检索结果-内蒙古大学图书馆

8th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2024

作者： Mustfa, Asia Kamal Abdulateef, Salwa Khalid Hameed, Qabas Amer Ahmed, Mohamed Aktham Al-Qaysi, Zaydoon Computer Science and Mathematics College Tikrit University Dept. Computer Science Tikrit Iraq

ISBN: (纸本)9798350354423

Image classification has grown increasingly popular due to the growing significance of machine learning and deep learning. Flower images may sometimes exhibit resemblances in terms of hue, form, and visual characteristics. The problem lies in the classification of flowers. This work employs a hybrid approach that integrates deep learning and machine learning techniques to classify 17 discrete flower species. In order to do this, we utilised the ResNet_50, PCA, and SVM architecture to classify several species from the 'Oxford-17' dataset. With this goal in mind, we have made efforts to improve our model in order to get more accuracy compared to similar methods. Prior to inputting our images into our pretrained model, we resized them, and subsequently fine-tuned the model. The dataset was partitioned into two distinct sets: a training set and a testing set. We attained a precision rate of 95.58% while utilising the 'Oxford-17' dataset. Our approach outperformed previous machine learning and deep learning-based methods on this dataset. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Microwave Marvels: Design and Computational Analysis of an Ultra-thin Metamaterial Absorber for C, X and K Band 6

Microwave Marvels: Design and Computational Analysis of an U...

引用

6th International Conference on Electrical engineering and Information and Communication Technology, ICEEICT 2024

作者： Tasnim, Nowshin Rattre, Naziya Hasan Shawon, Sarowar Morshed Alam, Mohammed Shamsul Alam, Touhidul Chittagong University of Engineering & Technology Dept. of Computer Science & Engineering Chittagong4349 Bangladesh International Islamic University Chittagong Dept. of Computer Science & Engineering Chittagong4318 Bangladesh University of Science & Technology Chittagong Dept. of Computer Science & Engineering Chattogram4202 Bangladesh Universiti Kebangsaan Malaysia Bangi43600 UKM Malaysia

ISBN: (纸本)9798350385779

Metamaterial absorbers are an advancement in material science as they provide more advantages in comparison to conventional materials. Achieving miniaturization with a multilayered structure is the primary challenge here. In this study, a novel metamaterial absorber design is proposed for microwave application. The proposed design is shaped as a squad of four segments where each segment contains an octagonal split ring and a central ring. The multi-layered design of the absorber helps to secure a high absorption rate. An extensive range of research is done to determine particular measurement units, and geometric shapes with the help of CST Studio Suit 2019. Here both ground and patch are designed using copper and the separator is designed with Roger. Moreover, the thickness of the absorber is only 3.4 mm which ensures its ultra-thin and lightweight nature. With an elaborated numerical analysis, it has been shown that the proposed absorber provides 90% to 99% absorption at the C, X, and K bands. Moreover, a concise computational analysis is accomplished with FR4 lossy, Rogers RT6010LM lossy, and Rogers RT5870LM lossy as dielectric constant. The key contribution of this research is the high absorption rate, coupled with minimal thickness and simple structure. © 2024 IEEE.

关键词： Metamaterials

来源：评论

学校读者我要写书评

暂无评论

Enhancing Question-Answering with Knowledge Graph Retrieval and Generation using LLMs

Enhancing Question-Answering with Knowledge Graph Retrieval ...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Gijre, Supraj Agrawal, Rishi Laddha, Priyash Keswani, Gunjan Shri Ramdeobaba College of Engineering and Management Dept. Computer Science and Engineering Nagpur India School of Computer Science and Engineering Ramdeobaba University Nagpur India

ISBN: (纸本)9798331517953

This paper describes a novel technique to improving Large Language Models (LLMs) for document analysis that employs knowledge graphs and retrieval-augmented generation (RAG). We are working on constructing a chatbot system that can handle and analyze large documents from a variety of fields. Our approach addresses basic LLM issues including context maintenance and hallucination avoidance. The system combines document chunking, vector embedding, and similarity search with graph-based knowledge representation. Users can upload large papers and answer questions accurately. We show that integrating standard information retrieval approaches with graph-based storage and LLM capabilities improves context awareness and response accuracy across a wide range of document genres. This strategy is especially promising for complicated publications such as financial reports. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

A Novel Conditional Wasserstein Deep Convolutional Generative Adversarial Network

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年 1-13页

作者： Roy, Arunava Dasgupta, Dipankar Dept. of Computer Science The University of Memphis Memphis TN USA

Generative Adversarial Networks (GAN) and their several variants have not only been used for adversarial purposes but also used for extending the learning coverage of different AI/ML models. Most of these variants are unconditional and do not have enough control over their outputs. Conditional GANs (CGANs) have the ability to control their outputs by conditioning their generator and discriminator with an auxiliary variable (such as class labels, and text descriptions). However, CGANs have several drawbacks such as unstable training, non-convergence and multiple mode collapses like other unconditional basic GANs (where the discriminators are classifiers). DCGANs, WGANs, and MMDGANs enforce significant improvements to stabilize the GAN training although have no control over their outputs. We developed a novel conditional Wasserstein GAN model, called CWGAN (a.k.a RD-GAN named after the initials of the authors' surnames) that stabilizes GAN training by replacing relatively unstable JS divergence with Wasserstein-1 distance while maintaining better control over its outputs. We have shown that the CWGAN can produce optimal generators and discriminators irrespective of the original and input noise data distributions. We presented a detailed formulation of CWGAN and highlighted its salient features along with proper justifications. We showed the CWGAN has a wide variety of adversarial applications including preparing fake images through a CWGAN-based deep generative hashing function and generating highly accurate user mouse trajectories for fooling any underlying mouse dynamics authentications (MDAs). We conducted detailed experiments using well-known benchmark datasets in support of our claims. IEEE

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

On the Rival Nature of Data: Tech and Policy Implications 25

On the Rival Nature of Data: Tech and Policy Implications

引用

4th ACM Symposium on computer science and Law, CS and LAW 2025

作者： Gordon-Tapiero, Ayelet Ligett, Katrina Nissim, Kobbi Hebrew University Dept. of Computer Science Jerusalem Israel Georgetown University Dept. of Computer Science WashingtonDC United States

ISBN: (纸本)9798400714214

Data is often thought of and treated as a non-rival good, which would imply that one person’s use of data does not inherently diminish its availability for others. Building on research in privacy and statistics, we argue that there exist many important settings in which data should be treated as a rival good. Our argument takes into account modern uses of data for statistics, machine learning, and a variety of other purposes, in conjunction with requirements of privacy protection and statistical validity. Excessive sharing or reuse of data about individuals can lead to leakage of sensitive personal information, potentially causing harm to those whose information is included in the data. Overuse of data in statistics or machine learning can lead to overfitting, i.e., models that perform well on training data but poorly on fresh unseen data. Recognizing the rival nature of data offers an opportunity to rethink the way data are managed and used. In an age where the training of AI models generates a massive appetite for data, this perspective has the potential to inform the creation of new regulation and technical infrastructure that will be able to safely and responsibly manage data, track their various uses, and ensure that privacy and statistical usefulness are respected and preserved. We observe that current EU regulation and existing approaches to science seeking to increase opportunities for data-sharing and reuse of data misconstrue the complex nature of data, inadvertently creating risks of privacy harms and overfitting, hence squandering the societal benefits that can be derived from data. Recognizing the rival nature of data has implications for policy and practice. Regulation should address the limitations and risks associated with data reuse and facilitate technological measures to track, analyze, and manage data usage with the goal of ensuring that privacy and statistical validity are maintained. © 2025 Copyright held by the owner/author(s).

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Virtual Video Game as a Clinical Tool for Psychological Assessment and Analysis

Virtual Video Game as a Clinical Tool for Psychological Asse...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Gope, Aditya Kumar Pohane, Karthik Jakkanwar, Shivam Ramasamy, Gobi Dept. of Computer Science Bangalore India

ISBN: (纸本)9798350309140

This paper proposes a very novel and dynamic approach to psychological assessment by utilising virtual video games as a psychometric tool. Traditional methods, such as interviews and surveys, often yield conscious responses, leading to potential inaccuracies. Leveraging the interactive and immersive nature of video games, our research aims to enhance the accuracy and engagement of data collection. We introduce a dynamic scale to quantify player responses, providing a structured framework for systematic assessment. Collected data can be analysed using statistical models or customised by experts to evaluate psychological indicators precisely. This research explores the benefits of virtual video games in improving the accuracy, engagement, and flexibility of psychological assessments, contributing to more effective solutions in clinical psychology. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

An Ensemble-based Deep Learning Model for Multi-class Flower Recognition

An Ensemble-based Deep Learning Model for Multi-class Flower...

引用

2023 International Conference on Next-Generation Computing, IoT and Machine Learning, NCIM 2023

作者： Rabbi, Md Fozle Dola, Sraboni Das Taha, Noorjahan Binte Kader Al Mahmud, Tamim Islam, Muhammad Nazrul Razzaque, Md. Abdur Al Faisal, Faiz Green University of Bangladesh Dept. of Computer Science and Engineering Dhaka Bangladesh Military Institute of Science and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh University of Dhaka Dept. of Computer Science and Engineering Dhaka1000 Bangladesh

ISBN: (纸本)9798350316001

Many species around the globe heavily depend on flowers, and even the use of flowers for medical purposes is enormous, which has been in practice since ancient times. In modern botany, agronomy, and species research, the identification and classification of flowers mainly depend on human intervention, which requires a lot of human resources, and the recognition accuracy rate is low. On the other hand, due to the vast number of flowers with different types, it is quite a challenge and increases the complexity of the accurate detection and classification process. Moreover, the traditional CNN model and other pre-trained models like- VGG16, VGG19, Xception, and MobileNet-V2 failed to ensure high validation accuracy. In this research, we have designed an ensemble-based deep learning model consisting of two pre-trained models DenseNet-201 and EfficientNet-B7, which we renamed 'FlowerConvNet'. This paper considers classifying five categories of flowers consisting of 4242 images, collected from the Kaggle flower recognition dataset. In this research study, the proposed deep learning model FlowerConvNet using transfer learning can obtain a competitive result with 95% validation accuracy. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Cloud Intrusion Detection: Internet of Things and Cloud Networks 1

Deep Learning-Driven Cloud Intrusion Detection: Internet of ...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Moon, Iffath Tanjim Islam Mondal, Md. Nazrul Rajshahi University of Engineering & Technology Dept. of Computer Science & Engineering Rajshahi6204 Bangladesh

ISBN: (纸本)9798331518578

In this paper, we have utilized deep learning approaches to detect cloud intrusion for the Internet of Things (IoT). The emerging growth of IoT and cloud environments has revolutionized many industries by allowing real-time data sharing and storage. Cloud platforms offer the essential infrastructure for managing the massive volumes of data produced by IoT devices. However, due to several flaws, including insufficient encryption, insecure APIs, and weak authentication, intruders can exploit the vulnerabilities to interrupt services and obtain unauthorized access. Therefore, deep learning can be an effective solution to detect cloud intrusion in IoT. In this research, we have developed individual convolutional neural network (CNN) and long short-term memory (LSTM) models, along with a hybrid CNN-LSTM model for multiclass classification and binary classification to detect cloud intrusion. In addition, we have examined which models perform the best for cloud intrusion detection for IoT among the individual and hybrid models. The proposed models are effective in detecting cloud intrusion, as CNN can extract spatial features, and LSTM can capture temporal dependencies from network traffic data. Furthermore, we have utilized one of the most recent and comprehensive datasets for IoT, the ToN-IoT dataset, containing real-world data. In multiclass classification, the hybrid CNN-LSTM has given the best performance, achieving an accuracy of 97.65%, precision of 97.72%, recall of 97.65%, f1 score of 97.67%, and AUC of 99.93%. In binary classification, all CNN, LSTM, and hybrid CNN-LSTM have demonstrated high performance, where LSTM has achieved the highest accuracy of 99.97%. Moreover, we have evaluated the performance of multiclass classification for detecting nine distinct kinds of attacks. In this instance, CNN has shown better performance in detecting backdoor attacks. Thus, this research can make the IoT platform more secure by efficiently detecting cloud intrusion. © 2025

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

EMRChain: Electronic Medical Records Management System using Blockchain 3

EMRChain: Electronic Medical Records Management System using...

引用

3rd IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2024

作者： Rajasekharan, Arjun Koshy, Rani College of Engineering Trivandrum Dept. of Computer Science and Engineering Kerala Thiruvananthapuram India College of Engineering Trivandrum Department of Computer Science and Engineering Kerala Thiruvananthapuram India

ISBN: (纸本)9798350354348

Electronic Medical Records (EMRs) are traditionally managed by central authorities, posing significant security risks such as data breaches, limited interoperability, and restricted patient control. This system leverages blockchain technology to address these issues, ensuring data remains immutable, transparent, and highly secure. Utilizing the Ethereum network and IPFS technology, our system provides a decentralized framework for storing and sharing medical records. Healthcare professionals, patients, and authorized parties can seamlessly exchange and access records through Ethereum's decentralized structure and smart contracts, enabling automated and auditable interactions. To enhance confidentiality, all data uploaded to IPFS undergoes AES 256-bit encryption, with the encrypted Content Identifier (CID) stored on the blockchain. This ensures that intercepted CIDs cannot be accessed without the decryption key. IPFS technology facilitates decentralized storage and retrieval, eliminating the need for a centralized server and improving scalability and resilience. Patients retain full control over their health information, granting or revoking access as necessary. This system ensures secure patient identification, precise access management, and data confidentiality while allowing authorized parties to track and trace record access and modifications. Our blockchain-based EMR management system addresses the inherent risks of traditional centralized systems by providing a secure, transparent, and decentralized solution. By leveraging Ethereum and IPFS, it enhances data security, patient control, and interoperability, thus paving the way for more robust and patient-centric healthcare information management. This approach ensures that healthcare data remains secure, patients maintain control over their information, and authorized parties can effectively manage and access the records. © 2024 IEEE.

关键词： Ethereum

来源：评论

学校读者我要写书评

暂无评论

Exploring Taiwan Monkeypox Virus (MPOX/MPXV) Clade IIb by Establishing Dataset and Clustering by using Sequence and Image Similarity Comparisons 24

Exploring Taiwan Monkeypox Virus (MPOX/MPXV) Clade IIb by Es...

引用

7th International Conference on Computational Intelligence and Intelligent Systems, CIIS 2024

作者： Wang, Tzung-Wei Li, Ming-Kuang Lou, Der-Chyuan Lin, Chun-Yuan Dept. of Electronics Engineering Chang Gung University Taoyuan Taiwan Dept. of Computer Science and Information Engineering Asia University Taiwan Taichung Taiwan Dept. of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan

ISBN: (纸本)9798400717437

Based on the MPXV Clade IIb cases in Taiwan, 175 segments were identified from OPG001 to OPG210. The first focus of this paper is on sequence analysis of the MPXV cases in Taiwan, detailing the procedures, including semi-automated segmentation and dataset creation from a large number of MPXV Clade IIb nucleotide sequences found in the NCBI and GISAID databases. The second feature highlights the pioneering establishment of an MPXV Clade IIb RNA 2nd structure image dataset in Taiwan, as such a dataset does not yet exist globally. The third characteristic involves the use of unsupervised learning methods for the rapid clustering of MPXV Clade IIb RNA 2nd structure images. This approach allows not only for the quick detection and clustering of unknown MPXV Clade IIb cases but also for the rapid identification of new MPXV mutations and structural changes. Compared to traditional sequence analysis, this new hybrid systematic method significantly enhances overall efficiency, improving processing speed by at least 24 hours when handling the alignment of 10 MPXV sequences from Taiwan. Future plans include using this prototype analytical model and method to accelerate the analysis of critical lethal factors in MPXV Clade IIb, such as D14L, ultimately helping biologists reduce the time required for analysis and antiviral drug development. © 2024 Copyright held by the owner/author(s).

关键词： Nucleotides

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：