检索结果-内蒙古大学图书馆

A Paradigm Shift to Causal Model-Driven Decision-Making With Generative AI 13th

A Paradigm Shift to Causal Model-Driven Decision-Making Wit...

13th International Conference on AI and Multimodal Services, AIMS 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： He, Sheng Ning, Yishuang Zhang, Liang-Jie Lei, Kai National Engineering Research Center for Supporting Software of Enterprise Internet Services Shenzhen518057 China Kingdee Research Kingdee International Software Group Co. Ltd. Shenzhen518057 China College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Peking University Shenzhen518055 China

ISBN: (纸本)9783031776809

In recent years, the rise of big data has popularized data-driven decision-making. However, the interpretability shortcomings of artificial intelligence (AI) models limit their reliability for critical decisions. This paper proposes a paradigm shift from conventional data-driven to causal model-driven decision-making, leveraging advancements in causal inference and large language models (LLMs). By applying the capabilities of generative AI, this paradigm shift enables the fusion of extensive domain knowledge, facilitating the development of causal models that capture the complexity of real-world systems and problems. The model-driven approach provides a better understanding of the causal mechanisms, relationships, and dynamics compared to correlational data-driven methods. Moreover, we introduce the concept of a composable business model based on modular causal components. We present a methodology for constructing robust causal model-driven decision frameworks, emphasizing the comprehensive utilization of generative AI to incorporate domain knowledge with causal inferences. Through an in-depth analysis of case studies across multiple domains, this model-driven approach empirically showcases its potential to improve decision quality, optimize resource allocation, and enhance process efficiency. Additionally, we critically discuss future research directions and challenges in the evolutionary trajectory of causal model-driven decision-making. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Pre-trained SAM as data augmentation for image segmentation

引用

CAAI Transactions on Intelligence Technology 2025年第1期10卷 268-282页

作者： Junjun Wu Yunbo Rao Shaoning Zeng Bob Zhang Yangtze Delta Region Institute(Huzhou) University of Electronic Science and Technology of ChinaHuzhouChina School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengduChina Pattern Analysis and Machine Intelligence Research Group Department of Computer and Information ScienceUniversity of MacaoMacaoChina

Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the ***,data augmentation mainly involved some simple transformations of ***,in order to increase the diversity and complexity of data,more advanced methods appeared and evolved to sophisticated generative ***,these methods required a mass of computation of training or *** this paper,a novel training-free method that utilises the Pre-Trained Segment Anything Model(SAM)model as a data augmentation tool(PTSAM-DA)is proposed to generate the augmented annotations for *** the need for training,it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved *** this way,annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation *** comparative experiments on three datasets are conducted,including an in-house dataset,ADE20K and *** this in-house dataset,namely Agricultural Plot Segmentation Dataset,maximum improvements of 3.77%and 8.92%are gained in two mainstream metrics,mIoU and mAcc,***,large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.

关键词： data augmentation image segmentation large model segment anything model

来源：评论

学校读者我要写书评

暂无评论

Connectivity in the era of the (I)IoT: about security, features and limiting factors of reconfigurable intelligent surfaces

引用

Discover Internet of Things 2023年第1期3卷 16页

作者： Lipps, Christoph Herbst, Jan Klingel, Steffen Franke, Lars Wolff, Alexander Rüb, Matthias Reddy, Rekha Rahm, Marco Schotten, Hans Dieter Intelligent Networks Research Group German Research Center for Artificial Intelligence Kaiserslautern67663 Germany Institute for Wireless Communication and Radio Positioning RPTU Kaiserslautern-Landau Kaiserslautern67663 Germany Department of Electrical and Computer Engineering Research Center OPTIMAS RPTU Kaiserslautern-Landau Kaiserslautern67663 Germany

What are the key drivers of the (Industrial) Internet of Things ((I)IoT)? Alongside the interconnection of the various devices, sensors, and actuators, it is above all the data collected and transmitted that is of particular significance, the (I)IoT itself is the source and recipient of various types of data. Within this, there are two main aspects that need to be considered: (i) the transmission of data with appropriate latency and reliability requirements, and (ii) the safeguarding of this data. Both requirements are taken into account during the development of the Sixth Generation (6G) Wireless Systems. This is conceived to deliver higher data rates, reduced cost deployment, and enhanced reliability while providing universal connectivity. Hence, to assist such a vast network domain, (new) 6G-enabling technologies are developed, which include Reconfigurable Intelligent Surfaces (RISs), that are capable of modifying and reconfiguring the wireless propagation channels. This work describes concepts on how security, in particular Physical Layer Security (PhySec) methods, can be supported by RISs. Furthermore, an effective impedance surface model is presented, allowing efficient simulation of beamsplitting and shaping properties of RISs. Finally, the applicability of the use cases is mentioned, with a particular focus on Visible Light Communication (VLC). © The Author(s) 2023.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Inclusiveness of Artificial Intelligence software in Enhancing Project Management Efficiency - A review and examples of quantitative measurement methods

Evaluating the Inclusiveness of Artificial Intelligence Soft...

引用

2024 International Conference on Artificial Intelligence, computer, Data Sciences, and Applications, ACDSA 2024

作者： Alevizos, Vasileios Georgousis, Ilias Simasiku, Akebu Messinis, Antonis Karypidou, Sotiria Malliarou, Dimitra Karolinska Institute Department of Learning Informatics Managament and Ethics Stockholm Sweden International Hellenic University Mlv Research Group Department of Computer Science Kavala Greece Zambia University Department of Computer Software Engineering Ndola Zambia Greece International Hellenic University Mlv Research Group Department of Computer Science Greece IntelliSolutions Athens Greece

ISBN: (纸本)9798350394528

The escalating integration of Artificial Intelligence (AI) in various domains, especially Project Management (PM), has brought to light the imperative need for inclusivity in AI systems. This paper investigates the role of AI software in augmenting both the inclusiveness and efficiency within the realm of PM. The research pivots around specific criteria that define and measure the inclusiveness of AI in PM, highlighting how AI, when developed with inclusiveness in mind, can significantly enhance project outcomes. However, there are inherent challenges in achieving this inclusiveness, primarily due to biases embedded in AI learning databases and the design and development processes of AI systems. The study offers a comprehensive examination of AI's potential to revolutionize PM by enabling managers to concentrate more on people-centric aspects of their work. This is achieved through AI's ability to perform tasks such as data collection, reporting, and predictive analysis more consistently and efficiently than human counterparts. However, the incorporation of AI in PM extends beyond mere efficiency;it represents a paradigm shift in the epistemology of PM, calling for a deeper understanding of AI's role and impact on society. Despite these advantages, the adoption of AI comes with significant challenges, particularly in terms of bias and inclusiveness. Biased AI learning databases, which use shared and reusable datasets, often perpetuate initially discriminatory algorithms. Moreover, unconscious biases and stereotypes of AI designers, developers, and trainers can inadvertently influence the behavior of the AI systems they create. This necessitates a paradigmatic shift in how AI systems are developed and governed to ensure they do not replicate or exacerbate existing social inequalities. The research proposes a methodological approach involving the development of criteria for inclusion and exclusion, alongside data extraction, to evaluate the inclusiveness and efficienc

关键词： Project management

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Federated Broad Learning for Privacy-Preserved Knowledge Sharing in the RIS-Aided Internet of Vehicles

引用

engineering 2024年第2期33卷 178-189页

作者： Xiaoming Yuan Jiahui Chen Ning Zhang Qiang(John)Ye Changle Li Chunsheng Zhu Xuemin Sherman Shen Qinhuangdao Branch Campus Northeastern UniversityQinhuangdao 066004China State Key Laboratory of Integrated Services Networks&the Research Institute of Smart Transportation Xidian UniversityXi’an 710071China Department of Electrical and Computer Engineering University of WindsorWindsorON N9B 3P4Canada Department of Electrical and Software Engineering University of CalgaryCalgaryAB T2N 1N4Canada SUSTech Institute of Future Networks Southern University of Science and TechnologyShenzhen 518055China Department of Electrical and Computer Engineering University of WaterlooWaterlooON N2L 3G1Canada

High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility *** order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client *** enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for *** problem is decoupled into two convex *** to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration *** on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their *** simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.

关键词： Knowledge sharing Internet of Vehicles Federated learning Broad learning Reconfigurable intelligent surfaces Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical vectorization for facial images

引用

Computational Visual Media 2024年第1期10卷 97-118页

作者： Qian Fu Linlin Liu Fei Hou Ying He School of Computer Science and Engineering Nanyang Technological University639798SingaporeSingapore Data61 Commonwealth Scientific and Industrial Research OrganisationSydney2015Australia Interdisciplinary Graduate School Nanyang Technological University and Alibaba Group639798SingaporeSingapore State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing100190China University of Chinese Academy of Sciences Beijing100049China

The explosive growth of social media means portrait editing and retouching are in high *** portraits are commonly captured and stored as raster images,editing raster images is non-trivial and requires the user to be highly *** at developing intuitive and easy-to-use portrait editing tools,we propose a novel vectorization method that can automatically convert raster images into a 3-tier hierarchical *** base layer consists of a set of sparse diffusion curves(DCs)which characterize salient geometric features and low-frequency colors,providing a means for semantic color transfer and facial expression *** middle level encodes specular highlights and shadows as large,editable Poisson regions(PRs)and allows the user to directly adjust illumination by tuning the strength and changing the shapes of *** top level contains two types of pixel-sized PRs for high-frequency residuals and fine details such as pimples and *** train a deep generative model that can produce high-frequency residuals *** to the inherent meaning in vector primitives,editing portraits becomes easy and *** particular,our method supports color transfer,facial expression editing,highlight and shadow editing,and automatic *** quantitatively evaluate the results,we extend the commonly used FLIP metric(which measures color and feature differences between two images)to consider *** new metric,illumination-sensitive FLIP,can effectively capture salient changes in color transfer results,and is more consistent with human perception than FLIP and other quality measures for portrait *** evaluate our method on the FFHQR dataset and show it to be effective for common portrait editing tasks,such as retouching,light editing,color transfer,and expression editing.

关键词： face editing vectorization Poisson editing color transfer illumination editing expression editing

来源：评论

学校读者我要写书评

暂无评论

Privacy engineering in the Wild: Understanding the Practitioners' Mindset, Organizational Aspects, and Current Practices

引用

IEEE Transactions on software engineering 2023年第9期49卷 4324-4348页

作者： Iwaya, Leonardo Horn Babar, Muhammad Ali Rashid, Awais JoondalupWA6027 Australia Research Group Department of Mathematics and Computer Science Karlstad65188 Sweden The University of Adelaide Centre for Research on Engineering Software Technologies AdelaideSA5005 Australia University of Bristol Bristol Cyber Security Group REPHRAIN: National Research Centre on Privacy Harm Reduction and Adversarial Influence Online Department of Computer Science BristolBS8 1QU United Kingdom

Privacy engineering, as an emerging field of research and practice, comprises the technical capabilities and management processes needed to implement, deploy, and operate privacy features and controls in working systems. For that, software practitioners and other stakeholders in software companies need to work cooperatively toward building privacy-preserving businesses and engineering solutions. Significant research has been done to understand the software practitioners' perceptions of information privacy, but more emphasis should be given to the uptake of concrete privacy engineering components. This research delves into the software practitioners' perspectives and mindset, organizational aspects, and current practices on privacy and its engineering processes. A total of 30 practitioners from nine countries and backgrounds were interviewed, sharing their experiences and voicing their opinions on a broad range of privacy topics. The thematic analysis methodology was adopted to code the interview data qualitatively and construct a rich and nuanced thematic framework. As a result, we identified three critical interconnected themes that compose our thematic framework for privacy engineering 'in the wild': (1) personal privacy mindset and stance, categorised into practitioners' privacy knowledge, attitudes and behaviours;(2) organizational privacy aspects, such as decision-power and positive and negative examples of privacy climate;and, (3) privacy engineering practices, such as procedures and controls concretely used in the industry. Among the main findings, this study provides many insights about the state-of-the-practice of privacy engineering, pointing to a positive influence of privacy laws (e.g., EU General Data Protection Regulation) on practitioners' behaviours and organizations' cultures. Aspects such as organizational privacy culture and climate were also confirmed to have a powerful influence on the practitioners' privacy behaviours. A conducive environment f

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Considerations in Prioritizing for Efficiently Refactoring the Data Clumps Model Smell: A Preliminary Study 19

Considerations in Prioritizing for Efficiently Refactoring t...

引用

19th International Conference on Evaluation of Novel Approaches to software engineering, ENASE 2024

作者： Baumgartner, Nils Iyenghar, Padma Pulvermüller, Elke Software Engineering Research Group School of Mathematics/Computer Science/Physics Osnabrück University Osnabrück49090 Germany innotec GmbH Hornbergstrasse 45 Filderstadt70794 Germany Faculty of Engineering and Computer Science HS Osnabrueck Osnabrück49009 Germany

ISBN: (纸本)9789897586965

This paper delves into the importance of addressing the data clumps model smell, emphasizing the need for prioritizing them before refactoring. Qualitative and quantitative criteria for identifying data clumps are outlined, accompanied by a systematic, simple but effective approach involving a weighted attribute system with threshold-based priority assignment. The paper concludes with an experimental evaluation of the proposed method, offering insights into critical areas for developers and contributing to improved code maintenance practices and overall quality. The approach presented provides a practical guide for enhancing software system quality and sustainability. © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： software design

来源：评论

学校读者我要写书评

暂无评论

COSIS: An AI-Enabled Digital Transformation Framework Integrating Large Language Models and Key Performance Indicators 21st

COSIS: An AI-Enabled Digital Transformation Framework Integr...

引用

21st International Conference on Services Computing, SCC 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Zhang, Liang-Jie Chen, Huan He, Sheng Li, Changhu Chen, Junyang Zhang, Haodi Du, Wenfeng Center for AI Services Computing College of Computer Science and Software Engineering Shenzhen University Shenzhen China SF Technology Co. Ltd. Shenzhen China Kingdee Research Kingdee International Software Group Co. Ltd. Shenzhen China

ISBN: (纸本)9783031769993

The rapid advancement of Artificial Intelligence (AI) and Large Language Models (LLMs) has significantly transformed various sectors of society, compelling enterprises to undertake comprehensive digital transformations to remain competitive in the AI era. This paper introduces COSIS, an AI-enabled digital trans-formation framework comprising five key dimensions: Culture, Operation, Strategy, Innovation, and Service. The COSIS framework provides a structured approach for enterprises to navigate the complexities of digital transformation by integrating AI and LLM technologies into their core functions. For each dimension, the paper identifies specific key performance indicators (KPIs) to measure the effectiveness of AI-enabled transformations. These KPIs enable enterprises to quantitatively assess progress and outcomes, ensuring alignment with strategic objectives and facilitating continuous improvement. Additionally, the paper discusses the implications of AI and LLM technologies on enterprise management team building in the AI era. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Human resource management

来源：评论

学校读者我要写书评

暂无评论

Anomaly-Based Intrusion DetectionModel Using Deep Learning for IoT networks

引用

computer Modeling in engineering & Sciences 2024年第10期141卷 823-845页

作者： Muaadh A.Alsoufi Maheyzah Md Siraj Fuad A.Ghaleb Muna Al-Razgan Mahfoudh Saeed Al-Asaly Taha Alfakih Faisal Saeed Faculty of Computing Universiti Teknologi Malaysia(UTM)Johor Bahru81310Malaysia DAAI Research Group College of Computing and Digital TechnologyBirmingham City UniversityBirminghamB47XGUK Department of Software Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11345Saudi Arabia

The rapid growth of Internet of Things(IoT)devices has brought numerous benefits to the interconnected ***,the ubiquitous nature of IoT networks exposes them to various security threats,including anomaly intrusion *** addition,IoT devices generate a high volume of unstructured *** intrusion detection systems often struggle to cope with the unique characteristics of IoT networks,such as resource constraints and heterogeneous data *** the unpredictable nature of network technologies and diverse intrusion methods,conventional machine-learning approaches seem to lack *** numerous research domains,deep learning techniques have demonstrated their capability to precisely detect *** study designs and enhances a novel anomaly-based intrusion detection system(AIDS)for IoT ***,a Sparse Autoencoder(SAE)is applied to reduce the high dimension and get a significant data representation by calculating the reconstructed ***,the Convolutional Neural Network(CNN)technique is employed to create a binary classification *** proposed SAE-CNN approach is validated using the Bot-IoT *** proposed models exceed the performance of the existing deep learning approach in the literature with an accuracy of 99.9%,precision of 99.9%,recall of 100%,F1 of 99.9%,False Positive Rate(FPR)of 0.0003,and True Positive Rate(TPR)of *** addition,alternative metrics,such as training and testing durations,indicated that SAE-CNN performs better.

关键词： IoT anomaly intrusion detection deep learning sparse autoencoder convolutional neural network

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：