检索结果-内蒙古大学图书馆

2025 International Russian Smart Industry Conference, SmartIndustryCon 2025

作者： Trapezin, Andrey Filianin, Ivan ITMO University Faculty of Programming and Infocommunications St. Petersburg Russia ITMO University Faculty of Software Engineering and Computer Engineering St. Petersburg Russia

ISBN: (纸本)9798331511241

The current research work addresses the problem of automating the delivery of machine learning models from MLflow to Kubernetes infrastructure. To solve the mentioned problem, a Kubernetes operator has been developed to automate the delivery of machine learning models to production by integrating MLflow for model tracking and Seldon Core for model serving. The developed operator allows data scientists to deploy models while maintaining the familiar MLflow environment. The operator's automatic deployment triggers upon tagging models in MLflow, greatly simplifying engineers' tasks and minimizing the need for manual infrastructure configuration. By automating configuration tasks and optimizing deployment workflows, the solution achieves a 40-50% reduction in model time to deployment (TTD) metric compared to manual processes and decreases error rates from 15% to around 3%. The practical relevance of the work is that it simplifies collaboration between data and infrastructure teams by providing a unified deployment framework, resulting in faster, more reliable, and automated integration of machine learning models into an organisation's business processes. © 2025 IEEE.

关键词： engineering education

来源：评论

学校读者我要写书评

暂无评论

Generalized Stochastic Petri Net Based Simulation of IoT Supported Dynamic Navigation in Teaching Building Evacuation

Generalized Stochastic Petri Net Based Simulation of IoT Sup...

引用

2022 International Conference on Cyber-Physical Social Intelligence, ICCSI 2022

作者： Strobing, Jordan Granit, Meghan Wang, Jiacun Zhao, Lin Monmouth University Dept. of Computer Science and Software Engineering NJ United States School of Safety Science and Engineering Xi'an Univ. of Sci. and Tech Xi'an China

ISBN: (数字)9781665498357

ISBN: (纸本)9781665498357

Emergency management and evacuation efficiency is important to ensure the safety of faculty and students in college. Teaching buildings are typically of multiple stories. When classes are in session, a teaching building may have a large number of students inside. In case of an event like a fire, people have to be evacuated as soon as possible. Due to panic, people may not use good judgement to choose optimal evacuation path, which can further cause congestion in a path to an exit. This study attempts to leverage the recent advances in information technology to dynamically guide evacuees. We use generalized stochastic Petri nets (GSPN) to model the evacuation process in a teaching building. The layout of the building, sizes of classrooms and hallways, number of people in each room, and people's decision pattern in choosing a direction to move are all parameters of the model. With simulation we can estimate the evacuation time-span. Moreover, by observing the state of GSPN model, we can analyze the congestion status of each simulated pathway, and based on that we can dynamically notify people to select the right path that lead them to an exit with the least amount of time. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Enhanced QoS Multicast Routing to Support RIS and Edge Computing in IoT-Enabled MANETs with CF-mMIMO

Federated Learning-Enhanced QoS Multicast Routing to Support...

引用

International Technical Conference o Circuits/Systems, computers and Communications (ITC-CSCC)

作者： Amalia Amalia Yushintia Pramitarini Ridho Hendra Yoga Perdana Kyusung Shim Beongku An Dept. of Software and Communications Engineering in Graduate School Hongik University Republic of Korea School of Computer Engineering and Applied Mathematics Hankyong National University Republic of Korea Dept. of Software and Communications Engineering Hongik University Republic of Korea

ISBN: (数字)9798350379051

ISBN: (纸本)9798350379068

In this paper, we propose a novel federated learning (FL)-enhanced quality of service (QoS) multicast routing, called FLQMR protocol, in IoT-enabled mobile ad-hoc networks (MANETs) with cell-free massive multiple input multiple output (CF -mMIMO). The main contributions of this paper can be summarized as follows. First, we consider the integration of cross-layer design, reconfigurable intelligent surfaces (RIS), FL, and edge computing to enhance network performance. Second, we design the FL framework to optimize routing decisions by selecting the best paths from the source node to multiple destinations. Third, we employ a cross-layer design that combines the physical layer information (i.e., mobility, position, SE) with the network layer information (i.e., route information) to establish a stable multicast tree from the source node to multiple destinations. The simulation results show that the proposed FLQMR protocol achieves a high packet delivery ratio, low routing delay, and low control overhead.

关键词： Cross layer design Simulation Quality of service Reconfigurable intelligent surfaces Routing Physical layer Ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Cur-CoEdge: Curiosity-Driven Collaborative Request Scheduling in Edge-Cloud Systems

Cur-CoEdge: Curiosity-Driven Collaborative Request Schedulin...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Yunfeng Zhao Chao Qiu Xiaoyun Shi Xiaofei Wang Dusit Niyato Victor C. M. Leung College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science and Engineering Nanyang Technological University Singapore College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

The collaboration between clouds and edges unlocks the full potential of edge-cloud systems. Edge-cloud platform has brought about significant decentralization, heterogeneity, complexity, and instability. These characteristics have posed unprecedented challenges to the optimal scheduling problem in the edge-cloud system, including inaccurate decision-making and slow convergence. In this paper, we propose a curiosity-driven collaborative request scheduling scheme in edge-cloud systems, namely Cur-CoEdge. To tackle the challenge of inaccurate decision-making, we introduce a time-scale and decision-level interaction mechanism. This mechanism employs a small-large-time-scale scheduling learning framework, facilitating mutual learning between different decision levels. To address the challenge of slow convergence, we investigate the underlying reasons, such as the sparse reward-setting in reinforcement learning. In response, we develop a curiosity-driven collaborative exploration approach that fosters intrinsic curiosity in the cloud and simultaneously motivates dispatchers to explore the environment both individually and collectively. The effectiveness of this collaborative exploration is also supported by theoretical proof of convergence. Finally, we implement a prototype system on a network hardware system along with two real-world traces. Evaluations demonstrate significant improvements, with up to a 26% increase in time efficiency, a 40% rise in system throughput, and a 71% enhancement in convergence speed.

关键词： Decision making Collaboration Prototypes Optimal scheduling Reinforcement learning Throughput Hardware

来源：评论

学校读者我要写书评

暂无评论

DeTable: Table data extraction model based on deep 10

DeTable: Table data extraction model based on deep

引用

10th International Conference on Networks, Communication and Computing, ICNCC 2021

作者： Fan, Yuxuan Tan, Huobin Liu, Yu Zhang, Jingxuan School Of Software Beihang University China School Of Computer Science And Engineering China

ISBN: (纸本)9781450385848

The rapid development of the information age leads to the mass production and frequent transmission of data, which is difficult to deal with by human alone. With the rise and development of artificial intelligence, the use of data is becoming more efficient. Table, as a special data form, has attracted wide attention gradually. However, extracting data from table subimages presents a number of challenges, including accurately detecting table regions in the image, and then detecting and extracting information from detected table rows and columns. While some progress has been made in table detection, extracting table contents remains a challenge because it involves more fine-grained table structure identification. In this paper, DeTable: table data extraction model based on deep learning is proposed. The model uses the interdependence between the twin tasks of table detection and table structure recognition to divide the text region and the box-line region of the table. Then, rows based on semantic rules are extracted from the identified table regions. The proposed models and extraction methods were evaluated on publicly available ICDAR 2019 and Marmot table datasets and the most advanced results were obtained. © 2021 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Construction and practice of curriculum pre-warning model based on data analysis 16

Construction and practice of curriculum pre-warning model ba...

引用

16th IEEE International Conference on computer Science and Education, ICCSE 2021

作者： Wei, Dongmei Zhong, Shifen He, Zhongxiu Tang, Jianmei Xihua University School of Computer Science and Software Engineering Chengdu610039 China

ISBN: (纸本)9781665414685

In view of the deficiency of the current academic early warning mechanism, the application of big data analysis technology in the course teaching management has become a popular trend of university teaching management. Taking the general education course 'big data and data analysis' teaching platform as an example, this paper collects the basic data and learning track data of the students' courses on this platform, and through attribute standardization and data standardization, carries out data collation and visual analysis, and excavates the key characteristics that affect the learning effect of the course. Through the construction of RFM model, K-means algorithm is used to cluster the students' curriculum situation, and three levels of early warning classification are concluded. According to the different warning, make the corresponding teaching strategy, and make accurate personalized teaching plan for students. Especially for the students with high early warning risk level, we should pay enough attention to develop corresponding intervention strategies to help more students complete the course successfully. Through these practices, we can solve the lag of early warning in the past, promote the transformation of colleges and universities from 'experience decision' to 'data driven decision', improve teaching, improve teaching effect, and optimize teaching management. © 2021 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Exploration and Practice of Big Data Literacy Cultivation Path for University Students

Exploration and Practice of Big Data Literacy Cultivation Pa...

引用

第17届国际计算机科学与教育大会（ICCSE 2022)

作者： Zhong Shifen Liu Rongqi Chen Honghong He Zhongxiu School of Computer and Software Engineering Xihua University

In the big data era, a large number of students with big data thinking are needed. Keeping pace with the development of the times, the big data course for a small number of non-computer majors was offered in our university in the early stage, and then a teaching scheme of the big data general course for all students in our university was proposed. The teaching scheme includes thematic teaching content, blended teaching method, course assessment, and evaluation mechanism which focus on teaching process and ability training. The scheme has been practiced for 5 semesters. According to the survey data, 99.2% of the students have a general or even deep understanding of big data after learning the course. The survey data shows that the big data general course is very effective in cultivating students' big data literacy. It also can effectively improve students' big data application ability.

关键词： big data data literacy general course blended teaching

来源：评论

学校读者我要写书评

暂无评论

Mittag–Leffler stability and synchronization of neutral-type fractional-order neural networks with leakage delay and mixed delays

引用

Journal of the Franklin Institute 2023年第1期360卷 327-355页

作者： Popa, Călin-Adrian Department of Mathematics West University of Timişoara Blvd. V. Pârvan No. 4 Timişoara300223 Romania Department of Computer and Software Engineering Polytechnic University Timişoara Blvd. V. Pârvan No. 2 Timişoara300223 Romania

In recent years, there have been a lot of studies focusing on the dynamics of fractional-order neural networks (FONNs). One problem is that the standard Lyapunov theory does not apply to fractional-order systems, so these studies rely on the use of Halanay-type lemmas to develop sufficient criteria for certain dynamic properties of FONNs, which frequently results in much more conservative criteria than the ones obtained for integer-order neural networks. The present research uses the Halanay-type lemma in a novel way, in order to obtain less conservative sufficient criteria than previous studies. On the other hand, the previous research only considers FONNs with some types of delays, thus limiting their applicability in real-life scenarios, where possibly many more types of delays are relevant. To address this issue, the paper discusses very general FONNs that include neutral-type delay, leakage delay, time-varying delays, and distributed delay. This is the first time such a general model for the fractional-order scenario has been developed, to our awareness. Three theorems, each based on a distinct Lyapunov-like function, are used to construct sufficient criteria, given in terms of linear matrix inequalities, which ensure, respectively, the Mittag–Leffler stability and synchronization, using two different and general state feedback control schemes, of the proposed networks. The usage of the free weighting matrix approach, among the first times in the context of FONNs, also significantly contributes to reducing the conservatism of the deduced sufficient conditions. One numerical example is provided to illustrate each of the three theorems. © 2022 The Franklin Institute

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based APT Malware and Variants Detection with Attribution Analysis

Deep Learning-Based APT Malware and Variants Detection with ...

引用

Pattern Recognition and Artificial Intelligence (PRAI), International Conference on

作者： Binhui Tang Peiyun Leng Xuxiang Shen Yuhang Wei School of Computer and Software Chengdu Jincheng College School of Cyber Science and Engineering Sichuan University Chengdu China School of Computer and Software Chengdu Jincheng College Chengdu China

Malware has become one of the most severe security threats in cyber security, among which APT malware attacks are more threatening than advanced sustainable threat attacks. In this paper, we perform APT malware and variant detection based on deep learning and analyze the results by detecting and attribution. The variant detection of APT malware can inhibit the spread of malicious code, which is important for network security detection and defense. This paper proposes a detection and classification method for APT malware and its variants based on deep learning. Firstly, the feature representation method of APT malware based on RGB images is proposed to solve the gradient explosion and gradient disappearance of grayscale map feature extraction and generate images with rich texture information, which can mine deeper features of APT malware attacks. Secondly, this paper also improves the convolutional neural network model by combining the Self-Attention mechanism with the spatial pyramid pool SPP-net to solve the problem of image input of different sizes, as the accuracy is above 92.14%. Then, the experiment results prove the predictive analysis of the model to understand the organization to which the APT attack belongs and the way of its specific attack, providing the possibility of tracing the source. Finally, the visual analysis of APT threat characteristics is presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Classification of Academic and Psychological Challenges in Higher Education

AI-Driven Classification of Academic and Psychological Chall...

引用

International Conference on New Trends in Computing Sciences (ICTCS)

作者： Seif Hshem Alazzam Mohammad Al-oudat Department of Software Engineering Philadelphia University of Jordan Amman Jordan Department of Computer Science Philadelphia University of Jordan Amman Jordan

ISBN: (数字)9798331523411

ISBN: (纸本)9798331523428

Students enrolled in university experience academic along with mental stressors, which negatively impact their academic results. The research implements artificial intelligence methods for classifying and forecasting the difficulties which higher education students encounter within Jordanian universities. An electronic questionnaire was designed through structured procedures and received validation from eight academics before being distributed to 1020 students. Statistical analysis through Statistical Package for the Social Sciences (SPSS) validated the questionnaire data while testing the reliability of its findings. Students were classified into four categories—Academic Difficulties and Academic and Psychological Challenges and Psychological Distress alongside Normal—through the utilization of the GPT-4o mini API as a Large Language Model (LLM). Machine learning algorithms were applied to evaluate classification performance. Support Vector Machine (SVM) demonstrated the best result among classification models with an accuracy rate of 88.2% while Logistic Regression came second with 87.7% accuracy. A significant number of 54.7% students faced academic challenges while 60.8% of students reported psychological issues. The generated results will assist educational institutions by guiding their early prevention programs along with choosing appropriate assistance methods to enhance educational outcomes.

关键词： Support vector machines Accuracy Statistical analysis Large language models Computational modeling Education Psychology Nearest neighbor methods Reliability Testing

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：