is the second step. The region's borders are established, and the entire image is divided into numerous smaller areas using a threshold. The vehicle image's most pertinent aspects or characteristics (features) that aid in precise detection are found in the third stage, feature selection. A region-based convolutional neural network (RCNN) is employed to determine the categorization. The Yolov5 method can be used to identify and categorize items. The Region-based Convolutional Neural Network (RCNN) approach enhances accuracy and temporal complexity over current segmentation algorithms. © 2024 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Exploring 2D representation and transfer learning techniques for indoor localization

引用

Multimedia Tools and Applications 2025年 1-13页

作者： Kerdjidj, O. Himeur, Y. Atalla, S. Copiaco, A. Sohail, S.S. Amira, A. Fadli, F. Mansoor, W. Gawanmeh, A. Centre of Development of Advanced Techniques Algiers Algeria College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Department of Computer Science University of Sharjah Sharjah United Arab Emirates Institute of Artificial Intelligence De Montfort University Leicester United Kingdom School of Computing Science and Engineering VIT Bhopal University Kothri Kalan India Department of Architecture & Urban Planning Qatar University Doha2713 Qatar

Indoor localization (IL) plays a critical role in various applications, including asset tracking, emergency response, and indoor navigation. Traditional methods relying on one-dimensional (1D) representations of received signal strength indicator (RSSI) data often suffer from limitations such as low accuracy, environmental sensitivity, and susceptibility to interference. To overcome these challenges, this paper proposes Scalogram-Based Transfer Learning for Indoor Localization (STL-IL), a novel framework that significantly enhances localization performance. The proposed approach transforms 1D RSSI signals into two-dimensional (2D) representations using scalogram-based time-frequency analysis, coupled with advanced transfer learning (TL) techniques. By leveraging the scalogram method to generate image representations of the data and employing diverse wavelet types. Furthermore, pre-trained deep learning models, including GoogleNet and SqueezeNet, are utilized to achieve state-of-the-art performance. Experimental results demonstrate that the STL-IL system achieves remarkable accuracy levels of 95% and 96% for SqueezeNet and GoogleNet, respectively. The proposed framework not only improves localization accuracy but also enhances robustness in dynamic and challenging environments, making it a promising solution for real-world indoor localization applications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Cybersecurity Technique for Detection of Upcoming Cyber Attacks 8

Machine Learning based Cybersecurity Technique for Detection...

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Lakshmi, Kanchi Lohitha Shobana, S. Kumar, Bathula Prasanna Glory, K.B. Kumar, Bonda Kiran Rani, Sandya Vasireddy Venkatadri Institute of Technology Department of Computer Science and Engineering Guntur India R.M.K Engineering College Department of It India Kkr & Ksr Institute of Technology and Sciences Department of Computer Science and Engineering AP Guntur India Koneru Lakshmaiah Education Foundation Department of Engineering English Andhra Pradesh State Vaddeswaram522302 India Kl Deemed to Be University Kl School of Architecture Department of Architecture Guntur District Vaddeswaram522302 India St. Martin's Engineering College Dept. of It Telangana Secunderabad India

ISBN: (纸本)9798350396638

Cyberattacks are prevalent in the age of the Internet. Each year, both the quantity and severity of cybercrimes increase. Protection against cyber-attacks has become a primary responsibility, Significant in the internet society of today. However, providing cyber security is a highly difficult task that requires experience in the field of attacks and the ability to evaluate the possibility of threats. The continual evolution of cyberattacks is the biggest challenge in this industry. This article describes the significance of cyber security and enumerates the hazards that exist in the present digital environment. The statistics and evaluation of cyberattacks demonstrate the seriousness of these occurrences. Several sorts of cyber security threats are outlined, along with the machine learning approaches that may be used to detect these attacks. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

OntoBlock: a novel ontological-based and blockchain enabled spectrum sensing framework for detection of malicious users in cognitive radio internet of things (CR-IoT) networks

引用

International Journal of Information technology (Singapore) 2024年第6期16卷 3913-3921页

作者： Marriwala, Nikhil Kumar Shukla, Vinod Kumar Raju, Ayalapogu Ratna Panda, Sunita S, Suma Purad, Hemavati C. Electronics and Communication Engineering Department University Institute of Engineering and Technology Kurukshetra University Haryana Kurukshetra India Information Technology Head of Academics–School of Engineering Architecture Interior Design Amity University Dubai Dubai International Academic City Dubai United Arab Emirates Department of Computer Science and Engineering Mahatma Gandhi Institute of Technology Hyderabad India Department of Electrical Electronics and Communication Engineering GITAM School of Technology Bengaluru Campus Karnataka Bengaluru India CMR Technical Campus Hyderabad India Department of AIML BITM Karnataka Ballari India

CR-IoT networks can benefit from the idea of blockchain technology to achieve accurate decisions in order to provide very high-accuracy spectrum sensing in the network. It allows for multi-user cooperation as the sensing readings are being exchanged in the spectrum. It leads to security issues in CR-IoT networks. Thus, in order to increase the quality of decision-making in spectrum sensing, the given paper introduces an ontological framework with a blockchain-enabled system to detect malicious users in networks. The proposed framework first captures network packets from available Wi-Fi, followed by the creation of blocks with private, public, and hash keys. The keys are used to encode information about the nodes, such as confidential information and their location, data relative to users, their position where packets are delivered, etc. This is subsequently followed by the generation of network ontology, which includes parsing, computation of similarity, and reduction in clustered packets. Finally, the performance of the suggested mechanism is validated using a set of evaluation measures such as authentication rate, intrusion rate, average network throughput time consumption, and energy efficiency. As seen from the findings, it is evident that the proposed framework performs better than existing recent studies, thereby improving the performance of CR-IoT networks. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Blockchain Cognitive radio Internet of things (IoT) Ontology Spectrum sensing

来源：评论

学校读者我要写书评

暂无评论

Using AI-Enabled Divergence and Convergence Patterns as a Quantitative Artifact in Design Education

引用

Journal of Mechanical Design 2024年第3期146卷 032301-032301页

作者： Chiu, Matt Sim, Wang Lin Mun, Nigel Silva, Arlindo Architecture and Sustainable Design Singapore University of Technology and Design Singapore487372 Singapore Computer Science and Design Singapore University of Technology and Design Singapore487372 Singapore Engineering Product Development Singapore University of Technology and Design Singapore487372 Singapore

Design education has traditionally relied heavily on physical integration as it involves a lot of hands-on work, group critiques, and collaborative projects, but the COVID-19 pandemic has fundamentally shifted the way teaching is done, which resulted in many institutions adapting to remote teaching and learning environments. This has created challenges for design educators who have had to find ways to evaluate students' progress in the absence of in-person interactions. In this paper, we are proposing a dashboard visualization approach that helps educators monitor the progression of the entire class of students using artificial intelligence (AI) by tracking a time-based evolution of a design statement. This approach uses various natural language processing (NLP) models to produce stock-like charts, which represent students' and student groups' progression through a series of divergence and convergence phases. These charts become a form of design artifact that allows educator(s) to gain a bird's-eye view of the class and react to groups that may require assistance;at the same time, it becomes a qualitative means of evaluation and comparison across students and groups. Toward the end, this paper also showcases a web-based platform that is publicly available using such methodology, a case study that applied so methodology and recommendations of future works possible. Copyright © 2024 by ASME.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

SiamCircle: Trajectory Representation Learning in Free Settings 23rd

SiamCircle: Trajectory Representation Learning in Free Sett...

引用

23rd International Symposium on Intelligent Data Analysis, IDA 2025

作者： Nasri, Maedeh Baratchi, Mitra Koutamanis, Alexander Rieffe, Carolien Department of Developmental Psychology Leiden University Leiden Netherlands Leiden Institute of Advanced Computer Science Leiden University Leiden Netherlands Faculty of Architecture and the Built Environment Delft University of Technology Delft Netherlands Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands Department of Psychology and Human Development Institute of Education UCL London United Kingdom

ISBN: (纸本)9783031913976

Trajectory representation learning (TRL) is an intermediate step in handling trajectory data to realize various downstream machine-learning tasks. While most previous TRL research focuses on modeling structured movements in large-scale urban spaces (e.g., cars or pedestrians on streets), this paper focuses on a more challenging scenario of modeling free movement in small-scale social spaces (e.g., children playing in a schoolyard). We present a TRL model, SiamCircle, to process raw trajectories without additional feature extraction to prevent information loss. SiamCircle adopts a Siamese network with Circle Loss to learn trajectory embeddings. Furthermore, SiamCircle employs a data augmentation process to enable self-supervised learning and enrich the input data to address the limited access to high-quality data and ground truth. We evaluate the performance of SiamCircle in downstream tasks using trajectory ranking and clustering performance via seven evaluation metrics collectively. Using an ablation study, we explored the impact of different loss functions on the model’s performance. Accordingly, we selected a 2-D convolutional design with Circle Loss as the best-performing model. In a comparative study, we compared our model against three other baselines. We observed up to 19% improvements in trajectory ranking tasks and achieved the highest average rank in supervised clustering tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Sorting

来源：评论

学校读者我要写书评

暂无评论

Leveraging Ethical Narratives to Enhance LLM-AutoML Generated Machine Learning Models

引用

Expert Systems 2025年第7期42卷

作者： Nelson, Jordan Pavlidis, Michalis Fish, Andrew Polatidis, Nikolaos Manolopoulos, Yannis School of Architecture Technology and Engineering University of Brighton Brighton United Kingdom Department of Computer Science University of Liverpool Liverpool United Kingdom Department of Informatics University of Nicosia Nicosia Cyprus

The growing popularity of generative AI and large language models (LLMs) has sparked innovation alongside debate, particularly around issues of plagiarism and intellectual property law. However, a less-discussed concern is the quality of code generated by these models, which often contains errors and encourages poor programming practices. This paper proposes a novel solution by integrating LLMs with automated machine learning (AutoML). By leveraging AutoML's strengths in hyperparameter tuning and model selection, we present a framework for generating robust and reliable machine learning (ML) algorithms. Our approach incorporates natural language processing (NLP) and natural language understanding (NLU) techniques to interpret chatbot prompts, enabling more accurate and customisable ML model generation through AutoML. To ensure ethical AI practices, we have also introduced a filtering mechanism to address potential biases and enhance accountability. The proposed methodology not only demonstrates practical implementation but also achieves high predictive accuracy, offering a viable solution to current challenges in LLM-based code generation. In summary, this paper introduces a new application of NLP and NLU to extract features from chatbot prompts, feeding them into an AutoML system to generate ML algorithms. This approach is framed within a rigorous ethical framework, addressing concerns of bias and accountability while enhancing the reliability of code generation. © 2025 The Author(s). Expert Systems published by John Wiley & Sons Ltd.

关键词： Expert systems

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：