检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zeng, Weichao Shu, Yan Li, Zhenhang Yang, Dongbao Zhou, Yu Institute of Information Engineering Chinese Academy of Sciences China VCIP TMCC DISSec College of Computer Science Nankai University China School of Cyber Security University of Chinese Academy of Sciences China

Centred on content modification and style preservation, Scene Text Editing (STE) remains a challenging task despite considerable progress in text-to-image synthesis and text-driven image manipulation recently. GAN-based STE methods generally encounter a common issue of model generalization, while Diffusion-based STE methods suffer from undesired style deviations. To address these problems, we propose TextCtrl, a diffusion-based method that edits text with prior guidance control. Our method consists of two key components: (i) By constructing fine-grained text style disentanglement and robust text glyph structure representation, TextCtrl explicitly incorporates Style-Structure guidance into model design and network training, significantly improving text style consistency and rendering accuracy. (ii) To further leverage the style prior, a Glyph-adaptive Mutual Self-attention mechanism is proposed which deconstructs the implicit fine-grained features of the source image to enhance style consistency and vision quality during inference. Furthermore, to fill the vacancy of the real-world STE evaluation benchmark, we create the first real-world image-pair dataset termed ScenePair for fair comparisons. Experiments demonstrate the effectiveness of TextCtrl compared with previous methods concerning both style fidelity and text accuracy. Project page: https://***/weichaozeng/TextCtrl. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pricing-Based Cooperative Relay Selection Scheme for Reliable Communications

引用

China Communications 2024年第8期21卷 30-44页

作者： Xiao Yulong Wu Yu Amr Tolba Chen Ziqiang Li Tengfei School of Communications and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China School of Cyber Security and Information Law Chongqing University of Posts and TelecommunicationsChongqing 400065China Department of Computer Science Community CollegeKing Saud UniversityRiyadh 11437Saudi Arabia

With the rapid development and application of energy harvesting technology,it has become a prominent research area due to its significant benefits in terms of green environmental protection,convenience,and high safety and ***,the uneven energy collection and consumption among IoT devices at varying distances may lead to resource imbalance within energy harvesting networks,thereby resulting in low energy transmission *** enhance the energy transmission efficiency of IoT devices in energy harvesting,this paper focuses on the utilization of collaborative communication,along with pricing-based incentive mechanisms and auction *** propose a dynamic relay selection scheme,including a ladder pricing mechanism based on energy level and a Kuhn-Munkre Algorithm based on an auction theory employing a negotiation mechanism,to encourage more IoT devices to participate in the collaboration *** results demonstrate that the proposed algorithm outperforms traditional algorithms in terms of improving the energy efficiency of the system.

关键词： cooperative communication edge net-work energy harvesting relay selection

来源：评论

学校读者我要写书评

暂无评论

Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance 39

Arbitrary Reading Order Scene Text Spotter with Local Semant...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lyu, Jiahao Wang, Wei Yang, Dongbao Zhong, Jinwen Zhou, Yu Institute of Information Engineering Chinese Academy of Science China VCIP & TMCC & DISSec College of Computer Science Nankai University China Shanghai Artificial Intelligence Laboratory China School of Cyber Security University of Chinese Academy of Sciences China

ISBN: (纸本)157735897X

Scene text spotting has attracted the enthusiasm of relative researchers in recent years. Most existing scene text spotters follow the detection-then-recognition paradigm, where the vanilla detection module hardly determines the reading order and leads to failure recognition. After rethinking the auto-regressive scene text recognition method, we find that a well-trained recognizer can implicitly perceive the local semantics of all characters in a complete word or a sentence without a character-level detection module. Local semantic knowledge not only includes text content but also spatial information in the right reading order. Motivated by the above analysis, we propose the Local Semantics Guided scene text Spotter (LSGSpotter), which auto-regressively decodes the position and content of characters guided by the local semantics. Specifically, two effective modules are proposed in LSGSpotter. On the one hand, we design a Start Point Localization Module (SPLM) for locating text start points to determine the right reading order. On the other hand, a Multi-scale Adaptive Attention Module (MAAM) is proposed to adaptively aggregate text features in a local area. In conclusion, LSGSpotter achieves the arbitrary reading order spotting task without the limitation of sophisticated detection, while alleviating the cost of computational resources with the grid sampling strategy. Extensive experiment results show LSGSpotter achieves state-of-the-art performance on the InverseText benchmark. Moreover, our spotter demonstrates superior performance on English benchmarks for arbitrary-shaped text, achieving improvements of 0.7% and 2.5% on Total-Text and SCUT-CTW1500, respectively. These results validate our text spotter is effective for scene texts in arbitrary reading order and shape. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Support Vector Machine to Lassa Fever Diagnosis

Lecture Notes on Data Engineering and Communications Technol...

引用

Lecture Notes on Data engineering and Communications Technologies 2023年 180卷 165-177页

作者： Nwankwo, Wilson Adigwe, Wilfred Umezuruike, Chinecherem Acheme, Ijegwa D. Nwankwo, Chukwuemeka Pascal Ojei, Emmanuel Oghorodi, Duke Department of Computer Science Edo State University Uzairue Nigeria Department of Computer Science Delta State University of Science and Technology Ozoro Nigeria College of Computing and Communication Studies Bowen University Iwo Nigeria Department of Software Engineering Delta State University of Science and Technology Ozoro Nigeria Department of Cyber Security Delta State University of Science and Technology Ozoro Nigeria

Lassa fever is a type of viral hemorrhagic fever with high fatality rate. Precise and prompt diagnosis and successful treatment of this disease is very important in the control and prevention of the spread as unrestricted spread can easily erupt into an epidemic. An insightful decision support system can help make quick and more exact findings on this disease. In this paper, an intelligent model is proposed for predicting Lassa fever is proposed. The Lassa fever dataset was extracted from the clinical records of patients from a known Specialist Teaching Hospital in Southern Nigeria. The relevant feature variables were identified and encoded in a manner appropriate for use in algorithmic analysis. The support vector classifier was used to develop a characterization model for the disease. Assessment and evaluation were based on exactness, accuracy, and affectability. Findings showed that the proposed system could improve and encourage quick decision-making as it utilizes real historical data to effectively characterize Lassa fever spread as well as promote the timely treatment and management of patients. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning-Based Early Warning Detection System for Business Customer Churn 5

A Novel Machine Learning-Based Early Warning Detection Syste...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Chandan, Radha Raman Ramaraj, S. Sarishma Praba Devi, P. Sj, Sultanuddin Indhuma, E. Department of Computer Science UP Varanasi221011 India Karpagam College of Engineering Department of Computer Science and Engineering TamilNadu Coimbatore India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Sona College of Technology Department of Management Studies Salem India Dhanalakshmi College of Engineering Dept of Cyber Security Tambaram Manimangalam Chennai India St. Martins Engineering College Department of Computer Science and Engineering Telangana Secunderabad India

ISBN: (纸本)9798350351378

This study presents an Early Warning Detection System (ML-EWDS) based on machine learning for reducing commercial customer turnover. Companies in all sectors need to be especially concerned about client churn in today's environment of volatile markets and plenty of consumer options. The ML-EWDS overcomes this difficulty by analyzing past customer data that has been augmented with Regency, Frequency, and Monetary (RFM) attributes using an ensemble learning model that includes a Random Forest classifier. The system's high accuracy (87.5%) and ROC-AUC (0.92) are the result of meticulous data preparation, model training, and cross-validation. Next, the ML-EWDS is put into action in a live business setting, where it alerts potentially churned consumers ahead of time. The solution significantly reduces turnover by 70% during a three-month assessment period, which has a beneficial effect on income. The ethical implementation of this technology is emphasized, with a focus on data protection and bias reduction. This study demonstrates the revolutionary potential of ML-EWDS in CRM, with implications for both academics and business and many possible avenues for further development. © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Save the Bruised Striver: A Reliable Live Patching Framework for Protecting Real-World PLCs 24

Save the Bruised Striver: A Reliable Live Patching Framework...

引用

19th European Conference on computer Systems, EuroSys 2024

作者： Zhou, Ming Wang, Haining Li, Ke Zhu, Hongsong Sun, Limin School of Cyber Science and Engineering Nanjing University of Science and Technology China Department of Electrical and Computer Engineering Virginia Tech China Nari Group Corporation State Grid Electric Power Research Institute School of Cyber Security University of Chinese Academy of Sciences China Institute of Information Engineering Cas China Virginia Tech. United States

ISBN: (纸本)9798400704376

Industrial Control Systems (ICS), particularly programmable logic controllers (PLCs) responsible for managing underlying physical infrastructures, often operate for extended periods without interruption. Thus, it is challenging to patch security vulnerabilities of ICS in a timely manner after disclosure because it often necessitates waiting for a rare downtime window. While live patching has been introduced to avoid downtime and maintenance costs, conventional live patching methods are not viable for closed-source PLCs. Without the source code, it is difficult to understand the system behaviors and determine binary patch equivalence. To address these challenges, we present a Reliable Live Patching framework called RLPatch for applying live patches to third-party binary without source code. We design RLPatch to capture real-time conditions and dynamic behaviors of PLCs, which enables DevOps engineers to identify major non-recoverable fault (MNRF) vulnerabilities and generate hot patches. The core of RLPatch is an update agent that inserts breakpoints over the original MNRF code and then directs execution to the patches. To ensure system reliability, we use the unique constraints of PLCs to integrate the update processes with the scan cycle. We leverage RLPatch to patch 20 real vulnerabilities in three widely used Rockwell PLCs. We evaluate RLPatch in a real-world gas pipeline, demonstrating its reliability and effectiveness in practice. © 2024 Owner/Author.

关键词： Programmable logic controllers

来源：评论

学校读者我要写书评

暂无评论

Predicting Mental States: Machine Learning Techniques for Personalized Mental Health Support 15

Predicting Mental States: Machine Learning Techniques for Pe...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Hepzibah, Grace Babu, Nirmal Varghese Division of Computer Science Engineering Karunya Institute of Technology and Science Karunya Nagar Tamil Nadu Coimbatore641114 India Division of Data Science and Cyber Security Karunya Institute of Technology and Science Karunya Nagar Tamil Nadu Coimbatore641114 India

ISBN: (纸本)9798331300579

As we know that individuals around the globe work difficult to keep up with this hustling world. In any case, due to this each person is managing with diverse wellbeing issues, one of the foremost known issue is sadness or stretch which may in the long run lead to passing or other brutal exercises. This project focuses on leveraging machine learning algorithms to predict psychological instability based on various attributes related to mental health. Developed as a web application using Django, users can upload datasets containing information such as age, gender, family history, and workplace environment. The data undergoes preprocessing, including handling missing values and label encoding. Subsequently, several classifiers including Decision Tree, Random Forest, SVC, MLP Classifier, KNeighbors Classifier, and Linear Discriminant Analysis are trained on the preprocessed data. Evaluation metrics such as accuracy, precision, recall, and F1-score are computed for each classifier. Users can also input personal data to obtain predictions about their psychological well-being. The system aims to offer insights into mental health conditions, enabling early detection and intervention. This project underscores the potential of machine learning in addressing mental health challenges through data-driven approaches. © Grenze Scientific Society, 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Detection and Recovery of RFID Harmonic Signal for Wi-Fi Interference

引用

Journal of Communications and Information Networks 2024年第4期9卷 330-339页

作者： Chao Gong Ping Li Panlong Yang Zhao Lv School of Computer Science and Technology Anhui UniversityHefei 230000China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui University of TechnologyMa’anshan 243032China School of Computer science School of Cyber Science and EngineeringNanjing University of Information Science and TechnologyNanjing 210000China

In the realm of the Internet of things(IoT),radio frequency identification(RFID)technology is essential for linking physical objects to digital *** introduction of harmonic technology has expanded RFID’s applications by improving sensitivity and enabling communication with wireless fidelity(Wi-Fi)***,this trend faces challenges,notably interference from strong Wi-Fi signals,which impacts RFID-based sensing *** paper proposes the WiFID(Wi-Fi and RFID)algorithm,which enables Wi-Fi devices to sense weak RFID harmonic *** subcarrier deallocation minimally reduces Wi-Fi throughput while effectively limiting interference with RFID harmonic *** validation on the universal software radio peripheral(USRP)platform demonstrates that WiFID successfully detects 90% of RFID harmonics at−30 dBm,with only a minimal 4%decrease in Wi-Fi throughput.

关键词： RFID harmonic wireless sensing Wi-Fi interference avoidence

来源：评论

学校读者我要写书评

暂无评论

Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles

Guardian of the Ensembles: Introducing Pairwise Adversariall...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Shukla, Shubhi Dalui, Subhadeep Alam, Manaar Datta, Shubhajit Mondal, Arijit Mukhopadhyay, Debdeep Chakrabarti, Partha Pratim Centre for Computational and Data Sciences Iit Kharagpur India Iit Kharagpur Computer Science and Engineering Department India Center for Cyber Security New York University Abu Dhabi United Arab Emirates Iit Kharagpur Department of Artificial Intelligence India Iit Patna Computer Science and Engineering Department India

ISBN: (纸本)9798331510831

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple classifiers in an ensemble. This paper proposes a new ensemble training using a Pairwise Adversarially Robust Loss (PARL) that by construction produces an ensemble of classifiers with diverse decision boundaries. PARL utilizes outputs and gradients of each layer with respect to network parameters in every classifier within the ensemble simultaneously. PARL is demonstrated to achieve higher robustness against black-box transfer attacks than previous ensemble methods as well as adversarial training without adversely affecting clean example accuracy. Extensive experiments using standard Resnet20, WideResnet28-10 classifiers demonstrate the robustness of PARL against state-of-the-art adversarial attacks. While maintaining similar clean accuracy and lesser training time, the proposed architecture has a 24.8% increase in robust accuracy (= 0.07) from the state-of-the art method. Code is available at: https://***/shubhishukla10/PARL © 2025 IEEE.

关键词： adversarial attack decision-boundary diversity defense ensemble models

来源：评论

学校读者我要写书评

暂无评论

ICP Registration Based on Overlapping Region

ICP Registration Based on Overlapping Region

引用

Image Processing, computer Vision and Machine Learning (ICICML), International Conference on

作者： Zhuoer Xiao School of Computer Science and Engineering School of Cyber Security) UESTC Chengdu China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

To solve the problem that ICP(Iterative Closest Point), a widely used fine registration algorithm, can degrade good initial registration results, this paper introduces a step of overlapping region extraction between the initial registration and fine registration to further enhance the accuracy of ICP. Furthermore, a method for determining overlapping regions based on grid partitioning is proposed, which resolves the issue of longer consumption of time for overlapping regions in large-scale point clouds. Experimental results indicate that the improved algorithm process reduces angular errors by approximately 50% and translational errors by approximately 60% compared to the pre-improvement process.

关键词： Point cloud compression computer vision Accuracy Costs Image processing Machine learning Approximation algorithms Partitioning algorithms

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：