检索结果-内蒙古大学图书馆

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Vahidhabanu, Y. Ramkumar, K. Bhatt, Chandradeep Srinivasan, M.L. Sasirekha, S.P. Saravanakumar, S. Kongunadu College of Engineering and Technology Department of Computer Science and Engineering Trichy India Rajalakshmi Institute of Technology Department of Computer Science and Engineering Tamilnadu Chennai India Graphic Era Hill University Graphic Era Deemed to Be University Department of Cse Uttarakhand Dehradun248007 India Karpagam Academy of Higher Education Department of Cse Eachanari Coimbatore India Dept. of Cse Faculty of Engineering & Technology Bengaluru India

ISBN: (纸本)9798350360165

many educational institutions employ data mining to keep track of their students' records, particularly their academic achievements, which is more significant. To improve their achievements, students' academic performances, as well as the institutions' overall results, must be evaluated. Furthermore, the prediction of students' academic accomplishment educational data mining has been a growing research area machine learning techniques are used to gather information from educational warehouses. As a result, this research proposes the hybrids pedagogical statistical model, a novel approach for analyzing student performance, to improve educational quality for students. The suggested methodology assesses student performance using diverse parameters that result in suitable outcomes. In addition, for obtaining the findings and accurately categorising student performance, the framework illustrates the synergy between the j 48 separator and the enn-based segmentation method. The model is put to the test using the weka environment's benchmark schooling dataset., which is available online. The findings suggest that the proposed model outperforms previous studies in assessing edm student performance. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Networks in Neuroimaging: A U-Net Model for Precise Brain Tumor Detection

Deep Neural Networks in Neuroimaging: A U-Net Model for Prec...

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： Deepak Upadhyay Kunj Bihari Sharma Mridul Gupta Abhay Upadhyay Satya Prakash Yadav Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era Deemed to be University Dehradun India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

This work holds the promise of being a considerable breakthrough in medical imaging diagnosis by studying advanced U-Net topologies for accurate brain tumour segmentation from magnetic resonance imaging (MRI) data. In this research, we present a more sophisticated pipeline that covers data preprocessing, robust model validation, and architecture tuning of the deep learning techniques. Performing accurately at 94.7% accuracy, the model showed a decent precision and recall rates with extremely promising results against traditional segmentation approaches as well as current deep learning frameworks. These results show how U-Net models could improve the diagnoses accuracy and guide personalized treatment tactics. Our research demonstrates the transformative ability of deep learning in medical diagnostics and opens a pathway for additional strides in individualized therapy, albeit diffuse tumour border segmentation barrier and MRI image heterogeneity limitations.

关键词： Deep learning Image segmentation Accuracy Magnetic resonance imaging Brain modeling Robustness Topology Telecommunication computing Planning Tuning

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Movie Reviews: Optimizing Predictions Through TF-IDF Vectorization

Sentiment Analysis of Movie Reviews: Optimizing Predictions ...

引用

Intelligent data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Mohd Irfan Anne Sreyas Venkatesam Hariharan Shanmugasundaram Mahendra Kumar Gourisaria Subrata Chowdhury Sudhansu Shekhar Patra Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Hyderabad Telangana India Department of Artificial Intelligence and Data Science Vardhaman College of Engineering Hyderabad India School of Computer Engineering Kalinga Institute of Industrial Technology (KIIT) Deemed to be University Bhubaneswar India Dept. of Computer Science and Engineering Sreenivasa Institute of Technology and Management Studies(A) Chittoor Andhra Pradesh India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

Sentiment analysis model is aimed to accurately interpret movie reviews, addressing challenges like sarcasm and noisy data. By integrating multiple machine learning classifiers Naive Bayes, Random Forest, K-Nearest Neighbors, Logistic Regression, Decision Tree, and XGBoost—the model enhances sentiment prediction accuracy. The Term Frequency-Inverse Document Frequency (TF-IDF) method is used to extract features from a dataset of 50,000 movie reviews. Performance is evaluated using accuracy, precision, recall, and F1-score, with Logistic Regression achieving the best results, including an highest accuracy of 84.33 % and an F1-score of 0.847. In comparison to traditional methods, this multi-classifier approach offers a deeper understanding of movie reviews and its influence on audience decisions. The study demonstrates the potential of using these machine learning techniques to provide real-time, scalable sentiment analysis, which is crucial for filmmakers and marketers seeking insights into audience satisfaction and box office performance.

关键词： Sentiment analysis Logistic regression Accuracy Reviews Predictive models Motion pictures Feature extraction Real-time systems Noise measurement Random forests

来源：评论

学校读者我要写书评

暂无评论

On Investigating a Better Audio Representation for Mood Classification in Indian Popular Music

On Investigating a Better Audio Representation for Mood Clas...

引用

Acoustics, Speech, and Signal Processing Workshops (ICASSPW), IEEE International Conference on

作者： Arathi K Hotha Durga Swetha V G Vaishali Kalyan Munukutla Abhijith V Gurram Shalini Joe Cheri Ross Dept. of Computer Science & Engineering NIT Calicut India Dept. of Mechanical Engineering NIT Calicut India Dept. of Biotechnology NIT Calicut India

ISBN: (数字)9798331519315

ISBN: (纸本)9798331519322

Developing a specialized music mood classifier for Indian popular music is essential due to the diverse musical traditions and languages in India. It enhances music recommendation systems and music therapy applications by accurately capturing Indian popular songs' emotional nuances. Considering the complexity of Indian popular music, the existing approaches in Western music have limitations. This investigation examines whether existing large audio models can improve the accuracy of music mood classification by generating more informative audio representations. Our dataset includes more than 338 songs from South Indian languages, ensuring diversity. The proposed architecture utilizes HuBERT and MERT representations of the audio. On comparing with the CNN-based baseline and a few related architectures, the proposed model performs better highlighting the potential of the music representation for mood classification in Indian popular music. Additionally, our analysis of pre-2000 songs revealed unique emotional tones that complicate predictions, emphasizing the stylistic differences between pre-2000 and post-2000 music.

关键词： Training Accuracy Mood Medical treatment Signal processing Predictive models Multiple signal classification Speech processing Music information retrieval Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Stochastic Error Injection for Optimizing Large Language Models in Arabic Spelling Correction

Efficient Stochastic Error Injection for Optimizing Large La...

引用

International Conference on New Trends in Computing sciences (ICTCS)

作者： Moath R. Khaleel Gheith A. Abandah Computer Engineering Department The University of Jordan Amman Jordan Dept. of Computer Science and Engineering American University of Sharjah UAE

ISBN: (数字)9798331523411

ISBN: (纸本)9798331523428

Spelling mistakes in written communication among Arabic speakers have become more common, especially with the rise of social media. Correcting these errors requires effective natural language processing (NLP) tools. This paper introduces a ByT5-based approach to address two types of spelling mistakes: directed and general. ByT5, a token-free, pre-trained transformer model, processes UTF-8 text as raw bytes, which minimizes preprocessing and enhances robustness. We perform experiments with varying error injection rates to identify the optimal rate for correction. Our results are evaluated on two test sets: Test200 and TSMTS. The findings demonstrate ByT5's strong performance in spelling error correction, reducing the character error rate (CER) from 5% to 1.37% on the Test200 set and from 5% to 1.77% on the TSMTS set. These test sets include real Arabic sentences containing actual spelling mistakes. Overall, our results show that this approach offers a promising solution for spelling error correction and contributes to generating effective synthetic datasets for training large language models.

关键词： Training Social networking (online) Large language models Stochastic processes Transformers Market research Natural language processing Robustness Error correction Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Game-Theoretic-Based Resource Allocation Algorithm for SCMA Max-Min Problem to Maximize Fairness

Game-Theoretic-Based Resource Allocation Algorithm for SCMA ...

引用

IEEE International Conference on Electronics and Communication engineering (ICECE)

作者： Maryam Cheraghy Meysam Soltanpour Belal Abuhaija Hemn Barzan Abdalla Kennedy Ehimwenma dept. Computer Science and Technology Wenzhou-Kean University Wenzhou China dept. Control Science and Engineering Shandong University Jinan China

ISBN: (数字)9798331517755

ISBN: (纸本)9798331517762

This paper tackles a joint optimization problem in uplink sparse code multiple access (SCMA) networks to enhance network fairness, i.e., Jain's fairness index (JFI). We propose a novel game-theoretic approach, the worst-case player first-strategy selection (WCPFSS) algorithm, to maximize the minimum achievable rate for all subcarriers while ensuring fair power allocation and optimized subcarrier assignment. This approach effectively manages user interference because each subcarrier acts as a player to exchange their strategies, which are clusters of users associated with each subcarrier. The simulation results confirm the superiority of the proposed WCPFSS method w.r.t. JFI for differential setup parameters.

关键词： Codes Simulation Clustering algorithms Interference Minimax techniques Resource management Indexes Uplink Game theory Optimization

来源：评论

学校读者我要写书评

暂无评论

Topic Relation Graph Construction to Identify Challenges in Introducing Programming in Indonesian K-12 Education 1

Topic Relation Graph Construction to Identify Challenges in ...

引用

1st IEEE International Conference on Smart Technology, ICE-SMARTec 2023

作者： Ayub, Mewati Karnalim, Oscar Toba, Hapnes Wijanto, Maresha Caroline Dulimarta, Hans Saputra, Williyandie Kotambunan, Tabitha Emanuella Master Program of Computer Science Maranatha Christian University Bandung Indonesia Ewha Womans University Dept. of Computer Science and Engineering Seoul Korea Republic of School of Computing Grand Valley State University MI United States Informatics Engineering Maranatha Christian University Bandung Indonesia

ISBN: (纸本)9798350306156

Programming can help K-12 students to develop their 21st-century core skills. Despite the benefits, programming is not common to be delivered in Indonesian K-12 education. There is a need to understand potential challenges in introducing programming to K-12 students. We developed a questionnaire survey covering four identified dimensions of challenges: administrative, facilities, teachers, and students. We also asked about common programming assessments and their preferred software features for teaching programming. Forty K-12 teachers were invited to complete the survey. The responses were analyzed with thematic analysis using a bigram-based Latent Dirichlet Allocation topic modeling and descriptive statistics. Our study shows that the challenges include limited learning modules, an insufficient number of computers, limited programming skills, and limited computational thinking skills. Scratch was the most common programming language used and many programming assessments were about debugging a program or writing a small program. Visualization and animation can be helpful in teaching programming. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Stochastic Analysis of the Gasper Protocol

A Stochastic Analysis of the Gasper Protocol

引用

IEEE Annual Conference on Pervasive Computing and Communications Workshops (PerCom)

作者： Cosimo Laneve Sergio Solmonte Adele Veschetti Dept. of Computer Science and Engineering University of Bologna Bologna Italy Department of Computer Science Technical University of Darmstadt Darmstadt Germany

Ethereum has recently switched to a Proof of Stake consensus protocol called Gasper. We analyze Gasper using PRISM+, an extension of the probabilistic model checker PRISM with primitives for modelling blockchain data types. PRISM+ is therefore used to rapidly and automatically analyze the robustness of Gasper when tuning, up or down, several basic parameters of the protocol, such as network latencies and number of validators. We also study the effectiveness of Gasper in updating stakes and its resilience to three attacks: the balance, bouncing and time attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advanced Underwater Image Quality Enhancement via Hybrid Super-Resolution Convolutional Neural Networks and Multi-Scale Retinex-Based Defogging Techniques

arXiv

引用

arXiv 2024年

作者： Gogireddy, Yugandhar Reddy Gogireddy, Jithendra Reddy Dept. Computational Intelligence SRM Institute of Science and Technology Chennai India Dept. Computer Science and Engineering SRM University AP India

The difficulties of underwater image degradation due to light scattering, absorption, and fog-like particles which lead to low resolution and poor visibility are discussed in this study report. We suggest a sophisticated hybrid strategy that combines Multi-Scale Retinex (MSR) defogging methods with Super-Resolution Convolutional Neural Networks (SRCNN) to address these problems. The Retinex algorithm mimics human visual perception to reduce uneven lighting and fogging, while the SRCNN component improves the spatial resolution of underwater photos.[11] Through the combination of these methods, we are able to enhance the clarity, contrast, and colour restoration of underwater images, offering a reliable way to improve image quality in difficult underwater conditions. The research conducts extensive experiments on real-world underwater datasets to further illustrate the efficacy of the suggested approach. In terms of sharpness, visibility, and feature retention, quantitative evaluation which use metrics like the Structural Similarity Index Measure (SSIM) and Peak Signal-to-Noise Ratio (PSNR) demonstrates notable advances over conventional techniques.[41] In real-time underwater applications like marine exploration, underwater robotics, and autonomous underwater vehicles, where clear and high-resolution imaging is crucial for operational success, the combination of deep learning and conventional image processing techniques offers a computationally efficient framework with superior results. Copyright © 2024, The Authors. All rights reserved.

关键词： Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

Insights into Zooplankton Abundance Dynamics in Tropical Temporary Ponds using Machine Learning and Explainable AI

Insights into Zooplankton Abundance Dynamics in Tropical Tem...

引用

International Conference on Innovations in science, engineering and Technology (ICISET)

作者： Shahriar Siddique Ayon Sharia Arfin Tanim Hadiur Rahman Nabil Maruful Islam Tonmoy Mohajan Kamruddin Nur Dept. of Computer Science American International University-Bangladesh Dhaka Bangladesh Dept. of Computer Science and Engineering International Islamic University Chittagong Chittagong Bangladesh Dept. of Electrical and Electronic Engineering Chittagong University of Engineering and Technology Chittagong Bangladesh

ISBN: (数字)9798350355499

ISBN: (纸本)9798350355505

Determining the health and resilience of ecosystems depends on an understanding of the dynamics of zooplankton abundance in tropical temporary ponds. Using ensemble modelling and explainable artificial intelligence (XAI) techniques, this paper explores the complex dynamics of zooplankton abundance in tropical temporary ponds. This study uses a Machine Learning framework to evaluate the predictive performance of models such as k-nearest Neighbors ($k N N$) regression, Random Forest Regression, Lasso Regression, Passive Aggressive Regression, Ridge Regression, and Ensemble Voting Regression. Among the machine learning models tested, the ensemble model, which combines ridge and ridge CV, performs best, with metrics such as MAE of 0.02, MSE of 0.00, and $\mathbf{R 2}$ of 1.00. The Shapley Additive ExPlanations (SHAP) analysis identifies ‘Rotifers’, ‘Culex’, ‘Chironomodidae’, and ‘Calanoids’ as significant predictors. data preprocessing techniques improve the dataset derived from a study of fish predation effects in tropical temporary ponds. Our research advances our understanding of zooplankton ecology and provides insights into conservation strategies and management practices in these ecosystems. Using ensemble modelling and explainable AI, we contribute to developing accurate predictive models for the long-term management of tropical temporary pond ecosystems.

关键词： Accuracy Explainable AI Biological system modeling Ecosystems Machine learning Predictive models Ecology Zooplankton Environmental management Resilience

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：