检索结果-内蒙古大学图书馆

DISTANCE BETWEEN SPECIES BY CONFUSION OPERATORS OF MULTI-CLASS CLASSIFIERS

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2025年第1期2025卷 171-182页

作者： Tarbă, Nicolae Irimescu, Ionela N. Pleavă, Ana M. Scarlat, Eugen N. Mihăilescu, Mona Doctoral School Computer Science and Engineering Department Faculty of Automatic Control and Computers National University of Science and Technology POLITEHNICA Bucharest Romania Applied Sciences Doctoral School National University of Science and Technology POLITEHNICA Bucharest Romania CAMPUS Research Center National University of Science and Technology POLITEHNICA Bucharest Romania Physics Dept National University of Science and Technology POLITEHNICA Bucharest Romania Physics Dept Research Center for Applied Sciences in Engineering National University of Science and Technology POLITEHNICA Bucharest Romania

We introduce a method to evaluate the similarities between classes of objects based on the confusion matrices coming from the multi-class machine learning (ML) predictors that operate in the vector space generated by the classes. Operation in the confusion domain allows us to use the distance as evaluation metric of the closeness of the relevant properties carried by the classes. We applied the method to semiquantitatively evaluate the effects of X-ray and carbon ion radiation on cultured SW1353 chondrosarcoma cells with respect to the non-irradiated reference. We prove that it is possible to draw useful information on the strength of cells nuclei changes. © 2025, Politechnica university of Bucharest. All rights reserved.

关键词： Radiation effects

来源：评论

学校读者我要写书评

暂无评论

Enhanced cyber-physical system with semantic technologies and machine learning to support smart farming 24

Enhanced cyber-physical system with semantic technologies an...

引用

24th International Conference on control systems and Computer Science, CSCS 2023

作者： Ciolofan, Sorin N. Dragoicea, Monica Popeanga, Daniel-Catalin Politehnica University of Bucharest Department of Computer Science Bucharest Romania Politehnica University of Bucharest Department of Automatic Control and Systems Engineering Bucharest Romania

ISBN: (纸本)9798350313390

An important aspect related to the effects of agricultural activities on the environment is represented by the nutrient loss in water and air (specifically nitrogen). The interactions between catchments hydrological processes, management of farm activities, climate changes and nitrogen losses constitute a complex phenomenon yet not well understood, being an important concern from the sustainable agriculture perspective. Nitrogen can be lost with water as leaching or runoff, or as gas as ammonia volatilization. Nitrous oxide (N2O) is particularly problematic because it is also a powerful greenhouse gas. The goal of the current article is to present innovative digital techniques to advance in understanding of this phenomena through an Information system that integrates Artificial Intelligence techniques such as Semantic Technologies and Machine Learning (ML) into Cyber-Physical systems (CPS) to support smart farming and sustainable agriculture. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Distributed automatic Domain-Specific Multi-Word Term Recognition Architecture using Spark Ecosystem 22

A Distributed Automatic Domain-Specific Multi-Word Term Reco...

引用

22nd International Symposium on Parallel and Distributed Computing, ISPDC 2023

作者： Truica, Ciprian-Octavian Istrate, Neculai-Ovidiu Apostol, Elena-Simona University Politehnica of Bucharest Faculty of Automatic Control and Computers Computer Science and Engineering Department Bucharest Romania

ISBN: (纸本)9798350341270

automatic Term Recognition is used to extract domain-specific terms that belong to a given domain. In order to be accurate, these corpus and language-dependent methods require large volumes of textual data that need to be processed to extract candidate terms that are afterward scored according to a given metric. To improve text preprocessing and candidate terms extraction and scoring, we propose a distributed Spark-based architecture to automatically extract domain-specific terms. The main contributions are as follows: (1) propose a novel distributed automatic domain-specific multi-word term recognition architecture built on top of the Spark ecosystem;(2) perform an in-depth analysis of our architecture in terms of accuracy and scalability;(3) design an easy-to-integrate Python implementation that enables the use of Big Data processing in fields such as Computational Linguistics and Natural Language Processing. We prove empirically the feasibility of our architecture by performing experiments on two real-world datasets. © 2023 IEEE.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Real-Time Notifier for Blockchain Events 22

Real-Time Notifier for Blockchain Events

引用

22nd RoEduNet Conference: Networking in Education and Research, RoEduNet 2023

作者： Tanase-Paris, Cristian Carabas, Costin Tapus, Nicolae University Politehnica of Bucharest Faculty of Automatic Control and Computers Computer Science and Engineering Department Bucharest Romania

ISBN: (纸本)9798350393651

Blockchain technology gained much traction in the last few years. These decentralized databases offer security, immutability, and scalability across various applications. Decentralized applications generate vast amounts of data, known as events, that are recorded on the blockchain and are public to anyone. Some people may see opportunities for financial gains in these events and would like to know when they occur. This paper proposes a solution to process and deliver those events as real-time alerts to the users. It uses existing technologies such as message queues, multithreading, and asynchronous processing and integrates them into a scalable architecture. The results we achieved in this paper show that for an evenly distributed network traffic, which does not entirely consists of transaction bursts, the proposed solution offers reliability, efficiency, and a suitable delivery time to those wishing to integrate it into their projects. With time, this solution, or improved architectures, may form the basis of the following big-data architectures for processing blockchain events. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Stochastic Optimization Problem Solved Using SVM Based Prediction For Photovoltaic Plants 27

Stochastic Optimization Problem Solved Using SVM Based Predi...

引用

27th International Conference on system Theory, control and Computing, ICSTCC 2023

作者： Colbu, Ștefania-Cristiana Băncilă, Daniel-Marian Popescu, Dumitru Olteanu, Severus-Constantin Petrescu-Niță, Alina Department of Automatic Control and Systems Engineering University POLITEHNICA of Bucharest Bucharest Romania Department of Mathematical Methods and Models University POLITEHNICA of Bucharest Bucharest Romania

ISBN: (纸本)9798350337983

In the current paper, a strategy for handling a stochastic optimization problem based on metaheuristic techniques is presented. This optimization problem is defined based on the impact of environmental factors such as temperature and irradiance on photovoltaic panels. The objective aims to solve the defined problem by finding an SVM model of a photovoltaic panel. To enhance the efficiency of power generation, this model will be utilized for the purpose of predicting the voltage linked to the Maximum Power Point of the panel. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

UPB at IberLEF-2023 AuTexTification: Detection of Machine-Generated Text using Transformer Ensembles

UPB at IberLEF-2023 AuTexTification: Detection of Machine-Ge...

引用

2023 Iberian Languages Evaluation Forum, IberLEF 2023

作者： Preda, Andrei-Alexandru Cercel, Dumitru-Clementin Rebedea, Traian Chiru, Costin-Gabriel Computer Science and Engineering Department Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest060042 Romania

This paper describes the solutions submitted by the UPB team to the AuTexTification shared task, featured as part of IberLEF-2023. Our team participated in the first subtask, identifying text documents produced by large language models instead of humans. The organizers provided a bilingual dataset for this subtask, comprising English and Spanish texts covering multiple domains, such as legal texts, social media posts, and how-to articles. We experimented mostly with deep learning models based on Transformers, as well as training techniques such as multi-task learning and virtual adversarial training to obtain better results. We submitted three runs, two of which consisted of ensemble models. Our best-performing model achieved macro F1-scores of 66.63% on the English dataset and 67.10% on the Spanish dataset. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Making children read more and better by integrating natural language processing and gamification techniques into mobile applications 24

Making children read more and better by integrating natural ...

引用

24th International Conference on control systems and Computer Science, CSCS 2023

作者： Voicu, George Catalin Ciolofan, Sorin N. Dragoicea, Monica Manager Emag Bucharest Romania Politehnica University of Bucharest Department of Computer Science Bucharest Romania Politehnica University of Bucharest Department of Automatic Control and Systems Engineering Bucharest Romania

ISBN: (纸本)9798350313390

It is well known that nowadays children tend to spend lot of time playing games on mobile devices at the expense of reading books. The current research aims to explore ways to design and develop a mobile application, attractive for children, that uses voice recognition technology and gamification techniques to help children read more and better and to track the progress of reading. The application is implemented with Flutter, Dart and Firebase and is addressed to children, the books being made available in encyclopedia format. By integrating technologies such as NLP and gamification the application aims to improve reading fluency among children, but also to give them the opportunity to accumulate new and exciting information in the same time. © 2023 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Real-time Image Identification for Vehicle Positioning system 4

Real-time Image Identification for Vehicle Positioning Syste...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Liu, Chun-Yu Huang, Ching-Huei Juang, Rong-Terng Feng Chia University Department of Automatic Control Engineering Taichung City Taiwan Institute of Aerospace and System Engineering Taipei Tech Taipei City Taiwan

ISBN: (纸本)9798350360721

An innovative vehicle real-time positioning method was developed to maximize the use of existing visible light camera systems on vehicles, especially in areas without Global Positioning system (GPS) signals or blind spots. This approach eliminates the need for additional positioning devices and leverages the potential of existing vehicle driver assistance systems. As vehicles are equipped with cameras for monitoring the surrounding environment, we optimized the use of these existing resources for an efficient and accurate innovation in vehicle positioning. Firstly, we used cameras in four directions (the front, rear, left, and right) of the vehicle to capture images. By integrating images in four directions and using a transformation algorithm, a complete top-down view was formed with geographic information to enhance positioning accuracy. The integrated top-down view image is useful for obtaining information on surrounding environments and identifying the vehicle's real-time location in parking lots. The developed method serves as a foundation for future applications in automated driving planning and positioning. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Vehicle string using spacing strategies for cooperative adaptive cruise control system

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and Computer Science 2021年第1期83卷 91-106页

作者： Luu, Duc Lich Lupu, Ciprian Department of Automatic Control and Systems Engineering Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania

The Co-operative Adaptive Cruise control (CACC) is one of the key subsystems of Connected and Automated Vehicles (CAVs) that have the potential to increase the road traffic capacity and improve traffic safety with shorter inter-vehicle spacing between vehicles. The spacing strategies are the core of all CACC control algorithms which are chosen based on design purposes for the system. This work presents a comparative research to evaluate the effectiveness of two spacing strategies, consisting of the constant spacing strategy and, constant time headway strategy, which is suitable for information flow topologies. The main focus of this research analyzes the benefits of operating mechanisms as well as the characteristics of each spacing strategy. The results of the simulations using software Matlab/Simulink have demonstrated the performances and applicability of each spacing policy. © 2021, Politechnica university of Bucharest. All rights reserved.

关键词： Adaptive cruise control

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Theoretical and Empirical Log-Normal Models for Wi-Fi Fingerprint Mapping in Indoor Positioning 6

Evaluation of Theoretical and Empirical Log-Normal Models fo...

引用

6th IEEE International Conference on Artificial Intelligence in engineering and Technology, IICAIET 2024

作者： Bin Mohamed Ghazali, Mohamed Aizad Kiring, Aroland Mihaylova, Lyudmila Yew, Hoe Tung Chung, Seng Kheau Farm, Yan Yan Faculty of Engineering Universiti Malaysia Sabah Sabah Kota Kinabalu Malaysia University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom

ISBN: (纸本)9798350389692

This paper evaluates both the theoretical and empirical log-normal models for Wi-Fi fingerprint mapping in indoor positioning systems. Wi-Fi fingerprinting, leveraging the ubiquitous IEEE 802.11 protocol, offers a practical solution for indoor localization where Global Positioning system (GPS) is ineffective. It involves generating empirical data by systematically measuring Wi-Fi Received Signal Strength (RSS) within a complex indoor environment and formulating a log-normal path loss model to predict signal behavior. A comparative analysis was conducted between the theoretical model, calibrated with empirical RSS data, and the actual RSS measurements. The results showed that while the theoretical model captured overall signal propagation trends, the empirical data revealed variations due to multipath effects and environmental obstacles. It demonstrated the practical use of Wi-Fi fingerprint mapping, theoretical modeling, and comparative analysis. The findings underscore the importance of empirical validation in refining theoretical models and optimizing deployment strategies for accurate and reliable indoor positioning. Future research should focus on mitigating multipath effects and enhancing the theoretical model accuracy through optimized access point (AP) placement and advanced signal processing techniques. © 2024 IEEE.

关键词： Global positioning system

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：