检索结果-内蒙古大学图书馆

ieee symposium on Visual Languages and Human-Centric Computing (VL/HCC)

作者： Nelson-Fromm, Tamara Univ Michigan Dept Comp Sci & Engn Ann Arbor MI 48109 USA

ISBN: (纸本)9781665445924

Social studies teachers regularly use digital tools to teach data literacy - the ability to understand, analyze and interpret data visualizations including charts, graphs, and timelines. These digital tools, such as websites for creating charts and graphs, aid in teaching data literacy as they allow students and teachers to visualize large numerical data sets that would be difficult to manipulate without the use of computational tools. However, the data visualization tools that are easily accessible to teachers are rarely built specifically for teaching and require methods for inputting or manipulating data with which teachers are unfamiliar. I propose that by examining how K-12 teachers understand data representations and building tools which scaffold that understanding, digital data visualization tools can be created that will be more usable by teachers and more likely to be adopted into classroom use.

关键词： visualization Education Buildings data visualization Tools

来源：评论

学校读者我要写书评

暂无评论

Developing Visualisations to Enhance an Insider Threat Product: A Case Study

Developing Visualisations to Enhance an Insider Threat Produ...

引用

ieee symposium on visualization for Cyber Security (VizSec)

作者： Graham, Martin Kukla, Robert Mandrychenko, Oleksii Hart, Darren Kennedy, Jessie Edinburgh Napier Univ Edinburgh Midlothian Scotland FortiNet Ltd Sunnyvale CA 94086 USA

ISBN: (纸本)9781665420853

This paper describes the process of developing data visualisations to enhance a commercial software platform for combating insider threat, whose existing UI, while perfectly functional, was limited in its ability to allow analysts to easily spot the patterns and outliers that visualisation naturally reveals. We describe the design and development process, proceeding from initial tasks/requirements gathering, understanding the platform's data formats, the rationale behind the visualisations' design, and then refining the prototype through gathering feedback from representative domain experts who are also current users of the software. Through a number of example scenarios, we show that the visualisation can support the identified tasks and aid analysts in discovering and understanding potentially risky insider activity within a large user base.

关键词： Human-centered computing visualization visualization application domains Visual Analytics Security and privacy Human and societal aspects of security and privacy Usability in security and privacy

来源：评论

学校读者我要写书评

暂无评论

Unrolling SGD: Understanding Factors Influencing Machine Unlearning 7

Unrolling SGD: Understanding Factors Influencing Machine Unl...

引用

7th ieee European symposium on Security and Privacy (ieee EuroS and P)

作者： Thudi, Anvith Deza, Gabriel Chandrasekaran, Varun Papernot, Nicolas Univ Toronto Toronto ON Canada Vector Inst Toronto ON Canada Univ Wisconsin Madison WI 53706 USA

ISBN: (纸本)9781665416146

Machine unlearning is the process through which a deployed machine learning model is made to forget about some of its training data points. While naively retraining the model from scratch is an option, it is almost always associated with large computational overheads for deep learning models. Thus, several approaches to approximately unlearn have been proposed along with corresponding metrics that formalize what it means for a model to forget about a data point. In this work, we first taxonomize approaches and metrics of approximate unlearning. As a result, we identify verification error, i.e., the l(2) difference between the weights of an approximately unlearned and a naively retrained model, as an approximate unlearning metric that should be optimized for as it subsumes a large class of other metrics. We theoretically analyze the canonical training algorithm, stochastic gradient descent (SGD), to surface the variables which are relevant to reducing the verification error of approximate unlearning for SGD. From this analysis, we first derive an easy-to-compute proxy for verification error (termed unlearning error). The analysis also informs the design of a new training objective penalty that limits the overall change in weights during SGD and as a result facilitates approximate unlearning with lower verification error. We validate our theoretical work through an empirical evaluation on learning with CIFAR-10, CIFAR-100, and IMDB sentiment analysis.

关键词： Measurement Training Deep learning Sentiment analysis Computational modeling Training data Stochastic processes

来源：评论

学校读者我要写书评

暂无评论

CoviFL: Edge-Assisted Federated Learning for Remote COVID-19 Detection in an AIoMT Framework 27

CoviFL: Edge-Assisted Federated Learning for Remote COVID-19...

引用

ieee symposium on Computers and Communications (ISCC)

作者： Bhattacharya, Aneesh Rana, Risav Udutalapally, Venkanna Das, Debanjan IIIT Naya Raipur Dept CSE Naya Raipur India IIIT Naya Raipur Dept ECE Naya Raipur India

ISBN: (纸本)9781665497923

Detection of COVID-19 has been a global challenge due to the lack of proper resources across all regions. Recently, research has been conducted for non-invasive testing of COVID-19 using an individual's cough audio as input to deep learning models. However, these methods do not pay sufficient attention to resource and infrastructure constraints for real-life practical deployment and the lack of focus on maintaining user data privacy makes these solutions unsuitable for large-scale use. We propose a resource-efficient CoviFL framework using an AIoMT approach for remote COVID-19 detection while maintaining user data privacy. Federated learning has been used to decentralize the CoviFL CNN model training and test the COVID-19 status of users with an accuracy of 93.01% on portable AIoMT edge devices. Experiments on real-world datasets suggest that the proposed CoviFL solution is promising for large-scale deployment even in resource and infrastructure-constrained environments making it suitable for remote COVID-19 detection.

关键词： AIoMT federated learning e-healthcare COVID-19 detection data privacy resource-efficient cough sound analysis

来源：评论

学校读者我要写书评

暂无评论

BABot: A Framework for the LLM-Based Chatbot Supporting Business Analytics in e-Commerce 16th

BABot: A Framework for the LLM-Based Chatbot Supporting Busi...

引用

16th International Conference on Computational Collective Intelligence (ICCCI)

作者： Gia Thinh Ngo Tran Thang Le Dinh Cuong Pham-Nguyen Univ Sci Fac Informat Technol Ho Chi Minh City Vietnam Vietnam Natl Univ Ho Chi Minh City Vietnam Univ Quebec Trois Rivieres Sch Business Quebec City PQ Canada

ISBN: (纸本)9783031708152;9783031708169

In recent times, there has been a surge in the use of chatbots built from large Language Models (LLMs). By leveraging text generation capabilities instead of being confined to a predefined script, LLM-based chatbots have gained popularity and exerted a significant influence on the development of chatbot technology. This paper presents a framework for a chatbot that conducts conversations about business analytics in e-commerce. The framework is based on GPT-4, an LLM model capable of generating responses to assist users in deriving business insights from data and making informed decisions. The proposed framework is constructed using a process that combines several techniques for data aggregation, data visualization, and insight generation incorporating with various prompt templates. It is implemented by integrating into Trivi, a customer-intelligent platform for SMEs. An experiment was carried out to evaluate its performance, using different datasets, revealing that this approach is slightly better than previous works.

关键词： LLM-based Chatbot Framework data analysis e-Commerce

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network Based Audio Reinforcement for Computer Assisted Rote Learning

引用

ieee ACCESS 2023年 11卷 39466-39483页

作者： Supitayakul, Parisa Yucel, Zeynep Monden, Akito Okayama Univ Grad Sch Nat Sci & Technol Okayama 7008530 Japan

The dual-channel assumption of the cognitive theory of multimedia learning suggests that importing a large amount of information through a single (visual or audio) channel overloads that channel, causing partial loss of information, while importing it simultaneously through multiple channels relieves the burden on them and leads to the registration of a larger amount of information. In light of such knowledge, this study investigates the possibility of reinforcing visual stimuli with audio for supporting e-learners in memorization tasks. Specifically, we consider three kinds of learning material and two kinds of audio stimuli and partially reinforce each kind of material with each kind of stimuli in an arbitrary way. In a series of experiments, we determine the particular type of audio, which offers the highest improvement for each kind of material. Our work stands out as being the first study investigating the differences in memory performance in relation to different combinations of learning content and stimulus. Our key findings from the experiments are: (i) E-learning is more effective in refreshing memory rather than studying from scratch, (ii) Non-informative audio is more suited to verbal content, whereas informative audio is better for numerical content, (iii) Constant audio triggering degrades learning performance and thus audio triggering should be handled with care. Based on these findings, we develop an ANN-based estimator to determine the proper moment for triggering audio (i.e. when memory performance is estimated to be declining) and carry out follow-up experiments for testing the integrated framework. Our contributions involve (i) determination of the most effective audio for each content type, (ii) estimation of memory deterioration based on learners' interaction logs, and (iii) the proposal of improvement of memory registration through auditory reinforcement. We believe that such findings constitute encouraging evidence the memory registration of e

关键词： visualization Electronic learning Task analysis Estimation Vocabulary Memory management Learning (artificial intelligence) E-learning neural networks artificial intelligence cognitive theory of multimedia learning cognitive load distinctiveness account perceptual decoupling adaptability educational data mining

来源：评论

学校读者我要写书评

暂无评论

Medvisiochat: A Multimodal large Language Model Framework for Interpretable Diagnosis with Visual Grounding in CXRs

Medvisiochat: A Multimodal Large Language Model Framework fo...

引用

ieee International symposium on Biomedical Imaging

作者： Ling Yang Zhanyu Wang Luping Zhou School of Electrical and Computer Engineering The University of Sydney Australia

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Multimodal large Language Models (MLLMs) have enhanced the interpretability of disease diagnosis, leading to more accurate outcomes and improved patient understanding. A key advancement is visual grounding, linking textual information with medical images like chest x-rays (CXRs) for deeper analysis. This approach combines visual details with expert medical language, enabling MLLMs to detect patterns and disease indicators effectively. However, challenges persist, particularly in multi-category classification and precise visual grounding in CXRs. To address this, we introduce MedVisioChat, an MLLM with visual grounding capabilities for seamless integration of medical images and diagnoses. Pre-trained on large datasets and fine-tuned with specific GPT-4 Turbo instructions, MedVisioChat aims to provide accurate, interactive diagnostics, demonstrating superiority over existing models and promising an inter-pretable visual medical diagnosis.

关键词： visualization Accuracy Grounding Biological system modeling large language models data models Medical diagnosis Medical diagnostic imaging X-ray imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Designing An Intelligent Architecture to Detect Malevolent E-Mail Using Machine Learning Approach 1

Designing An Intelligent Architecture to Detect Malevolent E...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Chaudhuri, Nandita Bhanja Chaudhuri, Sangeeta Bhanja GITAM Deemed to be University CSE Department Hyderabad India CMR Institute of Technology Department of Information Science & Engineering Bengaluru India

ISBN: (纸本)9798350361780

The most common method of remote communication in business, corporate, and personal life is email. It contains a vast amount of private data that is sent across the network. So, these mails have to be managed in an efficient manner for maximal and uninterrupted communication. Unfortunately, spam-a term for malevolent emails-many a time enters our e-mail accounts due to an individual's dishonest intentions. Spam puts more load on ISP servers and bandwidth, and consumers are responsible for bearing the additional costs incurred in handling this load. Spam emails are designed to send unsolicited commercials and useless proposals to specific people;therefore, it has been subject to laws in several jurisdictions. Consequently, the categorization of authentic emails from a large email dataset is the main intent of this study. Both synthetic data created from many email accounts and regular datasets gathered from the UCI Machine Learning Repository were used in the experiments. Subsequently, data was imported from multiple sources, and data transformation technique was applied to the dataset. 'Principal Component analysis' is used as an attribute selection strategy where significant attributes are identified. This paper describes classification of E-mails by Random Forest (RF algorithm). The improved dataset after PCA has been classified by 'Random Forest classification algorithm' which outperforms large datasets. Plot Layout, Receiver Operating Characteristics (ROC) graph, and bar chart visualization techniques are used to report the results. © 2024 ieee.

关键词： large datasets

来源：评论

学校读者我要写书评

暂无评论

InfoMat: A Tool for the analysis and visualization Sequential Information Transfer

InfoMat: A Tool for the Analysis and Visualization Sequentia...

引用

ieee International symposium on Information Theory

作者： Dor Tsur Haim Permuter School of Electrical and Computer engineering Ben-Gurion University of the Negev

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

Despite the popularity of information measures in analysis of probabilistic systems, proper tools for their visualization are not common. This work develops a simple matrix representation of information transfer in sequential systems, termed information matrix (InfoMat). The simplicity of the InfoMat provides a new visual perspective on existing decomposition formulas of mutual information, and enables us to prove new relations between sequential information theoretic measures. We study various estimation schemes of the InfoMat, facilitating the visualization of information transfer in sequential datasets. By drawing a connection between visual pattern in the InfoMat and various dependence structures, we observe how information transfer evolves in the dataset. We then leverage this tool to visualize the effect of capacity-achieving coding schemes on the underlying exchange of information. We believe the InfoMat is applicable to any time-series task for a better understanding of the data at hand.

关键词： visualization Pipelines data visualization Estimation Probabilistic logic Encoding Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

Alignment of Objects in 3D Space Using Radon Transform for Cargo-Mail Scanner 66

Alignment of Objects in 3D Space Using Radon Transform for C...

引用

66th International symposium ELMAR, ELMAR 2024

作者： Dobrovolny, Martin University of Pardubice Faculty of Electrical Engineering and Informatics Dept. of Electrical Engineering Pardubice Czech Republic

ISBN: (纸本)9798350375411

This paper presents the results of comparison of the proposed unique algorithm for object alignment in 3D space with the conventional approach based on Principal Component analysis. The proposed algorithm is based on the use of Radon Transform. The algorithm has been developed for the necessity of designing a 3D scanner for large-scale Cargo-Mail in the field of air logistics. Shipments are sorted in the logistics center of the external partner and then placed in air containers. Using the proposed method, the rotation compensation of objects in the 3D scanner space was effectively solved. Thanks to the proposed method, the scanner works without manual intervention of the operator. The proposed method is robust even for situations with poorly cropped background under packages. © 2024 ieee.

关键词： 3D scanning data alignment Point Cloud Principal Component analysis Radon transform

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：