检索结果-内蒙古大学图书馆

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Chatterjee, Priyadarshini Das, Surajit Siddiqui, Shadab B V Raju Institute Of Technology Department Of Computer Science And Engineering Medak Telengana Narsapur India B V Raju Institute Of Technology Department Of Artificial Intelligence And Data Science Medak Telengana Narsapur India Koneru Lakshmaiah Education Foundation Department Of Computer Science And Engineering Hyderabad India

ISBN: (纸本)9798350371567

Masking, in the context of image processing and computer vision, refers to the process of isolating specific regions or objects of interest within an image while suppressing or removing irrelevant information. It involves the creation of a mask, which is essentially a binary image that defines which pixels in the original image belong to the region of interest and which do not. The mask typically consists of black and white pixels, where white pixels represent the areas to be preserved or highlighted, and black pixels represent the areas to be ignored or masked out. This paper presents a novel approach aimed at enhancing the accuracy of masking algorithms for colposcopy images, a crucial component in the diagnosis of cervical cancer among women. While previous research has demonstrated promising outcomes in this domain, our study introduces a novel masking algorithm tailored specifically to improve segmentation accuracy. The colposcopy dataset utilized in this research is sourced from the International Agency for Research on Cancer in France. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

FasMe: Fast and Sample-efficient Meta Estimator for Precision Matrix Learning in Small Sample Settings 38

FasMe: Fast and Sample-efficient Meta Estimator for Precisio...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tan, Xiao Wang, Yiqin Shen, Yangyang Shen, Dian Wang, Meng Duan, Peibo Wang, Beilun School of Computer Science and Engineering Southeast University Nanjing China College of Design and Innovation Tongji University Shanghai China Department of Data Science & AI Monash University Melbourne Australia

Precision matrix estimation is a ubiquitous task featuring numerous applications such as rare disease diagnosis and neural connectivity exploration. However, this task becomes challenging in small sample settings, where the number of samples is significantly less than the number of dimensions, leading to unreliable estimates. Previous approaches either fail to perform well in small sample settings or suffer from inefficient estimation processes, even when incorporating meta-learning techniques. To this end, we propose a novel approach FasMe for Fast and Sample-efficient Meta Precision Matrix Learning, which first extracts meta-knowledge through a multi-task learning diagram. Then, meta-knowledge constraints are applied using a maximum determinant matrix completion algorithm for the novel task. As a result, we reduce the sample size requirements to O(log p/K) per meta-training task and O(log |G|) for the meta-testing task. Moreover, the hereby proposed model only needs O(p log ϵ−1) time and O(p) memory for converging to an ϵ-accurate solution. On multiple synthetic and biomedical datasets, FasMe is at least ten times faster than the four baselines while promoting prediction accuracy in small sample settings. © 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

English Offensive Text Detection using CNN based Bi-GRU model 2

English Offensive Text Detection using CNN based Bi-GRU mode...

引用

2nd International Conference on Information and Communication Technology, ICICT 2024

作者： Roy, Tonmoy Islam, Md Robiul Miazee, Asif Ahammad Antara, Anika Al Amin Hossain, Sunjim Data Analytics & Information Systems Utah State University Utah United States Computer Science William & Mary Virginia United States Computer Science Maharishi International University Iowa United States Electrical and Electronics Engineering Brac University Dhaka Bangladesh Computer Science Uttara University Dhaka Bangladesh Computer Science Northern University Dhaka Bangladesh

ISBN: (纸本)9798331508227

Over the years, the number of users of social media has increased drastically. People frequently share their thoughts through social platforms, and this leads to an increase in hate content. In this virtual community, individuals share their views, express their feelings, and post photos, videos, blogs, and more. Social networking sites like Facebook and Twitter provide platforms to share vast amounts of content with a single click. However, these platforms do not impose restrictions on the uploaded content, which may include abusive language and explicit images unsuitable for social media. To resolve this issue, a new idea must be implemented to divide the inappropriate content. Numerous studies have been done to automate the process. In this paper, we propose a new Bi-GRU-CNN model to classify whether the text is offensive or not. The combination of the Bi-GRU and CNN models outperforms the existing models. ©2024 IEEE.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Multi-Head Self-Attention Based Arabic News Recommendation System 6

Multi-Head Self-Attention Based Arabic News Recommendation S...

引用

6th International Conference on Advanced Aspects of Software engineering, ICAASE 2024

作者： Sabrina, Karboua Harrag, Fouzi Meziane, Farid Departement of Computer Science Mechatronics Laboratory Ferhat ABBAS University Setif 1 Setif Algeria Data Science Research Centre School of Computing and Engineering University of Derby United Kingdom

ISBN: (纸本)9798331522810

This paper introduces an Arabic News Recommendation System (ANRS) designed to enhance personalized news recommendations for Arabic-speaking users. By leveraging a multi-head self-Attention mechanism, the proposed model effectively captures complex dependencies within Arabic text, addressing challenges posed by the language's rich morphology and contextual nuances. The news encoder uses multi-head self-Attention to learn the meaning of Arabic news articles by analyzing interactions between words in titles, body text. Meanwhile, the user encoder models user preferences by examining previously read articles, also using multi-head self-Attention to capture connections between articles. Trained on a dataset of Arabic news articles and 15 million user interaction logs, ANRS achieves a high prediction accuracy of 98.6%, significantly outperforming traditional and deep learning-based Arabic recommendation models. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging Support Vector Machines for Detection of Network Traffic Attacks 4

Leveraging Support Vector Machines for Detection of Network ...

引用

4th International Conference on Advancement in Electronics and Communication engineering, AECE 2024

作者： Tiwari, Anurag Indian Institute of Technology School of Artificial Intelligence & Data Science Jodhpur India Babu Banarasi das Institute of Technology& Management Department of Computer Science & Engineering Lucknow India

ISBN: (纸本)9798350364729

Network security is crucial to ensure the protection of information systems in an increasingly connected world, and network traffic attack detection is an important aspect of maintaining system integrity. This study addresses this by investigating the use of a powerful and flexible machine learning algorithm, namely Support Vector Machines (SVM), to detect network traffic attacks. As a result, SVM has been successfully applied in different domains like network security, etc. In this study, SVM is applied for normal and malicious network traffic classification, including several attack types like Denial-of-Service (DoS), User-to-Root (U2R), and Remote-to-Local (R2L) attacks. To this end, the KDD Cup 99 dataset is employed for training and testing the model. These metrics are then used to evaluate the performance of the SVM-based intrusion detection system. The results demonstrate that SVM is able to recognize a high level of accurateness on network data traffic attacks as well as it has performed well in a difficult attack trends. In this case, the F1-scores for the Linear and RBF did result in 96.65/99.24, respectively, indicating that SVM also proved to be an effective algorithm choice in this example. Finally, the study either propose new algorithms or improve existing algorithms for SVM and demonstrate their effectiveness in the area of network security. In conclusion, this study reinforces the importance of SVM as an effective instrument in the detection of attacks on network traffic and strengthening cyber defense capabilities. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Towards Artist Recognition Based on Material Rendering. A Case Study for Recognition of Rembrandt and Van Dyck

Towards Artist Recognition Based on Material Rendering. A Ca...

引用

IS and T International Symposium on Electronic Imaging 2024: computer Vision and Image Analysis of Art 2024

作者： Huang, Jing Elgammal, Ahmed Department of Big Data and Software Engineering Chongqing University Chongqing China Department of Computer Science Rutgers University NJ United States

Can artists be recognized from the way they render certain materials, such as fabric, skin, or hair? In this paper, we study this problem with a focus on recognizing works by Rembrandt, Van Dyck, and other Dutch and Flemish artists from the same era. This paper proposes a novel material-based approach based on Swin Transformer and Cascade Mask R-CNN to address artist recognition task. We report the performance on a dataset of 644 images. Additionally, the model’s robustness to image variations is studied. © 2024, Society for Imaging science and Technology.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network 38

Regularized Adaptive Momentum Dual Averaging with an Efficie...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Huang, Zih-Syuan Lee, Ching-Pei Department of Computer Science and Information Engineering National Taiwan University Taipei106 Taiwan Department of Advanced Data Science Institute of Statistical Mathematics Tachikawa Tokyo190-8562 Japan

We propose a Regularized Adaptive Momentum Dual Averaging (RAMDA) algorithm for training structured neural networks. Similar to existing regularized adaptive methods, the subproblem for computing the update direction of RAMDA involves a nonsmooth regularizer and a diagonal preconditioner, and therefore does not possess a closed-form solution in general. We thus also carefully devise an implementable inexactness condition that retains convergence guarantees similar to the exact versions, and propose a companion efficient solver for the subproblems of both RAMDA and existing methods to make them practically feasible. We leverage the theory of manifold identification in variational analysis to show that, even in the presence of such inexactness, the iterates of RAMDA attain the ideal structure induced by the regularizer at the stationary point of asymptotic convergence. This structure is locally optimal near the point of convergence, so RAMDA is guaranteed to obtain the best structure possible among all methods converging to the same point, making it the first regularized adaptive method outputting models that possess outstanding predictive performance while being (locally) optimally structured. Extensive numerical experiments in large-scale modern computer vision, language modeling, and speech tasks show that the proposed RAMDA is efficient and consistently outperforms state of the art for training structured neural network. Implementation of our algorithm is available at https://***/ismoptgroup/RAMDA/. © 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

Robust Sign Language Recognition Leveraging Bi-LSTM with CNN 2

Robust Sign Language Recognition Leveraging Bi-LSTM with CNN

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Jansirani, S. Savitha, N. Kiruba Priyadharshini, V. Sruthi Sree, S.G. Jansons Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Coimbatore India Jansons Institute of Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534950

People who are partially or completely deaf are considered hearing impaired or silent. Communication is the primary obstacle they encounter. Sign Language Recognition (SLR) model provides a mechanism to improve accessibility and inclusion by facilitating smooth communication, which is used to address this issue. Traditional SLR systems frequently use alternative designs, such as CNNs alone or regular Recurrent Neural Networks (RNNs). However, that may not be able to handle long-term dependencies in video data or interpret sequence data. This paper uses a model which improves sequential pattern recognition and outperforms conventional RNNs in continuous recognition by combining CNN for visual feature extraction from ISL video frames with BiLSTM to capture temporal relationships. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Coexistence of 802.11 WLAN and 5G Networks using a Multi-Task Learning with Convolutional Neural Network Model 2

Enhancing the Coexistence of 802.11 WLAN and 5G Networks usi...

引用

2nd International Symposium on Information Technology and Digital Innovation, ISITDI 2024

作者： Putra, Dody Ichwana Ekariani, Shelvi Universitas Andalas Dept. of Computer Engineering Padang Indonesia Universitas Andalas Dept. of Mathematics and Data Science Padang Indonesia

ISBN: (纸本)9798350389241

The increasing need for high-speed internet for wireless devices has driven the development of 5G New Radio (NR) technology. The 5G NR operates in various spectrums such as sub-1 GHz, sub-6 GHz, and millimeter wave (mmWave) in the 26-28 GHz range. Conversely, the new standard Wi-Fi 6E operates on the unlicensed band and currently utilizes 2.4 GHz, 5 GHz, and 6 GHz. The coexistence of 5G NR sub-6 GHz and Wi-Fi 6E networks can result in interference and reduced performance for both technologies. To address this challenge, we introduce a Multi-Task Learning (MTL) approach using Convolutional Neural Networks (CNN) to improve the coexistence of 5G and Wi-Fi 6E networks. This proposes identifying and classifying packets transmitted and its modulation over both types of networks. The MTL-CNN model is trained to classify packets based on their type (e.g., 5G or Wi-Fi) and to identify the specific protocol used within each packet. We confirm the accuracy of this method with Wi-Fi and 5G signals produced by the MATLAB waveform simulator and subsequently deploy it on a hardware testbed using SDR. Our experimental results show that this method improves the accuracy of packet identification and classification, thus enhancing the coexistence between 5G and Wi-Fi 6E networks. MTL-CNN potentially leads to more efficient use of the wireless spectrum and improves the overall performance of wireless communication systems. © 2024 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Algorithm Based Task Scheduling in IoT Enabled Cloud Environment

引用

computers, Materials & Continua 2022年第4期71卷 1095-1109页

作者： R.Joshua Samuel Raj M.Varalatchoumy V.L.Helen Josephine A.Jegatheesan Seifedine Kadry Maytham N.Meqdad Yunyoung Nam Department of Information Science&Engineering CMR Institute of TechnologyBengaluru560037India Department of Computer Science&Engineering Cambridge Institute of TechnologyBengaluru560036India Department of Computer Applications CMR Institute of TechnologyBengaluru560037India Department of Computer Science&Engineering Swarnandhra College of Engineering and TechnologyNarasapur534280India Department of Applied Data Science Noroff University CollegeKristiansand4612Norway Department of Computer Techniques Engineering Al-Mustaqbal University CollegeHillah51001Iraq Department of Computer Science and Engineering Soonchunhyang University31538Korea

Internet of Things (IoT) is transforming the technical setting ofconventional systems and finds applicability in smart cities, smart healthcare, smart industry, etc. In addition, the application areas relating to theIoT enabled models are resource-limited and necessitate crisp responses, lowlatencies, and high bandwidth, which are beyond their abilities. Cloud computing (CC) is treated as a resource-rich solution to the above mentionedchallenges. But the intrinsic high latency of CC makes it nonviable. The longerlatency degrades the outcome of IoT based smart systems. CC is an emergentdispersed, inexpensive computing pattern with massive assembly of heterogeneous autonomous systems. The effective use of task scheduling minimizes theenergy utilization of the cloud infrastructure and rises the income of serviceproviders by the minimization of the processing time of the user job. Withthis motivation, this paper presents an intelligent Chaotic Artificial ImmuneOptimization Algorithm for Task Scheduling (CAIOA-RS) in IoT enabledcloud environment. The proposed CAIOA-RS algorithm solves the issue ofresource allocation in the IoT enabled cloud environment. It also satisfiesthe makespan by carrying out the optimum task scheduling process with thedistinct strategies of incoming tasks. The design of CAIOA-RS techniqueincorporates the concept of chaotic maps into the conventional AIOA toenhance its performance. A series of experiments were carried out on theCloudSim platform. The simulation results demonstrate that the CAIOA-RStechnique indicates that the proposed model outperforms the original version,as well as other heuristics and metaheuristics.

关键词： Internet of things cloud computing task scheduling metaheuristics resource allocation

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：