检索结果-内蒙古大学图书馆

11th International Conference on Electrical engineering, computer Science and informatics, EECSI 2024

作者： Badieah Chaerul Haviana, Sam Farisa Mulyono, Sri Salim, Channa Abdullah Adli, Muhammad Fatih Febriansah, Moh Taufik Wiktasari Sulaiman, Noor Suhana Yaqob, Azliza Universitas Islam Sultan Agung Informatics Engineering Department Semarang Indonesia Politeknik Negeri Semarang Computer Engineering Technology Semarang Indonesia University College of TATI Faculty of Computer Media and Technology Management Terengganu Malaysia

ISBN: (纸本)9798350355314

Topic modeling has become essential in a variety of text mining applications, such as document clustering and recommendation systems. This study investigates the potential of BERTopic, a transformer-based method that leverages BERT embeddings to recommend publication venues. Traditional topic modeling methods are made better by BERTopic, which uses the deep contextual embeddings that BERT (Bidirectional Encoder Representations from Transformers) offers. This investigation assesses the efficacy of BERTopic in clustering academic papers according to their content in order to suggest appropriate publication venues. We also compare the performance between different kinds of pre-trained sentence embedding models and input types (title, abstract, and title+abstract). The experimental results indicate that BERTopic performs well with the GARUDA dataset, which comprises 5272 records from three different research subjects. The results emphasize the transformative influence of the transformer-based model. The best performance of all cases was 99.17% mean average precision in the Top 3 position, using Title+Abstract as input data and all-mpnet-base-v2 as the sentence embedding model. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Method To Improve The Accuracy Of PV Curtailment To Maintain The System Stability in North Sulawesi and Gorontalo Power Grid 4

Method To Improve The Accuracy Of PV Curtailment To Maintain...

引用

4th International Conference on High Voltage engineering and Power Systems, ICHVEPS 2023

作者： Pratama, Arif Majiid Nusa Hashfi, Muhammad Irfan Dermawan, Ido Fandy Banjar-Nahor, Kevin Marojahan Hariyanto, Nanang School of Electrical Engineering and Informatics Bandung Indonesia Faculty of Computer Science Jakarta Indonesia Tomohon Indonesia

ISBN: (纸本)9798350318678

The penetration of renewable energy with high intermittencies, such as solar power, presents a challenge for the North Sulawesi and Gorontalo power grid. Currently, the largest photovoltaic plant in the region is Likupang PV with a capacity of 15 MWp, followed by Isimu PV with a capacity of 10 MWp. The daytime peak load of the electrical system is 330 MW, with the initial penetration of photovoltaics into the system at 7.58%. Due to the low stiffness of the system, which was measured at 22.32 Mw/Hz in 2022, the intermittence has a direct impact on the system's operation. The study method used for PV curtailment first determines the magnitude by analyzing the correlation between changes in multiple PV and changes in demand affecting frequency. The Pearson correlation coefficient is used to determine the magnitude of the correlation among these variables. If Likupang PV has a significant influence on changes in frequency, then it can become a curtailment target to limit the amount of power change due to intermittence. Secondly, through data mining, we can understand the function of the influence of changes in PV power on frequency changes. From this function, we can determine the operating limits of the PV to achieve the desired frequency operating range. Thirdly, in this study, this function is tested through simulations and experiments in the field to verify the accuracy of the required PV curtailment execution. By applying this approach, business owners can optimize the planning, regulation, and reliability of the electricity system, thereby mitigating power interruptions in solar power plants. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

An Innovated Microservices Identification Approach Based on Database and Source Code Analysis 6

An Innovated Microservices Identification Approach Based on ...

引用

6th IEEE Novel Intelligent and Leading Emerging Sciences Conference, NILES 2024

作者： Ashraf, Abdulrahman Yousef, Ahmed Hassan Mahdi, Hani Ain Shams University Itworx Education Yas Holding Computer and Systems Engineering Department Egypt Egypt University of Informatics Ain Shams University Egypt Ain Shams University Computer and Systems Engineering Department Egypt

ISBN: (纸本)9798350378511

Migrating from Monolithic architecture to Microservices architecture is a major change in how applications are designed, developed, and managed. This paper introduces an innovative approach for Microservices identification. Advanced techniques, including the OpenAI ChatGPT API, BERT embeddings, and community detection algorithms, are used to analyze both the database and the source code to find the optimal service boundaries. Thorough evaluations on benchmark applications demonstrate that this proposed technique surpasses cutting-edge solutions in structural modularity and maintains favorable values for other software quality metrics. This aids in identifying scalable Microservices. This research not only supports the modernization of software infrastructure but also advocates for sustainable development practices within the ever-changing field of distributed systems. © 2024 IEEE.

关键词： Decentralized systems

来源：评论

学校读者我要写书评

暂无评论

Brief Announcement: On the Existence of δ-Temporal Cliques in Random Simple Temporal Graphs 3

Brief Announcement: On the Existence of δ-Temporal Cliques ...

引用

3rd Symposium on Algorithmic Foundations of Dynamic Networks, SAND 2024

作者： Mertzios, George B. Nikoletseas, Sotiris Raptopoulos, Christoforos Spirakis, Paul G. Department of Computer Science Durham University United Kingdom Computer Engineering and Informatics Department University of Patras Greece Department of Mathematics University of Patras Greece Department of Computer Science University of Liverpool United Kingdom

ISBN: (纸本)9783959773157

We consider random simple temporal graphs in which every edge of the complete graph Kn appears once within the time interval [0, 1] independently and uniformly at random. Our main result is a sharp threshold on the size of any maximum δ-clique (namely a clique with edges appearing at most δ apart within [0, 1]) in random instances of this model, for any constant δ. In particular, using the probabilistic method, we prove that the size of a maximum δ-clique is approximately 2 log_ n with high probability (whp). What seems surprising is that, even though the random simple log δ1 temporal graph contains Θ(n2) overlapping δ-windows, which (when viewed separately) correspond to different random instances of the Erdős-Rényi random graphs model, the size of the maximum δ-clique in the former model and the maximum clique size of the latter are approximately the same. Furthermore, we show that the minimum interval containing a δ-clique is δ − o(δ) whp. We use this result to show that any polynomial time algorithm for δ-Temporal Clique is unlikely to have very large probability of success. © George B. Mertzios, Sotiris Nikoletseas, Christoforos Raptopoulos, and Paul G. Spirakis.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Heterogeneous Federated Learning via Approximate DNN Accelerators

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2024年第6期44卷 2054-2066页

作者： Pfeiffer, Kilian Balaskas, Konstantinos Siozios, Kostas Henkel, Jorg Karlsruhe Institute of Technology Chair for Embedded Systems Karlsruhe76131 Germany University of Patras Department of Computer Engineering and Informatics Patras26504 Greece Aristotle University of Thessaloniki Department of Physics Thessaloniki54124 Greece

In Federated Learning (FL), devices that participate in the training usually have heterogeneous resources, i.e., energy availability. In current deployments of FL, devices that do not fulfill certain hardware requirements are often dropped from the collaborative training. However, dropping devices in FL can degrade training accuracy and introduce bias or unfairness. Several works have tackled this problem on an algorithm level, e.g., by letting constrained devices train a subset of the server neural network (NN) model. However, it has been observed that these techniques are not effective w.r.t. accuracy. Importantly, they make simplistic assumptions about devices' resources via indirect metrics such as multiply accumulate (MAC) operations or peak memory requirements. We observe that memory access costs (that are currently not considered in simplistic metrics) have a significant impact on the energy consumption. In this work, for the first time, we consider on-device accelerator design for FL with heterogeneous devices. We utilize compressed arithmetic formats and approximate computing, targeting to satisfy limited energy budgets. Using a hardware-aware energy model, we observe that, contrary to the state of the art's moderate energy reduction, our technique allows for lowering the energy requirements (by 4×) while maintaining higher accuracy. © 1982-2012 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sign Language Recognition Using Deep Convolutional Neural Networks 14

Enhancing Sign Language Recognition Using Deep Convolutional...

引用

14th International Conference on Information, Intelligence, Systems and Applications, IISA 2023

作者： Kanavos, Athanasios Papadimitriou, Orestis Mylonas, Phivos Maragoudakis, Manolis University of the Aegean Department of Information and Communication Systems Engineering Samos Greece University of West Attica Department of Informatics and Computer Engineering Athens Greece Ionian University Department of Informatics Corfu Greece

ISBN: (纸本)9798350318067

The advancements in sensing technologies and AI algorithms have opened up a wide range of possibilities for developing applications to meet the needs of individuals who are deaf or hard of hearing. Sign language plays a vital role in the lives of people with hearing and speaking disabilities. This research aims to explore digital image processing and machine learning methods for efficiently building a sign language dataset and creating a sign language interface system. The proposed system utilizes a Convolutional Neural Network (CNN) to analyze and interpret hand gestures and poses, converting them into natural language. The developed CNN model specifically focuses on improving the accuracy of predicting the American Sign Language alphabet. Despite variations in dataset conditions and size, the model achieved an exceptional accuracy rate of 98.73%. Additionally, it demonstrated a low loss value of 0.0539, indicating its robust performance. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Embeddings for Greek Language Categorization 24

Transformer-Based Embeddings for Greek Language Categorizati...

引用

24th IEEE/ACIS International Conference on computer and Information Science, ICIS 2024

作者： Liapis, Charalampos M. Kyritsis, Konstantinos Perikos, Isidoros Paraskevas, Michael University of Patras Computer Technology Institute & Press 'Diophantus' Mathematics Dept. Patras26504 Greece University of Peloponnese Electrical and Computer Engineering Dept. Patras Greece University of Patras Computer Engineering and Informatics Department Patras Greece University of Peloponnese Computer Technology Institute and Press 'Diophantus' Electrical and Computer Engineering Dept. Patras Greece

ISBN: (纸本)9798350376647

The Greek School Network (GSN) provides support to students, teachers, and school units in secondary education across Greece. Handling numerous user queries manually can be challenging, necessitating the development of an automated system for accurate categorization of these queries. This paper presents a comparative study of various transformer-based models for multi-class text categorization of Greek language queries submitted to the GSN helpdesk. We introduce a new experimental balanced dataset and extract vector representations from eleven transformer-based models. These representations are evaluated using ten classic machine learning classifiers. Our findings highlight the superior performance of the Multilingual E5 Text Embeddings model, particularly when paired with the extreme gradient-boosting classifier. This combination demonstrates a clear advantage in accurately categorizing user queries, paving the way for more efficient automated helpdesk systems. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A transformer-based approach to Nigerian Pidgin text generation

引用

International Journal of Speech Technology 2024年第4期27卷 1027-1037页

作者： Garba, Kabir Kolajo, Taiwo Agbogun, Joshua B. Department of Computer Science Federal University Lokoja P.M.B 1154 Kogi State Lokoja Nigeria Department of Informatics Faculty of Engineering Built Environment & IT University of Pretoria Pretoria South Africa

This paper describes the development of a transformer-based text generation model for Nigerian Pidgin also known as Naijá, a popular language in West Africa. Despite its wide use, Nigerian Pidgin remains under-resourced, particularly in areas related to text generation and natural language processing. These difficulties are primarily due to technological constraints rather than the language’s fundamental attributes. There is currently a demand for Nigerian Pidgin-specific solutions because it is used in everyday communication and has a unique linguistic blend. This paper aims to close this gap by exploring the application of state-of-the-art transformer technology to develop a text generation model for Nigerian Pidgin. This work uses the public Afriberta-corpus dataset to optimize the Generative Pre-trained Transformer (GPT-2) model across a sizeable dataset. The performance evaluators, BLEU and Perplexity metrics provide a detailed breakdown of the model’s text quality and predictive accuracy. Despite the difficulties caused by a limited amount of training data, preliminary evaluations show that the model can generate coherent Nigerian Pidgin text. The performance evaluation yielded perplexity scores of 43.56 for variable target reference length and 43.26 for fixed text length. BLEU scores of 0.15 for fixed max length and 0.56 for variable reference target length. This highlights the quality of generated text and the significant improvement when the generated text length is aligned with the reference target. Our work was benchmarked against African American Vernacular (AAVE) revealing that BLEU scores for AAVE are significantly lower than those for Standard American English, with BLEU given as 0.26. Our Nigerian Pidgin model, with a BLEU score of 0.56, shows a better performance. However, both results suggest that both dialects are challenging for language models. Leveraging the pre-trained transformer-based language model and evaluation metrics, we showcase the mo

关键词： Controllable text Generation Natural Language Generation Natural Language Processing Nigerian pidgin Pre-trained Language models Transformers

来源：评论

学校读者我要写书评

暂无评论

Insights into research on blockchain for smart contracts: a bibliometric analysis

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Singh, Renu Gupta, Ashlesha Mittal, Poonam Faculty of Informatics and Computing J.C. Bose University of Science and Technology YMCA Faridabad India Department of Computer Science & amp Engineering Indraprastha Institute of Information Technology IIIT New Delhi India

Over the past few years, blockchain technology has gained significant attention. This surge in popularity can be attributed to the emergence of cryptocurrencies and the development of smart contracts. Cryptocurrency is a digital currency that eliminates the problem of double spending. Cryptocurrencies like Bitcoin, Ethereum, Litecoin, Stellar, Zcash, Maker, Aave, etc. become popular and are preferred for money transfers. Smart contracts are the next popular technology on the blockchain after cryptocurrency. It can be considered a piece of code that can execute automatically when the predefined conditions are fulfilled. Researchers believe that the potential of blockchain with smart contracts is only in its initial stages and that its true potential has yet to be fully discovered. Hence, an extensive bibliometric analysis is conducted to understand blockchain trends for smart contracts and to give future directions in this field. For this analysis, various steps are followed, starting with formulating the research question, defining the scope of our research, extracting and analyzing data, answering the research question, and finally, drawing a conclusion. This research paper will be fruitful for scholars and researchers, providing an extensive statistical and network analysis of extracted smart contracts publications. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Bibliometric analysis Blockchain Crypto contract Scientometrics Scopus Smart contracts VOSViewer

来源：评论

学校读者我要写书评

暂无评论

Evaluation of RIS-Enabled B5G/6G Indoor Positioning and Mapping using Ray Tracing Models 11

Evaluation of RIS-Enabled B5G/6G Indoor Positioning and Mapp...

引用

11th Workshop on Satellite Navigation Technology, NAVITEC 2024

作者： Kompostiotis, Dimitris Vordonis, Dimitris Paliouras, Vassilis Alexandropoulos, George C. Grec, Florin University of Patras Electrical and Computer Engineering Department Greece National and Kapodistrian University of Athens Department of Informatics and Telecommunications Greece Noordwijk Netherlands

ISBN: (纸本)9798350356854

A Reconfigurable Intelligent Surface (RIS) can significantly enhance network positioning and mapping, acting as an additional anchor point in the reference system and improving signal strength and measurement diversity through the generation of favorable scattering conditions and virtual line-of-sight paths. In this paper, we present a comprehensive framework aimed at user localization and scatterer position estimation in an indoor environment with multipath effects. Our approach leverages beam sweeping through codebook-based beamforming at an 1-bit RIS to scan the environment, applies signal component extraction mechanisms, and utilizes a super-resolution algorithm for angle-based positioning of both connected users and scatterers. To validate the system's effectiveness, accurate 3D ray tracing models are employed, ensuring the robustness and effectiveness of the proposed approach in practical scenarios. © 2024 IEEE.

关键词： Mapping

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：