检索结果-内蒙古大学图书馆

Multi-Task Learning Model with Data Augmentation for Arabic Aspect-Based Sentiment Analysis

computers, Materials & Continua 2023年第5期75卷 4419-4444页

作者： Arwa Saif Fadel Osama Ahmed Abulnaja Mostafa Elsayed Saleh Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Computer Science Faculty of Computer Sciences and EngineeringHodeidah UniversityYemen

Aspect-based sentiment analysis(ABSA)is a fine-grained *** fundamental subtasks are aspect termextraction(ATE)and aspect polarity classification(APC),and these subtasks are dependent and closely ***,most existing works on Arabic ABSA content separately address them,assume that aspect terms are preidentified,or use a pipeline *** solutions design different models for each task,and the output from the ATE model is used as the input to the APC model,which may result in error propagation among different steps because APC is affected by ATE *** methods are impractical for real-world scenarios where the ATE task is the base task for APC,and its result impacts the accuracy of ***,in this study,we focused on a multi-task learning model for Arabic ATE and APC in which the model is jointly trained on two subtasks simultaneously in a *** paper integrates themulti-task model,namely Local Cotext Foucse-Aspect Term Extraction and Polarity classification(LCF-ATEPC)and Arabic Bidirectional Encoder Representation from Transformers(AraBERT)as a shred layer for Arabic contextual text *** LCF-ATEPC model is based on a multi-head selfattention and local context focus mechanism(LCF)to capture the interactive information between an aspect and its ***,data augmentation techniques are proposed based on state-of-the-art augmentation techniques(word embedding substitution with constraints and contextual embedding(AraBERT))to increase the diversity of the training *** paper examined the effect of data augmentation on the multi-task model for Arabic *** experiments were conducted on the original and combined datasets(merging the original and augmented datasets).Experimental results demonstrate that the proposed Multi-task model outperformed existing APC *** results were obtained by AraBERT and LCF-ATEPC with fusion layer(AR-LCF-ATEPC-Fusion)and the proposed data augmentation

关键词： Arabic aspect extraction arabic sentiment classification AraBERT multi-task learning data augmentation

来源：评论

学校读者我要写书评

暂无评论

Predictive Value Chain Analysis to Improve Generalization Accuracy In Quality Assurance

Predictive Value Chain Analysis to Improve Generalization Ac...

引用

2024 International Conference on Control and Automation, Electronics, Robotics, Internet of Things, and Artificial Intelligence, CERIA 2024

作者： Harmayani Sihombing, Poltak Mahyudin Elveny, Marischa Universitas Sumatera Utara Postgraduate Program in Computer Science Faculty of Computer Science and Information Technology Medan Indonesia Universitas Sumatera Utara Faculty of Computer Science and Information Technology Medan Indonesia Universitas Sumatera Utara Faculty of Computer Science and Information Technology Postgraduate Doctorate in Computer Science Medan Indonesia

ISBN: (纸本)9798331511166

Adaptive predictive analysis model utilizing Spiking Neural Networks (SNNs) to enhance quality assurance processes in Smart Campus environments. Traditional predictive models often struggle with the dynamic and complex nature of educational data, leading to inaccurate predictions and inefficient decision-making. SNNs, inspired by biological neurons, are particularly suited for processing temporal data and adapting to evolving patterns. The proposed model integrates spike-timing-dependent plasticity (STDP) and dynamic weight adjustment to continuously learn and refine predictions in response to real-time data, ensuring improved accuracy and robustness. The study uses historical data from the Internal Quality Assurance System (SPMI) over a three-year period, focusing on key performance indicators such as student enrollment trends, faculty productivity, and resource utilization. Experimental results demonstrate that the SNN-based model outperforms traditional neural networks, achieving a 20% reduction in Mean Squared Error (MSE) and a higher R-squared value. These findings indicate that the model not only enhances predictive accuracy but also offers significant improvements in operational efficiency and resource management. By providing timely and precise insights, this model supports proactive decision-making in educational institutions, enabling administrators to optimize resource allocation, monitor academic quality, and anticipate future challenges. This research contributes to the growing field of artificial intelligence in education, offering a scalable, adaptive approach to managing complex data and improving institutional performance in real-time. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

High-Secured Image LSB Steganography Using AVL-Tree with Random RGB Channel Substitution

引用

computers, Materials & Continua 2024年第10期81卷 183-211页

作者： Murad Njoum Rossilawati Sulaiman Zarina Shukur Faizan Qamar Center of Cyber Security Faculty of Information Science and TechnologyUniversiti Kebangsaan MalaysiaBangiSelangor43600Malaysia Computer Science and Cyber Security Faculty of Engineering and Information TechnologyBirZeit UniversityBirZeitRamallahP.O.Box 14Palestine

Random pixel selection is one of the image steganography methods that has achieved significant success in enhancing the robustness of hidden *** property makes it difficult for steganalysts’powerful data extraction tools to detect the hidden data and ensures high-quality stego image ***,using a seed key to generate non-repeated sequential numbers takes a long time because it requires specific mathematical *** addition,these numbers may cluster in certain *** hidden data in these clustered pixels will reduce the image quality,which steganalysis tools can ***,this paper proposes a data structure that safeguards the steganographic model data and maintains the quality of the stego *** paper employs the AdelsonVelsky and Landis(AVL)tree data structure algorithm to implement the randomization pixel selection technique for data *** AVL tree algorithm provides several advantages for image ***,it ensures balanced tree structures,which leads to efficient data retrieval and insertion ***,the self-balancing nature of AVL trees minimizes clustering by maintaining an even distribution of pixels,thereby preserving the stego image *** data structure employs the pixel indicator technique for Red,Green,and Blue(RGB)channel *** green channel serves as the foundation for building a balanced binary ***,the sender identifies the colored cover image and secret *** sender will use the two least significant bits(2-LSB)of RGB channels to conceal the data’s size and associated *** next step is to create a balanced binary tree based on the green *** the channel pixel indicator on the LSB of the green channel,we can conceal bits in the 2-LSB of the red or blue *** first four levels of the data structure tree will mask the data size,while subsequent levels will conceal the remaining digits of secret *** embedding the bits i

关键词： Image steganography pixel random selection(PRS) AVL tree peak signal-to-noise ratio(PSNR) imperceptibility capacity

来源：评论

学校读者我要写书评

暂无评论

Enhancing Drone Security Through Multi-Sensor Anomaly Detection and Machine Learning

引用

SN computer science 2024年第5期5卷 651页

作者： Alzahrani, Mohammed Y. Department of Information Technology Faculty of Computer Science & amp Information Technology AlBaha University AlBaha Saudi Arabia

Unmanned Aerial Vehicles (UAVs), commonly referred to as drones, have determined numerous applications across industries, ranging from aerial surveillance to package shipping. As drones are used in vital operations, ensuring cyberattacks and anomalies protect them from attackers is now a big challenge. This research study presents a complete approach to enhancing drone safety by integrating multi-sensor anomaly detection and superior machine learning techniques. The proposed methodology capitalizes on the rich sensor suite embedded in present-day drones, encompassing GPS receivers, accelerometers, gyroscopes, cameras, communication modules, and more. Leveraging an array of sensors in drones, our technique detects abnormal drone behavior indicative of unauthorized access, GPS spoofing, communication jamming, and malicious activities. By extracting features from sensor records, we develop a robust anomaly detection framework using the “uav attack dataset” able to identify deviations from normal flight patterns, communication signals, and environmental interactions. Central to our methodology is the utilization of machine learning algorithms. These algorithms are skilled on labeled datasets containing numerous flight eventualities, each normal and hostile, together with the ones discovered inside the “uav attack dataset”. The obtained results are eventually evaluated using rigorous performance metrics to quantify their effectiveness in distinguishing genuine anomalies from benign variations. The findings of our study underscore the capacity of multi-sensor anomaly detection for drones. By harnessing the power of machine learning and sensor fusion, we exhibit the ability to hit upon attacks at an early level, mitigating capability harm and permitting rapid responses. This study contributes now not only to the field of drone safety but also to the broader panorama of self-sustaining systems protection, highlighting the importance of adaptive and proactive protection mech

关键词： Anomaly Detection Drone Security Machine Learning for Drones Multi-Sensor Anomaly Detection Sensor Fusion

来源：评论

学校读者我要写书评

暂无评论

Adaptive Optimal Discrete-Time Output-Feedback Using an Internal Model Principle and Adaptive Dynamic Programming

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 131-140页

作者： Zhongyang Wang Youqing Wang Zdzisław Kowalczuk the College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China IEEE the Department of Robotics and Decision Systems Faculty of ElectronicsTelecommunications and InformaticsGdańsk University of TechnologyGdansk 80-233Poland

In order to address the output feedback issue for linear discrete-time systems, this work suggests a brand-new adaptive dynamic programming(ADP) technique based on the internal model principle(IMP). The proposed method, termed as IMP-ADP, does not require complete state feedback-merely the measurement of input and output data. More specifically, based on the IMP, the output control problem can first be converted into a stabilization problem. We then design an observer to reproduce the full state of the system by measuring the inputs and outputs. Moreover, this technique includes both a policy iteration algorithm and a value iteration algorithm to determine the optimal feedback gain without using a dynamic system model. It is important that with this concept one does not need to solve the regulator equation. Finally, this control method was tested on an inverter system of grid-connected LCLs to demonstrate that the proposed method provides the desired performance in terms of both tracking and disturbance rejection.

关键词： Adaptive dynamic programming(ADP) internal model principle(IMP) output feedback problem policy iteration(PI) value iteration(VI)

来源：评论

学校读者我要写书评

暂无评论

A three-step SEM-Bayesian network approach for predicting the determinants of CloudIoT-based healthcare adoption

引用

International Journal of information technology (Singapore) 2024年 1-21页

作者： Altawaiha, Iyad Atan, Rodziah Yaakob, Razali Bin Abdullah, Rusli Bin Hj Department of Software Engineering and Information Systems Faculty of Computer Science and Information Technology Universiti Putra Malaysia (UPM) Serdang 43400 Malaysia Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia (UPM) Serdang 43400 Malaysia

Adopting the CloudIoT-based healthcare paradigm provides various prospects for medical IT and considerably enhances healthcare services. However, compared to the advanced development of CloudIoT-based healthcare systems, their usage is relatively low among healthcare professionals in hospitals. Thus, a study on the healthcare professionals acceptance and adoption of CloudIoT-based healthcare is critical. This study explores factors influencing healthcare professionals adoption of CloudIoT-based healthcare solutions by extending the Unified Theory of Acceptance and Use of technology 2 model. Data was collected from 300 healthcare professionals in Jordan through an online questionnaire developed using the Google^® form application. The Bayesian Network and Structural Equation Modeling techniques were used to analyze and validate the proposed model. The results revealed that the healthcare professional’s behavioral intention is directly affected by seven factors: performance expectancy, effort expectancy, facilitating conditions, habit, trust, privacy, and security. The results also indicate that trust mediates the influence of privacy, facilitating conditions, and performance expectancy on behavioral intention. The research results will aid CloudIoT service providers, healthcare organizations, designers, and developers by offering comprehensive knowledge of the significant factors of CloudIoT-based healthcare adoption. A better understanding of these factors will help these stakeholder groups enhance their services and speed up the adoption of CloudIoT in the healthcare area. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Adoption Bayesian network CloudIoT Healthcare professionals Structural equation modeling UTAUT2

来源：评论

学校读者我要写书评

暂无评论

Assessing and prioritizing crucial drivers for CloudIoT-based healthcare adoption: an analytic hierarchy process approach

引用

International Journal of information technology (Singapore) 2024年 1-18页

The CloudIoT paradigm has profoundly transformed the healthcare industry, providing outstanding innovation and practical applications. However, despite its many advantages, the adoption of this paradigm in healthcare settings remains limited. There is a lack of comprehensive understanding of the factors that ensure successful implementation. To address this issue, we have used the Analytic Hierarchy Process to prioritize 26 factors that could potentially influence the adoption of CloudIoT-based healthcare. These factors were derived from existing literature and categorized into four main groups: personal-specific, technology-specific, environment-specific, and organization-specific factors. Our findings revealed that performance expectancy, trust, facilitating conditions, task complexity, and perceived security are the top five critical factors influencing CloudIoT-based healthcare adoption. Interestingly, our results indicated that environmental factors were less influential than those in the other categories, with personal, technological, and organizational factors dominating the top ten significant factors. The insights from this study can help policymakers, CloudIoT service providers, healthcare providers, designers, and developers better understand the factors contributing to the successful implementation of CloudIoT-based healthcare. This understanding can guide decision-making and inform the development of strategies to promote the broader adoption of this innovative technology. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Adoption Analytic hierarchy process CloudIoT Factors Healthcare industry

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Deep Learning Approaches for Fake News Detection: A Systematic Review of Techniques, Challenges, and Advancements

引用

IEEE Access 2025年 13卷 90433-90466页

作者： Bashaddadh, Omar Omar, Nazlia Mohd, Masnizah Khalid, Mohd Nor Akmal Universiti Kebangsaan Malaysia Faculty of Information Science and Technology Centre for Artificial Intelligence Technology Bangi43600 Malaysia Seiyun University College of Computers Department of Computer Science Hadhramout Yemen Universiti Kebangsaan Malaysia Faculty of Information Science and Technology Centre for Cyber Security Bangi43600 Malaysia

In response to the escalating threat of fake news on social media, this systematic literature review analyzes recent advancements in machine learning and deep learning approaches for its automated detection. Following the PRISMA guidelines, we examined 90 peer-reviewed studies published between 2020 and 2024 to evaluate model effectiveness, identify limitations, and highlight emerging trends. Our analysis shows that deep learning models, particularly transformer-based architectures such as BERT, consistently outperform traditional machine learning methods, often achieving high accuracy (Acc), precision (P), recall (R), and F1-score (F1). For instance, a BERT-based model reported up to 99.9% accuracy on the Kaggle fake news dataset and above 98% on other public datasets, including ISOT, Fake-or-Real, and D3. Similarly, the GANM model demonstrated robust performance on the FakeNewsNet dataset by integrating text and social features. Transfer learning and multimodal models that incorporate user behaviour and network information significantly improve detection in diverse and low-resource environments. However, challenges persist in terms of dataset quality, model interpretability, domain generalisability, and real-time deployment. This review also underscores the limited adoption of few-shot and zero-shot learning techniques, highlighting a promising direction for future research on handling emerging misinformation with minimal training data. To support practical deployment, we advocate the development of explainable, multilingual, and lightweight models with a greater emphasis on human-centred evaluation and ethical considerations. Our findings provide a foundation for researchers and practitioners aiming to build scalable, trustworthy, and context-aware fake news detection systems for global use. © 2013 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Towards the Development of a Copyright Risk Checker Tool for Generative Artificial Intelligence Systems

引用

Digital Government: Research and Practice 2024年第4期5卷 1-21页

作者： Billiris, Grace Gill, Asif Oppermann, Ian Niazi, Mahmood Faculty of Engineering and Information Technology University of Technology SydneyNSW Australia Computer Science University of Technology SydneyNSW Australia University of Technology SydneyNSW Australia King Fahd University of Petroleum and Minerals Department of Information and Computer Science Dhahran Saudi Arabia

Generative Artificial Intelligence (GAI) is fundamentally changing the ways of working and blurring the boundaries between human and machine-generated contents. While there is an increasing interest in the adoption of GAI systems, such as ChatGPT and DALL-E, there are also serious concerns about the copyright of the contents - the inputs or generated as outputs by the GAI systems. Such concerns need to be identified and assessed to ensure the ethical and responsible use of GAI systems. Thus, this article aims to address the key research challenge: "how to identify and assess GAI system's copyright concerns"? In response, we propose the development of a Copyright Risk Checker (CRC) Tool. This tool has been formulated and evaluated using a recognised design science research methodology, drawing on an analysis of 10 legal cases across Australia, the United Kingdom, the United States, and Europe. The CRC Tool has undergone evaluation through an experimental scenario, and the results suggest that it is suitable for conducting an indicative copyright risk check of GAI systems. The outcomes of this preliminary assessment can be further examined by expert legal advisors for an in-depth analysis. The development of the CRC Tool provides a foundation for continued research and advancement in this significant area of study. © 2024 Copyright held by the owner/author(s).

关键词： Generative Artificial Intelligence Copyright Concern GAI Governance Copyright Regulations Independent Intellectual Effort Authorship

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep Convolutional Neural Networks in Mobile Face Recognition

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第23期17卷 4-19页

作者： Chi, Jing On, Chin Kim Zhang, Haopeng Chai, Soo See Faculty of Computing and Informatics University Malaysia Sabah Sabah Malaysia School Information and Electrical Engineering Hebei University of Engineering Hebei China Faculty of Computer Science and Information Technology Universiti Malaysia Sarawak Sarawak Malaysia

With the emergence of deep learning, Convolutional Neural Network (CNN) models have been proposed to advance the progress of various applications, including face recognition, object detection, pattern recognition, and number plate recognition. The utilization of CNNs in these areas has considerably improved security and surveillance capabilities by providing automated recognition solutions, such as traffic surveillance, access control devices, biometric security systems, and attendance systems. However, there is still room for improvement in this field. This paper discusses several classic CNN models, such as LeNet-5, AlexNet, VGGNet, GoogLeNet, and ResNet, as well as lightweight models for mobile-based applications, such as MobileNet, ShuffleNet, and EfficientNet. Additionally, deep CNN-based face recognition models, such as DeepFace, DeepID, FaceNet, and SphereFace, are explored, along with their architectural characteristics, advantages, disadvantages, and recognition accuracy. The results indicate that many scholars are researching lightweight face recognition, but applying it to mobile devices is impractical due to high computational costs. Furthermore, noise label learning is not robust in actual scenarios, and unlabeled face learning is expensive in manual labeling. Finally, this paper concludes with a discussion of the current problems faced by face recognition technology and its potential future directions for development. © 2023 by the authors of this article. Published under CC-BY. All Rights Reserved.

关键词： Neural network models

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：