检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Chiu, Ching-Yu Su, Alvin Wen-Yu Yang, Yi-Hsuan The Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University Academia Sinica Taiwan The Department of Computer Science and Information Engineering National Cheng Kung University Taiwan Yating Music Team Taiwan AI Labs Taiwan Research Center for IT Innovation Academia Sinica Taiwan

This paper presents a novel system architecture that integrates blind source separation with joint beat and downbeat tracking in musical audio signals. The source separation module segregates the percussive and non-percussive components of the input signal, over which beat and downbeat tracking are performed separately and then the results are aggregated with a learnable fusion mechanism. This way, the system can adaptively determine how much the tracking result for an input signal should depend on the input's percussive or non-percussive components. Evaluation on four testing sets that feature different levels of presence of drum sounds shows that the new architecture consistently outperforms the widely-adopted baseline architecture that does not employ source separation. Copyright © 2021, The Authors. All rights reserved.

关键词： Blind source separation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization

arXiv

引用

arXiv 2023年

作者： Du, Hongyang Zhang, Ruichen Liu, Yinqiu Wang, Jiacheng Lin, Yijing Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Cui, Shuguang Ai, Bo Zhou, Haibo Kim, Dong In The School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China The School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Shenzhen China The State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing100044 China School of Electronic Science and Engineering Nanjing University Jiangsu Nanjing210093 China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Generative Diffusion Models (GDMs) have emerged as a transformative force in the realm of Generative Artificial Intelligence (GenAI), demonstrating their versatility and efficacy across various applications. The ability to model complex data distributions and generate high-quality samples has made GDMs particularly effective in tasks such as image generation and reinforcement learning. Furthermore, their iterative nature, which involves a series of noise addition and denoising steps, is a powerful and unique approach to learning and generating data. This paper serves as a comprehensive tutorial on applying GDMs in network optimization tasks. We delve into the strengths of GDMs, emphasizing their wide applicability across various domains, such as vision, text, and audio generation. We detail how GDMs can be effectively harnessed to solve complex optimization problems inherent in networks. The paper first provides a basic background of GDMs and their applications in network optimization. This is followed by a series of case studies, showcasing the integration of GDMs with Deep Reinforcement Learning (DRL), incentive mechanism design, Semantic Communications (SemCom), Internet of Vehicles (IoV) networks, etc. These case studies underscore the practicality and efficacy of GDMs in real-world scenarios, offering insights into network design. We conclude with a discussion on potential future directions for GDM research and applications, providing major insights into how they can continue to shape the future of network optimization. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Universality of Winning Tickets: A Renormalization Group Perspective

arXiv

引用

arXiv 2021年

作者： Redman, William T. Chen, Tianlong Wang, Zhangyang Dogra, Akshunna S. Interdepartmental Graduate Program in Dynamical Neuroscience University of California Santa Barbara United States Department of Electrical and Computer Engineering University of Texas at Austin United States Department of Mathematics Imperial College London United Kingdom EPSRC CDT in Mathematics of Random Systems: Analysis Modelling and Simulation United Kingdom

Foundational work on the Lottery Ticket Hypothesis has suggested an exciting corollary: winning tickets found in the context of one task can be transferred to similar tasks, possibly even across different architectures. This has generated broad interest, but methods to study this universality are lacking. We make use of renormalization group theory, a powerful tool from theoretical physics, to address this need. We find that iterative magnitude pruning, the principal algorithm used for discovering winning tickets, is a renormalization group scheme, and can be viewed as inducing a flow in parameter space. We demonstrate that ResNet-50 models with transferable winning tickets have flows with common properties, as would be expected from the theory. Similar observations are made for BERT models, with evidence that their flows are near fixed points. Additionally, we leverage our framework to study winning tickets transferred across ResNet architectures, observing that smaller models have flows with more uniform properties than larger models, complicating transfer between them. © 2021, CC BY.

关键词： Statistical mechanics

来源：评论

学校读者我要写书评

暂无评论

Accuracy for Sentiment Analysis of Twitter Students on ELearning in Indonesia using Naive Bayes Algorithm Based on Particle Swarm Optimization 1

Accuracy for Sentiment Analysis of Twitter Students on ELear...

引用

1st International Conference on computer, Science, Engineering and Technology, ICComSET 2018

作者： Kartiko, Mohamad Sfenrianto Master of Computer Science Postgraduate Programs STMIK Nusa Mandiri Jakarta Indonesia Information Systems Management Department BINUS Graduate Program-Master of Information Systems Management Universitas Bina Nusantara Jakarta Indonesia

Students can use social media such as Twitter for online learning (E-Learning). This study aims to analyse an accuracy for the sentiments of students about E-Learning who use Indonesian on Twitter social media both positive and negative opinions. The algorithms used are Naive Bayes (NB). Then to optimize the accuracy of the calculation results, the Particle Swarm Optimization (NB-PSO) approach is used. In order to optimize accurate results, this study uses three experimental sequences (scenario 1, scenario 2, and scenario 2) for both NB and NB-PSO algorithms. Each scenario uses different positive and negative comments. The results of the experiment show that in scenario 1 an increase in accuracy is 10.00% for NB-PSO. Scenario 2 there is an increase in accuracy of 13.33% on NB-PSO. Meanwhile, in scenario 3 an increase in accuracy is 27.22% for NB-PSO. These results prove that the accuracy of NB-PSO is better than NB for all scenarios. © 2019 IOP Publishing Ltd. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An Agile Implementation Model for ERP 4

An Agile Implementation Model for ERP

引用

4th International Conference on Information Management and Technology, ICIMTech 2019

作者： Wijaya, Santo Fernandi Prabowo, Harjanto Kosala, Raymondus Raymond Meyliana Information Systems Department Computer Science Department Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Doctor of Computer Science Management Department Bina Nusantara University Jakarta11480 Indonesia

ISBN: (纸本)9781728133331

The growing impact of industrial dynamics will be a challenge to increase productivity. Productivity is a demand for improving organizational performance. ERP systems are a way to increase productivity. Therefore, ERP implementation is important to ensure that ERP runs well. Critical factors in ERP implementation must get serious attention to project management. Even so, the reality of ERP implementation is slowly, even tends to experience failure, resulting in highly expensive. The previous research that carried out ERP implementation showed that the failure reached 40%, and the achievement of the benefits of ERP implementation in Indonesia is still not optimal. It can be said that ERP implementation is a complexity project. For this reason, it is necessary to consider other implementation methods that can overcome the problem in implementing ERP. An agile method is a proactive and reactive alternative to handle the problem in implementing of ERP. The development of an agile ERP model is one way to achieve success in ERP implementation. This research methodology is a survey approach to the study of literature. This research will propose an agile ERP model which will be used as an effective guide for achieving the success of ERP implementation. © 2019 IEEE.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

Improving Rice Productivity in Indonesia with Artificial Intelligence 7

Improving Rice Productivity in Indonesia with Artificial Int...

引用

7th International Conference on Cyber and IT Service Management, CITSM 2019

作者： Liundi, Nicholas Darma, Aditya Wirya Gunarso, Rivaldi Warnars, Harco Leslie Hendric Spits School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781728129099

Indonesia is one of the biggest agriculture countries in the world with one of its major commodities, rice. Despite its vast paddy field and tropical resources, Indonesia still has not achieved food security. This paper explores ideas about how to present artificial intelligence that may increase rice productivity in Indonesia. Current situations of rice cultivation are mentioned start from existing technologies and systems used in Indonesia. Some artificial intelligence concepts are also introduced. Artificial Intelligence use in rice farming is then analyzed which ideas may be applicable to increase efficiency further. Those that are already implemented in rice farming include diseases and pest detection, prediction and estimation, and automated intelligent systems. In the proposed idea section, ideas to increase production are explored. Using advanced technologies may not be suitable for Indonesia's rice farmers. One argument is to minimize the differences in rice yield in different areas or so what we called yield gap. Factors such as weather, water, and harvest date are those with most impacts on the yield gap. It is beneficial to have a model that can predict the optimal planting date of rice since that will maximize the factors before. Among those implemented, a planting calendar prediction on rice-based on rainfall is already developed. However, rainfall is not the only factor. El-Nino occurrences and temperature changes also have a role in deciding when best to plant rice. The author suggests adding those two new variables, making three in total to the earlier neural network model may improve the overall result. © 2019 IEEE.

关键词： Productivity

来源：评论

学校读者我要写书评

暂无评论

Information system model for maize research to anticipate the impact of climate change on Indonesian food security

引用

AIP Conference Proceedings 2023年第1期2594卷

作者： A. S. Perbangsa F. A. Munawwar M. B. Pabendon B. Pardamean Information Systems Department School of Information Systems Bina Nusantara University Jakarta 11480 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Indonesia Cereals Research Institute Maros South Sulawesi 90514 Indonesia Computer Science Department BINUS Graduate Program Master of Computer Science Bina Nusantara University Jakarta 11480 Indonesia

As a rich country in genetic resources, Indonesia has the potential for strengthening food security. Maize is one of the commodities that greatly affect food security in Indonesia. Maize is also widely used as animal feed. The high demand for maize requires efforts to increase the productivity of sustainable cultivation. Various research efforts that have been carried out require the support of a comprehensive information system. This study aimed to build a research model for maize genetic resource information systems that can help search for superior varieties. The data collection method used was collecting genotype, phenotype, climate data and interviewing the maize breeders or researchers. As for the design of the model, this study used the Object-Oriented Analysis & Design (OOAD) method with notation from Unified Modelling Language (UML). The result of this research was a web-based model of information systems for maize research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An efficient multi-objective evolutionary approach for solving the operation of multi-reservoir system scheduling in hydro-power plants

arXiv

引用

arXiv 2021年

作者： Marcelino, Carolina Gil Leite, G.M.C. Delgado, C.A.D.M. De Oliveira, L.B. Wanner, E.F. Jiménez-Fernández, S. Salcedo-Sanz, S. Department of Signal Processing and Communications Universidad de Alcalá Spain Institute of Computing Federal University of Rio de Janeiro Brazil Post-Graduate Program in Systems Engineering and Computer Science Federal University of Rio de Janeiro Brazil Computing Department Federal Center of Technology Education of Minas Gerais Brazil

This paper tackles the short-term hydro-power unit commitment problem in a multi-reservoir system - a cascade-based operation scenario. For this, we propose a new mathematical modelling in which the goal is to maximize the total energy production of the hydro-power plant in a sub-daily operation, and, simultaneously, to maximize the total water content (volume) of reservoirs. For solving the problem, we discuss the Multi-objective Evolutionary Swarm Hybridization (MESH) algorithm, a recently proposed multiobjective swarm intelligence-based optimization method which has obtained very competitive results when compared to existing evolutionary algorithms in specific applications. The MESH approach has been applied to find the optimal water discharge and the power produced at the maximum reservoir volume for all possible combinations of turbines in a hydro-power plant. The performance of MESH has been compared with that of well-known evolutionary approaches such as NSGA-II, NSGA-III, SPEA2, and MOEA/D in a realistic problem considering data from a hydro-power energy system with two cascaded hydro-power plants in Brazil. Results indicate that MESH showed a superior performance than alternative multi-objective approaches in terms of efficiency and accuracy, providing a profit of $412,500 per month in a projection analysis carried out. © 2021, CC BY-NC-ND.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

The next cryptocurrency price movement prediction application uses patterned datasets

引用

AIP Conference Proceedings 2024年第1期3116卷

作者： Rizky Parlika Mustafid Basuki Rahmat Diponegoro University Information Systems Doctoral Study Program Graduate School 50241 Jl. Imam Bardjo SH Pleburan Semarang Indonesia University of Pembangunan Nasional “Veteran” Jawa Timur Department of Informaton Technology Faculty of Computer Science 60294 Rungkut Madya Gunung Anyar Surabaya Indonesia

Researchers and experts have developed various techniques, models, and methods to predict the price movements of cryptocurrencies, especially Bitcoin. However, among the many techniques studied in the literature, there is still a lack of focus on mining, creating, and developing datasets with specific patterns for predicting the next cryptocurrency price movement. This is an exciting reason to conduct further research. A web-based Patterned Dataset Application and a Telegram bot were constructed to address this issue. These tools read the price position of each cryptocurrency and predict the next price direction based on the last position indicated by the Patterned Dataset Application. The experiment’s results show that when the Patterned Dataset Application shows a diamond crash position, it is time to make a purchase; conversely, when it shows a diamond moon position, it is time to make a sale. It is hoped that by utilizing the Patterned Dataset Application, potential losses can be minimized, and there is more potential for profit in cryptocurrency trading. Even though the initial data source comes from Indonesia’s most prominent digital cryptocurrency trading market, according to coinmarketcap, namely Indodax, the results of this patterned dataset application can often describe the same cryptocurrency conditions globally. The novelty of this research is to produce a new way of predicting the next cryptocurrency price movement using patterned datasets. At the end of this paper, it will be proven that hypothesis 1 and hypothesis 2 on the results of the patterned dataset are true.

关键词：

来源：评论

学校读者我要写书评

暂无评论

cytoNet: Spatiotemporal network analysis of cell communities (vol 18, e1009846, 2022)

引用

PLOS COMPUTATIONAL BIOLOGY 2022年第11期18卷 e1009846页

作者： Mahadevan, A. S. Long, B. L. Hu, C. W. Ryan, D. T. Grandel, N. E. Department of Bioengineering University of Pennsylvania Philadelphia Pennsylvania United States of America. Department of Bioengineering Rice University Houston Texas United States of America. Systems Synthetic and Physical Biology Program Rice University Houston Texas United States of America. Department of Biomedical Engineering University of Texas at San Antonio San Antonio Texas United States of America. Biophysics Graduate Program University of California Berkeley California United States of America. Department of Oral & Maxillofacial Surgery University of Texas Health Science Center at San Antonio San Antonio Texas United States of America. Department of Electrical and Computer Engineering Rice University Houston Texas United States of America.

We introduce cytoNet, a cloud-based tool to characterize cell populations from microscopy images. cytoNet quantifies spatial topology and functional relationships in cell communities using principles of network science. Capturing multicellular dynamics through graph features, cytoNet also evaluates the effect of cell-cell interactions on individual cell phenotypes. We demonstrate cytoNet's capabilities in four case studies: 1) characterizing the temporal dynamics of neural progenitor cell communities during neural differentiation, 2) identifying communities of pain-sensing neurons in vivo, 3) capturing the effect of cell community on endothelial cell morphology, and 4) investigating the effect of laminin α4 on perivascular niches in adipose tissue. The analytical framework introduced here can be used to study the dynamics of complex cell communities in a quantitative manner, leading to a deeper understanding of environmental effects on cellular behavior. The versatile, cloud-based format of cytoNet makes the image analysis framework accessible to researchers across domains.

关键词： Calcium imaging Fluorescence imaging Growth factors Centrality Cell cycle and cell division Endothelial cells Network analysis Stem cells

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：