检索结果-内蒙古大学图书馆

International Symposium for Design and Technology of Electronics Packages (SIITME)

作者： Mihaela-Gabriela Boicu Marius-Alexandru Dobrea Mihaela Vasluianu Gabriela-Valentina Olteanu Giorgian Neculoiu Faculty of Automatic Control and Computer Science University POLITEHNICA of Bucharest Bucharest Romania Faculty of Hidrotechnics Technical University of Civil Engineering of Bucharest Bucharest Romania

ISBN: (数字)9798331539511

ISBN: (纸本)9798331539528

This article presents a study on the use of photovoltaic panels for storing electrical energy intended to power an HVAC unit placed in a residential room. To highlight this aspect, two specific scenarios will be considered. Thus, we aim to analyze whether the generated and stored energy is sufficient to fulfil the thermal comfort requirements of the user, while also considering the primary objective of minimizing energy consumption. To achieve this goal, the HVAC unit will be controlled by implementing a fuzzy system that determines its optimal activation based on the comfort level obtained from the user. The fuzzy system presents as inputs both environmental parameters and specific personal perception parameters of the user. The research results provide an insight into the efficiency of implementing photovoltaic energy storage systems for residential applications and propose solutions for optimizing energy consumption in the context of ensuring adequate thermal comfort. Thus, the study contributes to the development of sustainable and personalized energy solutions for smart homes.

关键词： Photovoltaic systems Fuzzy logic Energy consumption HVAC Electronic packaging thermal management control systems Ventilation Thermal analysis Fuzzy systems Energy storage

来源：评论

学校读者我要写书评

暂无评论

Post-Processing of Thresholding or Deep Learning Methods for Enhanced Tissue Segmentation of Whole-Slide Histopathological Images

Post-Processing of Thresholding or Deep Learning Methods for...

引用

18th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Marczyk, Michal Wrobel, Agata Merta, Julia Polanska, Joanna Department of Data Science and Engineering Silesian University of Technology Gliwice44-100 Poland Yale Cancer Center Yale School of Medicine New HavenCT06511 United States Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice44-100 Poland

Digital pathology allows for the efficient storage and advanced computational analysis of stained histopathological slides of various tissues. Tissue segmentation is a crucial first step of digital pathology aimed at eliminating background, pen markings, and other artifacts, reducing image size, and increasing the efficiency of further analysis. In most cases, color thresholding or deep learning models are used, but their effectiveness is reduced due to complex artifacts and huge color variations between slides. We propose a post processing method to increase the tissue segmentation performance of any initial segmentation algorithm. Using a set of 197 manually annotated histopathological images of breast cancer patients and 63 images of endometrial cancer patients, we tested our method with 3 thresholding techniques and 3 deep learning-based algorithms by calculating the Dice index, Jaccard index, precision, and recall. In both datasets, applying post processing increased precision and recall for thresholding methods and mostly precision for deep learning models. Overall, applying post-processing gave better tissue segmentation performance than initial segmentation methods, significantly increasing Dice and Jaccard indices. Our results proved that thanks to post-processing, the tissue segmentation pipeline is more robust to noises and artifacts commonly present in histopathological images. © 2025 by SCITEPRESS– science and Technology Publications, Lda.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A NEW COLLECTIONS FRAMEWORK FOR THE D PROGRAMMING LANGUAGE STANDARD LIBRARY

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

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2022年第3期84卷 95-106页

作者： Stăniloiu, Eduard Niţu, Răzvan Deaconescu, Răzvan Rughiniş, Răzvan Faculty of Automatic Control and Computer Science University PO-LITEHNICA of Bucharest Romania

D is a general purpose, high level and high performance, programming language capable of interfacing with the operating system API and system’s hardware. One of the core features of D is represented by ranges, a powerful and new approach of iterating through a set of elements. How-ever, being a state of the art feature, ranges are not used in the D ecosystem at their full potential. In this work we provide a new collections framework for the D Standard Library that is compatible with the existing algorithms and that provides an API similar to the one provided by ranges. Our implementation enables the collections to infer the safety of the operations from the contained, user provided, type. We show that our implementation may provide performance benefits of up to 2x compared to the existing standard library implementations, when used in conjunction with a custom allocator. © 2022, Politechnica University of Bucharest. All rights reserved.

关键词： Application programming interfaces (API)

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Secured Energy Management System for Automated Guided Vehicles

An Efficient and Secured Energy Management System for Automa...

引用

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Syu, Jia-Hao Lin, Jerry Chun-Wei Mrozek, Dariusz National Taiwan University Department of Computer Science and Information Engineering Taiwan Western Norway University of Applied Sciences Department of Computer Science Electrical Engineering and Mathematical Sciences Norway Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Poland

ISBN: (纸本)9781665480451

In this paper, we propose a Secure Energy Management System (SEMS) with anomaly detection and Q-Learning decision modules for Automated Guided Vehicles (AGV). The anomaly detection module is a multi-task learning network to simultaneously classify suppliers and predict the real supply quantities. The Q-learning decision module can then determine operating reserve and subsidies to manage the energy grid. Experimental results illustrate that the proposed anomaly detection module has an excellent performance in classifying malicious suppliers, excels at shaping supply distribution, and outperforms the existing benchmark systems. © 2022 IEEE.

关键词： Energy management

来源：评论

学校读者我要写书评

暂无评论

COSMOS FRAMEWORK: SIMULATION AND OPTIMIZATION OF 3D SEARCH

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

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2023年第1期85卷 3-14页

作者： Samoilă, Cosmin-Gabriel Dinoiu, Damian Sluşanschi, Emil-Ioan SDIALA Doctoral School University "Politehnica" of Bucharest Romania Faculty of Computer Science and Automatic Control University "Politehnica" of Bucharest Romania

In modern numerical simulations, in order to be reliable, a computer code needs to be accurate and fast. The Framework for Combining Optimization and Simulation Software (COSMOS) is a tool which allows for the seamless integration of numerical simulations with appropriate optimizations algorithm. In this paper we present the integration of different numerical solutions in order to simulate a search in a continuous 3D space. The simulations are performed on different computational scenarios revealing significant improvements and useful insights into alternative optimisation solutions. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Numerical models

来源：评论

学校读者我要写书评

暂无评论

IT'S ALL IN THE EMBEDDING! FAKE NEWS DETECTION USING DOCUMENT EMBEDDINGS

arXiv

引用

arXiv 2023年

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

With the current shift in the mass media landscape from journalistic rigor to social media, personalized social media is becoming the new norm. Although the digitalization progress of the media brings many advantages, it also increases the risk of spreading disinformation, misinformation, and malformation through the use of fake news. The emergence of this harmful phenomenon has managed to polarize society and manipulate public opinion on particular topics, e.g., elections, vaccinations, etc. Such information propagated on social media can distort public perceptions and generate social unrest while lacking the rigor of traditional journalism. Natural Language Processing and Machine Learning techniques are essential for developing efficient tools that can detect fake news. Models that use the context of textual data are essential for resolving the fake news detection problem, as they manage to encode linguistic features within the vector representation of words. In this paper, we propose a new approach that uses document embeddings to build multiple models that accurately label news articles as reliable or fake. We also present a benchmark on different architectures that detect fake news using binary or multi-labeled classification. We evaluated the models on five large news corpora using accuracy, precision, and recall. We obtained better results than more complex state-of-the-art Deep Neural Network models. We observe that the most important factor for obtaining high accuracy is the document encoding, not the classification model's complexity. © 2023, CC BY-NC-ND.

关键词： Embeddings

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

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

引用

International Symposium on Parallel and Distributed Computing

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

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Notifier for Blockchain Events

Real-Time Notifier for Blockchain Events

引用

Roedunet International Conference (RoEduNet)

作者： Cristian Tănase-Paris Costin Carabaș Nicolae Țăpuș Computer Science and Engineering Department Faculty of Automatic Control and Computers University Politehnica of Bucharest Bucharest Romania

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.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Acquisition and Monitoring of Environmental Parameters from High-altitude UAV Flight

Acquisition and Monitoring of Environmental Parameters from ...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Marius Dima Dan Popescu Loretta Ichim Petrișor Valentin Pârvu Faculty of Automatic Control and Computer Science National University of Science and Technology Politehnica Bucharest Bucharest Romania Faculty of Aerospace Engineering National University of Science and Technology Politehnica Bucharest Bucharest Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

Unmanned aerial vehicles can improve short- term weather forecasting by acquiring information from weather sensors and other sensors. With this information, there is the possibility of making relevant maps like solar radiation, pollen, emissions, particles, and others. Another advantage of this acquisition system is the high rate of flights, compared to the classic measurements made with the weather balloon, which is launched twice a day. In addition to the advantages listed above, we discuss the multiplication factor of the acquired data, these systems being able to operate in various geographical locations.

关键词： Weather forecasting Data integration Autonomous aerial vehicles Prediction algorithms Particle measurements control systems Sensors Solar radiation Monitoring Payloads

来源：评论

学校读者我要写书评

暂无评论

A Framework for Analyzing GPU-Executed Malware 23

A Framework for Analyzing GPU-Executed Malware

引用

23rd International Conference on control Systems and computer science Technologies, CSCS 2021

作者： Apostol, Teodor-Petrut Velea, Radu Deaconescu, Razvan University Politehnica of Bucharest Faculty of Automatic Control and Computers Computer Science and Engineering Department Romania

ISBN: (纸本)9781665439398

Graphics processing units (GPU) are an integral part of today's computing environment. The marketing emphasis on user experience pushes vendors to constantly look for better graphics hardware and newer drivers to integrate into their products. Most commodity GPUs function as accelerators for image and video processing tasks and are present (either as dedicated or integrated form factor) in everyday devices including desktops, laptops, smartphones or other portable gadgets. Recent trends have seen the GPU move to perform additional tasks such as offloading some of the computation from the CPU or solve highly parallel problems. As GPUs become more powerful and widespread they will naturally become a very attractive target for attackers. Cybercriminals will look for any vulnerability in the GPU hardware or software, and will try to use it as an attack vector to compromise the system. This paper presents some of the incidents that involve the use of GPUs to perform malicious actions and proposes a framework to allow analysts to inspect the code executed on the GPU and trigger security alerts. The proposed solution will look at the processes running inside an operating system, it will identify which of them require access to the GPU and will try to intercept and scan for any suspicious activities, similar to a conventional security solution. © 2021 IEEE.

关键词： Graphics processing unit

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：