检索结果-内蒙古大学图书馆

CLIP-Flow:Decoding images encoded in CLIP space

Computational Visual Media 2024年第6期10卷 1157-1168页

作者： Hao Ma Ming Li Jingyuan Yang Or Patashnik Dani Lischinski Daniel Cohen-Or Hui Huang Visual Computing Research Center College of Computer Science and Software EngineeringShenzhen UniversityShenzhen 518060China Department of Computer Science Tel Aviv UniversityTel Aviv 6997801Israel School of Computer Science and Engineering the Hebrew University of JerusalemJerusalem 91904Israel

This study introduces CLIP-Flow,a novel network for generating images from a given image or *** effectively utilize the rich semantics contained in both modalities,we designed a semantics-guided methodology for image-and text-to-image *** particular,we adopted Contrastive Language-Image Pretraining(CLIP)as an encoder to extract semantics and StyleGAN as a decoder to generate images from such ***,to bridge the embedding space of CLIP and latent space of StyleGAN,real NVP is employed and modified with activation normalization and invertible *** the images and text in CLIP share the same representation space,text prompts can be fed directly into CLIP-Flow to achieve text-to-image *** conducted extensive experiments on several datasets to validate the effectiveness of the proposed image-to-image synthesis *** addition,we tested on the public dataset Multi-Modal CelebA-HQ,for text-to-image *** validated that our approach can generate high-quality text-matching images,and is comparable with state-of-the-art methods,both qualitatively and quantitatively.

关键词： image-to-image text-to-image contrastive language-image pretraining(CLIP) flow StyleGAN

来源：评论

学校读者我要写书评

暂无评论

Crowd dynamics analysis and behavior recognition in surveillance videos based on deep learning

引用

Multimedia Tools and Applications 2024年 1-35页

作者： Ilyas, Anum Bawany, Narmeen Center for Computing Research Department of Computer Science and Software Engineering Jinnah University for Women Karachi Pakistan

Video surveillance is widely adopted across various sectors for purposes such as law enforcement, COVID-19 isolation monitoring, and analyzing crowds for potential threats like flash mobs or violence. The vast amount of data generated daily from surveillance devices holds significant potential but requires effective analysis to extract value. Detecting anomalous crowd behavior, which can lead to chaos and casualties, is particularly challenging in video surveillance due to its labor-intensive nature and susceptibility to errors. To address these challenges, this research contributes in two key areas: first, by creating a diverse and representative video dataset that accurately reflects real-world crowd dynamics across eight different categories;second, by developing a reliable framework, ‘CRAB-NET,’ for automated behavior recognition. Extensive experimentation and evaluation, using Convolutional Long Short-Term Memory networks (ConvLSTM) and Long-Term Recurrent Convolutional Networks (LRCN), validated the effectiveness of the proposed approach in accurately categorizing behaviors observed in surveillance videos. The employed models were able to achieve the accuracy score of 99.46% for celebratory crowd, 99.98% for formal crowd and 96.69% for violent crowd. The demonstrated accuracy of 97.20% for comprehensive dataset achieved by the LRCN underscores its potential to revolutionize crowd behavior analysis. It ensures safer mass gatherings and more effective security interventions. Incorporating AI-powered crowd behavior recognition like ‘CRAB-NET’ into security measures not only safeguards public gatherings but also paves the way for proactive event management and predictive safety strategies. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Shellfish

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Head and Neck Tumors Using Dual PET/CT Imaging:Comparative Analysis of 2D,2.5D,and 3D Approaches Using UNet Transformer

引用

computer Modeling in engineering & sciences 2024年第12期141卷 2351-2373页

作者： Mohammed A.Mahdi Shahanawaj Ahamad Sawsan A.Saad Alaa Dafhalla Alawi Alqushaibi Rizwan Qureshi Information and Computer Science Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Software Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Computer Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Department of Computer and Information Sciences Universiti Teknologi PetronasSeri Iskandar32610Malaysia Center for Research in Computer Vision(CRCV) University of Central FloridaOrlandoFL 32816USA

The segmentation of head and neck(H&N)tumors in dual Positron Emission Tomography/Computed Tomogra-phy(PET/CT)imaging is a critical task in medical imaging,providing essential information for diagnosis,treatment planning,and outcome *** by the need for more accurate and robust segmentation methods,this study addresses key research gaps in the application of deep learning techniques to multimodal medical ***,it investigates the limitations of existing 2D and 3D models in capturing complex tumor structures and proposes an innovative 2.5D UNet Transformer model as a *** primary research questions guiding this study are:(1)How can the integration of convolutional neural networks(CNNs)and transformer networks enhance segmentation accuracy in dual PET/CT imaging?(2)What are the comparative advantages of 2D,2.5D,and 3D model configurations in this context?To answer these questions,we aimed to develop and evaluate advanced deep-learning models that leverage the strengths of both CNNs and *** proposed methodology involved a comprehensive preprocessing pipeline,including normalization,contrast enhancement,and resampling,followed by segmentation using 2D,2.5D,and 3D UNet Transformer *** models were trained and tested on three diverse datasets:HeckTor2022,AutoPET2023,and *** was assessed using metrics such as Dice Similarity Coefficient,Jaccard Index,Average Surface Distance(ASD),and Relative Absolute Volume Difference(RAVD).The findings demonstrate that the 2.5D UNet Transformer model consistently outperformed the 2D and 3D models across most metrics,achieving the highest Dice and Jaccard values,indicating superior segmentation *** instance,on the HeckTor2022 dataset,the 2.5D model achieved a Dice score of 81.777 and a Jaccard index of 0.705,surpassing other model *** 3D model showed strong boundary delineation performance but exhibited variability across datasets,while the

关键词： PET/CT imaging tumor segmentation weighted fusion transformer multi-modal imaging deep learning neural networks clinical oncology

来源：评论

学校读者我要写书评

暂无评论

Adaptive Resource Planning for AI Workloads with Variable Real-Time Tasks

引用

computers, Materials & Continua 2023年第3期74卷 6823-6833页

作者： Sunhwa Annie Nam Kyungwoon Cho Hyokyung Bahn Department of Computer Science and Engineering Ewha UniversitySeoul03760Korea Embedded Software Research Center Ewha UniversitySeoul03760Korea

AI(Artificial Intelligence)workloads are proliferating in modernreal-time *** the tasks of AI workloads fluctuate over time,resourceplanning policies used for traditional fixed real-time tasks should be *** particular,it is difficult to immediately handle changes inreal-time tasks without violating the deadline *** cope with thissituation,this paper analyzes the task situations of AI workloads and findsthe following two ***,resource planning for AI workloadsis a complicated search problem that requires much time for ***,although the task set of an AI workload may change over time,thepossible combinations of the task sets are known in *** on theseobservations,this paper proposes a new resource planning scheme for AIworkloads that supports the re-planning of *** of generatingresource plans on the fly,the proposed scheme pre-determines resourceplans for various combinations of ***,in any case,the workload isimmediately executed according to the resource plan ***,the proposed scheme maintains an optimized CPU(Central Processing Unit)and memory resource plan using genetic algorithms and applies it as soonas the workload *** proposed scheme is implemented in the opensourcesimulator SimRTS for the validation of its *** show that the proposed scheme reduces the energy consumptionof CPU and memory by 45.5%on average without deadline misses.

关键词： Resource planning artificial intelligence real-time system task scheduling optimization problem genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Accurate threat hunting in industrial internet of things edge devices

引用

Digital Communications and Networks 2023年第5期9卷 1123-1130页

作者： Abbas Yazdinejad Behrouz Zolfaghari Ali Dehghantanha Hadis Karimipour Gautam Srivastava Reza M.Parizi Cyber Science Lab School of Computer ScienceUniversity of GuelphOntarioCanada Department of Electrical and Software Engineering University of CalgaryAlbertaCanada Department of Mathematics and Computer Science Brandon UniversityBrandonCanada College of Computing and Software Engineering Kennesaw State UniversityGAUSA Research Center for Interneural Computing China Medical UniversityTaichungTaiwanChina Department of Computer Science and Mathematics Lebanese American UniversityBeirut1102Lebanon

Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and *** kind of malicious or abnormal function by each of these devices can jeopardize the security of the entire ***,they can allow malicious software installed on end nodes to penetrate the *** paper presents a parallel ensemble model for threat hunting based on anomalies in the behavior of IIoT edge *** proposed model is flexible enough to use several state-of-the-art classifiers as the basic learner and efficiently classifies multi-class anomalies using the Multi-class AdaBoost and majority *** evaluations using a dataset consisting of multi-source normal records and multi-class anomalies demonstrate that our model outperforms existing approaches in terms of accuracy,F1 score,recall,and precision.

关键词： IIoT Threat hunting Edge devices Multi-class anomalies Ensemble methods

来源：评论

学校读者我要写书评

暂无评论

Transaction transmission model for blockchain channels based on non-cooperative games

引用

science China(Information sciences) 2023年第1期66卷 97-114页

作者： Peiyun ZHANG Chenxi LI Mengchu ZHOU Wenjun HUANG Abdullah ABUSORRAH Omaimah O.BAMASAG Engineering Research Center of Digital Forensics of Ministry of Education School of Computer and SoftwareNanjing University of Information Science and Technology School of Computer and Information Anhui Normal University Department of Electrical and Computer Engineering New Jersey Institute of Technology Center of Research Excellence in Renewable Energy and Power Systems Department of Electrical and Computer Engineering Faculty of Engineering and K.A.CARE Energy Research and Innovation CenterKing Abdulaziz University Department of Computer Science Faculty of Computing and Information Technology Center of Excellence in Smart Environment Research King Abdulaziz University

In blockchain networks, transactions can be transmitted through channels. The existing transmission methods depend on their routing information. If a node randomly chooses a channel to transmit a transaction, the transmission may be aborted due to insufficient funds(also called balance) or a low transmission rate. To increase the success rate and reduce transmission delay across all transactions, this work proposes a transaction transmission model for blockchain channels based on non-cooperative game *** balance, channel states, and transmission probability are fully considered. This work then presents an optimized channel transaction transmission algorithm. First, channel balances are analyzed and suitable channels are selected if their balance is sufficient. Second, a Nash equilibrium point is found by using an iterative sub-gradient method and its related channels are then used to transmit transactions. The proposed method is compared with two state-of-the-art approaches: Silent Whispers and Speedy Murmurs. Experimental results show that the proposed method improves transmission success rate, reduces transmission delay,and effectively decreases transmission overhead in comparison with its two competitive peers.

关键词： Blockchain channel transaction transmission channel balance channel state channel transmission probability non-cooperative game

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Multiobjective Evolutionary Algorithm for Filter Feature Selection in Multilabel Classification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4428-4442页

作者： Hancer, Emrah Xue, Bing Zhang, Mengjie Victoria University of Wellington Center for Data Science and Artificial Intelligence School of Engineering and Computer Science Wellington6140 New Zealand Mehmet Akif Ersoy University Department of Software Engineering Burdur15039 Turkey

Multilabel learning is an emergent topic that addresses the challenge of associating multiple labels with a single instance simultaneously. Multilabel datasets often exhibit high dimensionality with noisy, irrelevant, and redundant features. In recent years, multilabel feature selection (MLFS) has gained prominence as a crucial and emerging machine learning task due to its ability to handle such data effectively. However, existing approaches for MLFS often prioritize top-ranked features based on intrinsic data criteria, disregarding relationships within the feature subset. Additionally, compared with conventional feature selection, multiobjective evolutionary algorithms (MOEAs) have not been widely explored in the context of MLFS. This study aims to address these gaps by proposing a multimodal multiobjective evolutionary algorithm (MMOEA) called MMDE_SICD which incorporates a preelimination scheme, an improved initialization scheme, an exploration scheme inspired by genetic operations and a statistically inspired crowding distance scheme. The results show that the proposed MMDE_SICD algorithm can outperform a variety of MOEAs and MMOEAs as well as conventional MLFS algorithms. Notably, this study is the first of its kind to consider MLFS as a multimodal multiobjective problem. © 2020 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

3-Multi ranked encryption with enhanced security in cloud computing

引用

Digital Communications and Networks 2023年第2期9卷 313-326页

作者： YeEun Kim Junggab Son Reza M.Parizi Gautam Srivastava Heekuck Oh Major in Bio Artificial Intelligence Dept.of Computer Science and EngineeringHanyang UniversityAnsanRepublic of Korea Department of Computer Science Kennesaw State UniversityMariettaUSA Department of Software Engineering Kennesaw State UniversityMariettaUSA Department of Mathematics and Computer Science Brandon UniversityBrandonCanada Research Center for Interneural Computing China Medical UniversityTaichungTaiwanChina Dept.of Computer Science and Engineering Hanyang UniversityAnsanRepublic of Korea

Searchable Encryption(SE)enables data owners to search remotely stored ciphertexts selectively.A practical model that is closest to real life should be able to handle search queries with multiple keywords and multiple data owners/users,and even return the top-k most relevant search results when *** refer to a model that satisfies all of the conditions a 3-multi ranked search ***,SE schemes that have been proposed to date use fully trusted trapdoor generation centers,and several methods assume a secure connection between the data users and a trapdoor generation *** is,they assume the trapdoor generation center is the only entity that can learn the information regarding queried keywords,but it will never attempt to use it in any other manner than that requested,which is impractical in real *** this study,to enhance the security,we propose a new 3-multi ranked SE scheme that satisfies all conditions without these security *** proposed scheme uses randomized keywords to protect the interested keywords of users from both outside adversaries and the honest-but-curious trapdoor generation center,thereby preventing attackers from determining whether two different queries include the same ***,we develop a method for managing multiple encrypted keywords from every data owner,each encrypted with a different *** evaluation demonstrates that,despite the trade-off overhead that results from the weaker security assumption,the proposed scheme achieves reasonable performance compared to extant schemes,which implies that our scheme is practical and closest to real life.

关键词： Searchable encryption Multi-keyword search Multiple data owners/users Ranked search Enhanced security

来源：评论

学校读者我要写书评

暂无评论

Federated Learning for Enhanced Intrusion Detection in Smart City Environments 18

Federated Learning for Enhanced Intrusion Detection in Smart...

引用

18th International Conference on Open Source Systems and Technologies, ICOSST 2024

作者： Hamid, Soomaiya Bawany, Narmeen Zakaria Jinnah University for Women Center for Computing Research Department of Computer Science and Software Engineering Karachi Pakistan

ISBN: (纸本)9798331508692

The integration of IoT devices in smart cities enhances urban infrastructure, services, and governance but also introduces significant cybersecurity challenges. Traditional centralized Intrusion Detection Systems (IDS) face several issues, including data privacy concerns and high-power consumption due to centralized data processing. These challenges increase the risks of unauthorized access, data breaches, and privacy violations, undermining user trust and compliance with privacy regulations. Additionally, the centralization of data and processing leads to higher power consumption, making these systems less sustainable for widespread deployment in smart cities. This research addresses these issues by proposing a Federated Learning (FL)based intrusion detection framework for smart cities. FL enables collaborative and privacy-preserving model training across distributed IoT devices, mitigating the need to share sensitive data centrally. By aggregating local model updates, FL ensures data privacy and distributes the computational workload, significantly reducing power consumption compared to traditional centralized systems. The proposed model leverages advanced AI techniques and is trained using the IoTID20 dataset. The Flower framework, utilizing the FedAvg algorithm, facilitates the federated learning process. Our experimental results demonstrate that the global model achieves 98% accuracy, with individual clients achieving accuracies of around 85% to 98%. This approach provides continuous learning mechanisms, anomaly detection, and ensemble learning capabilities, enhancing the resilience of federated intrusion detection systems against emerging threats and adversarial attacks. This research systematically investigates the application of federated learning for intrusion detection in smart city networks, addressing key challenges and advancing the state-of-the-art in decentralized cybersecurity solutions. The proposed framework offers a robust, scalable, and privacyco

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

SeerahGPT: Retrieval Augmented Generation based Large Language Model 18

SeerahGPT: Retrieval Augmented Generation based Large Langua...

引用

18th International Conference on Open Source Systems and Technologies, ICOSST 2024

作者： Obaid, Surayya Bawany, Narmeen Zakaria Center for Computing Research Department of Computer Science and Software Engineering Jinnah Univesity for Women Karachi Pakistan

ISBN: (纸本)9798331508692

Large Language Models(LLMs) have become widely recognized in recent years for their exceptional performance in language generation capabilities. As a result, an unprecedented rise is seen in its use cases in various domains specifically involving Natural Language Processing(NLP). These models however perform suboptimally when exploited in the field of studies where authenticity of the generated content is a critical aspect. One such domain is usage of LLM for exploration of the life of Prophet Muhammad S.A.W(commonly referred to as Seerah). It is of utmost significance to ensure the authenticity and reliability in the sources used and reported by the LLM due to the sensitive nature of the domain. The contemporary LLMs, however, lack the explainability in their response due to their inherent black-box nature. In our study, we have presented a novel LLM named SeerahGPT that addresses this challenge with the help of retrieval-augmented generation (RAG). This technique enables the model to utilize both parametric and nonparametric memories for generating response of queries. Our model, built on the Llama-2-7b architecture, employs Sentence Transformer embedding to effectively retrieve relevant information. The model's capabilities are augmented by integrating it with a corpus having Islamic texts such as the Quranic translation and Hadith collections, and historical accounts. The model's performance is benchmarked against its base model using both quantitative and qualitative metrics. The comparative analysis with Llama-2-7b revealed that SeerahGPT incorporation with external knowledge sources, provided more authentic and verifiable responses, despite the others exhibiting greater fluency. Performance metrics such as BLEU, ROUGE, and METEOR indicated SeerahGPT's better accuracy and contextual handling. This study paves way for analysis of such sensitive domains in more efficient way that can be utilized in other complex domains such as Islamic theology and Fiqh or legal

关键词： Natural language processing 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：