检索结果-内蒙古大学图书馆

International Workshop on Secure Internet of Things (SIoT)

作者： Saulo Neves Matos Otávio Ferracioli Coletti Fernando Ugucioni Filho Ricardo C. C. L. de Carvalho Thomas V. B. Pinto Luiz G. D. de Barros Caetano Mazzoni Ranieri Bruno Eduardo Lopes Jó Ueyama Gustavo Pessin Institute of Mathematics and Computer Science University of sao Paulo Brazil Sao Carlos School of Engineering University of Sao Paulo Brazil Vale Institute of Technology Ouro Preto Brazil Graduate Program in Electrical Engineering Universidade Federal of Minas Gerais Belo Horizonte MG Brazil Vale -SA Vitoria Brazil

Conveyor belts are commonly used in the mining industry for efficient material transport. However, they are prone to failures such as idler anomalies, belt tears, and misalignment. Current monitoring systems only evaluate the conveyor or idle belt's condition at the installation point. This study proposes a method to detect faults in conveyor belts, specifically idler anomalies and belt deviation, using two IMUs installed at the lateral extremities of the belt to evaluate its health along its route. In a reduced-scale conveyor belt, we conducted experiments by collecting gyroscopes and accelerometer data in various scenarios, including normal conditions and anomaly situations. We modified the idlers' physical structure or changed the belt tracks to create these scenarios. We used similarity analysis techniques to compare the data collected and performed statistical hypothesis analysis to observe the influence of the anomaly scenarios on the gyroscope and accelerometer data. We used Dynamic Time Warping (DTW) for gyroscope data to compare ground truth with anomaly scenarios. For the acceleration data, we performed vibration analysis by converting the time domain data to the frequency using Fast Fourier Transform (FFT) and evaluating the difference in spectral density between the reference and anomaly data. Statistical hypothesis analysis revealed that anomaly scenar-ios influenced the gyroscope x-axis and z-axis more. According to the spectral density analysis of the accelerometer, it was revealed that belt misalignment on the y-axis may be detected.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Course-based online learning video retrieval system

引用

AIP Conference Proceedings 2023年第1期2654卷

作者： Faisal Ramadhan Aina Musdholifah 1Computer Science Program Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta Indonesia 2Department of Computer Science and Electronics Faculty of Mathematics and Natural Science Universitas Gadjah Mada Yogyakarta Indonesia

Audio-visual learning media, such as learning videos on YouTube, is an alternative representation of the learning media commonly used during the COVID-19 pandemic. There are many learning videos available on YouTube; thus, selecting the appropriate learning videos is a challenge in the research field of information retrieval. This study focuses on building an information retrieval system that can recommend online learning videos based on the user requirements, namely the course name and its syllabus. The proposed information retrieval system works through cosine similarity measurement to calculate the closeness between the course and its syllabus with video annotations. The video annotation consists of the title and description metadata of the video captured in real-time from YouTube using the YouTube API. The proposed information retrieval system provides the five most recommended learning videos based on the selected courses and their syllabus. The experimental results involving 40 respondents show that the online video retrieval system has a good performance proven by an accurate level of 80.5% that in line with the relevance score of 84. Furthermore, another three performance indicators also great, i.e., the values of novelty, serendipity, and increasing recommendation diversity are 78%, 77%, and 85.5, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Minuscule corrections to near-surface solar internal rotation using mode-coupling

arXiv

引用

arXiv 2023年

作者： Das, Srijan Bharati Kashyap, Samarth G. Oktay, Deniz Hanasoge, Shravan M. Tromp, Jeroen Department of Geosciences Princeton University PrincetonNJ United States Department of Astronomy and Astrophysics Tata Institute of Fundamental Research Mumbai India Department of Computer Science Princeton University PrincetonNJ United States Department of Geosciences and Program in Applied & Computational Mathematics Princeton University PrincetonNJ United States

The observed solar oscillation spectrum is influenced by internal perturbations such as flows and structural asphericities. These features induce splitting of characteristic frequencies and distort the resonant-mode eigenfunctions. Global axisymmertric flow — differential rotation — is a very prominent perturbation. Tightly constrained rotation profiles as a function of latitude and radius are products of established helioseismic pipelines that use observed Dopplergrams to generate frequency-splitting measurements at high precision. However, the inference of rotation using frequency-splittings do not consider the effect of mode-coupling. This approximation worsens for high-angular-degree modes, as they become increasingly proximal in frequency. Since modes with high angular degrees probe the near-surface layers of the Sun, inversions considering coupled modes could potentially lead to more accurate estimates of rotation very close to the surface. In order to investigate if this is indeed the case, we perform inversions for solar differential rotation, considering coupling of modes for angular degrees 160 ≤ ` ≤ 300 in the surface gravity f-branch and first-overtone p modes. In keeping with the character of mode coupling, we carry out a non-linear inversion using an eigenvalue solver. Differences in inverted profiles for frequency splitting measurements from MDI and HMI are compared and discussed. We find that corrections to the near-surface differential rotation profile, when accounting for mode-coupling effects, are smaller than 0.003 nHz and hence are insignificant. These minuscule corrections are found to be correlated with the solar cycle. We also present corrections to even-order splitting coefficients, which could consequently impact inversions for structure and magnetic fields. © 2023, CC BY.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

Integrating Robot-Based Resources to Foster Computational Thinking and Communication Skills in EFL Education: A Path Towards Sustainable Development 2nd

Integrating Robot-Based Resources to Foster Computational Th...

引用

2nd International Conference on Sustainable Development Using Machine Learning, Artificial Intelligence, and IoT, ICSD 2024

作者： Muthmainnah, Muthmainnah Al Yakin, Ahmad Seraj, Prodhan Mahbub Ibna Darmawati, Besse Elngar, Ahmed A. Obaid, Ahmed J. Teacher Training and Education Faculty Indonesian Language Study Program Universitas Al Asyariah Mandar Polewali Mandar Indonesia Teacher Training and Education Faculty Civic Education Study Program Universitas Al Asyariah Mandar Polewali Mandar Indonesia American International University Dhaka Bangladesh Badan Riset Dan Inovasi Nasional Jakarta Indonesia Faculty of Computers and Artificial Intelligence Beni-Suef University Beni-Suef City62511 Egypt Faculty of Computer Science and Mathematics University of Kufa Kufa Iraq

ISBN: (纸本)9783031717284

The current monolithic approach in teaching and assessing English as a foreign language (EFL) communication in Indonesia has resulted in a gap between students’ understanding of the nature of communication skills and their ability to use them correctly in their speaking, leading to anxiety, lack of self-confidence and lack of mastery vocabulary. Computational thinking (CT), a high-level approach to problem-solving and optimizing knowledge acquisition, was used to design solutions in this study using a Virtual Robot application to stimulate their speaking motivation. They are taught using a CT teaching model. To find out the impact of this method, Pre-test and post-tests were conducted. All undergraduate students showed considerable improvement in their use of vocabulary when speaking, a new level of agency and interest in learning English was evident and their dialogue confidence improved. In the field of English as a foreign language (EFL), CT is an important social mediation technique. This research is the best attempt to incorporate CT into the thinking process of students learning English with the virtual assistance of robot artificial intelligence. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Classical simulators as quantum error mitigators via circuit cutting

arXiv

引用

arXiv 2022年

作者： Liu, Ji Gonzales, Alvin Saleem, Zain H. Mathematics and Computer Science Division Argonne National Laboratory 9700 S Cass Ave LemontIL604391 United States Intelligence Community Postdoctoral Research Fellowship Program Argonne National Laboratory LemontIL United States

We introduce an error mitigation framework that mitigates errors in a quantum circuit using circuit cutting. Our framework can be implemented in polynomial time for a wide variety of quantum circuits. Our technique involves cutting the circuit in such a way that we run the circuit that needs to be executed on the quantum hardware whereas the error mitigation circuit is run on a simulator. We perform error mitigation qubit by qubit and then provide a way to combine the different probabilities from each of the individual qubit error mitigation runs such that the full circuit is error mitigated. We apply our framework to the VQE hardware-efficient ansatz acheiving estimated ground state energies very close to the noise-free simulation results. Copyright © 2022, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Exploring Low Rate Dos Attack Detection Methods: A Bibliometric Analysis and Roadmap for Further Research

Exploring Low Rate Dos Attack Detection Methods: A Bibliomet...

引用

International Conference on Data and Software Engineering (ICODSE)

作者： Anteng Widodo Adian Fatchur Rochim Budi Warsito Doctoral Program of Information System School of Postgraduated Studies Diponegoro University Semarang Indonesia Department of Information System Faculty of Engineering Muria Kudus University Kudus Indonesia Department of Computer Engineering Faculty of Engineering Diponegoro University Semarang Indonesia Department of Statistics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia

Low-Rate Denial of Service (LDoS) attacks, an emerging breed of DoS attacks, present a formidable challenge in terms of their detectability. Within the realm of network security, these attacks cast a substantial shadow over the availability and integrity of services. This study seeks to delve into the intricate mechanics of LDoS attacks and explore the landscape of developed detection methodologies. Employing bibliometric analysis, we employ a multifaceted approach to gather research insights pertaining to LDoS attack detection. This approach encompasses the examination of evolving research trends, scrutiny of widely cited scientific publications within the same domain, identification of prolific researchers shaping the field, and a judicious selection of reputable publishers for dependable information acquisition. Furthermore, our study undertakes a meticulous categorization and classification of previously proposed LDoS detection methods documented in well-established scientific literature. This endeavor not only provides a more profound comprehension of the evolutionary trajectory and thematic thrusts within LDoS attack detection research, but it also facilitates the identification of gaps and directions for future exploration. The culmination of these analytical efforts culminates in a comprehensive framework. This contribution manifests through structured categorization, classification, and a forward-looking research roadmap, which collectively serve as valuable tools for both current and aspiring researchers engaged in LDoS attack detection. In summary, this research not only delves into the complexities of LDoS attacks and their mechanisms but also augments the current understanding of detection capabilities. Through its nuanced contributions, this paper extends a helpful guide to the dynamic realm of LDoS attack detection, thus catalyzing advancements and insights for the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HiPoNet: A Topology-Preserving Multi-View Neural Network For High Dimensional Point Cloud and Single-Cell Data

arXiv

引用

arXiv 2025年

作者： Viswanath, Siddharth Madhu, Hiren Bhaskar, Dhananjay Kovalic, Jake Johnson, Dave Ying, Rex Tape, Christopher Adelstein, Ian Perlmutter, Michael Krishnaswamy, Smita Department of Computer Science Yale University New Haven United States Department of Genetics Yale University New Haven United States Department of Applied Physics Yale University New Haven United States Program in Computing Boise State University Idaho United States Cell Communication Lab Department of Oncology University College London Cancer Institute London United Kingdom Department of Mathematics Yale University New Haven United States Department of Mathematics Boise State University Idaho United States Computational Biology and Bioinformatics Program Yale University New Haven United States Wu-Tsai Institute Yale University New Haven United States Program for Applied Math Yale University New Haven United States

In this paper, we propose HiPoNet, an end-to-end differentiable neural network for regression, classification, and representation learning on high-dimensional point clouds. Single-cell data can have high dimensionality exceeding the capabilities of existing methods for point clouds which are tailored for 3D data. Moreover, modern single-cell and spatial experiments now yield entire cohorts of datasets (i.e. one on every patient), necessitating models that can process large, high-dimensional point clouds at scale. Most current approaches build a single nearest-neighbor graph, discarding important geometric information. In contrast, HiPoNet forms higher-order simplicial complexes through learnable feature reweighting, generating multiple data views that disentangle distinct biological processes. It then employs simplicial wavelet transforms to extract multiscale features—capturing both local and global topology. We empirically show that these components preserve topological information in the learned representations, and that HiPoNet significantly outperforms state-of-the-art point-cloud and graph-based models on single cell. We also show an application of HiPoNet on spatial transcriptomics datasets using spatial co-ordinates as one of the views. Overall, HiPoNet offers a robust and scalable solution for high-dimensional data analysis. © 2025, CC BY.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian deep learning is needed in the age of large-scale AI 24

Position: Bayesian deep learning is needed in the age of lar...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence Aitchison Julyan Arbel David Dunson Maurizio Filippone Vincent Fortuin Philipp Hennig José Miguel Hernández-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang Department of Mathematics The University of Manchester Manchester UK Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Spotify London UK Computational Neuroscience Unit University of Bristol Bristol UK Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany and Department of Computer Science Technical University of Munich Munich Germany and Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge UK Department of Mathematics University of Oslo Oslo Norway and Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative California Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London UK Department of Computer Science UC Irvine Irvine Department of Mathematics and Statistics Lancaster University Lancaster UK Department of Engineering Science University of Oxford Oxford UK Center for Data Science New York University New York Munich Center for Machine Learning Munich Germany and Department of Statistics LMU Munich Munich Germany DeepMind London UK and Department of Statistics University of Oxford Oxford UK Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences and Center for Data Science Computer Science Department New York University New York Department of Computer Science Purdue University West Lafayette

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diabetes Prediction Model for Better Clarification by using Machine Learning

Diabetes Prediction Model for Better Clarification by using ...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： J. Lysa Eben R. Jayasudha S. Ramya S. Kaliappan Shobha Aswal Khalid Ali Salem Al-Salehi Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology and Advanced Studies Chennai Tamilnadu India Department of Mathematics Dr.N.G.P.Institute of Technology Coimbatore India Department of Computer Science and Engineering Kongu Engineering College Erode Tamilnadu India Division of Research and Development Lovely Professional University Phagwara Punjab India School of Computing Graphic Era Hill University Dehradun India Biomedical engineering study program faculty of science and technology Airlangga University Surabaya Indonesia

Diabetes mellitus is one of the most pressing health concerns because so many people are afflicted by its disabling symptoms. Factors such as age, excess body fat, insufficient physical activity, a history of diabetes in one's family, a sedentary lifestyle, an unhealthy diet, hypertension, etc., all increase the likelihood of developing diabetes mellitus. Health complications are more common in people with diabetes, including cardiovascular disease, renal failure, stroke, blindness, and nerve injury. To validate a diagnosis of diabetes, hospitals typically perform a battery of procedures on the patient. Big data analytics has many vital applications in the healthcare sector. Numerous large computer systems are used in the healthcare sector. With the help of big data analytics, researchers can sift through mountains of data in search of previously unseen patterns and insights. Current techniques have a poor degree of precision in classification and forecast. While previous research has focused on factors such as glucose, body mass index, age, insulin, etc., the proposed model takes these into account and also the other factors that may be more relevant to the development of diabetes. The newer sample is superior to the older one based on categorization accuracy. A workflow algorithm for diabetes prognosis is also required to improve the accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comparative forecasting model of COVID-19 case in Indonesia 7

A comparative forecasting model of COVID-19 case in Indonesi...

引用

7th International Conference on mathematics, science, and Education 2020, ICMSE 2020

作者： Septiarini, T.W. Taufik, M.R. Prasetya, T.A.E. Department of Islamic Economics Faculty of Economics and Management University of Darussalam Gontor Ponorogo Indonesia Department of Occupational Safety and Health Faculty of Health Science University of Darussalam Gontor Ponorogo Indonesia Occupational Safety and Health Department Faculty of Vocational Studies University of Airlangga Surabaya Indonesia Research Methodology Program Department of Mathematics and Computer Science Faculty of Science and Technology Prince of Songkla University Pattani Campus Thailand

COVID-19 had been a disaster in Indonesia. Moreover, it is needed a study to analyze the trend of this case. The objectives of this study were (1) to propose the model for predicting COVID-19 using exponential smoothing, autoregressive integrated moving average (ARIMA), neural network, and fuzzy time series and (2) to compare the performance for each model by using RMSE as evaluation tool. In this study, the splitting data is implemented by 3:1 ratio on train and test data set. The results show that the neural network has the smallest error, 772.46 for RMSE. It means that neural network perform better than other forecasting model. Once, the characteristic data had big impact to building forecasting model whether in classical or modern model. © Published under licence by IOP Publishing Ltd.

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：