检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Miao, Wenjun Pang, Guansong Nguyen, Trong-Tung Fang, Ruohang Zheng, Jin Bai, Xiao School of Computer Science and Engineering Beihang University China School of Computing and Information Systems Singapore Management University Singapore Jiangxi Research Institute Beihang University China

Class incremental learning (CIL) aims to learn a model that can not only incrementally accommodate new classes, but also maintain the learned knowledge of old classes. Out-of-distribution (OOD) detection in CIL is to retain this incremental learning ability, while being able to reject unknown samples that are drawn from different distributions of the learned classes. This capability is crucial to the safety of deploying CIL models in open worlds. However, despite remarkable advancements in the respective CIL and OOD detection, there lacks a systematic and large-scale benchmark to assess the capability of advanced CIL models in detecting OOD samples. To fill this gap, in this study we design a comprehensive empirical study to establish such a benchmark, named OpenCIL. To this end, we propose two principled frameworks for enabling four representative CIL models with 15 diverse OOD detection methods, resulting in 60 baseline models for OOD detection in CIL. The empirical evaluation is performed on two popular CIL datasets with six commonly-used OOD datasets. One key observation we find through our comprehensive evaluation is that the CIL models can be severely biased towards the OOD samples and newly added classes when they are exposed to open environments. Motivated by this, we further propose a new baseline for OOD detection in CIL, namely Bi-directional Energy Regularization (BER), which is specially designed to mitigate these two biases in different CIL models by having energy regularization on both old and new classes. Its superior performance is justified in our experiments. All codes and datasets are open-source at https://***/mala-lab/OpenCIL. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

SPRGAN: Streamlined Progressive Refinement for Adversarial Point Cloud Video Upsampling

SPRGAN: Streamlined Progressive Refinement for Adversarial P...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Zhiyong Liu, Ruyu Wang, Chaochao Zhang, Xianchao Zhang, Jianhua Liu, Xiufeng School of Computer Science and Engineering Tianjin University of Technology Tianjin China School of Information Science and Technology Hangzhou Normal University Hangzhou China Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems Jiaxing University Zhejiang China Department of Technology Management and Economics Technical University of Denmark Lyngby Denmark

ISBN: (纸本)9798350368741

Getting dense, uniform, time-series point cloud data is critical for effective rendering. However, due to the limited computational power of edge devices, existing methods cannot achieve real-time results, which affects the visual quality of the consumer experience. To effectively address this issue, this paper presents a self-supervised adversarial upsampling method for point cloud video streams called SPR-GAN. In the generator, we design the Temporal Iterative Graph module to learn local features for each frame and captures long-range spatial information using three iterations of graph convolution operations. Then the Contextual Temporal Fusion module is developed to merge information between different frames, synthesizing temporal information and enriching the dynamic feature representation of the point cloud. Meanwhile, in the discriminator, we introduce the Efficient Shape module. Through dynamic graph convolution operations and stacked learning, it significantly improves the resolution efficiency of global shape information in point clouds. The final experiments show that the proposed method exhibits high practicality and superiority. The model achieves a good result on both the D-FAUST and DeformingThing4D-Animals datasets. © 2025 IEEE.

关键词： point cloud sequence Point cloud upsampling self-supervised temporal aggregation

来源：评论

学校读者我要写书评

暂无评论

Ontological Aspects of Developing Robust Control systems for Technological Objects

Ontological Aspects of Developing Robust Control Systems for...

引用

3rd International Conference on Intelligent Computing and Optimization, ICO 2020

作者： Lutskaya, Nataliia Vlasenko, Lidiia Zaiets, Nataliia Shtepa, Volodimir Automation and Computer Technologies of Management Systems Automation and Computer Systems National University of Food Technologies Kiev Ukraine Department of Higher Mathematics and Information Technology Polessky State University Pinsk Belarus

ISBN: (纸本)9783030681531

The ontological aspects of designing the efficient control systems of technological objects, which are operating in uncertain environment have been demonstrated in the research work. Design and monitoring of the control system have been outlined as the two basic tasks on the basis of the covered subject and problem domain of the research as well as the life cycle of the system. The subject domain, which consists of the ontology of objects and processes, has been described with the use of the system and ontological approach. The peculiarity of the developed ontological system lies in the knowledge on the uncertainty of technological objects and the conditions of their operation. The ontological system, which underlies the further development of an intelligent decision support system, has been formed alongside with the ontology of objectives. The advantage of the ontology based design lies in the scientific novelty of the knowledge presentation model and the practical relevance for designers, developers, and researchers of the control systems for technological objects operating in uncertain environment. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Harmonizing open banking in the European Union: an analysis of PSD2 compliance and interrelation with cybersecurity frameworks and standards

引用

International Cybersecurity Law Review 2024年第1期5卷 79-120页

作者： Gounari, Marianna Stergiopoulos, George Pipyros, Kosmas Gritzalis, Dimitris Dept. of Information & Communication Systems Engineering University of the Aegean Samos Greece Dept. of Computer Science Philips University Nicosia Cyprus Dept. of Informatics Athens University of Economics & Business Athens Greece

This paper focuses on the security protocols enacted in banking transactions across the European Economic Area (EEA), as stipulated by the Second or Revised Payment Service Directive (commonly referred to as ‘PSD2’ or simply ‘the Directive’). The study aims to comprehensively analyse the implementation and efficacy of these security measures within the specified jurisdiction. The Directive incorporates fundamental rights and obligations that all stakeholders are compelled to adhere to and delineates specific security measures and standards that both traditional banking institutions and third-party providers (TPP) are mandated to implement. In particular, one of the cardinal mandates for banking and financial institutions under PSD2 is the obligation to facilitate third-party access to customer data via open application programming interfaces (API). While this open banking paradigm and the consequent proliferation of data sharing unquestionably bring about various advantages, such as enhanced consumer choice and market competition, they concurrently expose the financial ecosystem to a slew of potential security vulnerabilities and privacy risks. Upon conducting a comprehensive review of the security requirements and measures stipulated under PSD2 and a comparative analysis with essential cybersecurity frameworks and standards (NIS2, Cybersecurity Act, GDPR, ISO 27001:22 and PCI DSS), we have ascertained a discernible lack of harmonisation and clarity concerning the technical security specifications for its effective implementation. This lacuna substantiates the challenges banks face in fully grasping the extensive spectrum of compliance obligations mandated by PSD2. The aim of this research is to offer a valuable contribution to both the comprehension and the pragmatic deployment of security standards in the context of banking transactions, as regulated by the PSD2. The paper serves as a valuable resource for traditional banking institut

关键词：

来源：评论

学校读者我要写书评

暂无评论

The effects of mobile marketing collaborator on consumers' impulse buying behavior in online marketplace during pandemic 6

The effects of mobile marketing collaborator on consumers' i...

引用

6th International Conference on information Management and Technology, ICIMTech 2021

作者： Kusuma, Alvita Vania Daniel, Juan Hasri, Raja Alan Oktavia, Tanty Gaol, Ford Lumban Hosoda, Takaaki Bina Nusantara University School of Information Systems Information Systems Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Advanced Institute of Industrial Technology Decision Science Department Tokyo Japan

ISBN: (纸本)9781665449373

This study analyzes the influence of the COVID-19 pandemic on impulse buying on the marketplace platform in Jakarta. This research is motivated because the COVID-19 pandemic period lasted quite a long time. Therefore, this research was conducted so that it can be useful for entrepreneurs or marketplace sellers during the COVID-19 pandemic. The research method used is descriptive quantitative method. Data collection techniques using questionnaires and literature study. The techniques used in statistical testing include validity testing, reliability testing, and hypothesis testing. When the research was conducted from September 2020 to January 2021. The results obtained were that there was a relationship between variables, such as mobile marketing, discounts, and lifestyle that could affect impulse buying on the marketplace even though they were moderately related. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

E-Business Startup: "universia" As University Collaborator System 8

E-Business Startup: "universia" As University Collaborator S...

引用

8th International Conference on ICT for Smart Society, ICISS 2021

作者： Oktavia, Tanty Kaslie Gaol, Ford Lumban Hosoda, Takaaki Bina Nusantara University School of Information Systems Information Systems Department Jakarta11530 Indonesia Bina Nusantara University Binus Graduate Program-Computer Science Computer Science Department Jakarta11530 Indonesia Advanced Institute of Industrial Technology Decision Science Department Tokyo Japan

ISBN: (纸本)9781665416979

According to Covid 19 pandemic every process has to shifting to collaborate with digital technology. One of the field that pushes to shift is Education field. Undergraduate education level, is one of many strategies to improve people competency. In Indonesia, the number of people has steadily increased. However, they have to improve their level of competency to compete with their competitor. According to this condition, many prospective student difficult to find information that their need to decide a place to study. There are many consideration factors that will involved in this decision. Therefore, in this research will build university collaborator system that can support analysis from prospective student perspective to choose education institution. To build this business design this study involve some analysis such as industrial competition will be using Porter Five Force's and supported by Business Model Canvas to define Universia's business model, as well as financial projections for the next seven years. According to the Porter Five Forces model, the information services market around universities still has a lot of room for new entrants. The results of the business model canvas analysis show that, despite being a newcomer to the sector, Universia has a number of value propositions that its competitors do not. Universia's product will be generated in the web based application. The application will be designed using Object Oriented Analysis and Design (OOAD) in conjunction with the Extreme Programming approach, which includes steps such as planning, designing, coding, and testing. The result of this study is a system collaborator that can be bridge between prospective student and university, so the prospective student can easily find the information that their need to choose university. © 2021 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Integrating Technology and Environmental Policy for Effective Air Quality Monitoring in Indonesia

Integrating Technology and Environmental Policy for Effectiv...

引用

Creative Communication and Innovative Technology (ICCIT), IEEE

作者： Mohammad Ifran Sanni Reza Dani Pramudya Hery Dieng Asep Jamaludin Sondang Visiana Sihotang Ihsan Nuril Hikam Dept. of Computer Systems University of Raharja Tangerang Indonesia Dept. of Information Technology Pandawan Sejahtera Indonesia Tangerang Indonesia Dept. of Information Systems Pelita Harapan University Tangerang Indonesia Dept. of Information Technology Bina Bangsa University Serang Indonesia Dept. of Digital Business Pandawan Sejahtera Indonesia Tangerang Indonesia

ISBN: (数字)9798350367492

ISBN: (纸本)9798350367508

Air quality monitoring is crucial for protecting ecosystems and public health, especially in Indonesia, a country with unique geographical and socio-economic characteristics facing complex environmental challenges. This study examines the multifaceted interactions of various factors affecting Indonesia’s air quality monitoring system, including industrial emissions, vehicular traffic, agricultural activities, and forest fires. Geographic factors like topography, wind patterns, and regional diversity significantly influence pollutant distribution and concentrations. Social and economic dimensions, such as rapid industrialization, urbanization, and population growth, also impact energy consumption patterns and air quality. This research employs a comprehensive methodological approach, combining literature review, data analysis, and the SmartPLS analytical model to understand these complexities. Data were collected from air monitoring agencies and scientific sources, focusing on variables such as industrial activity levels, traffic density, meteorological conditions, urbanization, and health impacts. The SmartPLS model was utilized to analyze complex cause- and-effect relationships between these variables. Results highlight significant variations in air quality across different regions and times, influenced by both environmental and human factors. Advanced sensor technologies and remote monitoring systems are identified as potential solutions to enhance monitoring coverage and accuracy, especially in remote areas. Collaboration between government, academia, and the private sector is emphasized as vital for developing a sustainable and effective air quality monitoring infrastructure. The study provides actionable recommendations for improving Indonesia’s air quality monitoring system, aiming to foster a cleaner and healthier environment. Enhanced monitoring can help identify and mitigate air quality issues, ensuring better public health outcomes and environmental protec

关键词： Climate change Analytical models Urban areas Surfaces Air quality Public healthcare Protection Socioeconomics Monitoring Meteorology

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap: Exploring Cybersecurity Careers for High School Students

Bridging the Gap: Exploring Cybersecurity Careers for High S...

引用

Frontiers in Education (FIE) Conference

作者： Gahangir Hossain Mikyung Shin Mehnaz Afrose Information Science University of North Texas Denton TX USA Special Education Illinois State University Normal IL USA Computer Information Systems West Texas A&M University Canyon USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This paper aims to present a comprehensive pathway for high school students in grades nine to twelve to pursue careers in cybersecurity. In an era described by way of virtual ubiquity, the paper highlights the vital importance of cybersecurity. It explores the demand for cybersecurity specialists, where there is a significant shortage of skilled professionals, and emphasizes the relevance of cybersecurity in safeguarding online sensitive information. The paper also explores key motivators for high school students, such as the allure of ethical hacking, the opportunity for innovative, hassle-fixing, and the promising profession prospects within the subject. There is a discussion about cybersecurity education for high school students, existing educational initiatives, and programs. This way, the paper presents an overview of various career pathways using cybersecurity career pathway tools. There is a discussion about the obstacles which high school students face on a regular basis in terms of cybersecurity, and some proposals about how to overcome those challenges.

关键词： Ethics Engineering profession Education Proposals computer security computer crime Faces

来源：评论

学校读者我要写书评

暂无评论

Preliminary Evaluation of Kyokko for Inter-FPGA Communication Framework CIRCUS

Preliminary Evaluation of Kyokko for Inter-FPGA Communicatio...

引用

IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Kaito Kitazume Norihisa Fujita Ryohei Kobayashi Taisuke Boku Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Center for Computational Sciences University of Tsukuba

In recent years, Field-Programmable Gate Arrays (FPGAs) are gaining attention as computational acceleration devices in the field of high-performance computing. By implementing specialized circuits that can be customiz... 详细信息

ISBN: (数字)9798350383454

ISBN: (纸本)9798350383461

关键词： Conferences High performance computing Circuits Cluster computing Low latency communication Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Architectures: A Performance Evaluation with Crop Yield Prediction Application

arXiv

引用

arXiv 2024年

作者： Mukherjee, Anwesha Buyya, Rajkumar Department of Computer Science Mahishadal Raj College West Bengal Mahishadal721628 India Laboratory School of Computing and Information Systems The University of Melbourne VIC3052 Australia

Federated learning has become an emerging technology for data analysis for IoT applications. This paper implements centralized and decentralized federated learning frameworks for crop yield prediction based on Long Short-Term Memory Network. For centralized federated learning, multiple clients and one server is considered, where the clients exchange their model updates with the server that works as the aggregator to build the global model. For the decentralized framework, a collaborative network is formed among the devices either using ring topology or using mesh topology. In this network, each device receives model updates from the neighbour devices, and performs aggregation to build the upgraded model. The performance of the centralized and decentralized federated learning frameworks are evaluated in terms of prediction accuracy, precision, recall, F1-Score, and training time. The experimental results present that ≥97% and >97.5% prediction accuracy are achieved using the centralized and decentralized federated learning-based frameworks respectively. The results also show that the using centralized federated learning the response time can be reduced by ∼75% than the cloud-only framework. Finally, the future research directions of the use of federated learning in crop yield prediction are explored in this paper. © 2024, CC BY.

关键词： Federated learning

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：