检索结果-内蒙古大学图书馆

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2024年第3期86卷 3-14页

作者： Weisz, Sergiu Țeugea, Ioan-Teodor Mihăilescu, Maria-Elena Mihai, Darius Carabaș, Mihai Țăpuș, Nicolae Faculty of Automatic Control and Computer Science National University of Science and Technology POLITEHNICA Bucharest Romania

Monitoring solutions have been a mainstay of cloud infrastructures for the past two decades. Because of this our conceptions about infrastructure need to be re-evaluated. The monitoring paradigm has shifted, and new solutions have appeared to supplant existing software. This paper will analyze the existing cluster monitoring software available, present their advantages and drawbacks. Based on the analysis we will present an applied use case of cluster monitoring based on the tools presented. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EVALUATION OF IBM WATSON SERVICES FOR IDS IMPLEMENTATION

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

引用

UPB Scientific Bulletin, Series C: Electrical Engineering and computer science 2024年第4期86卷 183-198页

作者： Vasilică, Bogdan-Valentin Anton, Florin-Daniel Ioniță, Anca Daniela Faculty of Automatic Control and Computer Science National University of Science and Technology POLITEHNICA Bucharest Romania

In this paper, the free services offered by IBM Watson are evaluated for the purpose of implementing an Intrusion Detection System in the context of offline network traffic analysis. It examines IBM Watson's role in IDS, detailing system architecture, network traffic capture, data processing, and algorithm selection with IBM Watson Studio, using the CIC-IDS2017 dataset. The study assesses AI algorithms like LGBM, XGB, Random Forest, and Extra Trees Classifier for detecting intrusions, concluding with an analysis of these algorithms' performance through precision, recall, and F measure metrics, evaluating the effectiveness of IBM Watson in a cloud-based IDS implementation. © 2024, Politechnica University of Bucharest. All rights reserved.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

An Occupant-Centric Comfort control Strategy Using Wearable Smart Devices in Smart-Buildings 12

An Occupant-Centric Comfort Control Strategy Using Wearable ...

引用

12th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, IDAACS 2023

作者： Boicu, Mihaela-Gabriela Fagarasan, Ioana Stamatescu, Grigore Vasluianu, Mihaela Fudulu, Cosmin-Florin Dobrea, Marius-Alexandru University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Romania Technical University of Civil Engineering of Bucharest Faculty of Hidrotechnics Romania

ISBN: (纸本)9798350358056

The paper presents a method of assessing thermal comfort in office rooms, using data collected from Fitbit bracelets. The result is a fuzzy system for the level of thermal comfort that wants to meet two objectives: reducing the energy consumption in the building and fulfilling the thermal comfort for the occupants. The representative factors taken into account in this study are: air temperature, relative humidity, user activity, clothing level and skin temperature. The proposed fuzzy system was modeled and simulated in the Matlab/SIMULINK development environment, showing satisfactory results after the analysis of the data taken over a period of several days. © 2023 IEEE.

关键词： comfort control strategy fuzzy control HVAC system smart-building Van Zuilen model

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

Energy Efficient Hardware Acceleration of Neural Networks wi...

引用

International Conference on computer Vision and Graphics, ICCVG 2022

作者： Przewlocka-Rus, Dominika Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e.g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e.g., quantisation, pruning, or dedicated lightweight architectures. Due to the logarithmic distribution of weights in neural network layers, a method providing high performance with significant reduction in computational precision (for 4-bit weights and less) is the Power-of-Two (PoT) quantisation (and therefore also with a logarithmic distribution). This method introduces additional possibilities of replacing the typical for neural networks Multiply and ACcumulate (MAC—performing, e.g., convolution operations) units, with more energy-efficient Bitshift and ACcumulate (BAC). In this paper, we show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 SoC FPGA can be at least 1.4x more energy efficient than the uniform quantisation version. To further reduce the actual power requirement by omitting part of the computation for zero weights, we also propose a new pruning method adapted to logarithmic quantisation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Energy-independent solution using a medium-power wind turbine to ensure the irrigation deficit in an isolated agricultural areal 24

Energy-independent solution using a medium-power wind turbin...

引用

24th International Conference on control Systems and computer science, CSCS 2023

作者： Fudulu, Cosmin-Florin Fagarasan, Ioana Boicu, Mihaela Gabriela Vasluianu, Mihaela Dobrea, Marius - Alexandru Neculoiu, Giorgian University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Romania Technical University of Civil Engineering of Bucharest Faculty of Hidrotechnics Romania

ISBN: (纸本)9798350313390

Smart agricultural systems require irrigation systems powered by renewable energy sources that are also adaptable for isolated areas without connection possibility to the electricity network or the water network. For such situations, in this paper, a solution is proposed using a wind turbine and a submersible pump to feed a water basin, subsequently irrigation is done by free fall. The developed solution is designed and simulated using a model of a medium-power wind turbine, and a battery storage element with the aim of providing the necessary electricity for irrigation of an agricultural area in Buzau, where there is a water deficit. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

On the Application of Robust Mean Shift Procedure for the Enhancement of Noisy Color Images 10

On the Application of Robust Mean Shift Procedure for the En...

引用

10th IEEE Jubilee International Conference on Computational Cybernetics and Cyber-Medical Systems, ICCC 2022

作者： Kusnik, Damian Smolka, Bogdan Silesian University of Technology Faculty of Automatic Control Electronics and Computer Science Gliwice Poland

ISBN: (数字)9781665481779

ISBN: (纸本)9781665481779

Image corruption due to noise disturbances severely decreases color image quality and therefore image enhancement is a vital step of the processing pipeline. Our approach modifies the standard Mean-Shift technique, so that the algorithm is able to work directly on noisy color images and offers very satisfying denoising results. The proposed Robust Mean-Shift is resistant to the mixed Gaussian and impulsive noise and can be used in various practical imaging tasks. The described technique has been validated on a database containing a variety of color images contaminated with various noise intensity levels and the obtained results show that it significantly excels the classical Mean-Shift algorithm. Image noise is to large extent suppressed, edges are sharpened and details are retained which enables the improvement of the image segmentation process. © 2022 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Evaluating the usage of Text to3D scene generation methods in Game-Based Learning 24

Evaluating the usage of Text to3D scene generation methods i...

引用

24th International Conference on control Systems and computer science, CSCS 2023

作者： Gradinaru, Alexandru Vrejoiu, Mihnea Moldoveanu, Florica Balutoiu, Maria-Anca University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania National Institute for Research and Development in Informatics Bucharest Romania

ISBN: (纸本)9798350313390

computer games as an educational tool significantly improved information retention, student involvement, and motivation. Despite the growing popularity and the demonstrated positive impact, little progress is made to let educators create games without learning game programming or investing massive amounts of time, money, and human resources. This paper considers the usage of procedural content generation in simplifying the generation of game environments. Given that most educational material is in text format, we evaluate the possibility of generating 3D scenes starting from natural language text. A comprehensive survey of the current methods is presented, analyzing whether they can be successfully used in game-based learning. The study discusses several current limitations and possible improvements, highlighting a need for better progress in the domain. © 2023 IEEE.

关键词： computer games

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Classification Using Deep and Quantum Neural Networks

Traffic Sign Classification Using Deep and Quantum Neural Ne...

引用

International Conference on computer Vision and Graphics, ICCVG 2022

作者： Kuros, Sylwia Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Quantum Neural Networks (QNNs) are an emerging technology that can be used in many applications including computer vision. In this paper, we presented a traffic sign classification system implemented using a hybrid quantum-classical convolutional neural network. Experiments on the German Traffic Sign Recognition Benchmark dataset indicate that currently QNN do not outperform classical DCNN (Deep Convolutuional Neural Networks), yet still provide an accuracy of over 90% and are a definitely promising solution for advanced computer vision. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

Decision System for Ensuring Thermal Comfort of Occupants in a Smart Building 24

Decision System for Ensuring Thermal Comfort of Occupants in...

引用

24th International Conference on control Systems and computer science, CSCS 2023

作者： Boicu, Mihaela-Gabriela Stamatescu, Grigore Fudulu, Cosmin-Florin Dobrea, Marius-Alexandru Vasluianu, Mihaela Neculoiu, Giorgian University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Romania Technical University of Civil Engineering of Bucharest Faculty of Hidrotechnics Romania

ISBN: (纸本)9798350313390

This paper presents the development of a system that uses fuzzy logic in order to evaluate the thermal comfort conditions expressed by means of a score by the occupants of an office room The inputs of the system are represented by three datasets relevant to the study: the air temperature, the positioning of the occupant and the level of activity carried out by the occupant. Based on the comfort score obtained, the HVAC system located at the room level will maintain a comfortable environment. The proposed solution also contributes to the minimization of energy consumption in buildings. In order to collect the data sets necessary for the study, we used the *** module as a wearable device. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

The Paradox of Motion: Evidence for Spurious Correlations in Skeleton-based Gait Recognition Models

arXiv

引用

arXiv 2024年

作者： Catruna, Andy Cosma, Adrian Radoi, Emilian Faculty of Automatic Control and Computer Science POLITEHNICA Bucharest Romania

Gait, an unobtrusive biometric, is valued for its capability to identify individuals at a distance, across external outfits and environmental conditions. This study challenges the prevailing assumption that vision-based gait recognition, in particular skeleton-based gait recognition, relies primarily on motion patterns, revealing a significant role of the implicit anthropometric information encoded in the walking sequence. We show through a comparative analysis that removing height information leads to notable performance degradation across three models and two benchmarks (CASIA-B and GREW). Furthermore, we propose a spatial transformer model processing individual poses, disregarding any temporal information, which achieves unreasonably good accuracy, emphasizing the bias towards appearance information and indicating spurious correlations in existing benchmarks. These findings underscore the need for a nuanced understanding of the interplay between motion and appearance in vision-based gait recognition, prompting a reevaluation of the methodological assumptions in this field. Our experiments indicate that"in-the-wild" datasets are less prone to spurious correlations, prompting the need for more diverse and large scale datasets for advancing the field. © 2024, CC BY-NC-ND.

关键词： Large datasets

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：