检索结果-内蒙古大学图书馆

2024 International Telecommunications Conference, ITC-Egypt 2024

作者： Rizk, Faris H. Mohamed, Mahmoud Elshabrawy Sameh, Basant Zaki, Ahmed Mohamed Eid, Marwa M. El-Kenawy, El-Sayed M. Computer Science and Intelligent Systems Research Center BlacksburgVA24060 United States Delta Higher Institute of Engineering and Technology Department of Communications and Electronics Mansoura35111 Egypt Delta University for Science and Technology Faculty of Artificial Intelligence Mansoura35111 Egypt

ISBN: (纸本)9798350351408

Such an analysis of different machine learning methods for predicting the achievement levels of students in Portuguese secondary education makes this essay. The research highlights the importance of accurate expectations of learners' results for education system administrations and respective policymakers. The current study makes use of the 'Student Performance in Portuguese Secondary education' dataset and employs machine learning algorithms, namely MLPRegressor, XGBoost, DecisionTreeRegressor, CatBoost, and KNeighborsRe-gressor, to the corpus. Performance metrics such as mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), etc., are used to judge every model's performance. The conclusion that can be drawn from the data is that the MLPRegressor model leads among the competitors, having an MSE equivalent of 0.0103, which is superior to others. The findings of this study are of great significance for educational institutions and policymakers as they work to make appropriate contact with students' performance prediction. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

RJoules: An Energy Measurement Tool for R 23

RJoules: An Energy Measurement Tool for R

引用

Proceedings of the 38th IEEE/ACM International Conference on Automated Software engineering

作者： Rajrupa Chattaraj Sridhar Chimalakonda Research in Intelligent Systems and Human Analytics Lab Department of Computer Science and Engineering Indian Institute of Technology Tirupati India

ISBN: (纸本)9798350329964

With the exponential growth of data, the demand for effective data analysis tools has increased significantly. R language, known for its statistical modeling and data analysis capabilities, has become one of the most popular programming languages among data scientists and researchers. As the importance of energy-aware software systems continues to rise, several studies investigate the impact of source code and different stages of machine learning model training on energy consumption. However, existing studies in this domain primarily focus on programming languages like Python and Java, resulting in a lack of energy measuring tools for other programming languages such as R. To address this gap, we propose "RJoules", a tool designed to measure the energy consumption of R code snippets. We evaluate the correctness and performance of RJoules by applying it to four machine learning algorithms on three different systems. Our aim is to support developers and practitioners in building energy-aware systems in R. The demonstration of the tool is available at https://***/yMKFuvAM-DE and related artifacts at https://***/RJoules/.

关键词： energy measurement

来源：评论

学校读者我要写书评

暂无评论

Optimization of Grayscale Image Security through the use of Hybrid Cryptographic Techniques based on Sine and Logistics Maps 4

Optimization of Grayscale Image Security through the use of ...

引用

4th International Conference on Innovative Research in Applied Science, engineering and Technology, IRASET 2024

作者： Koulouh, Fatima Safae, Amine Es-Sabry, Mohammed Mostafa, Merras Elakkad, Nabile Sidi Mohamed Ben Abdellah University Department Of Computer Science Morocco Abdelmalek Essaadi University Laboratory Of Information Security Intelligent Systems And Applications Tetouan Morocco High School Of Technology Moulay Ismail University Image Laboratory Morocco Sidi Mohamed Ben Abdellah University Laboratory Of Engineering Systems And Applications Morocco

ISBN: (纸本)9798350309508

This paper presents an innovative method for enhancing security improve the security of grayscale images by integrating hybrid cryptographic techniques, specifically taking advantage of the sine map and a dual application of the logistic map. The synergy of these chaotic systems reinforces the encryption process, the sinusoidal card generating pseudo-random sequences essential for the generation of cryptographic keys, and the double logistic card adding complexity and unpredictability. Hybridization exploits their complementary characteristics, contributing to the overall robustness of the encryptions system. The theoretical foundations of the sinusoidal map and the double logistic map are examined, highlighting their suitability for cryptographic applications. A comparative examination with established techniques showcases the effectiveness of the proposed method, both in terms of security and computational efficiency, experimental results showing resilience against various attacks, providing information for practical integration into image security frameworks. © 2024 IEEE.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Large Language Models for Unit Test Generation

Evaluation of Large Language Models for Unit Test Generation

引用

Innovations in intelligent systems and Applications Conference

作者： Metin Konuk Cem Baglum Ugur Yayan Computer Engineering Department Center of Intelligent Systems Applications Research (CISAR) Eskisehir Osmangazi University Eskisehir Türkiye

ISBN: (数字)9798350379433

ISBN: (纸本)9798350379440

In recent years, Artificial Intelligence (AI) has significantly transformed various industries, especially software development, through automation and enhanced decision-making processes. Traditional software testing, often manual and error-prone, cannot keep up with rapid development cycles and complex systems, leading to extended development times, higher costs, and undetected bugs. This study develops an AI-based platform using OpenAI models to generate and execute unit tests across multiple programming languages. By leveraging Large Language Models (LLMs) like GPT, we automate unit test creation, demonstrating proficiency in understanding and generating natural language to interpret code. Our web-based system architecture ensures efficient test generation and execution, significantly reducing manual effort and mitigating human error, thus revolutionizing software testing. Furthermore, we introduce unique evaluation metrics such as “Is Executable” and “Assertion Count” to assess the performance and effectiveness of the generated unit tests, providing a comprehensive measure of the models' capabilities.

关键词： Software testing Performance evaluation Technological innovation Large language models Natural languages systems architecture Manuals Software Test pattern generators Software development management

来源：评论

学校读者我要写书评

暂无评论

Worst-Case Integrity Attacks and Resilient State Estimation With Partially Secured Measurements

引用

IEEE Transactions on Control of Network systems 2025年

作者： Zhou, Jing Shang, Jun Chen, Tongwen University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada Tongji University Department of Control Science and Engineering Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Shanghai200092 China

This paper examines the problem of optimal deception attacks against state estimation with partially secured measurements, where smart sensors transmit innovation sequences to the remote end for information fusion. Due to resource limitations or defensive countermeasures, the adversary can only modify data packets transmitted through unreliable channels. Meanwhile, the attack should be synthesized with sophistication to deceive an anomaly detector. To investigate the vulnerabilities of such estimation systems without feedback links and enhance security performance, the optimal attack policy is derived by formulating and explicitly solving a convex optimization problem, with the goal of maximizing the sum of estimation errors. Subsequently, a novel attack detection and resilient state estimation algorithm is proposed to ensure an acceptable level of estimation accuracy. The theoretical performance metrics, including false alarm rates for the proposed detector, are provided. Finally, the effectiveness of the results is confirmed through numerical examples. © 2014 IEEE.

关键词： Optimal detection

来源：评论

学校读者我要写书评

暂无评论

Latest Innovations in intelligent Network-on-Chip Architectures: A Systematic Review

Latest Innovations in Intelligent Network-on-Chip Architectu...

引用

International Workshop on Network on Chip Architectures, NoCArc

作者： Elena Kakoulli Department of Computer Science Intelligent Systems Laboratory Neapolis University Pafos Pafos Cyprus Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (数字)9798331506421

ISBN: (纸本)9798331506438

This review investigates the latest advancements in intelligent Network-on-Chip (NoC) architectures, focusing on innovations from 2022 to 2024. The integration of Artificial Intelligence (AI) and Machine Learning (ML) into NoC designs has driven significant improvements in performance, scalability, energy efficiency, and security. Key contributions include AI/ML-driven techniques to optimize routing, reduce latency, manage power consumption, and enhancing security against emerging threats. Despite these advancements, challenges such as computational overhead and integration complexities remain. This review consolidates these findings, addresses existing challenges, and proposes future research directions to further leverage AI and ML for developing robust and adaptable NoC architectures.

关键词： Technological innovation Scalability Power system management computer architecture Network-on-chip Predictive models Routing Energy efficiency Complexity theory Security

来源：评论

学校读者我要写书评

暂无评论

Value-Compressed Sparse Column (VCSC): Sparse Matrix Storage for Single-cell Omics Data

Value-Compressed Sparse Column (VCSC): Sparse Matrix Storage...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Wolfgang, Seth Ruiter, Skyler Tunnell, Marc Triche, Timothy Carrier, Erin Debruine, Zachary University of Indiana Department of Intelligent Systems Engineering BloomingtonIN United States Purdue University Department of Computer Science West LafayetteIN United States Van Andel Institute Department of Epigenetics Grand RapidsMI United States Grand Valley State University College of Computing AllendaleMI United States

ISBN: (纸本)9798350362480

Genomics datasets, such as single-cell transcriptomics, are often very large and highly sparse, posing significant challenges for both storage and computation. As the scale of data generation accelerates, efficiently compressing these datasets becomes crucial. Current compression methods, like the popular Compressed Sparse Column (CSC) format, capitalize only on sparsity but overlook other properties like redundancy, which can offer additional opportunities for compression. Genomics data, especially single-cell assays, often exhibit high redundancy within columns, making traditional sparse formats inefficient for in-core computation. In this paper, we present two extensions to CSC: (1) Value-Compressed Sparse Column (VCSC) and (2) Index-and Value-Compressed Sparse Column (IVCSC). VCSC takes advantage of high redundancy within a column to further compress data up 1.9-fold over CSC on real data, without significant negative impact to performance characteristics. IVCSC extends VCSC by compressing index arrays through delta encoding and byte-packing, achieving up to a 4.4-fold decrease in memory usage over CSC on real data. Our benchmarks show that VCSC and IVCSC can be used in compressed form with little added computational cost. These formats represent a step forward in balancing the growing demands of data storage and processing in the era of large-scale genomics. © 2024 IEEE.

关键词： data redundancy matrix compression sparse data

来源：评论

学校读者我要写书评

暂无评论

Exploring the Integration of Educational Robotics and the Internet of Things in Learning Environments

Exploring the Integration of Educational Robotics and the In...

引用

International Conference on Distributed Computing in Sensor systems (DCOSS)

作者： Elena Kakoulli Salomi Evripidou Department of Computer Science Intelligent Systems Laboratory Neapolis University Pafos Pafos Cyprus Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus

ISBN: (数字)9798350369441

ISBN: (纸本)9798350369458

This study explores the integration of Educational Robotics (ER) and the Internet of Things (IoT) in learning environments, highlighting their collective impact on educational practices. It assesses ER and IoT’s application, challenges, and opportunities, offering insights into their role in enhancing pedagogy and learning outcomes. Specifically, our exploration uncovers the transformative potential of ER and IoT in fostering critical thinking, problem-solving skills, and digital literacy among students and reveals the pivotal role these technologies play in preparing learners for the demands of the digital age and Industry 4.0, while also highlighting the need for strategic implementation and teacher support. Our findings elucidate the potential of ER and IoT to innovate teaching strategies and curriculum design, serving as a guide for educational stakeholders, such as curriculum developers, educators, researchers, and policymakers, in leveraging these technologies to revolutionize instructional practices.

关键词： Training Information age Fourth Industrial Revolution Internet of Things Stakeholders Problem-solving Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Remote Aerial Vehicle Solutions for Weed Detection in Precision Agriculture

引用

IEEE Access 2025年 13卷 101440-101454页

作者： Shekhar S. Borah Aryan Anand Prabha Sundaravadivel Reginald Fletcher Krishna N. Reddy Department of Electrical and Computer Engineering Center for Robotics and Intelligent Systems The University of Texas at Tyler Tyler TX USA Crop Production Systems Research Unit USDA-Agricultural Research Service (ARS) Stoneville MS USA

This study presents a novel Remote Aerial Vehicle-based approach for detecting pigweeds in soybean (Glycine max) fields using a combination of deep learning and advanced image processing techniques. A custom, high-resolution dataset comprising RGB (red, green, and blue) and multispectral images was collected from USDA operated fields and manually annotated for target pigweed detection. Beyond incorporating YOLOv8 variants for real-time weed classification, this study integrates a comprehensive image processing pipeline, incorporating global thresholding, k-means clustering, 3D surface mapping, and spectral signature analysis to enhance interpretability and detection accuracy. A comparative evaluation of YOLOv8 nano, small, medium, and large models, along with Faster R-CNN, confirmed YOLOv8’s balance between detection accuracy and real-time performance for deployment in precision agriculture. The YOLOv8 nano model emerged as the most balanced in terms of precision (75.6%), recall (81.7%), and mAP@0.5 (81.5%), demonstrating effective weed detection performance under real field conditions. In addition, quadrant-level weed coverage and spatial heatmaps were generated to support targeted interventions. This study advances the current state of RAV based weed detection by providing a field-ready, explainable, and resource-efficient solution, contributing to sustainable farming and data-driven weed management practices.

关键词： Crops Deep learning Accuracy Autonomous aerial vehicles Agriculture Real-time systems Feature extraction Soil Precision agriculture Drones

来源：评论

学校读者我要写书评

暂无评论

Cardiac MRI Segmentation of Ventricular Structures and Myocardium Using U-Net Variants 5

Cardiac MRI Segmentation of Ventricular Structures and Myoca...

引用

5th International Conference on Advanced Research in Computing, ICARC 2025

作者： Wijesinghe, Chinthalanka B. Meedeniya, Dulani Yogarajah, Pratheepan University of Moratuwa Department of Computer Science and Engineering Moratuwa Sri Lanka Ulster University School of Computing Engineering and Intelligent Systems Londonderry United Kingdom

ISBN: (纸本)9798331530983

Accurate segmentation of the ventricular structures and myocardium from Cardiac Magnetic Resonance (CMR) images is essential to diagnose and manage cardiovascular diseases. This study systematically evaluates the performance of five U-Net variants in cardiac MRI segmentation using the Automated Cardiac Diagnosis Challenge (ACDC) dataset and a hybrid loss function combining Cross-Entropy and dice losses. Among the variants, the Feature Pyramid U-Net achieved the best performance, with Dice coefficients of 0.9388 (Left Ventricle), 0.8759 (Right Ventricle), and 0.8426 (Myocardium), showcasing its superior ability to capture multi-scale features and segment complex anatomical structures. The comprehensive and standardized evaluation conducted in this study provides valuable insights into the strengths and limitations of these architectures for cardiac segmentation. © 2025 IEEE.

关键词： Deep learning

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：