检索结果-内蒙古大学图书馆

Deep Learning Empowered Cybersecurity Spam Bot Detection for Online Social Networks

computers, Materials & Continua 2022年第3期70卷 6257-6270页

作者： Mesfer Al Duhayyim Haya Mesfer Alshahrani Fahd NAl-Wesabi Mohammed Alamgeer Anwer Mustafa Hilal Mohammed Rizwanullah Department of Natural and Applied Sciences College of Community-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversitySaudi Arabia Department of Computer Science King Khalid UniversityMuhayel AseerSaudi Arabia&Faculty of Computer and ITSana’a UniversitySana’aYemen Department of Information Systems King Khalid UniversityMuhayel AseerSaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

Cybersecurity encompasses various elements such as strategies,policies,processes,and techniques to accomplish availability,confidentiality,and integrity of resource processing,network,software,and data from *** this scenario,the rising popularity of Online Social Networks(OSN)is under threat from spammers for which effective spam bot detection approaches should be *** studies have developed different approaches for the detection of spam bots in *** those techniques primarily concentrated on hand-crafted features to capture the features of malicious users while the application of Deep Learning(DL)models needs to be *** this motivation,the current research article proposes a Spam Bot Detection technique using Hybrid DL model abbreviated as *** proposed SBD-HDL technique focuses on the detection of spam bots that exist in *** technique has different stages of operations such as pre-processing,classification,and parameter ***,SBD-HDL technique hybridizes Graph Convolutional Network(GCN)with Recurrent Neural Network(RNN)model for spam bot classification *** order to enhance the detection performance of GCN-RNN model,hyperparameters are tuned using Lion Optimization Algorithm(LOA).Both hybridization of GCN-RNN and LOA-based hyperparameter tuning process make the current work,a first-of-its-kind in this *** experimental validation of the proposed SBD-HDL technique,conducted upon benchmark dataset,established the supremacy of the technique since it was validated under different measures.

关键词： Cybersecurity spam bot data classification social networks twitter deep learning

来源：评论

学校读者我要写书评

暂无评论

Factors influencing Romanian teachers' choice of IT training to avoid issues raised by online education: A data mining approach 17

Factors influencing Romanian teachers' choice of IT training...

引用

17th International Conference on Development and Application systems, DAS 2024

作者： Simionescu, Corina Bărîlă, Adina-Luminița Danubianu, Mirela Grădinaru, Bogdănel Constantin Doctoral School of Applied Sciences and Engineering Computers and information technology Ștefan cel Mare University Suceava Romania Faculty of Electrical Engineering and Computer Science Ștefan cel Mare University Suceava Romania

ISBN: (纸本)9798350349290

Raising the students' academic performance and improving the overall quality of education is an important goal of our society. With the exploding development of information technologies, Educational Data Mining has become a growing activity that uses the essence of Data Mining concepts to help institutions learn useful information on various academic issues. Romanian schools are facing several problems and inequalities, many of which were accentuated during the Covid-19 pandemic, when, due to restrictions on physical proximity, classes were held entirely or partly online. This paper aims to presents an experimental study on modelling teachers' attitudes towards attending IT professional development courses to deliver quality online lessons. A real data set collected through a questionnaire answered by 956 teachers is used. The final goal was that, after the best-performing model was built, the features that are significant in this approach would be analyzed. These features are influential factors in teachers' choices. We initially considered four classification techniques, after which, we refined the optimization process for Random Forest, which proved, from the first experiments, the best performance. ©2024 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

LLaMA-Based Models for Aspect-Based Sentiment Analysis 14

LLaMA-Based Models for Aspect-Based Sentiment Analysis

引用

14th Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis, WASSA 2024

作者： Šmíd, Jakub Přibáň, Pavel Král, Pavel Department of Computer Science and Engineering University of West Bohemia Faculty of Applied Sciences Czech Republic NTIS – New Technologies for the Information Society Univerzitní 2732/8 Pilsen301 00 Czech Republic

ISBN: (纸本)9798891761568

While large language models (LLMs) show promise for various tasks, their performance in compound aspect-based sentiment analysis (ABSA) tasks lags behind fine-tuned models. However, the potential of LLMs fine-tuned for ABSA remains unexplored. This paper examines the capabilities of open-source LLMs fine-tuned for ABSA, focusing on LLaMA-based models. We evaluate the performance across four tasks and eight English datasets, finding that the fine-tuned Orca 2 model surpasses state-of-the-art results in all tasks. However, all models struggle in zero-shot and few-shot scenarios compared to fully fine-tuned ones. Additionally, we conduct error analysis to identify challenges faced by fine-tuned models. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Real-Time Exercise Repetition Counting System

AI-Driven Real-Time Exercise Repetition Counting System

引用

International Conference on Signal Processing and Communication (ICSC)

作者： Ratan Lal Rikriti Koirala Sai Swathi Thota Khaja Nayab Rasool Shaik School of Computer Science and Information Systems Northwest Missouri State University Maryville MO USA Faculty in the school of computer science and information systems Northwest Missouri State University USA School of computer science and information systems at Northwest Missouri State University USA

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

Real-time exercise detection is a challenging problem. Hence, we present a real-time exercise detection system that addresses the challenge of accurately monitoring exercises without the need for an expensive, real-life coach. Our approach leverages machine learning techniques to detect errors in exercises and provide actionable feedback, making fitness training more accessible and affordable. First, we collect a dataset, capturing multiple video frames with joint landmarks represented as key points in each image. These images are labeled with exercise actions such as curls, presses, and squats. Then, we perform data cleaning and splitting. After that we have trained and evaluated two machine learning models: Long Short-Term Memory (LSTM) networks and Random Forest based on metrics, namely, accuracy, precision, recall, F1 score. From our experimental results, we have found that the LSTM model outperforms the Random Forest, demonstrating its superior effectiveness in real-time exercise detection. Our results highlight the potential of AI-driven systems to provide personalized fitness guidance, opening doors to innovative solutions in the health and fitness industry.

关键词： Training Measurement Industries Presses Streaming media Signal processing Real-time systems Long short term memory Random forests Monitoring

来源：评论

学校读者我要写书评

暂无评论

Intelligent Deep Learning Based Automated Fish Detection Model for UWSN

引用

computers, Materials & Continua 2022年第3期70卷 5871-5887页

作者： Mesfer Al Duhayyim Haya Mesfer Alshahrani Fahd NAl-Wesabi Mohammed Alamgeer Anwer Mustafa Hilal Manar Ahmed Hamza Department of Natural and Applied Sciences College of Community-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversitySaudi Arabia Department of Computer Science King Khalid UniversityMuhayel AseerSaudi Arabia&Faculty of Computer and ITSana’a UniversitySana’aYemen Department of Information Systems King Khalid UniversityMuhayel AseerSaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

An exponential growth in advanced technologies has resulted in the exploration of Ocean *** has paved the way for new opportunities that can address questions relevant to diversity,uniqueness,and difficulty of marine *** Wireless Sensor Networks(UWSNs)are widely used to leverage such opportunities while these networks include a set of vehicles and sensors to monitor the environmental *** this scenario,it is fascinating to design an automated fish detection technique with the help of underwater videos and computer vision techniques so as to estimate and monitor fish biomass in water *** models have been developed earlier for fish ***,they lack robustness to accommodate considerable differences in scenes owing to poor luminosity,fish orientation,structure of seabed,aquatic plantmovement in the background and distinctive shapes and texture of fishes from different *** this motivation,the current research article introduces an Intelligent Deep Learning based Automated Fish Detection model for UWSN,named IDLAFD-UWSN *** presented IDLAFD-UWSN model aims at automatic detection of fishes from underwater videos,particularly in blurred and crowded ***-UWSN model makes use of Mask Region Convolutional Neural Network(Mask RCNN)with Capsule Network as a baseline model for fish ***,in order to train Mask RCNN,background subtraction process using GaussianMixtureModel(GMM)model is *** model makes use of motion details of fishes in video which consequently integrates the outcome with actual image for the generation of fish-dependent candidate ***,Wavelet Kernel Extreme Learning Machine(WKELM)model is utilized as a classifier *** performance of the proposed IDLAFD-UWSN model was tested against benchmark underwater video dataset and the experimental results achieved by IDLAFD-UWSN model were promising in comparison with other state-of-the-art methods under differe

关键词： Aquaculture background subtraction deep learning fish detection marine surveillance underwater sensor networks

来源：评论

学校读者我要写书评

暂无评论

BLOCK-SECURE: AI-Based Blockchain Enabled Secure Framework for IoMT Applications

BLOCK-SECURE: AI-Based Blockchain Enabled Secure Framework f...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Panchal, Barkha Bhatia, Jitendra Kumhar, Malaram Tanwar, Sudeep Dutta, Ashit Kumar Rodrigues, Joel J.P.C. Department of Computer Science and Engineering Institute of Technology Nirma University Ahmedabad India Dept. of Comp. Science and Information Systems College of Applied Sciences AlMaarefa University Saudi Arabia Amazonas State University AM Manaus Brazil

ISBN: (纸本)9798350350548

The Internet of Medical Things (IoMT) revolutionizes healthcare by integrating medical devices and systems with the internet. However, the vast amounts of sensitive medical data in IoMT networks pose significant security and privacy concerns. Traditional security measures often fall short in identifying the malicious data attacks within the IoMT ecosystems. This paper introduces an AI-based non-malicious data classification scheme based on blockchain. We applied and evaluated the machine learning (ML) classifiers, such as support vector machine (SVM), random forest (RF), and K-Nearest neighbor (KNN). We evaluated the proposed framework based on various performance metrics that includes accuracy, precision, recall, and F1 score. The accuracy using SVM obtained 75.3%, RF is 75.9%, and KNN is 84.3%. The results shows that KNN performs better than other models by the factor of 9%. © 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

Optimizing Customer Response Prediction in Auto Insurance: A Comparative Study of Machine Learning Models 2

Optimizing Customer Response Prediction in Auto Insurance: A...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Aburass, Sanad Dorgham, Osama Al Shaqsi, Jamil Rumman, Maha Abu Al Zarouni, Ahmed Maharishi International University Department Of Computer Science FairfieldIA United States School Of Information Technology Skyline University College Sharjah United Arab Emirates Al-Balqa Applied University Prince Abdullah Bin Ghazi Faculty Of Ict Al-Salt Jordan Sultan Qaboos University Information Systems Department Muscat Oman

ISBN: (纸本)9798350394962

This study examines various machine learning models to predict customer responses in the auto insurance industry. We focus on metrics like accuracy, precision, recall, and F1-score, carefully selecting threshold values to balance model performance with practical business applications. Our analysis reveals the XGB Classifier's superiority, achieving 99% accuracy and a 98% F1-score. We provide a comparative analysis of models, highlighting the XGB Classifier's strengths in handling complex data and its efficiency compared to other tested models, like Gaussian NB and Logistic Regression, which showed similar accuracies but varied in precision and recall. This study underscores the importance of choosing the right model and fine-tuning it for specific industry needs. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

UWB at WASSA-2024 Shared Task 2: Cross-lingual Emotion Detection 14

UWB at WASSA-2024 Shared Task 2: Cross-lingual Emotion Detec...

引用

14th Workshop on Computational Approaches to Subjectivity, Sentiment, and Social Media Analysis, WASSA 2024

ISBN: (纸本)9798891761568

This paper presents our system built for the WASSA-2024 Cross-lingual Emotion Detection Shared Task. The task consists of two subtasks: first, to assess an emotion label from six possible classes for a given tweet in one of five languages, and second, to predict words triggering the detected emotions in binary and numerical formats. Our proposed approach revolves around fine-tuning quantized large language models, specifically Orca 2, with low-rank adapters (LoRA) and multilingual Transformer-based models, such as XLM-R and mT5. We enhance performance through machine translation for both subtasks and trigger word switching for the second subtask. The system achieves excellent performance, ranking 1st in numerical trigger words detection, 3rd in binary trigger words detection, and 7th in emotion detection. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Timely Graduations: An Explainable AI Approach to Predict Academic Risks in South African Students

Enhancing Timely Graduations: An Explainable AI Approach to ...

引用

2023 IEEE International Conference on Electrical, computer and Energy Technologies, ICECET 2023

作者： Bokgoshi, Lenny Sixhaxa, Khanyisile Jadhav, Ashwini Nyamane, Seipati Ajoodha, Ritesh School of Computer Science and Applied Mathematics University of Witwatersrand Johannesburg South Africa University of Witwatersrand Science Teaching and Learning Unit Faculty of Science Johannesburg South Africa Sol Plaatje University Department of Computer Science and Information Technology Kimberley South Africa

ISBN: (纸本)9798350327816

With rising dropout rates and extended degree completion times in South African institutions, there's a pressing need to better understand and address the hurdles faced by students during their academic journey. This research harnesses the power of explainable AI to predict and classify students based on their likelihood of not completing their degrees on time. Utilizing synthetic data generated via a Bayesian network, we used predictive models that categorize students into four distinct risk profiles. This clarity in prediction not only illuminates the underlying causes of academic delays but also empowers faculty, advisors, and student support services with actionable insights. The goal of this research is to facilitate timely interventions, tailored support, and seamless transitions for students transferring between universities, ensuring more students can realize their academic aspirations within expected time frames. © 2023 IEEE.

关键词： academic performance at-risk students classification models Machine learning student attrition

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

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：