检索结果-内蒙古大学图书馆

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

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

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

Cyber-Physical systems - A New Approach for Keyless Entry systems 23

Cyber-Physical Systems - A New Approach for Keyless Entry Sy...

引用

23rd International Conference on control systems and Computer Science Technologies, CSCS 2021

作者： Balaban, Beatrix-May Sacala, Ioan Stefan Petrescu-Nita, Alina Claudia Pop, Florin University Politehnica of Bucharest Department of System Engineering Faculty of Automatic Control and Computers Bucharest Romania

ISBN: (纸本)9781665439398

Nowadays, intelligent vehicles are becoming more and more important in the transportation field. What makes such a vehicle vulnerable is the number of interconnected components that individually have a strong security but can cause weakness points when they are connected. The challenge is to design and build a powerful system that uses both cyber-physical components. The proposed model is a system with integrated modules for fingerprint and face recognition to certify that a driver has the right to access the vehicle. The aim is to develop a security system for intelligent vehicles that can be also a secure keyless entry system using the power of biometrics. When a driver approaches the car, a sensor will activate the recognition modules. Only after the total completion of the recognition process the driver is authenticated and has the right to use the vehicle. We simulated real-time face detection and eye tracking using Matlab 2020a. Face detection is performed using Viola-Jones algorithms and the tracking is made with bbox-es. Besides normal conditions, other tests were made to challenge the algorithm, for example: angle rotations, the use of glasses, face mask, glasses and face mask together. © 2021 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Trajectory Planning with B-Splines and the Schoenberg Quasi-Interpolant 63

Energy-Efficient Trajectory Planning with B-Splines and the ...

引用

63rd IEEE Conference on Decision and control, CDC 2024

作者： Marguet, Vincent Stoican, Florin Prodan, Ionela Univ. Grenoble Alpes Grenoble Inp Institute of Engineering and Management Univ. Grenoble Alpes. Lcis ValenceF-26000 France Politehnica University of Bucharest Acse Faculty of Automatic Control and Computers Bucharest Romania Institute for Logic and Data Science Bucharest Romania

ISBN: (纸本)9798350316339

Few studies address the challenge of minimizing energy consumption during trajectory generation, particularly in the context of multicopter dynamics, characterized by strong non-linearity. This paper introduces a novel approach by formulating energy consumption as a function of B-splines control points, enabling comprehensive optimization of total energy expenditure throughout the trajectory. To mitigate the complexity of representation, we leverage the Schoenberg quasi-interpolant, which not only facilitates the solution of the optimization problem but also effectively reduces computational overhead. The approach is validated through two distinct scenarios: a conventional trajectory used in precision agriculture, and a scenario involving more aggressive maneuvers. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Influence of power supply on airport navigation lamps photometric test accuracy

Influence of power supply on airport navigation lamps photom...

引用

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Kacper Podbucki Jakub Suder Tomasz Marciniak Adam Dąrowski Faculty of Automatic Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Division of Electronic Systems and Signal Processing Poznan University of Technology Poznań Poland

The paper presents research on the accuracy of measuring illuminance and chromaticity of airport lamps. The impact of the type of DC and AC power supply on measurement was assessed with the use of electronic sensors. BH1750 and BH1745 type sensors in a microprocessor system with an I 2 C interface were used for the measurements. A professional luxmeter was used for comparison purposes. Experimental tests were carried out under laboratory conditions for three types of halogen lamps: approach system lamps, runway centerline lamps, and touchdown zone lamps.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Prototyping of In-Pavement Airport Navigation Lamp Prism Classification

Fast Prototyping of In-Pavement Airport Navigation Lamp Pris...

引用

Signal Processing Algorithms, Architectures, Arrangements and Applications (SPA)

作者： Jakub Suder Tomasz Marciniak Division of Electronic Systems and Signal Processing Poznan University of Technology Faculty of Automatic Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Poznań Poland

The paper presents an analysis of fast selection of neural network for the purpose of visual analysis of mechanical wear on prism lenses of in-pavement airport navigational lighting systems. This issue is particularly important in terms of aviation safety and navigational lighting control, regulated by EASA and ICAO. The article is the next stage of the development of the system for the vision control of lamps, in which the concept of using a different neural network with an increased data set prepared by the authors is presented. The Deep Network Designer tool included in the Matlab 2022b environment was used. The solution using the GoogLeNet neural network allows for the classification of lamps with an accuracy of 88.37%.

关键词：

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

arXiv

引用

arXiv 2023年

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, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A new metric for evaluating the performance and complexity of computer programs: A new approach to the traditional ways of measuring the complexity of algorithms and estimating running times 23

A new metric for evaluating the performance and complexity o...

引用

23rd International Conference on control systems and Computer Science Technologies, CSCS 2021

作者： Folea, Rares Slusanschi, Emil-Ioan University Politehnica of Bucharest Faculty of Automatic Control and Computers Computer Science and Engineering Department Bucharest Romania

ISBN: (纸本)9781665439398

This paper presents a refined complexity calculus model: r-Complexity, a new asymptotic notation that offers better complexity feedback for similar programs than the traditional Bachmann-Landau notation, providing subtle insights even for algorithms that are part of the same conventional complexity class. The architecture-dependent metric represents an enhancement that provides better sensitivity with respect to discrete analysis. © 2021 IEEE.

关键词： Calculations

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Bracelet to Monitor Vital signs of COVID-19 Patients 5

Design and Development of a Bracelet to Monitor Vital signs ...

引用

5th International Conference on engineering Technology and its Applications, IICETA 2022

作者： Naji, Hasan K. Goga, Nicolae Karkar, Ammar J. M. Ali, Haider Abdullah Falahi, Mandana Al-Rawi, Abdullah Taher Huri University POLITEHNICA of Bucharest Doctoral School of Automatic Control and Computers Bucharest Romania University POLITEHNICA of Bucharest Faculty of Engineering in Foreign Languages Bucharest Romania University of Groningen Molecular Dynamics Group Groningen Netherlands University of Kufa IT Research and Development Centre Najaf Iraq University POLITEHNICA of Bucharest Faculty of Automatic Control and Computers Bucharest Romania Al-Karkh General Hospital Baghdad Iraq

ISBN: (纸本)9781665472159

COVID-19, which stands for Coronavirus disease 2019, is an infection caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), first reported in December 2019 in Wuhan, China. The new coronavirus has spread rapidly around the world, causing extensive deaths, and turning into a new global public health crisis. This paper proposes a prototype system to assist medical staff in identifying and monitoring COVID-19 symptoms by measuring vital signs. This study aims to help prevent hospitalization of patients in the ICU by continuously monitoring the patient's vital signs, which allows medical staff to diagnose the patient's health at the appropriate time. The use of sensors has grown in many areas over the past decade, especially in wearable healthcare devices. In this paper, the hardware components, and the design structure of the bracelet have been presented. The bracelet is responsible for measuring and transferring vital signs like body temperature, oxygen saturation, and heart rate to the Base control Unit. The Max 30100 and DS18B20 sensors are used to read the vital signs of the patient and transmit them to the microcontroller inside the bracelet. The microcontroller will send vital signs data to the Raspberry Pi to analyse, process, save, and display. The design and implementation of this bracelet have been done by developing a 3D printed model after examining several models on people of different ages. © 2022 IEEE.

关键词： COVID-19

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：