检索结果-内蒙古大学图书馆

Anomaly Detection for Log using AutoM and Auto-Sklearn Classification Algorithm 15

学校读者我要写书评

暂无评论

Anomaly Detection for Log using AutoM and Auto-Sklearn Class...

15th International Conference on computing Communication and Networking Technologies, ICCCNT 2024

作者： Karthik, G.M. Gupta, Ankur Gupta, Sh Rajesh Jha, Amaresh Sivasangari, A. Mishra, B.P. School of Computer Science and Engineering Vellore Institute of Technology Vellore632014 India Department of CSE RIMT University Godindgarh Mandi India Department of Management Sanskriti University Uttar Pradesh Mathura India School of Modern Media University of Petroleum and Energy Studies Dehradun India School of Computing Sathyabama Institute of Science and Technology Chennai India Department of Electronics JSS Academy of Technical Education NoidaSector-62 India

ISBN: (纸本)9798350370249

— In the realm of application development, logs represent a pivotal resource for the identification and comprehension of application performance, as well as the detection of anomalies, all of which are essential for ensuring the overall efficiency of an application. The proliferation of users has resulted in a substantial increase in the volume of logs available for analysis in the field of log analysis research. Typically, these logs exhibit an unstructured format, largely dictated by the developer's design choices. Consequently, there is a need for log parsing techniques to in still structure into these logs, enabling the application of machine learning algorithms for the prediction of anomalies. In the present research, the primary objective is the prediction of anomalies within Hadoop Distributed File System (HDFS) logs utilizing an AutoML (Automated Machine Learning) tool known as Auto-Sklearn. The research outcomes illustrate the effectiveness of the proposed model, which attains an impressive accuracy rate of 99% when applied to the dataset. This study underscores the critical role of logs in application development, highlights the importance of log structure transformation, and demonstrates the substantial predictive capabilities of the Auto-Sklearn model in the context of HDFS log analysis. ©2024 IEEE.

关键词： Anomaly detection

Comparison of Edge computing Scheduling Algorithms 18

学校读者我要写书评

暂无评论

Comparison of Edge Computing Scheduling Algorithms

18th Iberian Conference on Information Systems and Technologies, CISTI 2023

作者： Catali, Pedro S. Manacero, Aleardo Lobato, Renata S. Spolon, Roberta Cavenaghi, Marcos A. São Paulo State University - UNESP Computer Science and Statistics Department São José do Rio Preto Brazil São Paulo State University - UNESP Computing Department Bauru Brazil Humber Institute of Technology and Advanced Learning Toronto Canada

ISBN: (纸本)9789893347928

Through the advancement of the Internet of Things (IoT), the development of devices for task automation, data extraction, and communication between devices has become increasingly easy. But as a result, tens of zettabytes of data are being generated every year, causing excessive bandwidth consumption as well as slow response times for devices. One of the ways to solve the problem is with the use of Edge computing networks, such paradigm allows the transfer of the data processing to the edges of the network. Since the Edge is mostly composed of devices of varied and limited computational capacity, a good way to distribute the tasks that must be processed is needed. Therefore, efficient, and well tested, scheduling algorithms are a way to distribute tasks in such a way that the time required to perform them is minimized. This work explores the comparison o three distinct scheduling algorithms in Edge computing: the Modified Monte Carlo Tree Search;the Improved Binary Grey Wolf Optmizer and the Application-aware Scheduling Algorithm, analyzing their speed and efficiency as an evaluation metric, using the iSPD grid simulator. © 2023 ITMA.

关键词： Scheduling algorithms

Integrating IoT in Transportation for Smart City Development for Secured Data Processing 4

学校读者我要写书评

暂无评论

Integrating IoT in Transportation for Smart City Development...

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Priya, R. Lakshmi, R. Anandha Sudha, C. Pal, Souvik Ali, Ghassan Ahmed Alajmani, Samah H. Vels Institute of Science Technology and Advanced Studies Dept. of Computer Applications Chennai India Anna Adarsh College for Women Dept. of Computer Applications Chennai India SSKV College of Arts and Science for Women Dept. of Computer Applications Kanchipuram India Saveetha College of Liberal Arts & Sciences Saveetha Institute of Medical & Technical Sciences Chennai India Universiti Islam Sultan Sharif Ali Faculty of Islamic Technology Brunei College of Computer & IT Taif University Department of Information Technology Saudi Arabia

ISBN: (纸本)9798350353266

In this study, we propose the architecture and implementation of an IoT and machine learning powered Integrated Transport Management (ITM-SCD)for Smart City Development to mitigate the issues described above. The design takes all potential transportation system difficulties into account by utilizing many scenarios. The model integrates the various city systems into a single, cohesive whole, with an emphasis on secured data. People's movements can be monitored that smart transportation, healthcare, and entertainment can be provided. We discuss the challenges of transit security and smart city applications, as well as possible solutions based on AI and ML. Then, for smart health, transportation, and energy, some solutions to these privacy and security issues are offered. © 2024 IEEE.

关键词： Traffic congestion

Quantum computing Society of the Philippines: An NGO Perspective on Promoting Quantum Information, science, and Technology in the Philippines 5

学校读者我要写书评

暂无评论

Quantum Computing Society of the Philippines: An NGO Perspec...

5th IEEE International Conference on Quantum computing and Engineering, QCE 2024

作者： Lopez, Dylan Josh Domingo Peramo, Elmer Ayson, Jabez Mendoza Masongsong, Angela Nicole S. Raquel, Lance Dominic C. Corpus, Bobby O. Department of Computer Technology De La Salle University Manila Philippines Advanced Science and Technology Institute Department of Science and Technology Quezon City Philippines Electronics Engineering Department Don Honorio Ventura State University Pampanga Philippines STEM Department De La Salle University Integrated School Manila Philippines Department of Physics University of San Carlos Cebu City Philippines Quantum Computing Society of the Philippines Manila Philippines

ISBN: (纸本)9798331541378

The development of Quantum Information science and Technology (QIST) as an emerging technology among developed and developing countries has caught the attention of governments, industries, and educational institutions. However, not all countries have equal starting points in promoting QIST amongst different sectors. Several players in various countries promote QIST as a discipline and education. Although significant developments in quantum technology are focused in Western countries, great innovation can also be seen in Eastern countries, specifically Asia. The Philippines is one of several developing countries in Asia that is in the process of adopting QIST in multiple sectors. In this paper, the Quantum computing Society of the Philippines (QCSP) is introduced as one of the arms of the country for promoting QIST to the public. Further in this paper, the initial impact of QIST promotion on various communities across the Philippines through multiple activities and educational efforts is explained. Several critical success stories for different audiences were described, wherein initial acceptance of QIST was evident through hackathons and lecture series. Events held show improvement in interest and proficiency in the foundations of QIST. © 2024 IEEE.

关键词： Quantum computers

Efficient Exact Quadrature of Regular Solid Harmonics Times Polynomials Over Simplices in R3

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kaneko, Shoken Duraiswami, Ramani Department of Computer Science Institute for Advanced Computer Studies University of Maryland College ParkMD20742 United States

A generalization of a recently introduced recursive numerical method [1] for the exact evaluation of integrals of regular solid harmonics and their normal derivatives over simplex elements in R3 is presented. The original Quadrature to Expansion (Q2X) method [1] achieves optimal per-element asymptotic complexity, however, it considered only constant density functions over the elements. Here, we generalize this method to support arbitrary degree polynomial density functions, which is achieved in an extended recursive framework while maintaining the optimality of the complexity. The method is derived for 1- and 2- simplex elements in R3 and can be used for the boundary element method and vortex methods coupled with the fast multipole method. © 2023, CC BY-NC-ND.

关键词： Boundary element method

Layer potential quadrature on manifold boundary elements with constant densities for Laplace and Helmholtz kernels in R3

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kaneko, Shoken Duraiswami, Ramani Department of Computer Science Institute for Advanced Computer Studies University of Maryland College ParkMD20742 United States

A method is proposed for evaluation of single and double layer potentials of the Laplace and Helmholtz equations on piecewise smooth manifold boundary elements with constant densities. The method is based on a novel two-term decomposition of the layer potentials, derived by means of differential geometry. The first term is an integral of a differential 2-form which can be reduced to contour integrals using Stokes’ theorem, while the second term is related to the element curvature. This decomposition reduces the degree of singularity and the curvature term can be further regularized by a polar coordinate transform. The method can handle singular and nearly singular integrals. Numerical results validating the accuracy of the method are presented for all combinations of single and double layer potentials, for the Laplace and Helmholtz kernels, and for singular and nearly singular integrals. © 2023, CC BY-NC-ND.

关键词： Numerical methods

Streaming quantum state purification for general mixed states

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Grier, Daniel Leung, Debbie Li, Zhi Pashayan, Hakop Schaeffer, Luke Department of Mathematics Department of Computer Science and Engineering University of California San Diego United States Institute for Quantum Computing University of Waterloo Canada Perimeter Institute for Theoretical Physics Canada National Research Council of Canada Canada Dahlem Center for Complex Quantum Systems Freie Universität Berlin Germany Research Institute Taiwan Department of Computer Science Institute for Advanced Computer Studies Joint Center for Quantum Information and Computer Science University of Maryland United States

Given multiple copies of a mixed quantum state with an unknown, nondegenerate principal eigenspace, quantum state purification is the task of recovering a quantum state that is closer to the principal eigenstate. A streaming protocol relying on recursive swap tests has been proposed and analysed for noisy depolarized states with arbitrary dimension and noise level. Here, we show that the same algorithm applies much more broadly, enabling the purification of arbitrary mixed states with a nondegenerate principal eigenvalue. We demonstrate this through two approaches. In the first approach, we show that, given the largest two eigenvalues, the depolarized noise is the most difficult noise to purify for the recursive swap tests, thus the desirable bounds on performance and cost follow from prior work. In the second approach, we provide a new and direct analysis for the performance of purification using recursive swap tests for the more general noise. We also derive simple lower bounds on the sample complexity, showing that the recursive swap test algorithm attains optimal sample complexity (up to a constant factor) in the low-noise regime. © 2025, CC BY.

关键词：

A Second-Order Semi-Implicit Method for the Inertial Landau-Lifshitz-Gilbert Equation

学校读者我要写书评

暂无评论

Numerical Mathematics(Theory,Methods and Applications) 2023年第1期16卷 182-203页

作者： Panchi Li Lei Yang Jin Lan Rui Du Jingrun Chen School of Mathematical Sciences Soochow UniversitySuzhou 215006China School of Computer Science and Engineering Macao University of Science and TechnologyMacao SARChina Center for Joint Quantum Studies and Department of Physics School of ScienceTianjin University92 Weijin RoadTianjin 300072China Mathematical Center for Interdisciplinary Research Soochow UniversitySuzhou 215006China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhouJiangsu 215123China School of Mathematical Sciences University of Science and Technology of ChinaHefeiAnhui 230026China

Electron spins in magnetic materials have preferred orientations collectively and generate the macroscopic *** dynamics spans over a wide range of timescales from femtosecond to picosecond,and then to *** Landau-Lifshitz-Gilbert(LLG)equation has been widely used in micromagnetics simulations over *** theoretical and experimental advances have shown that the inertia of magnetization emerges at sub-picosecond timescales and contributes significantly to the ultrafast magnetization dynamics,which cannot be captured intrinsically by the LLG ***,as a generalization,the inertial LLG(iLLG)equation is proposed to model the ultrafast magnetization ***,the LLG equation is a nonlinear system of parabolic type with(possible)***,the iLLG equation is a nonlinear system of mixed hyperbolic-parabolic type with degeneracy,and exhibits more complicated *** behaves as a hyperbolic system at sub-picosecond timescales,while behaves as a parabolic system at larger timescales spanning from picosecond to *** hybrid behaviors impose additional difficulties on designing efficient numerical methods for the iLLG *** this work,we propose a second-order semiimplicit scheme to solve the iLLG *** second-order temporal derivative of magnetization is approximated by the standard centered difference scheme,and the first-order temporal derivative is approximated by the midpoint scheme involving three time *** nonlinear terms are treated semi-implicitly using one-sided interpolation with second-order *** each time step,the unconditionally unique solvability of the unsymmetric linear system is proved with detailed discussions on the condition ***,the second-order accuracy of the proposed method in both time and space is *** sub-picosecond timescales,the inertial effect of ferromagnetics is observed in micromagnetics simulations,in consistency wi

关键词： Inertial Landau-Lifshitz-Gilbert equation semi-implicit scheme second-order accuracy micromagnetics simulations

Application of Artificial Neural Networks for Investigation of Pressure Filtration Performance, a Zinc Leaching Filter Cake Moisture Modeling

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kazemi, Masoume Moradkhani, Davood Alipour, Alireza A. Zanjan University Department of Materials Science and Engineering Iran Institute for Advanced Studies in Basic Sciences Department of Computer Science Iran

Machine Learning (ML) is a powerful tool for material science applications. Artificial Neural Network (ANN) is a machine learning technique that can provide high prediction accuracy. This study aimed to develop an ANN model to predict the cake moisture of the pressure filtration process of zinc production. The cake moisture was influenced by seven parameters: temperature (35 ℃ and 65 ℃), solid concentration (0.2 and 0.38 g/L), pH (2, 3.5, and 5), air-blow time (2, 10, and 15 min), cake thickness (14, 20, 26, and 34 mm), pressure, and filtration time. The study conducted 288 tests using two types of fabrics: polypropylene (S1) and polyester (S2). The ANN model was evaluated by the Coefficient of determination (R2), the Mean Square Error (MSE), and the Mean Absolute Error (MAE) metrics for both datasets. The results showed R2 values of 0.88 and 0.83, MSE values of 6.243×10-07 and 1.086×10-06, and MAE values of 0.00056 and 0.00088 for S1 and S2, respectively. These results indicated that the ANN model could predict the cake moisture of pressure filtration in the zinc leaching process with high accuracy. © 2023, CC0.

关键词： Machine learning