检索结果-内蒙古大学图书馆

Comparison of machine learning techniques to predict students’ CGPA by using course learning outcomes datasets

Human-Intelligent Systems Integration 2025年 1-11页

作者： Siraj, Saima Dahri, Fida Hussain Chandio, Jamil Ahmed Jalbani, Akhtar Hussain Laghari, Asif Ali Quaid-E-Awam University of Engineering Science & Technology Nawabshah Pakistan School of Computer Science and Engineering Southeast University Nanjing China Shah Abdul Latif University Khairpur Pakistan Software College Shenyang Normal University Shenyang China

As technology advances, traditional teaching, training, and performance evaluation approaches are being replaced by computer-based tools (CBT) such as online video courses, online exams, offline video classes, and flip classes. To improve the teaching and learning performance of the students, the education system (ES) assesses the course learning outcomes (CLO) by using the bloom taxonomy (BT). Owing to the abrupt COVID-19 epidemic, traditional classrooms are molded into online classes; therefore, it is very hard to assess the CLO because physical and online teaching pedagogies are heterogeneous, and it is very hard to classify either content has been generated by the students or any other online sources used to answer the questions. Thus, it is necessary to construct the classification model using artificial intelligence (AI) techniques and to assist educational stakeholders like schools, colleges, universities, NGOs, and the government in measuring student performance. This research proposes a comparative analysis of machine learning techniques to mitigate all the above-stated problems. It proposes methods to perform data cleaning in its first phase, whereas the second phase constructs classification models using machine learning algorithms such as decision tree, support vector machine, and random forest. In the third phase, performance evaluation is performed to estimate the results. The highest accuracy was achieved using a decision tree with 96.99% and 10 k-fold cross-validation. This research contributes (a) a real-world dataset and (b) the highest classification accuracy to analyze education.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey on Intelligent Solutions for Increased Video Delivery Quality in Cloud-Edge-End Networks

引用

IEEE Communications Surveys and Tutorials 2025年第2期27卷 1363-1394页

作者： Shi, Wanxin Li, Qing Yu, Qian Wang, Fulin Shen, Gengbiao Jiang, Yong Xu, Yang Ma, Lianbo Muntean, Gabriel-Miro Tsinghua University Tsinghua Shenzhen International Graduate School Shenzhen518055 China Fudan University School of Computer Science Shanghai200433 China Peng Cheng Laboratory Department of Strategic and Advanced Interdisciplinary Research Shenzhen518066 China Institute of Future Networks Southern University of Science and Technology Shenzhen518055 China Tecorigin Software Department Shanghai200120 China Peng Cheng Laboratory Department of Strategic and Advanced Interdisciplinary Research Shenzhen518055 China Northeastern University College of Software Shenyang110819 China Dublin City University Performance Engineering Laboratory School of Electronic Engineering DublinD09 DD7R Ireland

The digital age has brought a significant increase in video traffic. This traffic growth, driven by rapid Internet advancements and a surge in multimedia applications, presents both challenges and opportunities to video transmissions. Users seek high-quality video content, prompting service providers to offer high-definition options to improve user experience and increase profits. However, traditional end-to-end best-effort networks struggle to meet the demands of extensive video streaming and ensure good user Quality of Experience (QoE), especially in high user mobility scenarios or fluctuating network conditions. Addressing some of these challenges, content delivery networks (CDN) are instrumental in delivering video content, but they are under increased pressure to support high quality and reduce their deployment and maintenance costs. Currently, cloud-edge-end fusion technologies have become one of the optimization directions for network services due to their flexibility and scalability. At the same time, in the context of the recent advancements in computing-focused network paradigms, intelligent enhancement techniques (e.g., super-resolution), commonly utilized in image optimization, have been adopted as a pivotal solution for increasing video delivery quality. To illustrate the essence and employment of the intelligent enhancement solutions for video streaming, this paper first outlines the video streaming process, discusses relevant evaluation metrics, and examines aspects related to the intelligent solutions. Then the paper presents the intelligent enhancement process of video streaming, analyzes various typical intelligent models for content enhancement and highlights their distinct characteristics. This exploration delves deeper into various intelligent quality-improved solutions, scrutinizing their applicability across different transmission scenarios like Video on Demand (VoD) and live streaming, and shedding light on their strengths and weaknesses from

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

What Drives the Use of Generative Artificial Intelligence to Promote Educational Sustainability? Evidence from SEM-ANN Approach

引用

TechTrends 2025年 1-15页

作者： Arpaci, Ibrahim Al-Emran, Mostafa Al-Qaysi, Noor Al-Sharafi, Mohammed A. Management Information Systems College of Business Administration Gulf University for Science and Technology Mishref Kuwait Department of Software Engineering Faculty of Engineering and Natural Sciences Bandirma Onyedi Eylul University Balikesir Turkey Department of Computer Science and Engineering College of Informatics Korea University Seoul 02841 South Korea Faculty of Engineering & IT The British University in Dubai Dubai United Arab Emirates Engineering Technical College Al-Bayan University Baghdad Iraq Information and Communication Technology Research Group Scientific Research Center Al-Ayen University Thi-Qar Iraq IRC for Finance and Digital Economy KFUPM Business School King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia

The literature on generative “Artificial Intelligence” (AI) in education primarily focuses on its immediate benefits and applications, such as personalized learning, student engagement, and content generation. However, there is a notable absence of empirical research concerning the holistic use of generative AI within educational institutions and its long-term impact on educational sustainability. This study investigates the factors that predict the use of generative AI and its subsequent influence on educational sustainability. This study enhanced the extended “Unified Theory of Acceptance and Use of Technology” (UTAUT-2) by including personal innovativeness as an external variable and educational sustainability as an outcome. A hybrid methodology, integrating “Structural Equation Modeling” (SEM) and “Artificial Neural Network” (ANN), was used to evaluate the research model using data collected from 1,011 university students. The SEM analysis confirmed all hypotheses. Specifically, a positive relationship was found between use behavior and educational sustainability. These results show that the combined variables collectively account for 63% and 66% of the variance in use behavior and educational sustainability, respectively. The sensitivity analysis identified habit as the most important predictor of use behavior. The findings offer both theoretically important and practically valuable implications for designing user-centered AI integration in education. © Association for Educational Communications & Technology 2025.

关键词： Artificial intelligence Educational sustainability SEM-ANN UTAUT-2

来源：评论

学校读者我要写书评

暂无评论

Resilience to deception attacks in consensus tracking control of incommensurate fractional-order power systems via adaptive RBF neural network

引用

Expert Systems with Applications 2025年 283卷

作者： Sharafian, Amin Naeem, H.M. Yasir Ullah, Inam Ali, Ahmad Qiu, Li Bai, Xiaoshan College of Mechatronics and Control Engineering Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China

This paper addresses the consensus control problem for incommensurate fractional-order multi-agent power systems vulnerable to sensor deception attacks within their communication networks. To overcome this problem, an adaptive Radial Basis Function neural network (RBFNN) state observer is employed to estimate the system uncertainties in the presence of malicious attacks. Additionally, a compensation mechanism is implemented to mitigate the effects of unknown time-varying gains in the system output induced by deception attacks. Within the adaptive backstepping framework, the proposed control strategy ensures that all system signals remain bounded while enabling all followers to achieve consensus with the leader's trajectory. The effectiveness of the proposed control approach is further validated through MATLAB simulations, demonstrating its ability to enhance stability and reliability in power systems. © 2025 Elsevier Ltd

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Leveraging Language-based Representations for Better Solving Symbol-related Problems with Large Language Models 31

Leveraging Language-based Representations for Better Solving...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wang, Yile Cheng, Sijie Sun, Zixin Li, Peng Liu, Yang College of Computer Science and Software Engineering Shenzhen University Shenzhen China Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University Beijing China Tsinghua University Beijing China Jiangsu Collaborative Innovation Center for Language Competence Jiangsu China

ISBN: (纸本)9798891761964

Symbols such as numerical sequences, chemical formulas, and table delimiters exist widely, playing important roles in symbol-related tasks such as abstract reasoning, chemical property prediction, and tabular question-answering. Compared to tasks based on natural language expressions, large language models (LLMs) have limitations in understanding and reasoning on symbol-based representations, making it difficult for them to handle symbol-related problems. In this paper, we propose symbol-to-language (S2L), a method that converts symbol-based representations to language-based representations, providing valuable information for language models during reasoning. We found that, for both closed-source and open-source LLMs, the capability to solve symbol-related problems can be largely enhanced by incorporating such language-based representations. For example, by employing S2L for GPT-4, there can be substantial improvements of +21.9% and +9.5% accuracy for 1D-ARC and Dyck language tasks, respectively. There are also consistent improvements in other six general symbol-related tasks such as table understanding and Tweet analysis. We release the GPT logs in https://***/THUNLP-MT/symbol2language. © 2025 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

Comparative Analysis of Differential Privacy Implementations on Synthetic Data

Comparative Analysis of Differential Privacy Implementations...

引用

IEEE Annual Computing and Communication Workshop and Conference (CCWC)

作者： Huwida E. Said Qusay H. Mahmoud Mandeep Goyal Faiza Hashim Department of Computing and Applied Technolgy College of Technological Innovation Zayed University Dubai UAE Department of Electrical Computer and Software Engineering Ontario Tech University Oshawa ON Canada Department of Computer Science and Software Engineering College of Information Technology UAE University AI-Ain UAE

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

Differential privacy offers a promising solution to balance data utility and user privacy. This paper compares two prominent differential privacy tools-PyDP and IBM's diffprivlib-that are applied to a synthetic dataset with medical attributes. We evaluate these tools based on their effectiveness in maintaining data privacy while preserving the statistical integrity of the data. Our results reveal that PyDP provides synthetic data that closely matches real-world data, making it appropriate for tasks requiring accuracy while striking a better balance between data utility and privacy. However, IBM's diffprivlib is more suitable for privacy-critical applications due to its stronger privacy guarantees, but at the cost of increased noise and decreased data utility. This paper contributes to the practical understanding of implementing differential privacy in machine learning and software applications and enhances the tools available for developers in sensitive data environments.

关键词： Differential privacy Costs Accuracy Conferences Noise Machine learning software Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Partitioning-Based Inter-Chip Redistribution Layer Routing for Fan-Out Wafer-Level Packaging

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Xu, Haoyang Huang, Xing Zhuang, Zhen Yu, Zhiwen Guo, Bin Chao, Kai-Yuan Yu, Bei Ho, Tsung-Yi Wong, Martin D. F. Northwestern Polytechnical University School of Computer Science Xi’an China Harbin Engineering University College of Computer Science and Technology Harbin China The Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong Siemens Digital Industries Software WilsonvilleOR United States Hong Kong Baptist University Hong Kong

In modern advanced fan-out wafer-level packaging (FOWLP), redistribution layers (RDLs) are used to implement efficient interconnections among chips, where both flexible vias and irregular pad structures can be deployed to realize highly integrated heterogeneous systems. With the sharp increase in chip densities, however, it becomes challenging to fully utilize the routing resources in RDLs. The routing graph without optimized resource planning can lead to significant deterioration in the solution quality of RDL design. Furthermore, prior work determines via locations in the RDLs before identifying wire routes, thus offsetting the advantages of flexible vias and irregular pads. To systematically solve the RDL routing problem in FOWLP, in this paper, we propose a hierarchical partitioning-based inter-chip routing method considering both flexible vias and irregular pads, so that optimized RDL solutions can be generated automatically and efficiently. The proposed method includes the following key techniques: 1) a channel planning method for optimized routing region partition and a dynamic routing graph-based pathfinding method for efficient global routing, 2) a binarysearch-based hierarchical tile segmentation method for conflict removal and wirelength reduction, 3) a novel monotonicityanalysis-based access point optimization method and a staggered via planning strategy for both wirelength and detour reduction, and 4) a geometry-based detailed routing algorithm for innertile wire routing. The experimental results demonstrate that the proposed algorithm leads to 100% routablility and 4.8% wirelength reduction on average compared to the state-of-the-art work, with a maximum reduction rate of 10.3% across all the benchmarks. © 1982-2012 IEEE.

关键词： Chip scale packages

来源：评论

学校读者我要写书评

暂无评论

Stochastic Geometry Based Semantic Performance Analysis For Text Semantic Communication

引用

IEEE Transactions on Communications 2025年

作者： Zhu, Heng Zhu, Kun Zhang, Yang Niyato, Dusit Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China Collaborative Innovation Center of Novel Software Technology and Industrialization China Nanyang Technological University School of Computer Science and Engineering Singapore639798 Singapore

Semantic communication has recently garnered substantial attention due to its potential to alleviate bandwidth constraints and improve network capacity. Nonetheless, existing studies primarily concentrate on network architecture and overlook the communication performance analysis. Therefore, this paper seeks to derive semantic-oriented error probability. Specifically, we develop a novel text semantic communication framework that comprises distinct semantic and physical layers. In the semantic layer, we employ latent Dirichlet allocation (LDA) to extract text topics and evaluate the topic distribution. Given an expected transmission accuracy, we propose a dichotomy to determine the minimal number of topics. These acquired topics, along with their respective distributions, are defined as the text semantic features. In the physical layer, the semantic features are encoded into a binary sequence and modulated with conventional methods. The relationship between the semantic and physical layers is uncover by associating coding of the semantic features with the symbol error probability (SEP). Considering a scenario wherein base stations (BSs) following a specific Poisson point process (PPP), we derive the approximate SEP and semantic inference error probability (SIEP) for multiple coding strategies. Simulation results show that the proposed text semantic communication network enables effective text transmission and the derived error probability accurately reflect the performance of an actual communication system. © 1972-2012 IEEE.

关键词： Latent Dirichlet allocation Semantic communication Semantic inference error probability Stochastic geometry

来源：评论

学校读者我要写书评

暂无评论

Multiscale drought assessment with analyzing agricultural, meteorological, and hydrological impacts multi-index approaches (1991–2021)

引用

Theoretical and Applied Climatology 2025年第5期156卷 1-21页

作者： Zhou, Mingwu Haseeb, Muhammad Tahir, Zainab Mahmood, Syed Amer Arif, Hania Abdullah-Al-Wadud, M. Tariq, Aqil Department of Water Resources and Civil Engineering Hetao College Mongolia Autonomous Region Inner Bayannur 015000 China Institute of Environmental Engineering and Research University of Engineering and Technology Lahore P.O. Box 54780 Lahore Pakistan Institute of Space Science University of the Punjab Lahore 54780 Pakistan Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh 11543 Saudi Arabia Department of Wildlife Fisheries and Aquaculture College of Forest Resources Mississippi State University Mississippi State 39762 - 9690 MS United States

The increasing frequency of droughts as global temperatures rise requires the development of precise and reliable criteria for drought evaluation. This research used three standard drought indices: the Standardized Precipitation Index (SPI), the Standardized Precipitation Evapotranspiration Index (SPEI), and the Reconnaissance Drought Index (RDI) to assess drought conditions in five districts of Punjab, Pakistan, from 1991 to 2021. A key innovation of this research is the integration of multiple timescales (3-, 6-, and 12-months) to analyze agricultural, meteorological, and hydrological droughts, providing a more comprehensive drought assessment. The RDI calculation noticed that all districts experienced moderate to extreme droughts, with values ranging from -1.0 to -2.5. Moderate to severe droughts happened in all districts, with critical drought years including 1993, 2000, 2001, 2005, 2018, and 2021 resulting in considerable wheat production decreases of 2.74 tons/ha. Based on 3-, 6-, and 12-month timescale estimations for SPI and SPEI, the research indicated major droughts occurred in 1991, 1993, 2000, 2001, 2003, 2016, 2018, and 2021, which were consistent throughout all five districts of Punjab. The study indicated that the Bahawalpur and Rahim Yar Khan districts were most vulnerable to droughts. This study’s comparative assessment of SPI, SPEI, and RDI highlights that SPI is highly effective for detecting short-term agricultural droughts, while SPEI provides a more detailed perspective on long-term climatic variability. RDI, which integrates precipitation and evapotranspiration, is particularly useful for assessing hydrological drought impacts in semi-arid regions. The study underscores the importance of selecting appropriate drought timescales, where SPI-3 is optimal for agricultural droughts, while SPI-6 and SPI-12 provide insights into hydrological and meteorological droughts, respectively. The findings of this research offer innovative insights for enhanci

关键词：

来源：评论

学校读者我要写书评

暂无评论

GLoT: A Novel Gated-Logarithmic Transformer for Efficient Sign Language Translation

arXiv

引用

arXiv 2025年

作者： Shahin, Nada Ismail, Leila Lab Department of Computer Science and Software Engineering College of Information Technology UAE University Al-Ain United Arab Emirates Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates Emirates Center for Mobility Research UAE University Al-Ain United Arab Emirates

Machine Translation has played a critical role in reducing language barriers, but its adaptation for Sign Language Machine Translation (SLMT) has been less explored. Existing works on SLMT mostly use the Transformer neural network which exhibits low performance due to the dynamic nature of the sign language. In this paper, we propose a novel Gated-Logarithmic Transformer (GLoT) that captures the long-term temporal dependencies of the sign language as a time-series data. We perform a comprehensive evaluation of GloT with the transformer and transformer-fusion models as a baseline, for Sign-to-Gloss-to-Text translation. Our results demonstrate that GLoT consistently outperforms the other models across all metrics. These findings underscore its potential to address the communication challenges faced by the Deaf and Hard of Hearing community. © 2025, CC BY.

关键词： Neural machine translation

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：