检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, IaiCT 2024

作者： Yang, Janghoon Computer Science Program Division of Science and Engineering Penn State Abington AbingtonPA United States

ISBN: (纸本)9798350353464

While deep learning can offer a promising approach to sentiment analysis, it often presents challenges in complexity and explainability. Alternatively, sentiment analysis based on dictionaries has been explored. In this paper, subword-level dictionaries in English are considered to address performance degradation resulting from domain mismatches. To work at subword level, a framework based on naïve bayes machine learning algorithm is exploited. Furthermore, stopwords at the subword level have been proposed to remove additional interference intrinsic to subword tokenization. Numerical experiments demonstrate that the proposed method achieves higher accuracy and F1 scores compared to the conventional dictionary-based method when there is a mismatch between the dictionary and the corpus of documents while performing marginally worse than state-of-the-art deep learning methods when applied to datasets from the same domain. ©2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Computational Optimization of RIS-Enhanced Backscatter and Direct Communication for 6G IoT:A DDPG-Based Approach with Physical Layer Security

引用

computer Modeling in engineering & sciences 2025年第3期142卷 2191-2210页

作者： Syed Zain Ul Abideen Mian Muhammad Kamal Eaman Alharbi Ashfaq Ahmad Malik Wadee Alhalabi Muhammad Shahid Anwar Liaqat Ali College of Computer Science and Technology Qingdao UniversityQingdao266071China School of Electronic Science and Engineering Southeast UniversityNanjing210018China Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah80200Saudi Arabia Department of Quality Assurance Al-Kawthar UniversityKarachi75300Pakistan Department of Computer Science Immersive Virtual Reality Research GroupKing Abdulaziz UniversityJeddah80200Saudi Arabia Department of AI and Software Gachon UniversitySeongnam-si13120Republic of Korea Department of Electrical Engineering University of Science and TechnologyBannu28100Pakistan

The rapid evolution of wireless technologies and the advent of 6G networks present new challenges and opportunities for Internet ofThings(IoT)applications,particularly in terms of ultra-reliable,secure,and energyefficient *** study explores the integration of Reconfigurable Intelligent Surfaces(RIS)into IoT networks to enhance communication *** traditional passive reflector-based approaches,RIS is leveraged as an active optimization tool to improve both backscatter and direct communication modes,addressing critical IoT challenges such as energy efficiency,limited communication range,and double-fading effects in backscatter *** propose a novel computational framework that combines RIS functionality with Physical Layer Security(PLS)mechanisms,optimized through the algorithm known as Deep Deterministic Policy Gradient(DDPG).This framework adaptively adapts RIS configurations and transmitter beamforming to reduce key challenges,including imperfect channel state information(CSI)and hardware limitations like quantized RIS phase *** optimizing both RIS settings and beamforming in real-time,our approach outperforms traditional methods by significantly increasing secrecy rates,improving spectral efficiency,and enhancing energy ***,this framework adapts more effectively to the dynamic nature of wireless channels compared to conventional optimization techniques,providing scalable solutions for large-scale RIS *** results demonstrate substantial improvements in communication performance setting a new benchmark for secure,efficient and scalable 6G *** work offers valuable insights for the future of IoT networks,with a focus on computational optimization,high spectral efficiency and energy-aware operations.

关键词： Computational optimization reconfigurable intelligent surfaces(RIS) 6G networks IoT and DDPG physical layer security(PLS) backscatter communication

来源：评论

学校读者我要写书评

暂无评论

Youtube Video Recommendation using user-based Collaborative Filtering and Graph Neural Networks Approaches to Improve users Personalized Experience 15

Youtube Video Recommendation using user-based Collaborative ...

引用

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

作者： Rock, Alvino C. Jebaseeli, T.Jemima Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore641114 India

ISBN: (纸本)9798331300579

YouTube's video recommendation method stands as a pinnacle in the realm of content discovery in enhancing user engagement on the *** User-Based Collaborative Filtering recommendation method relies on a robust foundation of data collection, encompassing user interactions, metadata, and content *** advanced deep learning techniques, videos and users are transformed into vectors within a high-dimensional space, forming the basis for understanding complex *** algorithm's training process involves the utilization of vast datasets, allowing the model to discern patterns in user behavior and content *** and rankings are determined in real-time, ensuring adaptability to evolving user *** feedback loop, fueled by user interactions, continuously refines the algorithm, striking a balance between user satisfaction and content ***'s commitment to preventing content bubbles is evident in the incorporation of diversity-enhancing strategies, introducing randomness and exploration to broaden user content *** remains a hallmark, tailoring recommendations based on individual user histories, preferences, and *** the recommendation method has significantly improved content discovery and user satisfaction, it is not without *** considerations, privacy concerns, and the need for algorithmic transparency remain focal points in ongoing *** forward, the future holds exciting possibilities, with emerging technologies poised to shape the evolution of YouTube's video recommendation method. © Grenze Scientific Society, 2024.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Ensemble of deep learning models with Walrus Optimization Algorithm for accurate botnet recognition and classification

引用

Iran Journal of computer science 2025年 1-18页

作者： Chacko, Ashwathy Anda Edwin, E. Bijolin Thanka, M. Roshni Ebenezer, V. Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Division of Data Science and Cyber Security Karunya Institute of Technology and Sciences Coimbatore India

The rapid growth of Internet of Things (IoT) networks has introduced significant security challenges, with botnet attacks being one of the most prevalent threats. These attacks exploit vulnerabilities in IoT devices, leading to severe disruptions and damage to critical infrastructures. Detecting botnet attacks in IoT environments is challenging due to the large volume of data, the dynamic nature of traffic, and the diverse attack patterns. To address these issues, we propose a novel approach called Walrus Optimized Ensemble Deep Learning for Anomaly-Based Recognition Classifier (WOAEDL-ABRC), which leverages a combination of advanced machine learning techniques for effective botnet detection. The methodology of this research involves four key components: (1) data preprocessing through min–max normalization to scale the features appropriately, (2) feature selection using the social cooperation search algorithm (SCSA) to identify the most informative attributes, (3) an ensemble deep learning model combining convolutional autoencoder (CAE), bidirectional gated recurrent unit (BiGRU), and deep belief network (DBN) for robust anomaly detection, and (4) hyperparameter optimization using the Walrus Optimization Algorithm (WAOA), which fine-tunes the model parameters for optimal performance. This ensemble approach ensures that the model benefits from the strengths of each individual technique while mitigating the weaknesses of others. The dataset used for this research includes network traffic data from IoT environments, consisting of various botnet attack scenarios and normal traffic patterns. The data undergoes extensive preprocessing and feature selection to reduce dimensionality and enhance the model’s performance. The implementation is carried out in Python using TensorFlow for deep learning, with the WAOA applied to optimize hyperparameters. The results demonstrate the effectiveness of the WOAEDL-ABRC in detecting botnet attacks, achieving superior accuracy, precision

关键词： Botnet recognition Deep learning Feature selection Internet of things Walrus Optimization Algorithm

来源：评论

学校读者我要写书评

暂无评论

Context is King: Rethinking Query Expansion in Modern Search Engines

Context is King: Rethinking Query Expansion in Modern Search...

引用

2025 International Conference on Artificial Intelligence and Data engineering, aiDE 2025

作者： Batri, Krishnan Lakshmi, S. Ramesh, S. Sangeetha, N. Annamalai, S. School of Computer Science and Engineering Bengaluru India Electronics and Communication Engineering Bengaluru India City Engineering College Department of AI&ML Bengaluru India

ISBN: (纸本)9798331527518

In the era of digital information overload, search engines have evolved beyond simple keyword matching to embrace context-aware methodologies. However, the task of accurately interpreting user intent remains a critical challenge, with traditional query expansion techniques often falling short of capturing semantic and contextual nuances. This paper critically examines the evolution of query expansion strategies, highlighting their limitations and exploring state-of-the-art techniques such as machine learning models, knowledge graphs, and transformer-based systems like BERT and GPT. Experimental results compare traditional methods like synonym expansion with modern approaches, demonstrating the superior relevance and diversity of results from context-aware systems. The study underscores the importance of integrating real-time contextual signals and dynamic user preferences to enhance search engine performance, paving the way for more personalized and accurate retrieval systems. © 2025 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Robust Detector Designing for FDA-MIMO Radar With Training Data in Gaussian Noise

引用

IEEE Transactions on Aerospace and Electronic Systems 2025年第3期61卷 7787-7802页

作者： Gui, Limin Huang, Bang Wang, Wen-Qin University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China King Abdullah University of Science and Technology Computer Electrical and Mathematical Science and Engineering Division Thuwal23955 Saudi Arabia Huzhou313001 China

This article presents the design of robust detectors for frequency diverse array multiple-input multiple-output radar in the presence of Gaussian noise with an unknown covariance matrix. It aims to address the challenge of detecting the target of a coherent return from an appointed cell under test. Our primary focus is on the case of signal mismatch, specifically considering the 2-D mismatch, including the target and the Doppler steering vectors. To tackle these issues, we introduce a fictitious signal with a specified structure in addition to the nominal steering vector, thereby forming a new hypothesis testing model. By making use of this model, we further derive robust detectors utilizing the generalized likelihood ratio test (GLRT) and the Wald test in the presence of training data. Besides, a parametric detector is implemented, which includes robust GLRT as a particular case. The proposed detectors own constant false alarm rate properties under the null hypothesis. The effectiveness of designed algorithms is verified by comparing their performance with those of their given counterparts. Moreover, numerical examples illustrate that the functionality of presented detectors is better compared to GLRT, adaptive matched filter, Wald, and multiple-input multiple-output Wald detectors in terms of robustness against signal mismatches. © 1965-2011 IEEE.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

A Faster Algorithm for Recognizing Directed Graphs Invulnerable to Braess s Paradox 23

A Faster Algorithm for Recognizing Directed Graphs Invulnera...

引用

23rd Symposium on Algorithmic Approaches for Transportation Modelling, Optimization, and Systems, ATMOS 2023

作者： Matsubayashi, Akira Saito, Yushi Division of Electrical Engineering and Computer Science Kanazawa University Japan

ISBN: (纸本)9783959773027

Braess s paradox is a counterintuitive and undesirable phenomenon, in which for a given graph with prescribed source and sink vertices and cost functions for all edges, removal of edges decreases the cost of a Nash flow from source to sink. The problem of deciding if the phenomenon occurs is generally NP-hard. In this paper, we consider the problem of deciding if, for a given graph with prescribed source and sink vertices, Braess s paradox does not occur for any cost functions. It is known that this problem can be solved in O(nm2) time for directed graphs, where n and m are the numbers of vertices and edges of the input graph, respectively. In this paper, we propose a faster O(m2) time algorithm solving this problem for directed graphs. Our approach is based on a simple implementation of a known characterization that the subgraph of a given graph induced by all source-sink paths is series-parallel. The faster running time is achieved by speeding up the simple implementation using another characterization that a certain structure is embedded in the given graph. Combined with a known technique, the proposed algorithm can also be used to design a faster O(km2) time algorithm for directed graphs with k source-sink pairs, which improves the previous O(knm2) time algorithm. © 2023 Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

SCADBIN: A Blockchain-based Security Framework for Electronic Health Record Management 14

SCADBIN: A Blockchain-based Security Framework for Electroni...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Fasila, K.A. Mathew, Sheena Division of Computer Engineering School of Engineering Cochin University of Science and Technology Kerala India Computer Science and Engineering Muthoot Institute of Technology and Science Kerala India

Tremendous increase in the use of distributed Internet of Things (IoT) based applications leads to the evolution of huge amount of data every second. As the volume of data and correspondingly the number of users increase, the need for protecting information also increases. Among various distributed IoT applications, healthcare industry is in the dominating position. The management of Electronic Health Record (EHR) is a serious matter of concern since this includes the patient’s personal as well as health related information. This work proposes the use of an efficient security framework for EHR management. SCADBIN stands for Security using Cellular Automata, Dynamic key and Blockchain for IoT Networks. This architecture provides multilevel protection to EHRs starting from the data acquisition phase till the data access phase by a requesting node. Thus, SCADBIN assures end to end protection to EHRs. The paper explains the methodology and implementation details. The comparison of this architecture with existing methods is provided at the end with valid experimental results. © Grenze Scientific Society, 2023.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Emergent classical spin liquid phases in an Ising lattice via size effects

引用

Physical Review B 2024年第2期109卷 L020303-L020303页

作者： Pratik Brahma Sayeef Salahuddin Department of Electrical Engineering and Computer Sciences University of California Berkeley California 94720 USA Materials Science Division Lawrence Berkeley National Laboratory Berkeley California 94720 USA

We show that a classical spin liquid phase can emerge from an ordered magnetic state in the two-dimensional frustrated Shastry-Sutherland Ising lattice due to lateral confinement. Two distinct classical spin liquid states are stabilized: (i) long-range spin-correlated dimers, and (ii) exponentially decaying spin-correlated disordered states, depending on widths of W=3n, 3n+1 or W=3n+2,n being a positive integer. Stabilization of spin liquids in a square-triangular lattice moves beyond the conventional geometric paradigm of kagome, triangular, or tetrahedral arrangements of antiferromagnetic ions, where spin liquids have been discussed conventionally.

关键词： Phase diagrams Spin liquid Classical spin models Lattice types Ising model Transfer matrix calculations

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Dataset of Real-scene Images for Text Detection and Recognition in Persian 14

A Comprehensive Dataset of Real-scene Images for Text Detect...

引用

14th International Conference on computer and Knowledge engineering, ICCKE 2024

作者： Souzanchi, Iman Rahimi, Ramin Anvari, Mohammad Ali Majidi Baniasadi, Atefeh Sadeghi, Ashkan Mohammadi, Mohammad Reza PART AI Research Center Tehran Iran School of Computer Engineering Iran University of Science and Technology Tehran Iran

ISBN: (纸本)9798331511272

— Extracting text from scene images is a widely utilized field owing to the abundance of information available in scene images and their potential utilization in computer vision applications such as self-driving cars, text translation, information extraction from invoices, shopfronts, license plate retrieval, etc. Nonetheless, this field presents challenges because of the varying fonts, styles, sizes, and other characteristics of the text. Despite the existence of numerous studies on scene text recognition for languages such as English that employ deep learning models, a major barrier to implementing these models in Persian is the lack of an appropriate and sufficient dataset both in terms of quantity and quality. This paper aims to introduce a comprehensive collection of Persian scene images obtained from diverse sources, including newspapers, magazines, books, business cards, road signs, advertising billboards, shopfronts, invoices, and scanned documents. This dataset comprises over 250k annotated text lines from 5000 images, including various lengths, fonts, and sizes that have been prepared under different conditions, including varying brightness and viewing angles. Additionally, more than 2,500,000 images of meaningful sentences have been synthesized since the annotation of real data is so expensive. In order to assess the efficacy of our dataset, a scene text recognition model was trained from existing models, and a word accuracy of 83.9% was achieved on challenging test images. ©2024 IEEE.

关键词： Image annotation

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：