检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Cai, Hongfei Liu, Chi Shen, Sheng Qu, Youyang Gui, Peng Faculty of Data Science City University of Macau China Design and Creative Technology Vertical Torrens University Australia NSW Australia Shandong Provincial Key Laboratory of Computer Networks Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China

The rapid progression of generative AI (GenAI) technologies has heightened concerns regarding the misuse of AI-generated imagery. To address this issue, robust detection methods have emerged as particularly compelling, especially in challenging conditions where the targeted GenAI models are out-of-distribution or the generated images have been subjected to perturbations during transmission. This paper introduces a multi-feature fusion framework designed to enhance spatial forensic feature representations with incorporating three complementary components, namely noise correlation analysis, image gradient information, and pretrained vision encoder knowledge, using a cross-source attention mechanism. Furthermore, to identify spectral abnormality in synthetic images, we propose a frequency-aware architecture that employs the Frequency-Adaptive Dilated Convolution, enabling the joint modeling of spatial and spectral features while maintaining low computational complexity. Our framework exhibits exceptional generalization performance across fourteen diverse GenAI systems, including text-to-image diffusion models, autoregressive approaches, and post-processed deepfake methods. Notably, it achieves significantly higher mean accuracy in cross-model detection tasks when compared to existing state-of-the-art techniques. Additionally, the proposed method demonstrates resilience against various types of real-world image noise perturbations such as compression and blurring. Extensive ablation studies further corroborate the synergistic benefits of fusing multi-model forensic features with frequency-aware learning, underscoring the efficacy of our approach. © 2025, CC BY-NC-SA.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Smart Warehouse Solutions for Efficient Onion Buffer Stock Management System

Smart Warehouse Solutions for Efficient Onion Buffer Stock M...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Ramakrishnan Raman L. Ramalingam Kamal Kishorbhai Sutaria Manika Kamthan S. Sangeetha S. Murugan Symbiosis International (Deemed University) Symbiosis Institute of Business Management Pune & Pune Maharashtra India Department of Artificial Intelligence and Data Science Chennai Institute of Technology (Autonomous) Chennai Tamil Nadu India Faculty of Engineering and Technology Parul Institute of Engineering and Technology Parul University Vadodara Gujarat India Symbiosis Law School Symbiosis International (Deemed University) Pune Maharashtra India Department of Computer Science and Engineering Karpagam College of Engineering Coimbatore Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

This research study presents an innovative smart warehouse system for onion buffer stock management. The system includes an RFID reader, a central controlling unit, a displaying unit, a temperature sensor, a moisture sensor, a relay, a cooling fan, storage nodes, and a cloud server. The RFID reader automatically tracks onion crates or pallets in the warehouse, enabling real-time visibility and traceability. The central controlling unit coordinates activities and collects data from sensors. Onions are stored at appropriate temperatures and moisture levels via sensors. Warehouse workers can monitor this data in real-time on the displaying unit once the central controlling unit processes it. Maintaining temperature and humidity need the relay and cooling fan. Based on sensor data, the main controlling unit activates the cooling fan to avoid onion spoiling. Storage nodes in the warehouse store onion bags and pallets. These nodes have RFID tags or sensors for convenient tracking of stock. data analysis, storage, and integration depend on the cloud server. It allows advanced data analytics, forecasting, and decision-making. It also helps suppliers, distributors, and retailers communicate and distribute products efficiently. Real-time visibility, smart monitoring, and proactive management of storage conditions advance efficient operations, prevent spoiling, and improve onion supply chain efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TARGET SPECIFIC DE NOVO DESIGN OF DRUG CANDIDATE MOLECULES WITH GRAPH TRANSFORMER-BASED GENERATIVE ADVERSARIAL networks

arXiv

引用

arXiv 2023年

作者： Ünlü, Atabey Çevrim, Elif Sarıgün, Ahmet Yiğit, Melih Gökay Çelikbilek, Hayriye Bayram, Osman Güvenilir, Heval Ataş Koyaş, Altay Kahraman, Deniz Cansen Olğaç, Abdurrahman Rifaioğlu, Ahmet Banoğlu, Erden Doğan, Tunca Biological Data Science Lab Dept. of Computer Engineering Hacettepe University Turkey Dept. of Bioinformatics Graduate School of Health Sciences Hacettepe University Turkey Dept. of Chemistry Middle East Technical University Turkey Dept. of Physics Middle East Technical University Turkey Dept. of Computer Engineering Middle East Technical University Turkey Dept. Of Artificial Intelligence Engineering Bahcesehir University Turkey Cancer Systems Biology Lab Graduate School of Informatics Middle East Technical University Turkey Dept. of Pharmaceutical Chemistry Faculty of Pharmacy Gazi University Turkey Laboratory of Molecular Modeling Evias Pharmaceutical R&D Ltd Turkey Dept. of Electrical and Electronics Engineering Iskenderun Technical University Turkey Institute for Computational Biomedicine Heidelberg University Germany

Discovering novel drug candidate molecules is one of the most fundamental and critical steps in drug development. Generative deep learning models, which create synthetic data given a probability distribution, offer a high potential for designing de novo molecules. However, for them to be useful in real-life drug development pipelines, these models should be able to design drug-like and target-centric molecules. In this study, we propose an end-to-end generative system, DrugGEN, for the de novo design of drug candidate molecules that interact with intended target proteins. The proposed method represents molecules as graphs and processes them via a generative adversarial network comprising graph transformer layers. The system is trained using a large dataset of drug-like compounds and target-specific bioactive molecules to design effective inhibitory molecules against the AKT1 protein, which is critically important in developing treatments for various types of cancer. We conducted molecular docking and dynamics to assess the target-centric generation performance of the model, as well as attention score visualisation to examine model interpretability. Results indicate that our de novo molecules have a high potential for interacting with the AKT1 protein at the level of its native ligands. Using the open-access DrugGEN codebase, it is possible to easily train models for other druggable proteins, given a dataset of experimentally known bioactive molecules. © 2023, CC BY-NC-SA.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

PURSUhInT: In Search of Informative Hint Points Based on Layer Clustering for Knowledge Distillation

arXiv

引用

arXiv 2021年

作者： Keser, Reyhan Kevser Ayanzadeh, Aydin Aghdam, Omid Abdollahi Kilcioglu, Caglar Toreyin, Behcet Ugur Ure, Nazim Kemal Research Group Informatics Institute Istanbul Technical University Turkey Department of Computer Science and Electrical Engineering University of Maryland Baltimore County United States Arcelik Research and Development Turkey Artificial Intelligence and Data Science Application and Research Center Istanbul Technical University Turkey

One of the most efficient methods for model compression is hint distillation, where the student model is injected with information (hints) from several different layers of the teacher model. Although the selection of hint points can drastically alter the compression performance, conventional distillation approaches overlook this fact and use the same hint points as in the early studies. Therefore, we propose a clustering based hint selection methodology, where the layers of teacher model are clustered with respect to several metrics and the cluster centers are used as the hint points. Our method is applicable for any student network, once it is applied on a chosen teacher network. The proposed approach is validated in CIFAR-100 and ImageNet datasets, using various teacher-student pairs and numerous hint distillation methods. Our results show that hint points selected by our algorithm results in superior compression performance compared to state-of-the-art knowledge distillation algorithms on the same student models and datasets. © 2021, CC BY-NC-ND.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Financial Fraud Detection using Quantum Graph Neural networks

arXiv

引用

arXiv 2023年

作者： Innan, Nouhaila Sawaika, Abhishek Dhor, Ashim Dutta, Siddhant Thota, Sairupa Gokal, Husayn Patel, Nandan Khan, Muhammad Al-Zafar Theodonis, Ioannis Bennai, Mohamed Quantum Physics and Magnetism Team LPMC Faculty of Sciences Ben M’sick Hassan II University of Casablanca Morocco Quantum Formalism Fellow Zaiku Group Ltd Liverpool United Kingdom Indian Institute of Technology Bombay India Department of Data Science and Engineering Indian Institute of Science Education and Research Bhopal India Dwarkadas J. Sanghvi College of Engineering India Guru Nanak Institutions Technical Campus Hyderabad India ASTI Academy Dubai United Arab Emirates Vellore Institute of Technology Chennai India School of Computer Science and Applied Mathematics University of the Witwatersrand 1 Jan Smuts Ave Braamfontein Johannesburg Gauteng2000 South Africa Department of Physics School of Applied Mathematical and Physical Sciences National Technical University of Athens Greece

Financial fraud detection is essential for preventing significant financial losses and maintaining the reputation of financial institutions. However, conventional methods of detecting financial fraud have limited effectiveness, necessitating the need for new approaches to improve detection rates. In this paper, we propose a novel approach for detecting financial fraud using Quantum Graph Neural networks (QGNNs). QGNNs are a type of neural network that can process graph-structured data and leverage the power of Quantum Computing (QC) to perform computations more efficiently than classical neural networks. Our approach uses Variational Quantum Circuits (VQC) to enhance the performance of the QGNN. In order to evaluate the efficiency of our proposed method, we compared the performance of QGNNs to Classical Graph Neural networks using a real-world financial fraud detection dataset. The results of our experiments showed that QGNNs achieved an AUC of 0.85, which outperformed classical GNNs. Our research highlights the potential of QGNNs and suggests that QGNNs are a promising new approach for improving financial fraud detection. © 2023, CC BY.

关键词： Timing circuits

来源：评论

学校读者我要写书评

暂无评论

VEIN: High Scalability Routing Algorithm for Blockchain-based Payment Channel networks

VEIN: High Scalability Routing Algorithm for Blockchain-base...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Qianyun Gong Chengjin Zhou Le Qi Jianbin Li Jianzhong Zhang Jingdong Xu Institute of Systems and Networks College of Computer Science Nankai University Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Shijiazhuang Huayan Traffic Technology Co. Ltd.

ISBN: (纸本)9781665416597

The payment channel networks (PCNs), as the main method of blockchain off-chain expansion, have received extensive attention in recent years. Using the PCNs, two unconnected parties in a transaction can forward payments through existing payment channels of other nodes, which dramatically reduces interactions with the blockchain. But in large-scale dynamic PCNs, the routing mechanism is a challenge. Existing PCNs routing algorithms have some limitations. The landmark routing destroys the decentralization of blockchain. The static routing requires nodes having a global view and ultra-high computing power, which can not be applied to light nodes. We propose VEIN, a dynamic multi-path source routing algorithm, which is suitable for not only full nodes but also light nodes. We present an ingenious routing protocol, a modified max-flow algorithm to find edge-disjoint paths, and a path selection algorithm to deal with the NP-hard multi-path selection problem. Extensive experiments show that VEIN increases the transaction success ratio by 34% with the state-of-art algorithm, and realizes multiple orders of magnitude reduction in storage. In addition, we implement a prototype of VEIN on the Ethereum testnet to verify its feasibility.

关键词： Privacy Heuristic algorithms Veins Scalability Conferences Prototypes Routing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Blood Bank Management with Cloud-Hosted Long Short-Term Memory Models for Inventory Forecasting and Utilization

Optimizing Blood Bank Management with Cloud-Hosted Long Shor...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： R. Aiyshwariya Devi Sree Southry S S. Rajanarayanan S. Chandra Sekaran Audithan Sivaraman S. Srinivasan Department of Artificial Intelligence and Data Science R.M.K. College of Engineering and Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Sona College of Technology Salem Tamil Nadu India Department of Computer Science and Engineering Vinayaka Mission’s Research Foundation (DU) Vinayaka Mission’s Kirupananda Variyar Engineering College Salem Tamil Nadu India Department of Computer Science and Engineering P.S.V College of Engineering and Technology Krishnagiri Tamil Nadu India Department of Information Technology Netaji Subhas University of Technology (Govt of NCTDelhi) Jafferpur New Delhi India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

This research presents an innovative method for blood bank management using Cloud-based Long Short-Term Memory (LSTM) models for precise inventory forecasting and optimization. The objective of this research is to increase blood bank efficiency by utilizing LSTM models to accurately estimate demand, optimize inventory levels, and enhance overall resource utilization. The system uses cloud computing to provide real-time demand forecasting, minimizing blood waste and assuring a reliable supply for healthcare requirements. LSTM models use historical data to identify long-term trends and variations in blood demand, facilitating accurate inventory forecasting. This predictive system optimizes the allocation process, resulting in improve resource utilization and increased operational efficiency. In compared to traditional techniques, the proposed system provides a more scalable and flexible solution by using cloud technology to provide continuous monitoring and dynamic modifications of inventory levels. It provides a robust framework for management of blood supply and enhancing patient care for improved resource management. Future enhancements may include broadening the system to incorporate real-time multi-source data integration and investigating hybrid machine learning models to better optimize demand forecasts.

关键词： Cloud computing Computational modeling Demand forecasting Medical services Predictive models Real-time systems Resource management Blood Long short term memory Optimization

来源：评论

学校读者我要写书评

暂无评论

FLDDoS: DDoS Attack Detection Model based on Federated Learning

FLDDoS: DDoS Attack Detection Model based on Federated Learn...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Jiachao Zhang Peiran Yu Le Qi Song Liu Haiyu Zhang Jianzhong Zhang Institute of Systems and Networks Nankai University College of Computer Science Tianjin China Tianjin Key Laboratory of Network and Data Security Technology Tianjin China Shijiazhuang Huayan Traffic Technology Co. Ltd.

ISBN: (纸本)9781665416597

Recently, DDoS attack has developed rapidly and become one of the most important threats to the Internet. Traditional machine learning and deep learning methods can-not train a satisfactory model based on the data of a single client. Moreover, in the real scenes, there are a large number of devices used for traffic collection, these devices often do not want to share data between each other depending on the research and analysis value of the attack traffic, which limits the accuracy of the model. Therefore, to solve these problems, we design a DDoS attack detection model based on federated learning named FLDDoS, so that the local model can learn the data of each client without sharing the data. In addition, considering that the distribution of attack detection datasets is extremely imbalanced and the proportion of attack samples is very small, we propose a hierarchical aggregation algorithm based on K-Means and a data resampling method based on SMOTEENN. The result shows that our model improves the accuracy by 4% compared with the traditional method, and reduces the number of communication rounds by 40%.

关键词： Deep learning Privacy data privacy Computational modeling Clustering algorithms Denial-of-service attack Collaborative work

来源：评论

学校读者我要写书评

暂无评论

Various Modulation Types Classification on the Air by Convolutional Neural Network 23

Various Modulation Types Classification on the Air by Convol...

引用

Proceedings of the 7th International Conference on Future networks and Distributed Systems

作者： Yousif I Hammadi Mokhalad Abdulameer Kadhim Alsaeedi Omar Abdulkareem Mahmood Aws Zuhair Sameen Mohammed Saleh Ali Muthanna Ahmed Aziz Ammar Muthanna Dep. of Medical Instruments Engineering Techniques Bilad Alrafidain University College Iraq Department of Communications Engineering University of Diyala Iraq Department of Medical Instrumentation Engineering Techniques Al-Farahidi University Iraq Institute of Computer Technologies and Information Security Southern Federal University Russia Department of computer science Benha university Egypt and International Business Management Department Tashkent State University of Economics Uzbekistan Department of Telecommunication Networks and Data Transmission The Bonch Bruevich Saint Petersburg State University of Telecommunications Russia and Department of Applied Probability and Informatics Peoples Friendship University of Russia Russia

ISBN: (纸本)9798400709036

Deep learning (DL), a relatively recent AI technique, has been successfully applied to the problem of automated modulation categorization (AMC), with promising results. An essential part of developing the spectrum-sensing capabilities needed by software-defined radio is carrying out radio signal classification jobs, which we did in this research by introducing a better deep neural architecture. Different detection techniques were utilized in the literature; however, DL neural networks are recently utilized in this field. Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) which is one variation of the RNN network, and other techniques are some of the employed DL architectures in the field of AMC. In this paper, Convolutional Neural Network (CNN) model has been built to automatically classify ten-modulation formats correctly. The suggested CNN network is constructed mainly of six-Convolutional layers. The overall number of trainable parameters in the proposed network is 1,757,962. Thus, the network accuracy, which was achieved during the training reached more than 90%. Python programming packages have been used to implement the suggested approach using *** platform, which provides wide-range of facilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics for Ear Health Management Using IoT and Ensemble Learning

Predictive Analytics for Ear Health Management Using IoT and...

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Saravanan, S.K. Parvathy, Palaniraj Rajidurai Meenakshi, R. Prabu, K. Ganeshbabu, T.R. Meenakshi, B. Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Big Data and Network Security Tamil Nadu Chennai India Mphasis Corporation ChandlerAZ United States Chennai Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Gojan School of Business and Technology Department of Electronics and Communication Engineering Redhills Tamil Nadu Chennai India Department of Electronics and Communication Tamil Nadu Namakkal India Sri Sairam Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331527495

Proactive health monitoring solutions are becoming more important due to a growing population of older people. To better manage the ear health of the elderly, this research investigates ensemble learning methods within the domain of predictive analytics using the Internet of Things (IoT). It provides an ensemble learning approach that uses IoT capabilities to predict potential ear health problems in this population. It evaluates the efficacy of many ensembles learning approaches, including bagging, boosting, and stacking, using real-world sensor data acquired from IoT devices. Our results show that ensemble learning methods considerably improve prediction accuracy compared to standalone models. Ensemble learning overcomes the limitations of individual algorithms and maximizes their combined prediction potential by efficiently combining varied models. Our findings have important implications for the management of healthcare for the elderly, providing new opportunities to enhance early diagnosis and intervention techniques for ear health concerns via the use of predictive analytics provided by the IoT. It highlights the potential of ensemble learning approaches to improve predictive analytics in the senior healthcare sector, especially with IoT-driven solutions. © 2025 IEEE.

关键词： mHealth

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：