检索结果-内蒙古大学图书馆

4th IEEE International Conference on Electrical, computer, and Energy Technologies, ICECET 2024

作者： Bachani, Viren Roychowdhury, Anish Dasgupta, Abhijit Ei-Alfy, Hazem BSc. Data Science SP Jain School of Global Management Sydney Australia SP Jain School of Global Management Data Science Dept. Sydney Australia SP Jain School of Global Management Data Science Dept. Mumbai India School of Computer Science University of Sydney Sydney Australia Alexandria University Faculty of Engineering Alexandria Egypt

ISBN: (纸本)9798350395914

Image segmentation is a prerequisite to almost all computer vision applications. It enables the extraction of meaningful information from visual inputs by partitioning images into segments with shared features. This review paper begins by outlining different image segmentation tasks. It then surveys a broad spectrum of segmentation techniques, ranging from classical frameworks to deep-learning (DL) architectures. We perform this through a systematic literature analysis across a handful of applications as part of our methodology. A key contribution of our survey is that it elaborates on a few situations where classical approaches outperform DL-based methods in accuracy, along with the added advantage of computational efficiency. In some cases, these findings also provoke interest in revisiting classical methods, prompting strategies that leverage the strengths of both paradigms. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

The Effect of Social Media Influencers on Business Sustainability: Understanding Customer Behavior Change Towards Sustainable Usage Patterns 6

The Effect of Social Media Influencers on Business Sustainab...

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Herlina, Maria Grace Budiharto, Alexandra Li Lukito, Elizabeth Margaretha Iskandar, Karto Management Department BINUS Business School Undergraduate Program Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331539603

The study aims to fill existing research gaps by creating a new framework that explores the impact of social media influencers on sustainable usage patterns, focusing on business sustainability as a mediating factor. In this research, non-probability judgmental and purposive sampling methods were used. Due to the size and distribution of the population, sampling was also chosen based on the researcher's own judgment and experience. Structural equation modeling (SEM) is used as the data analysis method. Path coefficient analysis yielded significant findings. Social media influencers were found to influence business sustainability significantly. Apart from that, social media influencers have a significant negative affect on sustainable usage patterns. Business sustainability also significantly influences sustainability usage patterns, with a powerful influence. This enriches the dynamics of business sustainability, proposing new knowledge about how it influences this relationship. © 2024 IEEE.

关键词： Sustainable development goals

来源：评论

学校读者我要写书评

暂无评论

Beyond Labels and Topics: Discovering Causal Relationships in Neural Topic Modeling 24

Beyond Labels and Topics: Discovering Causal Relationships i...

引用

33rd ACM Web Conference, WWW 2024

作者： Tang, Yi-Kun Huang, Heyan Shi, Xuewen Mao, Xian-Ling School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Data Science and Artificial Intelligence Dongbei University of Finance and Economics Liaoning Dalian China

ISBN: (纸本)9798400701719

Topic models that can take advantage of labels are broadly used in identifying interpretable topics from textual data. However, existing topic models tend to merely view labels as names of topic clusters or as categories of texts, thereby neglecting the potential causal relationships between supervised information and latent topics, as well as within these elements themselves. In this paper, we focus on uncovering possible causal relationships both between and within the supervised information and latent topics to better understand the mechanisms behind the emergence of the topics and the labels. To this end, we propose Causal Relationship-Aware Neural Topic Model (CRNTM), a novel neural topic model that can automatically uncover interpretable causal relationships between and within supervised information and latent topics, while concurrently discovering high-quality topics. In CRNTM, both supervised information and latent topics are treated as nodes, with the causal relationships represented as directed edges in a Directed Acyclic Graph (DAG). A Structural Causal Model (SCM) is employed to model the DAG. Experiments are conducted on three public corpora with different types of labels. Experimental results show that the discovered causal relationships are both reliable and interpretable, and the learned topics are of high quality comparing with eight start-of-the-art topic model baselines. © 2024 ACM.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

CMNEE: A Large-Scale Document-Level Event Extraction dataset based on Open-Source Chinese Military News 30

CMNEE: A Large-Scale Document-Level Event Extraction Dataset...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhu, Mengna Xu, Zijie Zeng, Kaisheng Xiao, Kaiming Wang, Mao Ke, Wenjun Huang, Hongbin Laboratory for Big Data and Decision National University of Defense Technology China School of Computer Science and Engineering Southeast University China Computer Science and Technology Tsinghua University China

ISBN: (纸本)9782493814104

Extracting structured event knowledge, including event triggers and corresponding arguments, from military texts is fundamental to many applications, such as intelligence analysis and decision assistance. However, event extraction in the military field faces the data scarcity problem, which impedes the research of event extraction models in this domain. To alleviate this problem, we propose CMNEE, a large-scale, document-level open-source Chinese Military News Event Extraction dataset. It contains 17,000 documents and 29,223 events, which are all manually annotated based on a pre-defined schema for the military domain including 8 event types and 11 argument role types. We designed a two-stage, multi-turns annotation strategy to ensure the quality of CMNEE and reproduced several state-of-the-art event extraction models with a systematic evaluation. The experimental results on CMNEE fall shorter than those on other domain datasets obviously, which demonstrates that event extraction for military domain poses unique challenges and requires further research efforts. Our code and data can be obtained from https://***/Mzzzhu/CMNEE. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Graph Contrastive Learning for Truth Inference 40

Graph Contrastive Learning for Truth Inference

引用

40th IEEE International Conference on data Engineering, ICDE 2024

作者： Liu, Hao Liu, Jiacheng Tang, Feilong Li, Peng Chen, Long Yu, Jiadi Zhu, Yanmin Gao, Min Yang, Yanqin Hou, Xiaofeng Chinese University of Hong Kong Department of Computer Science and Engineering Hong Kong East China Normal University School of Data Science and Engineering Shanghai China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China University of Aizu School of Computer Science and Engineering Japan Simon Fraser University School of Computing Science Canada

ISBN: (纸本)9798350317152

Crowdsourcing has become a popular paradigm for collecting large-scale labeled datasets by leveraging numerous annotators. However, these annotators often provide noisy labels due to varying expertise. Truth inference aims to infer accurate consensus labels from noisy crowdsourced annotations. Existing approaches rely heavily on hand-engineered assumptions or ground truth data, limiting their applicability. To address this, we propose GOVERN, a graph contrastive learning framework for truth inference without such external supervision. GOVERN employs a novel graph data augmentation strategy to generate views capturing worker coordination patterns. A contrastive objective then encourages invariant representations across views, enabling the discovery of features related to the hidden consensus. Further, a label correction method based on k-nearest neighbors refines noisy pseudo-labels to supervise model training. Comprehensive experiments on 9 real-world datasets demonstrate that GOVERN outperforms state-of-the-art truth inference techniques. © 2024 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

CrossFi: A Cross Domain Wi-Fi Sensing Framework Based on Siamese Network

引用

IEEE Internet of Things Journal 2025年第12期12卷 20138-20155页

作者： Zhao, Zijian Chen, Tingwei Cai, Zhijie Li, Xiaoyang Li, Hang Chen, Qimei Zhu, Guangxu Shenzhen Research Institute of Big Data Shenzhen518115 China Sun Yat-sen University School of Computer Science and Engineering Guangzhou510275 China Wuhan University School of Electronic Information Wuhan430072 China

In recent years, Wi-Fi sensing has garnered significant attention due to its numerous benefits, such as privacy protection, low cost, and penetration ability. Extensive research has been conducted in this field, focusing on areas, such as gesture recognition, people identification, and fall detection. However, many data-driven methods encounter challenges related to domain shift, where the model fails to perform well in environments different from the training data. One major factor contributing to this issue is the limited availability of Wi-Fi sensing datasets, which makes models learn excessive irrelevant information and over-fit to the training set. Unfortunately, collecting large-scale Wi-Fi sensing datasets across diverse scenarios is a challenging task. To address this problem, we propose CrossFi, a siamese network-based approach that excels in both in-domain scenario and cross-domain scenario, including few-shot, zero-shot scenarios, and even works in few-shot new-class scenario where testing set contains new categories. The core component of CrossFi is a sample-similarity calculation network called CSi-Net, which improves the structure of the siamese network by using an attention mechanism to capture similarity information, instead of simply calculating the distance or cosine similarity. Based on it, we develop an extra Weight-Net that can generate a template for each class, so that our CrossFi can work in different scenarios. Experimental results demonstrate that our CrossFi achieves state-of-the-art performance across various scenarios. In gesture recognition task, our CrossFi achieves an accuracy of 98.17% in in-domain scenario, 91.72% in one-shot cross-domain scenario, 64.81% in zero-shot cross-domain scenario, and 84.75% in one-shot new-class scenario. © 2014 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Joint DRL and ASL-Based 'Cloud-Edge-End' Collaborative Caching Optimization for Metaverse Scenarios 30

Joint DRL and ASL-Based 'Cloud-Edge-End' Collaborative Cachi...

引用

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Wan, Zheng Zhao, Shenglu Dong, Xiaogang Huang, Zhekai Tan, Yifeng Jiangxi University of Finance and Economics School of Computer and Artificial Intelligence Nanchang China Jiujiang University School of Computer and Big Data Science Jiujiang China

ISBN: (纸本)9798331515966

With the emergence of the Metaverse concept, the rendering and transmission of 3D virtual scenes demand high-bandwidth, high-quality real-time rendering technology, as well as ultra-reliable low-latency communication (URLLC). However, the current 5G network technology faces unprecedented challenges. The 3D Gaussian Splatting technique renders realistic scenes from sparse input views, providing a novel solution to these challenges. This paper proposes a cloud-edge-end collaborative caching optimization scheme based on deep reinforcement learning and asynchronous federated learning (termed Gaussian Splatting Actor-Critic, GSAC) for 3D Gaussian Splatting rendering near terminals. This scheme leverages asynchronous federated learning technology to predict user behavior trajectories in real time while ensuring user data privacy. It integrates the ActorCritic strategy of deep reinforcement learning and graph convolutional network (GCN) technology to dynamically adjust caching strategies, thereby improving cache hit rates and reducing cache switching frequency. Simulation experiments demonstrate that compared to existing technologies, the GSAC scheme significantly outperforms in terms of target sub-scenario cache hit rates and cache switching frequency. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

So Far Yet So Near: Time Series data Augmentation with Exploring non-Semantic Boundaries based on Reinforcement Learning

So Far Yet So Near: Time Series Data Augmentation with Explo...

引用

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

作者： Li, Haoran Zhang, Zhibo Kang, Jiarong Jiang, Xun Gong, Xiaoli Zhang, Jin Sun, Zhe Cichocki, Andrzej College of Computer Science Nankai University Tianjin China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Faculty of Medicine Faculty of Health Data Science Juntendo University Japan Systems Research Institute Polish Academy of Science Warsaw Poland

ISBN: (纸本)9798350368741

data augmentation effectively expands feature distribution in time series classification, enhancing downstream task performance. However, existing techniques often fail to maintain semantic consistency between augmented and original time series data, causing label noise and thereby degrading downstream task performance. We argue that data augmentation should preserve time series semantic consistency and expand the non-semantic information space. In this paper, we reformulate data augmentation as a semantic path planning problem between original data and augmented data, modeled as a Markov Decision Process (MDP). We propose a reinforcement learning-based algorithm (RL) named FreqSYN, where the action space is defined by a set of learnable Gaussian kernels that perturbs the frequency domain of the original data to generate augmented samples. The confidence coefficients of augmented data in semantically relevant classification tasks are used as a reward to iteratively refine the FreqSYN. Our method is validated across four datasets, achieving state-of-the-art performance, with a 2% improvement in F1 score over the SimPSI method. The code and models are available at https://***/NKU-EmbeddedSystem/FreqSYN. © 2025 IEEE.

关键词： data argumentation frequency domain augmentation Gaussian kernel prediction time series

来源：评论

学校读者我要写书评

暂无评论

Cosmetics Recommendation System Based on Ingredients Using Cosine Similarity

Cosmetics Recommendation System Based on Ingredients Using C...

引用

data science and Its Applications (ICoDSA), International Conference on

作者： Sekar Alisha Firdaus Laksmi Dwi Nurmuthia Raina Imtiyaz Alexander Agung Santoso Gunawan Karli Eka Setiawan Data Science Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350365351

ISBN: (纸本)9798350365368

In the rapidly evolving beauty industry, consumers are often bombarded with an overwhelming array of skincare brands and products, making the quest for the perfect skincare regimen a daunting task. This saturation of the market not only confuses consumers but also poses the risk of resource wastage and potential skin damage due to incompatible ingredient combinations. To mitigate these challenges, our research presents an innovative recommendation system designed to streamline the product selection process. Utilizing the principle of cosine similarity, our methodology involves a detailed analysis of the ingredients contained in various skincare products. A quantitative foundation for evaluating ingredient lists of various skincare products is provided by cosine similarity, a mathematical metric that evaluates the similarity between two non-zero vectors by computing the cosine of the angle between them. Our algorithm generates customized product recommendations by thoroughly comprehending the intricate interactions among different constituents. This bespoke approach simplifies the decision-making process for consumers, enabling them to make well-informed choices that cater to their unique skin health needs. The effectiveness of our recommendation system is validated through comprehensive user feedback, demonstrating its potential to redefine the paradigm of personalized skincare recommendations within the beauty industry. Through providing customers with critical information and encouraging a culture of knowledgeable choice, we see a time when customized skincare products will not only increase customer satisfaction but also brand loyalty, which will be a big step toward the democratization of customized skincare.

关键词： Industries Measurement Deep learning Diversity methods Skin Vectors Software

来源：评论

学校读者我要写书评

暂无评论

Automated Adversarial-Attack Removal with SafetyNet Using ADGIT

Automated Adversarial-Attack Removal with SafetyNet Using AD...

引用

International Conference on Smart Computing & Communications (ICSCC)

作者： Steven Halim Arvio Anandi Vyos Devin Alexander Agung Santoso Gunawan Karli Eka Setiawan Data Science Program Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798350363104

ISBN: (纸本)9798350363111

In the realm of artificial intelligence (AI), a notable challenge has surfaced: adversarial attacks, these attacks involve altering input data to mislead AI models. Developing defensive measures against adversarial attacks is necessary for a more reliable AI system to protect its users from potential harm. In response to the risk of adversarial attacks, this study aims to mitigate the risk of such attacks, especially in image classification tasks, by proposing Adversarial Detection Guided Input Transformation (ADGIT) as an architecture designed to handle such attacks. In this study, the author will experiment with creating such architecture and measure the quality of the proposed technique. ADGIT works by utilizing SafetyNet as an adversarial detector to detect and cleanse adversarial attacks. The author concludes that the proposed technique could improve robustness against adversarial attacks increasing consistent prediction accuracy from 43% to 60% and reconstructing adversarial input images to be more similar to their unperturbed version, with reconstructed images' PSNR score on 0.007 perturbation increased from 43.1182 to 89.0999. The technique proposed could be used as a new defensive measure and improving robustness against adversarial attacks. Although ADGIT is capable of handling adversarial samples, ADGIT has a drawback in performance speed due to the extra preprocessing step.

关键词： Accuracy Perturbation methods Detectors computer architecture Robustness data models Security Artificial intelligence Image reconstruction Image classification

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：