检索结果-内蒙古大学图书馆

Rough set model based on variable universe

CAAI Transactions on Intelligence Technology 2022年第3期7卷 503-511页

作者： Qingzhao Kong Xueer Chang Department of Science Jimei UniversityXiamenChina Digital Fujian Big Data Modeling and Intelligent Computing Institute XiamenChina

Rough set theory has a very good effect in information processing and knowledge *** an information table,the current scholars regard all objects as a universe,and then establish various rough set ***,in the analysis of many data problems,it is more reasonable to select parts of objects which are useful to us or can meet the actual needs as a ***,in order to make up for the deficiency of traditional models,a new model is introduced from the perspective of variable ***,some interesting properties of this model,such as approximation sets,reduct of attributes and maximum part of universe,are *** the study of this paper,it can be seen that the model developed in our paper is not only more accurate but also more effective in describing uncertain knowledge.

关键词： approximation universe describing

来源：评论

学校读者我要写书评

暂无评论

Integrated Simulation Research of Multi-natural Energy-driven Unmanned Surface Vehicle

Integrated Simulation Research of Multi-natural Energy-drive...

引用

2023 International Conference on Applied Mathematics and Digital Simulation, AMDS 2023

作者： Chen, Ao Chen, Tianding He, Hong Wang, Hui Fan, Yimei Yu, Xin School of Physics and Information Engineering Minnan Normal University Fujian Province China School of Computing and Information Science Fuzhou Institute of Technology Fujian Province China School of Data and Computer Science Xiamen Institute of Technology Fujian Province China

In response to the limitations of existing unmanned surface vehicles in complex marine environments, where they often fail to meet the requirements for extended endurance, broad operational range, offshore missions, and prolonged operational durations, an autonomous Unmanned Surface Vehicle (NUSV) has been designed and developed. The NUSV is propelled by wind, solar, and wave energy sources. Concerning wind energy, a micro wind energy storage mechanism based on a spiral spring has been designed to enable power generation in low-wind conditions. A wave energy transmission device, complete with a dynamic model, has been devised for wave energy. This device converts torque generated from wave action in different directions into a unified torque, providing continuous power to drive the generator. Solar energy is harnessed using Maximum Power Point Tracking (MPPT) algorithms to ensure optimal operation of the solar panels. The electrical energy generated from these three natural sources is stored using Pulse Width Modulation (PWM) and DC-DC Boost converters. A programmable logic controller manages and allocates this stored electrical energy for the NUSV's equipment, including underwater propulsion systems, surface cameras, laser radar, GPS, and other electronic devices. This integration of wind, solar, and wave energy sources enables the NUSV to meet power demands, allowing for long-duration operations at sea, extended offshore missions, wide operational ranges, and prolonged mission durations. © Published under licence by IOP Publishing Ltd.

关键词： DC-DC converters

来源：评论

学校读者我要写书评

暂无评论

Towards Enhancing Children's science Education using Augmented Reality and Computer Vision 14

Towards Enhancing Children's Science Education using Augment...

引用

14th IEEE Global Engineering Education Conference, EDUCON 2023

作者： Joshi, Sahi Agbo, Friday Joseph Jormanainen, Ilkka School of Computing University of Eastern Finland Joensuu Finland Willamette University Computing and Data Science SalemOR United States

ISBN: (纸本)9798350399431

Today's technological advancements in mobile technologies and the growing number of mobile devices are extremely beneficial in the mobile learning process. This study is a work in progress that discusses the possibilities of integrating Augmented Reality (AR) and computer vision (CV) into science education which uses deep learning to detect animals in real-time and teach children to classify animals, and learn about their habitat, sound, and important facts. In this study, the Design science Research (DSR) is used which is a pragmatic approach to creating substantial knowledge for problem-solving through the development of artifacts. The mobile application - AnimalCircle - was developed following the DSR method, and initial users' study was conducted to investigate the efficacy of the use of AR and CV in mobile learning on children's science education and if it can enhance children learning experience. Semi-structured interviews were conducted with children studying at primary level class in Kathmandu district of Nepal between the age groups of 6-12. The findings show that children are positive toward usage of AnimalCircle app in their learning process because they find it beneficial and effective in their learning. However, most children also found it difficult and complained of getting confused during their initial usage. Therefore, significant efforts are required to improve the usage of these technologies in the mobile app and to provide a child-friendly learning experience. © 2023 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Predicting Particulate Matter Values in Metropolitan Areas Using Machine Learning 23

Predicting Particulate Matter Values in Metropolitan Areas U...

引用

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Leiva-Araos, Andrés Vemuri, Tushya Mena, David Liu, Xudong School of Computing University of North Florida Jacksonville United States Instituto Data Science Universidad del Desarrollo Santiago Chile

ISBN: (纸本)9798350374889

Atmospheric particulate matter (PM), such as PMIO and PM2.5, significantly impacts ecosystems, climate, and human health. Previous studies have shown that black carbon, a type of PM2.5, significantly contributes to global warming. To this end, this study introduces a set of advanced neural network models aimed at improving air quality predictions within ur-ban environments, specifically targeting PM2.5 and PMIO. By harnessing data from Chile's National Air Quality Information System (SINCA), we employ a diverse array of neural networks, including convolutional neural networks (CNNs), long short-term memory networks (LSTMs), a hybrid CNN-LSTM model called ConvLSTM, transformers, and XGBoost models. Our empirical results show that these models are adept at forecasting air pollution trends, with CNN in particular outperforming all other models, providing crucial insights for real-time environmental monitoring. Our innovative approach enables policymakers and public health officials to take timely and effective measures to combat urban air pollution, thereby enhancing the overall quality of life in metropolitan areas. © 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

Towards Assessing Cycleway Pavement Surface Roughness Using an Action Camera with IMU and GPS 11

Towards Assessing Cycleway Pavement Surface Roughness Using ...

引用

11th International Conference on Vehicle Technology and Intelligent Transport Systems, VEHITS 2025

作者： Baig, Muhammad Hassam Antonio Ayala Garcia, Jeziel Qureshi, Waqar Shahid Ullah, Ihsan School of Computer Science University of Galway Galway Ireland Data Science Institute University of Galway Galway Ireland

ISBN: (纸本)9789897587450

This paper introduces an autonomous and cost-effective method for assessing cycleway pavement roughness, using an action camera equipped with high-resolution sensors including an Inertial Measurement Unit (IMU) and a Global Positioning System (GPS). The methodology utilizes simplified quarter car model for bicycles, without manual intervention, to calculate International Roughness Index (IRI) for cycleway surface quality evaluation. It utilizes our novel approach to determine stable section from which average acceleration orientation vector is computed. For analysis we propose a corrected-roughness index (CRI), which is a quantized version of IRI. Experiments conducted on asphalt cycleways in Ireland revealed strong correlations between vehicle vibration and surface roughness. Results further demonstrate the consistency of the proposed model across different bikes through comparative analysis. Observations indicate bias in vibration data, influenced by different tire sizes and the mechanical features of the bicycles. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Asphalt pavements

来源：评论

学校读者我要写书评

暂无评论

AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading 23

AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Duan, Zhuohui Feng, Hao Liu, Haikun Liao, Xiaofei Jin, Hai Li, Bangyu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133458

The key-value separation is renowned for its significant mitigation of the write amplification inherent in traditional LSM trees. However, KV separation potentially increases performance overhead in the management of Value region, especially for garbage collection (GC) operation that is used to reduce the redundant space occupation. In response, many efforts have been made to optimize the GC mechanism for KV separation. However, our analysis indicates that such solution based on trade-offs between CPU and I/O overheads cannot simultaneously satisfy the three requirements of KV separated systems in terms of throughput, tail latency, and space usage. This limitation hinders their real-world application. In this paper, we introduce AegonKV, a "three-birds-one-stone" solution that comprehensively enhances the throughput, tail latency, and space usage of KV separated systems. AegonKV first proposes a SmartSSD-based GC offloading mechanism to enable asynchronous GC operations without competing with LSM read/write for bandwidth or CPU. AegonKV leverages offload-friendly data structures and hardware/software execution logic to address the challenges of GC offloading. Experiments demonstrate that AegonKV achieves the largest throughput improvement of 1.28-3.3 times, a significant reduction of 37%-66% in tail latency, and 15%-85% in space overhead compared to existing KV separated systems. © 2025 FAST. All Rights Reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

The Evaluation of Classroom Teaching Quality of College Business English Translation Based on AI and Central Tendency Adaptive Enhancement

引用

Journal of Combinatorial Mathematics and Combinatorial computing 2024年 119卷 53-62页

作者： Xiao, Ting Li, Qiong School of Foreign Languages Xiangtan Institute of Technology Xiangtan411100 China Faculty of Data Science City University of Macao 999078 China Department of Science and Technology Hunan Industry Polytechnic Changsha410208 China

Student-centeredness is a teaching theory proposed by British and American scholars in linguistics, psycholinguistics, applied linguistics, and second language acquisition theory."The student-centered approach is different from the traditional teacher-centered approach, but it is implemented in a teacher-led environment. In this study, word2vec, paragraph2vec, pos2vec and LDA (latent dirichlet allocation) are combined to form a semantic representation vector for college business English translation. The key point of the college business English translation reform is to update the concept and theoretical understanding, so as to improve the teachers’ business English teaching theory and teaching practice, and to do a good job of college business English translation reform. Finally, it is shown that the proposed intelligent evaluation framework is more accurate than the traditional method in terms of automatic grading and rubric generation for college business English translation. © 2024 the Author(s), licensee Combinatorial Press.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Comparison of Various Computational Models for Accurate Stroke Prediction and Interpretation Using LIME and SHAP Kernels 1

Comparison of Various Computational Models for Accurate Stro...

引用

1st International Conference for Women in computing, InCoWoCo 2024

作者： Arun, Chalana B Anusha, M. Kodipalli, Ashwini Gargi, N. Harish, L. Devamane, Shridhar B Global Academy of Technology Dept. of Artificial Intelligence and Data Science Bangalore India School of Computing Amrita Vishwavidhyapeetam Department of Computer Science Mysuru India

ISBN: (纸本)9798331518943

Stroke is one dangerous illness that kills people. Stroke is so called because of the way it strikes people down. Across the globe, it is among the main causes of mortality and disability. It requires early identification and precise measures to be taken in order to prevent stroke and further damages to the brain and other parts of body. Our study investigates the use of machine learning techniques that includes Random Forest, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Free Classifier, Random Forest Classifier, Naive Bares and multiple Boosting Classifiers. The 'Healthcare dataset Stroke data' is the dataset used, which is preprocessed and then trained upon by Ml. models. For Random Forest Classifier, the maximum accuracy observed was 94.91%, and upon Hyper parameter Tuning- there was rise in accuracy to 95.64%, Evaluation criteria like F1-score, precision, and recall provides additional evidence for the effectiveness of these models: Further in order to explain how each feature contributes differently to each prediction we have made use of two popular techniques for XAT, LIME and SHAP. LIVE and SHIP provides local, interpretable explanations and global explanations respectively. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Digital Shadows: A Comprehensive Exploration of Network Forensics Methodologies 2

Unveiling the Digital Shadows: A Comprehensive Exploration o...

引用

2nd IEEE International Conference on Emerging Research in Computational science, ICERCS 2024

作者： Nandini, Dhanalakota Sai Jyothika Lanitha, B. Azath, H. Ganeshan, R. Ahmed, Sajjad VIT Bhopal University Kothrikalan School of Computing Science and Engineering Sehore India Karpagam Academy of Higher Education Department of Artificial Intelligence and Data Science Coimbatore India VIT Bhopal University School of Computing Science and Engineering Sehore India

ISBN: (纸本)9798331534950

The Internet has experienced significant growth in attacks that affect network security features such as confidentiality, integrity, and availability. Network security and network forensics work together to ensure system integrity, availability, and confidentiality. Network security measures prevent unau-theorized access, attacks, and breaches, while network forensics investigates and analyses the aftermath of security incidents. Network forensics refers to the process of collecting, analyzing, and preserving digital evidence from network activity in order to investigate and respond to security incidents, breaches, or other malicious activities. It involves reconstructing the events to determine attack methods, compromised data, and potential perpetrators. It lies at the intersection of digital forensics, incident response and network security. This paper is going to analyse the methodologies which are used in network forensics and application of new technologies in each network forensics methodology through ten figures. This paper critically examines network forensics methodologies, focusing on the evolution of these methods and the integration of emerging technologies. It assesses new strategies and discusses inherent issues and limitations of existing techniques, emphasizing the need for cutting-edge techniques to enhance the effectiveness of network forensic processes. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

SAMIC: Segment Anything Model for Integrated Circuit Image Analysis

SAMIC: Segment Anything Model for Integrated Circuit Image A...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Ng, Yong-Jian Tee, Yee-Yang Cheng, Deruo Gwee, Bah-Hwee College of Computing and Data Science Nanyang Technological University Singapore School of Electrical and Electronic Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350350821

Circuit annotation is crucial in analyzing integrated circuit (IC) images for hardware assurance. While deep learning algorithms perform well in circuit annotation, they are highly reliant on labeled training data, which are extremely costly to obtain. The Segment Anything Model (SAM) excels in segmenting natural images but performs sub-optimally on IC images due to the domain gap between IC images and natural images. In this paper, we introduce SAMI C which extends the application of SAM for effective annotation of IC images. We curated an extensive dataset of IC images from four different devices and developed a novel training methodology for SAM models in IC image segmentation. Our experiments show that SAMIC outperforms the original SAM model by 36.78 % and improves accuracy by 6.35 % compared to the second-best technique. © 2024 IEEE.

关键词： Image annotation

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：