检索结果-内蒙古大学图书馆

37th Annual European Simulation and Modelling Conference, ESM 2023

作者： Zhang, Xiao Paz, Iván Nebot, Àngela Soft Computing Research Group Intelligent Data Science and Artificial Intelligence Research Center Universitat Politècnica de Catalunya Barcelona Spain

ISBN: (纸本)9789492859280

When confronted with imbalanced datasets, traditional classifiers frequently struggle to correctly categorize samples from the minority class, adversely impacting the overall predictive performance of machine learning models. Current oversampling techniques generally focus on data interpolation through neighbor selection, often neglecting to uncover underlying data structures and relationships. This study introduces a novel application for RuLer, an algorithm originally developed for identifying sound patterns in the artistic domain of live coding. When adapted for data oversampling (as Ad-RuLer), the algorithm shows significant promise in addressing the challenges associated with imbalanced class distribution. We undertake a thorough comparative evaluation of Ad-RuLer against established oversampling algorithms such as SMOTE, ADASYN, Tomek-links, Borderline-SMOTE, and KmeansSMOTE. The evaluation employs various classifiers including logistic regression, random forest, and XGBoost, and is conducted over six real-world biomedical datasets with varying degrees of imbalance. © 2023 ESM. All Rights Reserved.

关键词： Classification data synthesis Imbalanced data Oversampling Rule-based approach

来源：评论

学校读者我要写书评

暂无评论

SCTAP: Supporting Scenario-Centric Trigger-Action Programming based on Software-Defined Physical Environments 23

SCTAP: Supporting Scenario-Centric Trigger-Action Programmin...

引用

32nd ACM World Wide Web Conference, WWW 2023

作者： Sun, Bingkun Shen, Liwei Peng, Xin Wang, Ziming Fudan University China School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

ISBN: (纸本)9781450394161

The physical world we live in is accelerating digitalization with the vigorous development of Internet of Things (IoT). Following this trend, Web of Things (WoT) further enables fast and efficient creation of various applications that perceive and act on the physical world using standard Web technologies. A popular way for creating WoT applications is Trigger-Action Programming (TAP), which allows users to orchestrate the capabilities of IoT devices in the form of "if trigger, then action". However, existing TAP approaches don't support scenario-centric WoT applications which involve abstract modeling of physical environments and complex spatio-temporal dependencies between events and actions. In this paper, we propose an approach called SCTAP which supports Scenario-Centric Trigger-Action Programming based on software-defined physical environments. SCTAP defines a structured and conceptual representation for physical environments, which provides the required programming abstractions for WoT applications. Based on the representation, SCTAP defines a grammar for specifying scenario-centric WoT applications with spatio-temporal dependencies. Furthermore, we design a service-based architecture for SCTAP which supports the integration of device access, event perception, environment representation, and rule execution in a loosely-coupled and extensible way. We implement SCTAP as a WoT infrastructure and evaluate it with two case studies including a smart laboratory and a smart coffee house. The results confirm the usability, feasibility and efficiency of SCTAP and its implementation. © 2023 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Intelligent Compound Selection of Anti-cancer Drugs Based on Multi-Objective Optimization

Intelligent Compound Selection of Anti-cancer Drugs Based on...

引用

2023 International Conference on Intelligent Supercomputing and BioPharma, ISBP 2023

作者： Liu, Xiaoyan Xu, Zhiwei Liu, Guangwen Liu, Limin Inner Mongolia University of Technology College of Data Science and Application Hohhot China Chinese Academy of Sciences Institute of Computing Technology Beijing China

ISBN: (纸本)9798350397789

In the compound selection process of anti-cancer drugs, safety properties such as drug activity and pharmacokinetics need to be considered simultaneously. To construct a more complete and precise drug screening mechanism, this paper proposed an intelligent compound selection method for anti-cancer drugs based on multi-objective optimization. The proposed model is executed in the MapReduce environment. Quantitatively analyze the biological activity of the compound, and qualitatively analyze the properties of pharmacokinetics and safety properties (Absorption, Distribution, Metabolism, Excretion, and Toxicity) to build a multi-objective optimization model. Guided by Pareto optimization theory, the set of non-inferior solution values was determined, and the compound combination that satisfies the optimization goal was found by genetic optimization. On this basis, a Monte Carlo hypothesis test was used to determine the equipped range of the compounds. Finally, an example of the compound selection of anti-breast cancer drugs is given, and the experimental evaluation proves that the algorithm can screen compounds limitedly, which provides a basis for anti-cancer drug synthesis. © 2023 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

R2V-PPI: Enhancing Prediction of Protein-Protein Interactions Using Word2Vec Embeddings and Deep Neural Networks 4

R2V-PPI: Enhancing Prediction of Protein-Protein Interaction...

引用

4th International Conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Oviya, I.R. Sravya N, Shanmukha Raja, Kalpana Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science Engineering Chennai601103 India Yale University Section for Biomedical Informatics and Data Science School of Medicine New HavenCT United States

ISBN: (纸本)9798350343670

Proteins play a crucial role in living organisms, and understanding protein-protein interactions is vital for comprehending their functions and aiding drug discovery. In recent years, advanced deep learning models have been developed to predict protein-protein interactions from sequences. However, these large-scale approaches often suffer from deficiencies, resulting in both false positive and false negative predictions. Traditional encoding methods struggle to effectively represent the semantic meaning of individual residues in protein sequences and their impact on neighbouring residues. To overcome these deficiencies, we propose a novel method named R2V-PPI (Residue-to-Vector embeddings based Protein-Protein Interaction Framework) that effectively represents protein sequences and predicts protein-protein interactions. Inspired by Word2Vec, R2V-PPI learns informative representations of individual amino acid residues, capturing the context and relationships between them in raw protein sequences. These representations provide valuable input features for a downstream deep learning model. Our methodology offers a robust and versatile approach for predicting protein-protein interactions, especially when structural information is limited or unavailable. Evaluation on the S. cerevisiae dataset demonstrates that R2V-PPI outperforms existing state-of-the-art machine learning models. © 2024 IEEE.

关键词： Deep Learning Machine Learning Protein Feature Encoding Protein Protein interaction Protein sequence

来源：评论

学校读者我要写书评

暂无评论

Air Pollutant Prediction Using Shallow Architecture Machine Learning Algorithms 8th

Air Pollutant Prediction Using Shallow Architecture Machine ...

引用

8th World Conference on Smart Trends in Systems Security and Sustainability, WorldS4 2024

作者： Olaifa, Moses Malele, Vusumuzi Department of Computer Systems Engineering Faculty of ICT Tshwane University of Technology Pretoria South Africa Unit of Data Science and Computing Vaal Campus North-West University Vanderbijlpark South Africa

ISBN: (纸本)9789819786947

Over the past few decades, mortality rates associated with air quality pollution have risen in numerous countries around the globe. This pollution stems from different factors such as meteorological conditions, human activities from urban industrialization, vehicular emission, and so on. Air pollution constituents such as NO2, CO, SO, and coarse and fine particulate matter for different locations have been analyzed to learn both correlation and inter-dependency for long and short terms. However, many of these studies overlook datasets collected using low-cost tools and equipment. Most of the time, datasets of this nature are marred with inconsistencies and gaps at irregular intervals. This may render the air pollutant data unsuitable. In order to test the suitability of machine learning algorithms on such dataset, this study conducts a time-series forecast analysis using the prophet algorithm. Two additional models including linear regressor and random forest regressor are trained and tested on the same dataset and a comparative analysis of the three models is performed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

关于权的非交换对称空间

引用

中国科学：数学 2023年第12期53卷 1789-1798页

作者：吐尔德别克 Department of Computing and Data Science Astana IT UniversityAstana 010000Kazakhstan

本文定义一种关于一个给定权的非交换对称空间,讨论该空间的性质,并且证明在等距同构意义下该空间与权的选择无关.进一步地,本文也引入一种非交换对称Hardy空间,研究此Hardy空间的基本性质,并且给出此Hardy空间也在等距同构意义下与权... 详细信息

本文定义一种关于一个给定权的非交换对称空间,讨论该空间的性质,并且证明在等距同构意义下该空间与权的选择无关.进一步地,本文也引入一种非交换对称Hardy空间,研究此Hardy空间的基本性质,并且给出此Hardy空间也在等距同构意义下与权的选择无关.

关键词：局部有限的正规的忠实的权非交换对称空间非交换对称Hardy空间半有限von Neumann代数

来源：评论

学校读者我要写书评

暂无评论

Hash Table Notional Machines: A Comparison of 2D and 3D Representations 2024

Hash Table Notional Machines: A Comparison of 2D and 3D Repr...

引用

1st ACM Virtual Global computing Education Conference V. 1, SIGCSE Virtual 2024

作者： Lewis, Colleen M. Miller, Craig S. Jeuring, Johan Pearce, Janice L. Petersen, Andrew Siebel School of Computing and Data Science University of Illinois Urbana-Champaign UrbanaIL United States School of Computing DePaul University ChicagoIL United States Department of Information and Computing Sciences Utrecht University Utrecht Netherlands Department of Computer Science Berea College BereaKY United States Department of Mathematical and Computational Sciences University of Toronto Mississauga MississaugaON Canada

ISBN: (纸本)9798400705984

Background: Notional machines appear to be an essential aspect of computing education, but there are few papers that identify strengths and weaknesses of particular notional machines. Purpose: This article fills a gap in the notional machine literature by using a randomized controlled trial to compare the effectiveness of different notional machine representations. Methods: Our study used notional machines for two hash table algorithms: chaining and open addressing. Students were randomly assigned a video sequence using either 2D or 3D representations. Findings: We found minimal effect of 2D vs 3D representational form on students' learning and perceptions of helpfulness. Implications: Our paper provides an example of how educational research can inform the design and evaluation of notional machines. © 2024 Owner/Author.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Preserving model privacy for Federated Reinforcement Learning in Complementary Environments 23

Preserving model privacy for Federated Reinforcement Learnin...

引用

15th International Conference on Machine Learning and computing, ICMLC 2023

作者： Xuan, Pengyu Chen, Aiguo Sha, Zexin University of Electronic Science and Technology of China Chengdu China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu China

ISBN: (纸本)9781450398411

Federated reinforcement learning (FRL) uses data from multiple partners interacting with the environment to train a global decision model while maintaining data privacy. In specific situations, it is necessary to protect not only data privacy but also model privacy. That is, our objective is to collaboratively train a global model that can be used privately and independently by the initiator. We refer to this need for model privacy preservation as model monopolization. It allows the task initiator to ensure the privacy of the model during the training process and to own the trained model alone. To the best of our knowledge, model monopolization protection in Federated Reinforcement Learning has not been studied. We propose monopolized federated reinforcement learning in complementary environments via function transformation. We also provide contribution metrics to ensure the sustainability of monopolized federated reinforcement learning and to provide a quantitative basis for task initiators to give back to task participants. The experimental results show that our method achieved model monopolization by training agents in the Grid-world. © 2023 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing lemon grading: an automated CNN-based approach for enhanced quality assessment

引用

International Journal of Information Technology (Singapore) 2024年第7期16卷 4155-4166页

作者： Sanyal, Samriddha Adhikary, Rahul Choudhury, Suvra Jyoti School of Computing and Data Science FLAME University Maharashtra Pune 412115 India Centurion University of Technology and Management Odisha Parlakhemundi 761211 India Indian Institute of Information Technology Maharashtra Nagpur 441108 India

Lemons, renowned for their versatile applications in the culinary world and various industries, have become a staple commodity worldwide. The demand for high-quality lemons continues to soar, underscoring the need for reliable and efficient grading methods. Traditional lemon grading, which is largely reliant on human expertise, often falls prey to subjectivity, human errors, and time-consuming processes. In this paper, we propose a CNN-based lemon grading model to automate and improve the accuracy of lemon quality assessment. The proposed model utilizes CNNs in a modular and sequential fashion for extracting pertinent features from lemon images and categorizing them into distinct quality grades. A comprehensive dataset of lemon images with corresponding quality labels is used to train and validate the model. The experimental results demonstrate the effectiveness of the CNN-based approach in accurately grading lemons, offering a promising solution for enhancing efficiency and objectivity in the lemon grading process. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2024.

关键词： CNN modular organization Deep learning Incremental learning Lemon health detection

来源：评论

学校读者我要写书评

暂无评论

Preventing Fraud in E-tickets Validation Using The 2FA Approach 5

Preventing Fraud in E-tickets Validation Using The 2FA Appro...

引用

5th International Conference on Computer and Applications, ICCA 2023

作者： Alnuaimi, Lolwa Hassan Jaam, Jihad Al John Moores University School of Computing and Data Sciences Dept. of Computer Science Oryx Universal College in Partnership with Liverpool Doha Qatar

ISBN: (纸本)9798350303254

Electronic ticketing (e-ticket) systems employing QR codes or barcodes are essential in the digital era but come with cybersecurity risks like fraud, counterfeiting, and ticket scalping. This study explores the cybersecurity implications of large-scale event e-ticketing, with a focus on comprehending these technologies and improving security. It introduces the Ticket_Events application, which combines online registration and the secure generation of QR-coded electronic tickets. The app mandates QR code scanning at the event venue and encourages the use of location services for enhanced verification, preventing ticket swapping and potential fraud. The primary objective is to create a dependable e-ticketing application centered on ownership verification. In conclusion, the study delves into the intricacies of e-ticketing and barcode scanning, pinpoints challenges, and proposes solutions to fortify the security of digital ticket delivery. © 2023 IEEE.

关键词： Bar codes

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：