检索结果-内蒙古大学图书馆

Performance *** Comparative Analysis of Multimodal Bilinear Pooling Fusion Approaches for Deep Learning-Based Visual Arabic-Question Answering systems

引用

computer Modeling in Engineering & sciences 2025年第4期143卷 373-411页

作者： Sarah M.Kamel Mai A.Fadel Lamiaa Elrefaei Shimaa I.Hassan Electrical Engineering Department Faculty of Engineering at ShoubraBenha UniversityCairo11629Egypt Computer Science Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer and Systems Engineering Faculty of Engineering and TechnologyBadr University in Cairo(BUC)Cairo11829Egypt Communication Systems Engineering Department Faculty of EngineeringBenha National UniversityObour11846QalyubiaEgypt

Visual question answering(VQA)is a multimodal task,involving a deep understanding of the image scene and the question’s meaning and capturing the relevant correlations between both modalities to infer the appropriate *** this paper,we propose a VQA system intended to answer yes/no questions about real-world images,in *** support a robust VQA system,we work in two directions:(1)Using deep neural networks to semantically represent the given image and question in a fine-grainedmanner,namely ResNet-152 and Gated Recurrent Units(GRU).(2)Studying the role of the utilizedmultimodal bilinear pooling fusion technique in the *** the model complexity and the overall model *** fusion techniques could significantly increase the model complexity,which seriously limits their applicability for VQA *** far,there is no evidence of how efficient these multimodal bilinear pooling fusion techniques are for VQA systems dedicated to yes/no ***,a comparative analysis is conducted between eight bilinear pooling fusion techniques,in terms of their ability to reduce themodel complexity and improve themodel performance in this case of VQA *** indicate that these multimodal bilinear pooling fusion techniques have improved the VQA model’s performance,until reaching the best performance of 89.25%.Further,experiments have proven that the number of answers in the developed VQA system is a critical factor that *** the effectiveness of these multimodal bilinear pooling techniques in achieving their main objective of reducing the model *** Multimodal Local Perception Bilinear Pooling(MLPB)technique has shown the best balance between the model complexity and its performance,for VQA systems designed to answer yes/no questions.

关键词： Arabic-VQA deep learning-based VQA deep multimodal information fusion multimodal representation learning VQA of yes/no questions VQA model complexity VQA model performance performance-complexity trade-off

来源：评论

学校读者我要写书评

暂无评论

Intelligent indoor metasurface robotics

引用

National science Review 2023年第8期10卷 20-32页

作者： Hanting Zhao Shengguo Hu Hongrui Zhang Zhuo Wang Hao Dong Philipp del Hougne Tie Jun Cui Lianlin Li State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Center on Frontiers of Computing Studies School of Computer Science Peking University The French National Centre for Scientific Research(CNRS) University of Rennes State Key Laboratory of Millimeter Waves Southeast University

Intelligent indoor robotics is expected to rapidly gain importance in crucial areas of our modern society such as at-home health care and factories. Yet, existing mobile robots are limited in their ability to perceive and respond to dynamically evolving complex indoor environments because of their inherently limited sensing and computing resources that are, moreover, traded off against their cruise time and payload. To address these formidable challenges, here we propose intelligent indoor metasurface robotics(I2MR),where all sensing and computing are relegated to a centralized robotic brain endowed with microwave perception; and I2MR's limbs(motorized vehicles, airborne drones, etc.) merely execute the wirelessly received instructions from the brain. The key aspect of our concept is the centralized use of a computation-enabled programmable metasurface that can flexibly mold microwave propagation in the indoor wireless environment, including a sensing and localization modality based on configurational diversity and a communication modality to establish a preferential high-capacity wireless link between the I2MR's brain and limbs. The metasurface-enhanced microwave perception is capable of realizing low-latency and high-resolution three-dimensional imaging of humans, even around corners and behind thick concrete walls, which is the basis for action decisions of the I2MR's brain. I2MR is thus endowed with real-time and full-context awareness of its operating indoor environment. We implement, experimentally, a proof-of-principle demonstration at ～2.4 GHz, in which I2MR provides health-care assistance to a human inhabitant. The presented strategy opens a new avenue for the conception of smart and wirelessly networked indoor robotics.

关键词： intelligent metasurfaces intelligent robotics edge devices IoT 6G

来源：评论

学校读者我要写书评

暂无评论

Delayed Squeezed Dedicated Path Protection in Spectrally-Spatially Flexible Optical networks 12

Delayed Squeezed Dedicated Path Protection in Spectrally-Spa...

引用

12th International Workshop on Resilient networks Design and Modeling, RNDM 2022

作者： Lechowicz, Piotr Knapinska, Aleksandra Walkowiak, Krzysztof Wroclaw University of Science and Technology Department of Systems and Computer Networks Poland

ISBN: (数字)9781665486774

ISBN: (纸本)9781665486774

Spectrally-spatially flexible optical networks (SSFONs) are proposed as a scalable solution to satisfy future capacity requirements in backbone optical networks. With the growing heterogeneity of network services, various protection mechanisms can be applied against network failures. SS-FONs are built on top of flex-grid, allowing for squeezed protection mechanism where the fraction of bandwidth is protected. Meanwhile, particular network request can serve non-time-crucial content, and their protected traffic can be postponed using assistive storage. In this work, we propose a novel protection approach, namely, delayed squeezed dedicated path protection (DSDPP), where protected requests, instead of transmitting squeezed bandwidth on the backup path, are transmitting full bandwidth but during a shorter period than the primary request. In more detail, the overall volume of backup requests in DSDPP matches the volume of conventionally squeezed requests. According to the conducted experiments, DSDPP decreases bandwidth blocking probability on average by around 16.9% when compared to squeezed dedicated path protection (SDPP). © 2022 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Fostering Digital Innovation in Indonesia: The Role of STEM-AI Skills in Overcoming Talent Deficits and Gender Stereotypes 4

Fostering Digital Innovation in Indonesia: The Role of STEM-...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Halim, Erwin Zahra, Amalia Maryani Wulandhari, Lili Ayu Fitrianah, Devi Puspita, Virienia School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Communication Department Jakarta11480 Indonesia

ISBN: (纸本)9798331506490

This research explores the optimization of digital talent in advanced industries, particularly in the context of rapid digital transformation. Despite the increasing importance of digital talent for gaining a competitive edge, several challenges persist. In Indonesia, for example, there is a significant shortage of digitally skilled workers, with the World Bank reporting a gap of 9 million skilled individuals over the past 15 years. Additionally, artificial intelligence (AI) is expected to impact 9.5 million jobs, further exacerbating the demand for digital skills. Furthermore, the employability of graduates remains low, largely due to inadequate training, poor language proficiency, and limited cultural sensitivity. Many companies face difficulties in finding qualified individuals, quickly upskilling their workforce, and fostering an innovative organizational culture. This study seeks to evaluate the factors influencing digital talent performance in the context of these challenges. It examines seven key variables: digital readiness, digital technology adoption, relevance of AI, digital skills, individual performance, problem-solving ability, and overall digital talent performance. Hypotheses were tested using Partial Least Squares Structural Equation Modeling (PLS-SEM). Data was collected from 378 participants, primarily students with STEM backgrounds, in the Jabodetabek area of Indonesia in November 2024. The findings reveal that all hypotheses are significant, with results indicating that user satisfaction and the perceived value of digital talent in Indonesia have a notable impact on continued usage intentions in digital roles. © 2024 IEEE.

关键词： digital readiness digital talent performances digital technology individual performance STEM-AI

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Semantic communications for Image Transmission Over MIMO Interference Channels 16

Benchmarking Semantic Communications for Image Transmission ...

引用

16th International Conference on Wireless communications and Signal Processing, WCSP 2024

作者： Wang, Yanhu Guo, Shuaishuai Dong, Anming Zhao, Hui School of Control Science and Engineering Shandong University China School of Computer Science and Technology Qilu University of Technology China Eurecom Communication Systems Department France

ISBN: (纸本)9798350390643

Semantic communications offer promising prospects for enhancing data transmission efficiency. However, existing schemes have predominantly concentrated on point-to-point transmissions. In this paper, we aim to investigate the validity of this claim in interference scenarios compared to baseline approaches. Specifically, our focus is on general multiple-input multiple-output (MIMO) interference channels, where we propose an interference-robust semantic communication (IRSC) scheme. This scheme involves the development of transceivers based on neural networks (NNs), which integrate channel state information (CSI) either solely at the receiver or at both transmitter and receiver ends. Moreover, we establish a composite loss function for training IRSC transceivers, along with a dynamic mechanism for updating the weights of various components in the loss function to enhance system fairness among users. Experimental results demonstrate that the proposed IRSC scheme effectively learns to mitigate interference and outperforms baseline approaches, particularly in low signal-tonoise (SNR) regimes. © 2024 IEEE.

关键词： Radio transceivers

来源：评论

学校读者我要写书评

暂无评论

Battery Management System for Polish Hybrid Residential Photovoltaic Power Plants 13th

Battery Management System for Polish Hybrid Residential Pho...

引用

13th International Conference on Image Processing and communications, IP and C 2023, 13th International Conference on computer Recognition systems, CORES 2023

作者： Parczyk, Pawel Burduk, Robert Department of Systems and Computer Networks Wroclaw University of Science and Technology Wybrzeże Wyspiańskiego 27 Wroclaw Poland

ISBN: (纸本)9783031416293

Growing share of Renewable Energy Sources (RES) in Polish electricity system has motivated the Polish government to make changes in the law. Those changes decrease the economic profit of using photovoltaic power plants, but incentivize the use of hybrid systems equipped with batteries. In this paper, the state-of-the-art battery management system, which maximizes self-consumption has been compared to our own time-based proposal, which is focused on economic profit. We used real-life measurements from a 6kWp residential power plant to compare both battery management systems. The results show that controlling batteries with our model allows us to save more money. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

Towards Threat Modelling of IoT Context-Sharing Platforms 22

Towards Threat Modelling of IoT Context-Sharing Platforms

引用

22nd International Symposium on Network Computing and Applications, NCA 2024

作者： Goudarzi, Mohammad Shaghaghi, Arash Finn, Simon Stiller, Burkhard Jha, Sanjay School of Computer Science and Engineering UNSW Sydney Australia Australia Communication Systems Group Department of Informatics University of Zurich Switzerland Cisco Australia

ISBN: (纸本)9798331510183

The Internet of Things (IoT) involves complex, interconnected systems and devices that depend on context-sharing platforms for interoperability and information exchange. These platforms are, therefore, critical components of real-world IoT deployments, making their security essential to ensure the resilience and reliability of these "systems of systems." In this paper, we take the first steps toward systematically and comprehensively addressing the security of IoT context-sharing platforms. We propose a framework for threat modelling and security analysis of a generic IoT context-sharing solution, employing the MITRE ATT&CK framework. Through an evaluation of various industry-funded projects and academic research, we identify significant security challenges in the design of IoT context-sharing platforms. Our threat modelling provides an in-depth analysis of the techniques and sub-techniques adversaries may use to exploit these systems, offering valuable insights for future research aimed at developing resilient solutions. Additionally, we have developed an open-source threat analysis tool that incorporates our detailed threat modelling, which can be used to evaluate and enhance the security of existing context-sharing platforms. ©2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Improving Prediction of Chronic Kidney Disease Using KNN Imputed SMOTE Features and TrioNet Model

引用

computer Modeling in Engineering & sciences 2024年第6期139卷 3513-3534页

作者： Nazik Alturki Abdulaziz Altamimi Muhammad Umer Oumaima Saidani Amal Alshardan Shtwai Alsubai Marwan Omar Imran Ashraf Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department College of Computer Science and Engineering University of Hafr Al-BatinHafarAl-Batin39524Saudi Arabia Department of Computer Science&Information Technology The Islamia University of BahawalpurP.O.Box 63100BahawalpurPakistan Department of Computer Science College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityP.O.Box 151Al-Kharj11942Saudi Arabia Information Technology and Management Illinois Institute of TechnologyChicagoIL 60616-3793USA Information and Communication Engineering Yeungnam UniversityGyeongsan38541Korea

Chronic kidney disease(CKD)is a major health concern today,requiring early and accurate *** learning has emerged as a powerful tool for disease detection,and medical professionals are increasingly using ML classifier algorithms to identify CKD *** study explores the application of advanced machine learning techniques on a CKD dataset obtained from the University of California,UC Irvine Machine Learning *** research introduces TrioNet,an ensemble model combining extreme gradient boosting,random forest,and extra tree classifier,which excels in providing highly accurate predictions for ***,K nearest neighbor(KNN)imputer is utilized to deal withmissing values while synthetic minority oversampling(SMOTE)is used for class-imbalance *** ascertain the efficacy of the proposed model,a comprehensive comparative analysis is conducted with various machine learning *** proposed TrioNet using KNN imputer and SMOTE outperformed other models with 98.97%accuracy for *** in-depth analysis demonstrates the model’s capabilities and underscores its potential as a valuable tool in the diagnosis of CKD.

关键词： Precisionmedicine chronic kidney disease detection SMOTE missing values healthcare KNNimputer ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Challenges to VANET When RFID Tags Utilized: a Study 3

Cybersecurity Challenges to VANET When RFID Tags Utilized: a...

引用

3rd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer Engineering, MI-STA 2023

作者： Shembesh, Ainor H. Darbi, Mariam K. Benamer, Sami Younis, Younis A. Libyan International Medical University Faculty of It Computer Networks Department Benghazi Libya University of Benghazi Faculty of Information Technology Departwmtnt of Inforamtion Systems Benghazi Libya University of Benghazi Faculty of Information Technology Department of Communication and Computer Networks Benghazi Libya

ISBN: (纸本)9798350319897

An emerging new technology called the Vehicular Ad Hoc Network (VANET) uses wireless technologies to enhance inter-vehicle communications and traffic safety. Due to its hybrid network designs, node movement characteristics, and novel application scenarios, VANET differs from other types of ad hoc networks. Moreover, the VANET utilizes some technologies for navigating. One of these technologies is Radio Frequency Identification (RFID) technology, which is used in many fields and applications to facilitate good communication and management of resources. Although RFID technology helps reduce the complexity of everyday life, it faces some challenges, the most important of that is security, which will be addressed in this paper. This paper extensively surveys the most severe cybersecurity challenges and attacks on VANET-RFID. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Tamil Sign Language Recognition Tool for the Deaf and Hard-of-Hearing Community.

Machine Learning-based Tamil Sign Language Recognition Tool ...

引用

2023 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Prabhu, D. Dhivyadharshini, K. Lokeswari, S. Pavithra Devi, T. Harithaa, S. Preethi, S. Sri Sairam Engineering College Department of Computer Science and Business Systems Chennai India Sri Sairam Institute of Technology Department of Computer and Communication Engineering Chennai India

ISBN: (纸本)9798350348910

This paper proposes a machine learning-based Tamil sign language recognition tool for the deaf and hard-of-hearing community. The tool uses computer vision techniques to capture the hand gestures of sign language users and processes them using convolutional neural networks (CNN) to recognize the corresponding Tamil alphabet or word. The proposed system consists of two main stages: data collection and model training. During the data collection stage, a dataset of Tamil sign language gestures is created by recording videos of sign language users performing various gestures. In the model training stage, the dataset is preprocessed and augmented, and a CNN is trained to recognize the gestures. The proposed system achieves a recognition accuracy of 85% on the test dataset, which is a significant improvement over the existing system. The proposed tool can be deployed on a mobile device or a web application, making it easily accessible to the deaf and hard-of-hearing community. © 2023 IEEE.

关键词： Statistical tests

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：