检索结果-内蒙古大学图书馆

5th International Conference on Image Processing and Capsule Networks, ICIPCN 2024

作者： Panchal, Rupal K Snehkunj, Rupal Panchal, Vinaykumar V Sarvajanik University Surat395001 India Shree Ramkrishna institute of computer education & applied sciences college Sarvajanik University Gujarat Surat India Amazon India Development Center Telangana Hyderabad500032 India

ISBN: (纸本)9798350367171

Nowadays cyber world faces a significant security challenges such as network intrusion attacks, while sharing data through the network. To ensure the security and confidentiality of the data shared through the network, several techniques were developed. The major significant issues obtained in network intrusion are high false alarm rates with low detection rates and speed. Various learning techniques are introduced to evaluate the network intrusion detection. This review study analyzes different attack types, defense mechanisms, and recent scientific investigations conducted in this field in addition to discussing about the intrusion detection systems, and methodology with the exploration of its challenges along with the future scope. Furthermore, the review provides information about the accessible datasets, well-known IDS tools, and detailed explanations of the benefits and drawbacks of specific IDSs. This study evaluates 25 existing research articles with the analysis of diverse techniques and approaches that are examined under various datasets. In addition to this, the evaluation of distinct performance metrics is briefly discussed. The limitations and future scope of each method will be assessed and the major significance of intrusion detection methods present the road map for future researchers focusing on network attack detection. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Prediction of Geopolymer Concrete Compressive Strength Using Convolutional Neural Networks

引用

computer Modeling in Engineering & sciences 2024年第5期139卷 1455-1486页

作者： Kolli Ramujee Pooja Sadula Golla Madhu Sandeep Kautish Abdulaziz S.Almazyad Guojiang Xiong Ali Wagdy Mohamed Department of Civil Engineering VNR Vignana Jyothi Institute of Engineering and TechnologyHyderabadTelangana500090India Department of Information Technology VNR Vignana Jyothi Institute of Engineering and TechnologyHyderabadTelangana500090India Department of Computer Science LBEF Campus(Asia Pacific University of Technology&InnovationMalaysia)Kathmandu44600Nepal Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia Guizhou Key Laboratory of Intelligent Technology in Power System College of Electrical EngineeringGuizhou UniversityGuiyang550025China Operations Research Department Faculty of Graduate Studies for Statistical ResearchCairo UniversityGiza12613Egypt Applied Science Research Center Applied Science Private UniversityAmmanJordan

Geopolymer concrete emerges as a promising avenue for sustainable development and offers an effective solution to environmental *** attributes as a non-toxic,low-carbon,and economical substitute for conventional cement concrete,coupled with its elevated compressive strength and reduced shrinkage properties,position it as a pivotal material for diverse applications spanning from architectural structures to transportation *** this context,this study sets out the task of using machine learning(ML)algorithms to increase the accuracy and interpretability of predicting the compressive strength of geopolymer concrete in the civil engineering *** achieve this goal,a new approach using convolutional neural networks(CNNs)has been *** study focuses on creating a comprehensive dataset consisting of compositional and strength parameters of 162 geopolymer concrete mixes,all containing Class F fly *** selection of optimal input parameters is guided by two distinct *** first criterion leverages insights garnered from previous research on the influence of individual features on compressive *** second criterion scrutinizes the impact of these features within the model’s predictive *** to enhancing the CNN model’s performance is the meticulous determination of the optimal *** a systematic trial-and-error process,the study ascertains the ideal number of epochs for data division and the optimal value of k for k-fold cross-validation—a technique vital to the model’s *** model’s predictive prowess is rigorously assessed via a suite of performance metrics and comprehensive score ***,the model’s adaptability is gauged by integrating a secondary dataset into its predictive framework,facilitating a comparative evaluation against conventional prediction *** unravel the intricacies of the CNN model’s learning trajectory,a loss plot is deployed to elucidate its learning rat

关键词： Class F fly ash compressive strength geopolymer concrete prediction deep learning convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Bridging the Communication Gap—A Pilot Course on Interdisciplinary Requirements Engineering

Bridging the Communication Gap—A Pilot Course on Interdisci...

引用

Joint of REFSQ 2025 Workshops, Doctoral Symposium, Posters and Tools Track, and Education and Training Track, REFSQ 2025

作者： Gieshoff, Anne Catherine Ruiz, Marcela Schuler, Martin Wahler, Michael Zurich University of Applied Sciences School of Applied Linguistics Institute of Translation and Interpreting Winterthur Switzerland Zurich University of Applied Sciences School of Engineering Institute of Computer Science Winterthur Switzerland

Teaching the practical aspects of requirements engineering is challenging due to the lack of effective tools, methods, and practices for teaching requirements elicitation, especially for novices. The research community has proposed various solutions to measure the effectiveness of elicitation techniques, such as interviews. However, there is limited research on teaching experiences that address both technical and communication skills. To address this, we implemented an innovative interdisciplinary pilot course for final-year computer science and applied linguistics students at our university. Linguistics students conceptualized a language learning application, acting as the stakeholders, while computer science students elicited requirements through interviews. This collaboration provided realistic stakeholder interaction and insight into the software development process for linguistics students. This paper details the setup of the interdisciplinary pilot course, presents the course evaluation results, and shares the lessons learned from this unique educational endeavor. © 2025 Copyright for this paper by its authors.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Generation of synthetic data with low-dimensional features for condition monitoring utilizing Generative Adversarial Networks 26

Generation of synthetic data with low-dimensional features f...

引用

26th International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2022

作者： Wagner, Fabian König, Timo Benninger, Moritz Kley, Markus Liebschner, Marcus Faculty for Electronics and Computer Science University of Applied Sciences Aalen Aalen73430 Germany Institute for Drive Technology University of Applied Sciences Aalen Aalen73430 Germany

Condition monitoring of machine elements for end-of-line quality control is an essential part of product assurance in many production areas. Therefore, the monitored machine elements are often separated in different condition classes and are classified via conventional signal processing and machine learning methods. Especially for machine learning algorithms, collection of a sufficient amount of data from each class is particularly relevant so that balanced training datasets, regarding the condition classes, are available. In reality, however, in most cases significantly more data is captured from good system states. This results in unbalanced data sets, which can be counteracted with synthetically generated data. Generative Adversarial Networks (GAN) are a suitable approach to generate synthetic measurement data. In the scope of this paper, a use case is considered, in which bearings are monitored in an end-of-line control via acoustic signals. The generation of such data requires a high computational effort. To reduce this effort, a suitable signal pre-processing method is presented, which allows the reduction of the generated feature dimension. The synthetic data based on low-dimensional features is subsequently evaluated regarding its suitability for the condition classification. It is shown that with synthetically generated data with low-dimensional features a similar classification accuracy can be achieved as with real data, making the synthetic data suitable for data augmentation in the use case. © 2022 The Authors. Published by Elsevier B.V.

关键词： Condition monitoring

来源：评论

学校读者我要写书评

暂无评论

Technology for robust, low-latency frequency and phasor estimation and evaluation with a real HV short-circuit event

Technology for robust, low-latency frequency and phasor esti...

引用

CIRED 2024 Vienna Workshop

作者： Gerd Bumiller Institute of Computer Science Hochschule Ruhr West University of Applied Sciences Bottrop Germany

ISBN: (数字)9781837241224

With the increasing share of decentralized generation, the handling of faults requires additional attention, which is why fault-ride-through simulations are required in several countries for grid connection above a certain power. The scenarios are severe voltage dips caused by short circuits in the high-voltage grid and elimination after 60-150 ms. The aim is to prevent such an event from leading to a cascading failure of a significant proportion of decentralized generation and a subsequent imbalance between generation and consumption. Such scenarios also pose a challenge for the measurement of grid frequency, RoCoF and phasors. The assumption of a stationary behavior of the signals during the averaging interval of the measurement period is no longer valid and the results are clearly incorrect. On the one hand, such an event offers many opportunities to estimate the grid status, but no analysis is possible without reliable measurement data. On the other hand, these scenarios also often cause phase jumps in the positive sequence phasor, which leads to enormous RoCoFs and large frequency deviations in measurements based on phase-locked loops (PLL). If the behavior of an inverter, which mostly use PLLs, depends on the measured frequency, as is common in photovoltaic (PV) inverters and battery systems, a measurement error can cause a highly synchronous disturbance in a large number of inverters. In this article, we present the concept of a normalized time base with a fixed ratio to the angle of the fundamental. In this time base, the signals are periodic again and the harmonics are orthogonal again, even if the frequency of the fundamental varies. In a discrete-time implementation with interpolated sampling, this concept is applied to an in-quadrature PLL with adaptive filtering on the positive sequence phasor, but the filter can be optimally and robustly designed and rigidly implemented in the normalized time base. In an FPGA-based implementation, the phasors and the f

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison Between Quality Index and Total Vector Error Metric for Power Quality Measurements

Comparison Between Quality Index and Total Vector Error Metr...

引用

IEEE International Workshop on applied Measurements for Power Systems (AMPS)

作者： Lukas Duhme Gerd Bumiller Institute of Computer Science Hochschule Ruhr West University of Applied Sciences Bottrop Germany

ISBN: (数字)9798350375312

ISBN: (纸本)9798350375329

The power grid is transforming due to an increasing share of participants connected to the grid via power electronics. This results in a degradation of the power quality (PQ) and dynamic stability leading to a rising necessity of power quality measurement. The power flow analysis is performed by phase measurements on the fundamental frequency, while harmonic phase measurements would also allow this for harmonic components. Due to the permanent decrease in power quality, this must be permanently analyzed. The quality can be defined via the Total Vector Error (TVE). One problem with the TVE is that it can only be calculated if a reference signal is available, which is not the case for field measurements. Therefore, a quality index (QI) was presented in earlier publications, which can be calculated without a reference signal. The application of the QI has proven to be difficult in previous measurements, as it behaves differently when applied to signals depending on a number of disturbance variables. It is therefore difficult to determine a specific threshold, as different thresholds are acceptable for each environment. To solve this problem, we introduce new metrics to evaluate what type of error will cause the QI to drop and a metric to estimate the TVE based on the QI and the type of disturbance identified. This has the advantage that with the TVE there are well-defined thresholds for certain applications, which can then be applied by measuring the QI and estimating the TVE on the fly.

关键词： Power measurement Phase measurement Power quality Measurement uncertainty Power system harmonics Harmonic analysis Vectors Frequency measurement Indexes Standards

来源：评论

学校读者我要写书评

暂无评论

Adaptive Filtering Based on Normalized Time Scale for the Measurement of Phasors in Short Intervals

Adaptive Filtering Based on Normalized Time Scale for the Me...

引用

IEEE International Workshop on applied Measurements for Power Systems (AMPS)

作者： Gerd Bumiller Lukas Duhme Institute of Computer Science Hochschule Ruhr West University of Applied Sciences Bottrop Germany

ISBN: (数字)9798350375312

ISBN: (纸本)9798350375329

Short-circuit events occur more or less regularly on high-voltage lines, some events are caused by lightning, others are caused by equipment faults. If the short-circuit does not disappear by itself, the short-circuit event is eliminated within 60–150 ms and a reconnection of the lines is automatically attempted after a few seconds. Such events, which are triggered on high-voltage lines, can cause considerable voltage dips and phase jumps of the positive sequence phasor at all voltage levels. An example of a real event is presented that far exceeds the tested values of PMUs. Magnitude and phase jumps disturb the control loops in inverters and phasor measurement units, but also offer the possibility of grid characterization through distributed measurements, if it's possible to identify a steady state within this very short interval. In this article, we present the normalized time base with a fixed ratio to the angle of the fundamental. In this time base, the signals are again strictly periodic with a constant period duration, even if the frequency of the fundamental varies. This enables the definition of short filters with notches on all harmonics. In a discrete-time implementation with interpolated sampling, this concept is applied to an in-quadrature PLL with adaptive filtering on the positive sequence phasor, but the filter can be optimally and robustly designed and rigidly implemented in the normalized time base. In an implementation, the phasors and the frequency are calculated 16 times per line cycle and are therefore available approx. 800 times per second. The measurement interval of two line cycle duration is very short and is suitable for the identification of a steady state during these short circuit events.

关键词： Time-frequency analysis Semiconductor device measurement Power measurement High-voltage techniques Time measurement Phasor measurement units Inverters Frequency measurement Steady-state Phase locked loops

来源：评论

学校读者我要写书评

暂无评论

Constructing the ChatGPT for PDF Files with Langchain - AI 7

Constructing the ChatGPT for PDF Files with Langchain - AI

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Prem Jacob, T. Bizotto, Beatriz Lucia Salvador Sathiyanarayanan, Mithileysh Sathyabama Institute of Science And Technology Department of Computer Science And Engineering Chennai India University Center Unifacvest Department of Social And Applied Sciences Lages Brazil Research & Innovation MIT Square London United Kingdom

ISBN: (纸本)9798350359299

Queries in PDFs can be time-consuming and labor-intensive because of the unstructured nature of the PDF document type and the need for accurate and relevant search results. By applying cutting-edge algorithms for natural language processing to examine PDF documents and extract relevant data, LangChain solves these difficulties. It makes use of an easy search interface, adjustable filters, and efficient indexing and retrieval mechanisms to enhance the search experience. To efficiently retrieve relevant information from PDF documents, users can annotate critical portions, store queries, and create bookmarks with LangChain. The characteristics of LangChain improve overall productivity and greatly simplify PDF querying. Semantic search, driven by the latest Transformer language models, represents a significant evolution in information retrieval systems. This research work explores the capabilities of semantic search to efficiently retrieve documents from large collections in response to natural language queries. Unlike traditional keyword-based approaches, semantic search connects the power of Transformer models to discern meaning, providing users with more contextually relevant and accurate results within seconds. This technology not only enhances the user experience by delivering superior matches from document collections but also lays the foundation for tackling more intricate tasks, like text summarization and question-answering. The research investigates the impact of semantic search on information retrieval efficiency and accuracy, comparing its performance with conventional methods. The findings presented herein not only showcase the immediate benefits of semantic search but also open paths for future research and development in natural language processing and its applications. © 2024 IEEE.

关键词： Information retrieval systems

来源：评论

学校读者我要写书评

暂无评论

Windows to reduced leakage and interference without any influence on harmonic components of phasor and power flow measurements

Windows to reduced leakage and interference without any infl...

引用

CIRED 2024 Vienna Workshop

作者： Gerd Bumiller Institute of Computer Science Hochschule Ruhr West University of Applied Sciences Bottrop Germany

ISBN: (数字)9781837241224

The changes in the electricity grid pose new challenges for the measurement of power flows in the grid. The non-linear behavior on both the generation and load side can lead to the simultaneous observation of reversed power flows on different harmonics on one line. In order to gain a comprehensive understanding of the power flows, it is necessary to measure the harmonic components separately. This requires the measurement of voltage and current with usable phase information, such as in harmonic phase measurement. In conjunction with a fluctuating fundamental frequency, leakages occur in existing technologies, which devalue the phase information of the harmonics. In order to eliminate the symptoms of this problem, increasingly complex methods are used or the phase information is often omitted altogether. With the increasing use of power electronics, interharmonic disturbances are also increasing. At the same time, fast control loops lead to an increase in volatility, whereby the usual duration of steady-state behavior decreases, which makes it necessary to reduce the averaging times for measurements. This work focuses on the measurement of harmonic signal components as they are usually performed for synchrophasors, harmonic phases or power quality measurements in electrical power systems. A class of windows is defined which, in combination with a periodic superposition of the signals, has no influence on the measurement of harmonic components. The combination of special windows and superposition shown here is invisible for harmonic signal components, but can significantly reduce the measurement errors caused by incorrect estimation of the fundamental frequency and inter-harmonic signal components. The commonly used rectangular window is a member of this class and is used as a reference for the evaluation. However, Bartlett, Hann and sine ramp base windows can also be designed as members of this class. All windows have a length of 2 timing intervals and are executed w

关键词：

来源：评论

学校读者我要写书评

暂无评论

MUCE: a multilingual use case model extractor using GPT-3

引用

International Journal of Information Technology (Singapore) 2022年第3期14卷 1543-1554页

作者： Bajaj, Deepali Goel, Anita Gupta, S.C. Batra, Hunar Department of Computer Science Shaheed Rajguru College of Applied Sciences for Women University of Delhi Delhi India Department of Computer Science Dyal Singh College University of Delhi Delhi India Department of Computer Science Indian Institute of Technology Delhi India

During the software requirement specification, the use case-based approach is used for requirements elicitation and analysis, for object-oriented software development. For identifying the use cases, traditionally, manual approach is used. Though some researchers have used semi-automated NLP techniques but it requires each word in a sentence to be tagged with its part-of-speech. In this paper, we exploit Generative Pre-trained Transformer-3 (GPT-3) for identifying the use case model by parsing the given software requirements. GPT-3 is an autoregressive language model that uses deep learning to produce human-like text. It is a language prediction model that can be tuned with Few-Shot learning to extract functional requirements in a multilingual setting. We present MUCE, a Multilingual Use Case model Extractor tool for the extraction of use cases, actors and their relationships from the given users’ software requirements. Further, not all requirement documents are English-centric and might be written in some native language. In such scenario, an automated, multilingual tool for structuring the use case model will really be a boon. The benefit of such an automated tool is that it helps in extracting use cases model as requirements specification quickly;overcoming the worries involved in manual ways. This tool can also prove to be a feedback to improve and fine-tune functional requirements so as to make them more complete. We evaluated the performance of our tool using Confusion Matrix. We authenticate our findings by validating various user requirements case studies written in different languages particularly, English, Spanish and French. Our tool performs better than existing state-of-the-art use case model extraction techniques. Our research endeavor will assist software designers and architects to generate actors and use cases instantaneously from the given users’ software requirement documents, and save their time. © 2022, The Author(s), under exclusive licence to B

关键词： Autoregressive language model Generative Pre-trained Transformer-3 (GPT-3) Natural language processing Pre-trained deep learning model Self-attention Software requirement specification (SRS)

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：