检索结果-内蒙古大学图书馆

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Balakrishnan, Roshni M. Pati, Peeta Basa Singh, Rimjhim Padam Santhanalakshmi, S. Kumar, Priyanka Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidhyapeetham Bengaluru India Department of Computer Science University of Texas Saint Antonio United States

Assessments constitute a fundamental and inevitable component of any educational journey. Manual effort required for the evaluation of these assessments is very high. Automation of the evaluation process and grading helps in making the review process more efficient, objective, and scalable, thereby reducing the workload of human reviewers. Automating the grading process for multiple-choice and short-answer assessments is relatively straightforward, but it poses significant challenges when applied to the evaluation of formal languages, particularly in the context of mathematical assessments. In this paper a model that automatically evaluates and grades the Quadratic Equation problems is presented. The study is conducted using a manually curated dataset comprising 1200 solutions to various quadratic equation problems. Embeddings of the quadratic solutions are generated using Google's T5 Model. These embeddings are then used to train different traditional and ensembled machine learning models along with complex Deep learning models like LSTM and Bi LSTM. An in-depth analysis of the fine-tuned T5 model's performance, evaluating its effectiveness in comparison with the pretrained T5 model in automatic grading of quadratic equation problems has been explored. Fine-tuning significantly contributes to the reduction of error by 70% and a noticeable increase in the R2 value to 97%. © 2024 Elsevier B.V.. All rights reserved.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

How Trees and Traps Become Part of the Language Vocabulary - Postulating the Need for a New Meta-Concept for Composite Elements 17

How Trees and Traps Become Part of the Language Vocabulary -...

引用

17th IFIP WG 8.1 Working Conference on the Practice of Enterprise Modeling Forum, 1st International Workshop on Models for Simulation, M4S 2024, 2nd International Workshop on the Foundations and Applications of Capabilities in Enterprises, Transformations, and ESG Initiatives, FACETE 2024, Workshop on Advancing Enterprise Modelling through Digital Transformation, FAIR Data Management, and Blockchain Integration, AEM 2024, Tools and Demos, PoEM-Companion 2024

作者： Döller, Victoria Research Group Knowledge Engineering Faculty of Computer Science University of Vienna Vienna Austria UniVie Doctoral School Computer Science DoCS University of Vienna Vienna Austria

This paper discusses the need for a new meta-concept termed compound type, which represents composite structures in models that cannot be captured by traditional object types. Compound types allow for the expression of overt concepts that emerge from the mere coexistence of other modeling elements. This can be, in particular, seen in the example of trees that are instantly perceived by humans as a unit. The constituting nodes and edges are subordinate to this structure. The pervasiveness and relevance of compound types are illustrated in several more examples from various modeling languages and domains, including process modeling, Petri Nets, and ER diagrams, where concepts like processes, traps or ERD constructs are essential but not directly represented in the language's metamodel. By introducing the meta-concept of compound types on the meta2level, the paper aims to extend the expressiveness and functionality of modeling languages, ensuring they can handle these complex structures. This allows for "speaking" about compound instances within the vocabulary of the language, making them available to actors not exhibiting human cognition, i.e. machines. An attempt is made to neatly integrate the new meta-concept in the meta2model and put it in context to the established meta-concepts. In the end, composite types are determined as a means of operationalizing the model. © 2024 Copyright for this paper by its authors.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Securing Mobile Cloud Data Offloading in Blockchain Using Deep Deterministic Policy Gradient with Game Theory 4

Securing Mobile Cloud Data Offloading in Blockchain Using De...

引用

4th International Conference on Multimedia Processing, Communication and Information Technology, MPCIT 2024

作者： Matheen Fathima, G. Shakkeera, L. Sharmasth Vali, Y. School of Computer Science Engineering & Information Science Presidency University Itgalpura Rajanukunte Yelahanka Bengaluru560064 India

ISBN: (数字)9798350375466

ISBN: (纸本)9798350375466

In the era of ubiquitous connectivity and the proliferation of mobile devices, the demand for efficient and secure data offloading to the cloud has become paramount. This paper presents a novel framework that supports deep reinforcement learning and blockchain technology to enable secure and efficient mobile cloud data offloading. Addressing the challenge of optimizing data offloading decisions in mobile cloud environments by implementing a Deep Deterministic Policy Gradient algorithm (DDPG) to determine the optimal data offloading strategy. To incentivize user participation, introducing a game-theoretic reward mechanism that considers user contributions based on the offloading decisions made by the DDPG agent. This ensures a fair and efficient allocation of resources while maximizing overall system utility. Furthermore, integrating blockchain technology to ensure the security and integrity of the offloaded data's. By recording transactions on an immutable and transparent ledger, to provide a robust mechanism for data provenance, access control, and tamper-proof storage. The experimental results demonstrate the efficacy of the proposed framework in determining optimal strategies for data offloading decisions, enhancing user participation, and ensuring data security in mobile cloud environments. The evaluation of the system and the security analysis revealed advancements in the resource-efficient access control architecture, which attained reduced network latency while also delivering robust security and data privacy compared to existing data sharing models. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Analyzing Cross-Layer Design Approaches for Quality of Service in Wireless Networks 15

Analyzing Cross-Layer Design Approaches for Quality of Servi...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Shreenidhi, H.S. Acharjya, Kalyan Saraswat, Nidhi Jain School of Engineering and Technology Department of Computer Science and Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & technology Uttar Pradesh India Sanskriti University Department of Computer Science Engineering Uttar Pradesh Mathura India

ISBN: (纸本)9798350370249

Analyzing move-Layer layout procedures for satisfactory of provider (Qu 's) in Wi-Fi networks is of widespread importance to enhance network overall performance. Go-Layer optimization integrates distinct layers consisting of the physical, medium get right of entry to control (MAC), and community layers. Those layers are combined to successfully model the stop-to-cease network performance for each Wi-Fi and wired systems. Go-layer optimization can be used to improve the Qu's via numerous mechanisms, which include aid allocation, scheduling, adaptive modulation, and energy manipulate. These optimization techniques can be used to implement several Qu's-oriented functions together with safety in opposition to congestion, resilience to node and link failures, and adaptive visitors engineering. In this paper, we analyses numerous procedures to move-layer optimization that are appropriate for adapting the Qu's to dynamic situations in Wi-Fi networks. We talk the advantages and downsides of each method, and offer a complete overview on the modern-day studies trends. Eventually, we advise a framework for further research in this region. © 2024 IEEE.

关键词： Adaptive Optimization Performance Procedures Satisfactory Successfully Techniques

来源：评论

学校读者我要写书评

暂无评论

Real-time Health Monitoring of Patients in Emergencies Through Machine Learning And IoT Integrated With Edge Computing 14

Real-time Health Monitoring of Patients in Emergencies Throu...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Mishra, Amit Kumar Sharma, Rahul Singh, Jagendra Singh, Prabhishek Diwakar, Manoj Tiwari, Mohit Graphic Era Hill University Department of Computer Science & Engineering Dehradun India D. Y. Patil International University Pune India School of Computer Science Engineering and Technology Bennett University Greater Noida India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Bharati Vidyapeeth's College of Engineering Dept. of Computer Science & Engineering Delhi India

ISBN: (纸本)9798350344837

With employing the Internet of Things (IoT) sensors and modern-day machine learning algorithms, this study presents a modern inquiry at the intersection of healthcare and era. This have a look at studies the capability of Long ShortTerm Memory (LSTM) and Artificial Neural Network (ANN) fashions in forecasting affected person fitness consequences by utilising the exploitation of sensor facts inclusive of temperature, blood strain, ECG, EEG, and pulse price. The study extensively examines the models' performance utilising a broad variety of performance benchmarks. Results demonstrate that once compared to the LSTM model, the ANN version performs better in terms of prediction accuracy, precision, do not forget, and Fl score. This enhanced accuracy indicates how effectively the ANN model can spot challenging patterns in the dataset. The predicted fitness possibilities for 15 human individuals also are proved in a result table, reaffirming the ANN models constant advantage in prediction. This look at proactive patient care, more intelligent treatment regimens, and improved overall patient outcomes is driving the business and is a significant step towards personalised, data-driven healthcare solutions. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Multi-Task Framework Using Mamba for Identity, Age, and Gender Classification from Hand Images 15

A Multi-Task Framework Using Mamba for Identity, Age, and Ge...

引用

15th International Conference on Information and Knowledge Technology, IKT 2024

作者： Rezasoltani, Amirabbas Hosseini, Alireza Toosi, Ramin Akhaee, Mohammad Ali School of Mathematics Statistics and Computer Science College of Science University of Tehran Tehran Iran School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Adak Vira Iranian Rahjoo Company Tehran Iran

ISBN: (纸本)9798331522254

Biometric authentication is crucial for secure access, surpassing traditional password-based methods vulnerable to breaches. Non-intrusive techniques like hand-based biometrics offer unique advantages, using physiological traits to identify individuals and predict soft biometrics such as age and gender. However, most current systems are designed with a single-purpose focus. In this field, Convolutional Neural Networks (CNNs) are typically utilized but struggle to capture long-range dependencies in images. Transformers, while more effective at handling such relationships, come with high computational costs. To overcome these challenges, this study introduces a novel multi-task learning framework that predicts identity, age, and gender simultaneously. The framework integrates the efficient long-range dependency modeling of Mamba, utilizing Visual State-Space Models (VSS) to capture both local and global patterns with reduced computational complexity. Experiments on the 11k Hands dataset demonstrate superior or competitive performance compared to existing methods. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Developing Lexicons for Enhanced Sentiment Analysis in Software engineering:An Innovative Multilingual Approach for Social Media Reviews

引用

computers, Materials & Continua 2024年第5期79卷 2771-2793页

作者： Zohaib Ahmad Khan Yuanqing Xia Ahmed Khan Muhammad Sadiq Mahmood Alam Fuad AAwwad Emad A.A.Ismail School of Automation Beijing Institute of TechnologyBeijing100081China Department of Computer Science and Technology University of Science and Technology BannuKPKBannu28100Pakistan School of Computer Science and Engineering Central South UniversityChangsha410083China Department of Quantitative Analysis College of Business AdministrationKing Saud UniversityP.O.Box 71115Riyadh11587Saudi Arabia

Sentiment analysis is becoming increasingly important in today’s digital age, with social media being a significantsource of user-generated content. The development of sentiment lexicons that can support languages other thanEnglish is a challenging task, especially for analyzing sentiment analysis in social media reviews. Most existingsentiment analysis systems focus on English, leaving a significant research gap in other languages due to limitedresources and tools. This research aims to address this gap by building a sentiment lexicon for local languages,which is then used with a machine learning algorithm for efficient sentiment analysis. In the first step, a lexiconis developed that includes five languages: Urdu, Roman Urdu, Pashto, Roman Pashto, and English. The sentimentscores from SentiWordNet are associated with each word in the lexicon to produce an effective sentiment score. Inthe second step, a naive Bayesian algorithm is applied to the developed lexicon for efficient sentiment analysis ofRoman Pashto. Both the sentiment lexicon and sentiment analysis steps were evaluated using information retrievalmetrics, with an accuracy score of 0.89 for the sentiment lexicon and 0.83 for the sentiment analysis. The resultsshowcase the potential for improving software engineering tasks related to user feedback analysis and productdevelopment.

关键词： Emotional assessment regional dialects SentiWordNet naive bayesian technique lexicons software engineering user feedback

来源：评论

学校读者我要写书评

暂无评论

Investigation of Single Channel Speech Enhancement: A Comparative Study 4

Investigation of Single Channel Speech Enhancement: A Compar...

引用

4th International Conference on Neural Networks, Information and Communication engineering, NNICE 2024

作者： Ma, Songqi Lv, Zhen Du, Fei Zhang, Xiao University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China University of Science and Technology Beijing School of Advance Engineering Beijing China

ISBN: (纸本)9798350394375

Noise is a critical factor that impacts speech quality. Speech signals are often disturbed by noise during acquisition and transmission. Speech enhancement technology represents an important method to eliminate noise from noisy signal and extract clean speech, which holds significant value in the field of speech recognition, speech communication. This study first categorizes the prior characteristics of different types of noise, followed by an exposition and implementation of representative speech enhancement methods, including traditional signal processing methods and deep learning algorithms. Through three metrics of evaluation, the performance of various speech enhancement algorithms in distinct noise environments is compared, and the Entropy Weight-Topsis (EW-Topsis) method is used for synthesis. Finally, the applicability and development trends of existing speech enhancement algorithms were discussed. The innovation of this study lies in the comparison of different algorithms in various noisy environments using different evaluation metrics. Previous research has mainly focused on two of the evaluation, algorithms and noise. This study presents a comprehensive comparison to synthesize three aspects, providing a unified evaluation reference. © 2024 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Analysis of FUTCOM and NASDAQ Commodities for Gold using Machine Learning and Technical Analysis 4

Comprehensive Analysis of FUTCOM and NASDAQ Commodities for ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Lynda, D. Rakesh, S. Thirugnanasambandam, Kalaipriyan School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Tamilnadu Chennai India Centre for Smart Grid Technologies School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Tamilnadu Chennai India

ISBN: (纸本)9798331540364

This paper covers commodity stock market (FUTCOM and NASDAQ) data using machine learning and technical analysis. Commodity stock markets play a crucial role in global economies, affecting everything from raw material prices to consumer goods. Their inherent volatility and sensitivity to geopolitical and economic factors make them challenging to predict. Addressing the prime problem of price fluctuations, this research highlights the need for accurate forecasting models, where machine learning can significantly enhance decision-making and risk management. It includes data preprocessing, RNN model creation, future price prediction, descriptive stats, correlation analysis, volatility, trend analysis, seasonality, volume analysis, and Monte Carlo simulation. Using Pandas, NumPy, TensorFlow, and Plotly libraries, it provides insights into market trends and forecasting. Results are intended for market participants and decision-makers, © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Exploring the Effect of Different Features Enhancement Methods on Wild Animal Classification 21

Exploring the Effect of Different Features Enhancement Metho...

引用

21st International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Li, Xu Li, Jianping Khoury College of Computer Science Northeastern university BostonMA02115 United States School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu610054 China

ISBN: (纸本)9798331519254

This study investigates the impact of various feature enhancement methods on the accuracy of a deep learning model used for the classification of wild animal. We specifically compare three attention-based mechanisms, Convolutional Block Attention Module (CBAM)., Dual Attention Network (DANet), and Bottleneck Attention Module (BAM), each enhancing feature focus through different attention structures. Using the Animal Image Dataset from Kaggle, we evaluate the classification performance across 90 animal species. The CBAM achieves the highest test accuracy of 92.2 %, while DANet got 91.58% and the accuracy for BAM is 88.5%. In addition, a model applied all three methods sequentially was also examined, its redundancy and overfitting lead to a slight decrease in accuracy, which is 89.73%. Our findings suggest that the CBAM's sequential attention mechanism highlight the important features in the most effective way, making it a suitable choice for complex multi-class image classification tasks. © 2024 IEEE.

关键词： Invertebrates

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：