检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Distributed computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Byeon, Haewon Nair, Rajit Mahalakshmi, V. Khalaf, Mohammed I. Kaushik, Bharat Shabaz, Mohammad Inje University Department Of Ai And Software Gimhae50834 Korea Republic of School Of Computing Science & Engineering Vit Bhopal University Bhopal India College Of Engineering And Computer Science Jazan University Department Of Computer Science Jazan45142 Saudi Arabia Al Maarif University College Department Of Computer Science Al Anbar 31001 Iraq Masters University Of Northern Iowa IA United States Model Institute Of Engineering And Technology J&K Jammu India

ISBN: (纸本)9798350318609

Perioperative nutrition evaluation is crucial for patient care and resource efficiency in healthcare. This work proposes a deep learning-based perioperative nutrition evaluation tool that leverages sophisticated machine learning to improve predictions and assist clinicians in making better choices. As surgical techniques become more complex and medical technology progresses, a thorough postoperative nutrition study becomes more important than ever. An extensive review demonstrates that the recommended strategy performs better than other machine learning techniques. Our model's accuracy, precision, memory, and F1-score let it predict surgical outcomes more accurately. The higher AVC-ROC and AVC-PR values of the suggested approach show that it performs particularly well. Its sensitivity-specificity balance is demonstrated by this. Our approach generates fewer errors, according to the confusion matrix analysis, which makes it reliable for healthcare decisions. Our work enhances critical healthcare by assessing nutrition with state-of-the-art techniques. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

DeNC: Unleash Neural Codecs in Video Streaming with Diffusion Enhancement 39

DeNC: Unleash Neural Codecs in Video Streaming with Diffusio...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhou, Qihua Li, Ruibin Guo, Jingcai Huang, Yaodong Xu, Zhenda Cui, Laizhong Guo, Song College of Computer Science and Software Engineering Shenzhen University China Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

ISBN: (纸本)157735897X

Recent years have witnessed the rise of Neural-enhanced Video Streaming (NeVS), which integrates neural restoration models into video codecs for higher compression-restoration performance. Despite its benefit, existing work has not well explored the full potential of NeVS paradigm, due to: (1) post-streaming restoration by decoder while lacking the proactive collaboration of encoder, (2) end-to-end optimization based on conventional rate-distortion theory, which has been verified that low distortion is not always a synonym for high perceptual quality, and (3) coupled design for domain-specific tasks that cannot generalize to various video codecs. Observing these limitations, our objective is not to incrementally present an improved restoration model. Instead, we focus on the encoder-decoder synergy, i.e., the codec, which is non-trivial since it inherently strikes the rate-distortion-perception trade-off of NeVS. Aiming at this target, we propose the Diffusion-enhanced Neural Codec (DeNC), a plug- and-play module for current NeVS paradigm, to significantly reduce the required bitrates while preserving high perceptual quality of restored videos. Our key design is twofold. First, DeNC improves the encoder’s compression efficiency by simultaneously reducing the resolution and color bit-depth of frame referencing. Second, DeNC empowers the decoder with perception-oriented restoration capability by making its diffusion-based restoration process aware of the encoder’s compression conditions. Real-world evaluations show that DeNC improves compression ratios with nearly an order of magnitude and achieves much higher restoration quality (e.g., 93+ VMAF and 23% higher MOS) over the latest baselines. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Online Multi-Object Tracking Based On Global Feature Enhancement Network And Historical Feature Complement Iteration

Online Multi-Object Tracking Based On Global Feature Enhance...

引用

Cognitive computing and Complex Data (ICCD), International Conference on the

作者： Zunwang Ke Puping An Gang Wang Yugui Zhang School of Software Xinjiang University Urumqi China School of Computing and Data Engineering NingboTech University Ningbo China Institute of Semiconductors Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

Multi-object tracking is an important part of computer vision and plays a crucial role in many real-world application scenarios. The existing integrated tracking framework loses the key features of the target when fusing features and iteratively updating the trajectory apparent features, resulting in tracking instability. In order to solve the above problems, this paper proposes an online multi-object tracking method based on global feature enhancement network and historical feature complement iteration. In this method, a dual global feature fusion unit is used to replace the global feature enhancement network of summation or splicing operation, which is used to extract more discriminative key features and enhance the recognition ability of objects in multiple scenes. In addition, the historical features are used to supplement the iterative mechanism, which introduces random features and average features from the historical appearance features stored in the trajectory as supplementary features to supplement the lack of object features in the current frame. Comprehensive experiments are carried out on MOT15, MOT16, MOT17, and MOT20 datasets, in which the MOTA score of 73.2% is achieved on MOT16 dataset, indicating that the proposed method has good tracking performance. Source code: http://***/Anbping/gfen-hfci

关键词： Computer vision Target tracking Splicing Source coding Computational modeling Feature extraction Trajectory Iterative methods Object tracking Cognitive systems

来源：评论

学校读者我要写书评

暂无评论

Analysis of Bitcoin Fork by Colored Petri Nets

Analysis of Bitcoin Fork by Colored Petri Nets

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Zeyu Zhou Ding Liu Tatiana R. Shmeleva Dmitry A. Zaitsev School of Mechano-Electronic Engineering Xidian University Xi'an China Max Planck Institute for Software Systems Kaiserslautern and Saarbruecken Germany School of Computing University of Derby UK

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Bitcoin is under the threat of fork since it operates with a distributed ledger. Predicting the fork probability in advance is beneficial for taking early action to avoid malicious attacks. In this study, we compose a colored Petri net model of Bitcoin. Our model consists of a given number of nodes, and each node has five subpages representing the node structure: proof of work, broadcast blocks, verify blocks, and the process of adding blocks to blockchain, respectively. Simulation results of fork probability can be easily obtained and analyzed by observing the data in the measuring components of subpages. The results show that our model correctly simulates the fork probability: on recent Bitcoin data, compared with the results of the wide-known SimBlock simulator, a difference of some 4.3% has been obtained. Thus, taking into account vivid graphical representation, our model has certain advantages for the developing techniques of attack avoidance.

关键词： Network topology Distributed ledger Simulation Petri nets Bitcoin Probability Proof of Work Topology Security Propagation delay

来源：评论

学校读者我要写书评

暂无评论

An AI Multi-Model Approach to DeFi Project Trust Scoring and Security

An AI Multi-Model Approach to DeFi Project Trust Scoring and...

引用

IEEE International Conference on Blockchain (Blockchain)

作者： Viraaji Mothukuri Reza M. Parizi James L. Massa Abbas Yazdinejad Decentralized Science Lab College of Computing and Software Engineering Kennesaw State University USA Cyber Science Lab School of Computer Science University of Guelph Ontario Canada

ISBN: (数字)9798350351590

ISBN: (纸本)9798350351606

Rampant scams plague decentralized finance (DeFi) projects, creating a DeFi credibility problem that limits the impact of DeFi advances in the availability and variety of financial services. This paper presents a novel solution to the DeFi credibility problem by developing an AI multi-model that generates TrustScore ratings for DeFi projects and clear explanations of the scores. We generate DeFi-project TrustScore by aggregating multiple factors that provide DeFi investors with a holistic view of DeFi project trustworthiness. To rate a DeFi project with a TrustS core, we combine the output of four AI pipelines that analyze smart contract code vulnerabilities, suspicious transactions, anomalous price changes to smart contracts, and social media scam sentiment. Applying four factors exponentially improves the trust-score accuracy over the single-factor approaches done historically. Two of the factors, anomalous price change, and social media sentiment, have not been used before to detect DeFi fraud. Furthermore, we enhanced the most critical factor, smart-contract code vulnerability detection, with the latest Large Language Models (LLMs). Our overall system is a multi-model composed of a TrustS core Explainer LLM that aggregates individual pipeline results, a fine-tuned GPT model to audit smart contract code, the Prophet forecasting tool, FinBERT tailored for financial Natural Language Processing (NLP), and XGBoost for classification. The proposed approach identifies a significant proportion of known fraudulent DeFi projects and generates an accurate and explained TrustScore. Thus, we address the DeFi credibility problem so that investors can make reliable decisions about DeFi projects.

关键词： Codes Accuracy Social networking (online) Smart contracts Pipelines Finance Decentralized applications

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Risks Quantification in the Internet of Things 7

Cybersecurity Risks Quantification in the Internet of Things

引用

7th IEEE International Conference on Recent Advances and Innovations in engineering, ICRAIE 2022

作者： Alagappan, Annamalai Baptist Andrews, Leo John Sampath Kumar, V. Raj, Raymon Antony Sarathkumar, D. Botho University Faculty of Engineering and Technology Department of Network and Infrastructure Management Gaborone Botswana Botho University Faculty of Computing Department of Software Engineering Botswana Grant Thornton Plot 50370 Acument Park Fair Grounds Gaborone Botswana Kongu Engineering College Department of Electrical and Electronics Engineering Tamilnadu India

ISBN: (纸本)9781665489102

A dynamic platform, the Internet of Things uses data, which in turn invites cybersecurity risks. In a dynamic and complicated world, many organisations are putting more of their attention into understanding cyber threats and attempting to quantify their exposure. This paper highlights and goes into great detail on standard cyber risk assessment methods while focusing on the assessment of cybersecurity threats in IoT and its vectors through a risk-based approach employing machine learning algorithms. Based on the statistical research, it can be determined that the CAQ model utilising J48 classifies at 94 percent, while the Bayesian method performs in evaluating possible risks at 82 percent. The Bayes algorithm also aids in estimating complicated risks coming from various sources, aids in comprehending how risk variables originate and connect in an IoT environment, and aids in determining what controls are necessary for quantifying and reducing them. © 2022 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Approach Towards software Regression Testing Quality Optimization 25

A Data-Driven Approach Towards Software Regression Testing Q...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Moubayed, Abdallah Alhindawi, Nouh Alsakran, Jamal Injadat, MohammadNoor Kanan, Mohammad King Fahd University of Petroleum & Minerals Computer Engineering Department Interdisciplinary Research Center for Intelligent Secure Systems Dhahran Saudi Arabia Arizona State University School of Computing and Augmented Intelligence GilbertAZ United States Jadara University Department of Software Engineering Irbid Jordan Fairleigh Dickinson University Canada Zarqa University Data Science & Artificial Intelligence Department Zarqa Jordan University of Business and Technology Department of Industrial Engineering Jeddah Saudi Arabia

ISBN: (纸本)9798331540012

software testing is very important in software development to ensure its quality and reliability. As software systems have become more complex, the number of test cases has increased, which presents the challenge of executing all the tests in a limited time frame. Various test case prioritization techniques have been introduced to solve this problem. These methods aim to identify and implement the most critical tests first. In this paper, we propose an implementation of a dynamic test case prioritization strategy to improve software quality by increasing code coverage with special attention to edge case handling. Edge case test prioritization is a technique that improves test efficiency by selecting extreme case scenarios that can reveal critical bugs or unexpected behavior early in development, improving overall software reliability and dependability. In order to prioritize test cases, this paper presents a regression-based method that makes use of machine learning algorithms. The approach leverages previous performance data to optimize regression testing efficiency by examining variables like test time and execution status. Performance evaluations, when compared against industry standards and cutting-edge techniques, show how effective these algorithms are at correctly prioritizing test cases and identifying faults. This study offers simplified yet reliable solutions for regression testing optimization by shedding light on the efficacy of regression algorithms, such as Random Forest and decision trees. © 2024 IEEE.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Features Extraction and Cross-Stage Features Fusion Network for Small Object Detection (Mcfn)

SSRN

引用

SSRN 2024年

作者： Bian, Deng Tang, Mingwei Xu, Haowen Lin, Miaogui Cai, Tao Qi, Tang Lv, Shixuan Xiong, Jianqiao Wen, Ya Hu, Jie School of Computer and Software Engineering Xihua University Chengdu610039 China School of Computing and Artificial Intelligence Southwest Jiaotong University Sichuan Province Chengdu611756 China

Recently, object detection has been a hot topic in the field of computer vision and has advanced significantly. Despite the fact that today’s detectors can detect small objects, there are still deficiencies in the extraction and fusion of critical features in the detection process. As a result of the limited feature expression of small objects, the model is unable to capture the essential discriminative information required for follow-on tasks. To mitigate this challenge, we propose a Multi-Scale Feature Extraction and Cross-Stage Feature Fusion Network for small object detection (MCFN) Through the extraction of rich multi-scale feature information, MCFN can enhance small object detection effectiveness. Firstly, a Multi-Scale Feature Extraction module (MSFE) is presented that captures target object features at different scales, offering high-quality feature information for further processing. Secondly, as part of feature manipulation, a Cross-Stage Feature Pyramid Network (CSFPN) is used to integrate feature maps across layers, allowing the model to utilize both abstract information from higher-level feature maps and detailed information from lower-level feature maps. Finally, experiments on the VisDrone-DET2019 and constellation datasets show that our MCFN achieves excellent performance in small object detection, outperforming other mainstream object detectors. © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CLIP-Driven Multi-Scale Instance Learning for Weakly Supervised Video Anomaly Detection

CLIP-Driven Multi-Scale Instance Learning for Weakly Supervi...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhangbin Qian Jiawei Tan Zhilong Ou Hongxing Wang School of Big Data and Software Engineering Chongqing University China Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Ministry of Education China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Existing weakly supervised video anomaly detection methods mainly employ Multiple Instance Learning (MIL) to identify abnormal snippets in untrimmed videos. However, the semantics and presentations of anomalies frequently exhibit ambiguity that MIL is difficult to tackle. Moreover, MIL suffers from false alarms due to its independent optimization of each instance, neglecting temporal correlation between adjacent snippets. Consequently, we badly need to better connect abnormal presentations and their semantics, as well as to enable multi-temporal-scale anomaly discovery. This paper proposes a CLIP-Driven Multi-Scale Instance Learning (CMSIL) framework with two branches including Vision-Language (VL) and Multi-Scale Instance Learning (MSIL). The VL branch leverages the powerful visual concept priors from Contrastive Language-Image Pre-training (CLIP) to generate pseudo anomalies, thereby providing suspected anomaly cues for model training guidance. The MSIL branch utilizes a feature pyramid to fully mine fine-grained temporal dependencies by employing MIL within each pyramid level to learn anomalous patterns across different temporal scales. By collaborating with the two branches, the proposed CMSIL shows better proficiency in handling anomalies with varying durations. Extensive experiments on the XD-Violence and UCF-Crime datasets demonstrate the superior performance of our method. The code is available at https://***/casperZB/CMSIL.

关键词： Training Visualization Correlation Codes Semantics Focusing Streaming media Anomaly detection Optimization Context modeling

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Editable Portrait Synthesis with 3D GAN Inversion

High-Fidelity Editable Portrait Synthesis with 3D GAN Invers...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jindong Xie Jiachen Liu Yupei Lin Jinbao Wang Xianxu Hou Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Information Engineering Guangdong University of Technology Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Information Processing School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The 3D generative adversarial network (GAN) inversion converts an image into 3D representation to attain high-fidelity reconstruction and facilitate realistic image manipulation within the 3D latent space. However, previous approaches face challenges regarding the trade-off between the reconstruction ability and editability. That is, reversing a real-world image to a low-dimensional latent code would inevitably lead to information loss, and achieving a near-perfect reconstruction using high-rate triplane representation often limits the ability to manipulate the image freely in the latent space. To address these issues, we propose a novel latent conditioning encoder-based framework with the alignment between the low-dimensional latent and high-dimensional triplane. A non-semantic guided editing strategy bridges the intrinsic relation between the latent condition and triplane generation, making it possible to edit the high-dimensional representation by latent manipulation. As a result, our method can achieve high-fidelity reconstruction and editing simultaneously by directly controlling the latent code. Experimental results demonstrate that our approach excels in reconstruction and editing quality compared to previous 3D inversion methods. Furthermore, our method can also edit even real faces with large poses and out-of-domain cases.

关键词： Bridges Three-dimensional displays Codes Signal processing Generative adversarial networks Vectors Acoustics Speech processing Image reconstruction Faces

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：