Exploring the Association between Climate Change and Human Development: A Visual Analytics Study

This study explores the complex relationship between climate change and human development. The aim is to understand how climate change affects human development across countries, regions, and the global population. Visual analytics were used to examine the impact of various climate change indicators on different aspects of human development. The study highlights the urgent need for climate change action and encourages policymakers to make decisive moves. Climate change adversely affects numerous aspects of daily life, leading to significant consequences that must be addressed through policy changes and global governance recommendations. Key findings include that regions with higher CO2 emissions experience a significantly higher incidence of life-threatening diseases compared to regions with lower emissions. Additionally, higher CO2 emissions correlate with consistent death rates. Increased pollution exposure is associated with a higher prevalence of life-threatening diseases and higher rates of malnutrition. Moreover, greater mineral depletion is linked to more frequent life-threatening diseases, suggesting that industrialization contributes to adverse health effects. These results provide valuable insights for policy and decision-making aimed at mitigating the impact of climate change on human development.

Visual analytics tool for the interpretation of hidden states in recurrent neural networks

In this paper,we introduce a visual analytics approach aimed at helping machine learning experts analyze the hidden states of layers in recurrent neural networks.Our technique allows the user to interactively inspect how hidden states store and process information throughout the feeding of an input sequence into the network.The technique can help answer questions,such as which parts of the input data have a higher impact on the prediction and how the model correlates each hidden state configuration with a certain output.Our visual analytics approach comprises several components:First,our input visualization shows the input sequence and how it relates to the output(using color coding).In addition,hidden states are visualized through a nonlinear projection into a 2-D visualization space using t-distributed stochastic neighbor embedding to understand the shape of the space of the hidden states.Trajectories are also employed to show the details of the evolution of the hidden state configurations.Finally,a time-multi-class heatmap matrix visualizes the evolution of the expected predictions for multi-class classifiers,and a histogram indicates the distances between the hidden states within the original space.The different visualizations are shown simultaneously in multiple views and support brushing-and-linking to facilitate the analysis of the classifications and debugging for misclassified input sequences.To demonstrate the capability of our approach,we discuss two typical use cases for long short-term memory models applied to two widely used natural language processing datasets.

VisQAC: Visual Analytics for Online Q&A Communities

Online question and answer(Q&A)communities,which allow users to exchange knowledge by asking and answering questions,have become increasingly popular.As a result of user active participation,these communities store overwhelming volumes of information.However,existing related methods are unable to meet community operators’needs for analyzing multi-dimensional Q&A sequences and understanding user behavior.In this paper,collaborating with domain experts in online community,we present a system,VisQAC,which explores the patterns of Q&A sequence and user behavior.In the system,a novel visual design is proposed,which is combined with flexible mapping measures for analyzing critical characteristics of sequence data.Moreover,a timeline visualization method is designed to visualize data with categorical attributes and its correlation can be displayed flexibly by choosing time mode and time granularity.The usefulness and effectiveness of the system are demonstrated with several case studies of VisQAC with community operators based on the Zhihu dataset.Our evaluation shows that VisQAC is beneficial to the understanding of Q&A sequence and associated user behavior.

Hotshots of Spatio-temporal Behavior of Chinese Residents in the Context of Big Data:Visual Analysis Based on CiteSpace

By using CiteSpace software to create a knowledge map of authors,institutions and keywords,the literature on the spatio-temporal behavior of Chinese residents based on big data in the architectural planning discipline published in the China Academic Network Publishing Database(CNKI)was analyzed and discussed.It is found that there was a lack of communication and cooperation among research institutions and scholars;the research hotspots involved four main areas,including“application in tourism research”,“application in traffic travel research”,“application in work-housing relationship research”,and“application in personal family life research”.

On Development of Platform for Organization Security Threat Analytics and Management (POSTAM) Using Rule-Based Approach

The integration of organisation’s information security policy into threat modeling enhances effectiveness of security strategies for information security management. These security policies are the ones which define the sets of security issues, controls and organisation’s commitment for seamless integration with knowledge based platforms in order to protect critical assets and data. Such platforms are needed to evaluate and share violations which can create security loop-hole. The lack of rules-based approaches for discovering potential threats at organisation’s context, poses a challenge for many organisations in safeguarding their critical assets. To address the challenge, this paper introduces a Platform for Organisation Security Threat Analytic and Management (POSTAM) using rule-based approach. The platform enhances strategies for combating information security threats and thus improves organisations’ commitment in protecting their critical assets. R scripting language for data visualization and java-based scripts were used to develop a prototype to run on web protocol. MySQL database management system was used as back-end for data storage during threat analytic processes.

Exploring the Characteristics of Data Breaches: A Descriptive Analytic Study

Data breaches have massive consequences for companies, affecting them financially and undermining their reputation, which poses significant challenges to online security and the long-term viability of businesses. This study analyzes trends in data breaches in the United States, examining the frequency, causes, and magnitude of breaches across various industries. We document that data breaches are increasing, with hacking emerging as the leading cause. Our descriptive analyses explore factors influencing breaches, including security vulnerabilities, human error, and malicious attacks. The findings provide policymakers and businesses with actionable insights to bolster data security through proactive audits, patching, encryption, and response planning. By better understanding breach patterns and risk factors, organizations can take targeted steps to enhance protections and mitigate the potential damage of future incidents.

Analysis of Gestational Diabetes Mellitus (GDM) and Its Impact on Maternal and Fetal Health: A Comprehensive Dataset Study Using Data Analytic Tool Power BI

Gestational Diabetes Mellitus (GDM) is a significant health concern affecting pregnant women worldwide. It is characterized by elevated blood sugar levels during pregnancy and poses risks to both maternal and fetal health. Maternal complications of GDM include an increased risk of developing type 2 diabetes later in life, as well as hypertension and preeclampsia during pregnancy. Fetal complications may include macrosomia (large birth weight), birth injuries, and an increased risk of developing metabolic disorders later in life. Understanding the demographics, risk factors, and biomarkers associated with GDM is crucial for effective management and prevention strategies. This research aims to address these aspects comprehensively through the analysis of a dataset comprising 600 pregnant women. By exploring the demographics of the dataset and employing data modeling techniques, the study seeks to identify key risk factors associated with GDM. Moreover, by analyzing various biomarkers, the research aims to gain insights into the physiological mechanisms underlying GDM and its implications for maternal and fetal health. The significance of this research lies in its potential to inform clinical practice and public health policies related to GDM. By identifying demographic patterns and risk factors, healthcare providers can better tailor screening and intervention strategies for pregnant women at risk of GDM. Additionally, insights into biomarkers associated with GDM may contribute to the development of novel diagnostic tools and therapeutic approaches. Ultimately, by enhancing our understanding of GDM, this research aims to improve maternal and fetal outcomes and reduce the burden of this condition on healthcare systems and society. However, it’s important to acknowledge the limitations of the dataset used in this study. Further research utilizing larger and more diverse datasets, perhaps employing advanced data analysis techniques such as Power BI, is warranted to corroborate and expand upon the findings of this research. This underscores the ongoing need for continued investigation into GDM to refine our understanding and improve clinical management strategies.

AVA:An automated and AI-driven intelligent visual analytics framework

With the incredible growth of the scale and complexity of datasets,creating proper visualizations for users becomes more and more challenging in large datasets.Though several visualization recommendation systems have been proposed,so far,the lack of practical engineering inputs is still a major concern regarding the usage of visualization recommendations in the industry.In this paper,we proposed AVA,an open-sourced web-based framework for Automated Visual Analytics.AVA contains both empiric-driven and insight-driven visualization recommendation methods to meet the demands of creating aesthetic visualizations and understanding expressible insights respectively.The code is available at https://github.com/antvis/AVA.

TCEVis:Visual analytics of traffic congestion influencing factors based on explainable machine learning

Traffic congestion is becoming increasingly severe as a result of urbanization,which not only impedes people’s ability to travel but also hinders the economic development of cities.Modeling the correlation between congestion and its influencing factors using machine learning methods makes it possible to quickly identify congested road segments.Due to the intrinsic black-box character of machine learning models,it is difficult for experts to trust the decision results of road congestion prediction models and understand the significance of congestion-causing factors.In this paper,we present a model interpretability method to investigate the potential causes of traffic congestion and quantify the importance of various influencing factors using the SHAP method.Due to the multidimensionality of these factors,it can be challenging to visually represent the impact of all factors.In response,we propose TCEVis,an interactive visual analytics system that enables multi-level exploration of road conditions.Through three case studies utilizing actual data,we demonstrate that the TCEVis system offers advantages for assisting traffic managers in analyzing the causes of traffic congestion and elucidating the significance of various influencing factors.

IMVis: Visual analytics for influence maximization algorithm evaluation in hypergraphs

Influence maximization(IM)algorithms play a significant role in hypergraph analysis tasks,such as epidemic control analysis,viral marketing,and social influence analysis,and various IM algorithms have been proposed.The main challenge lies in IM algorithm evaluation,due to the complexity and diversity of the spreading processes of different IM algorithms in different hypergraphs.Existing evaluation methods mainly leverage statistical metrics,such as influence spread,to quantify overall performance,but do not fully unravel spreading characteristics and patterns.In this paper,we propose an exploratory visual analytics system,IMVis,to assist users in exploring and evaluating IM algorithms at the overview,pattern,and node levels.A spreading pattern mining method is first proposed to characterize spreading processes and extract important spreading patterns to facilitate efficient analysis and comparison of IM algorithms.Novel visualization glyphs are designed to comprehensively reveal both temporal and structural features of IM algorithms’spreading processes in hypergraphs at multiple levels.The effectiveness and usefulness of IMVis are demonstrated through two case studies and expert interviews.

Web-based spatiotemporal visualization of marine environment data

With long-term marine surveys and research,and especially with the development of new marine environment monitoring technologies,prodigious amounts of complex marine environmental data are generated,and continuously increase rapidly.Features of these data include massive volume,widespread distribution,multiple-sources,heterogeneous,multi-dimensional and dynamic in structure and time.The present study recommends an integrative visualization solution for these data,to enhance the visual display of data and data archives,and to develop a joint use of these data distributed among different organizations or communities.This study also analyses the web services technologies and defines the concept of the marine information gird,then focuses on the spatiotemporal visualization method and proposes a process-oriented spatiotemporal visualization method.We discuss how marine environmental data can be organized based on the spatiotemporal visualization method,and how organized data are represented for use with web services and stored in a reusable fashion.In addition,we provide an original visualization architecture that is integrative and based on the explored technologies.In the end,we propose a prototype system of marine environmental data of the South China Sea for visualizations of Argo floats,sea surface temperature fields,sea current fields,salinity,in-situ investigation data,and ocean stations.An integration visualization architecture is illustrated on the prototype system,which highlights the process-oriented temporal visualization method and demonstrates the benefit of the architecture and the methods described in this study.

Spatial/temporal indexing and information visualization genre for environmental digital libraries

Protecting and preserving our environmental systems require the ability to understand the spatio-temporal distri- bution of soils, parent material, topography, and land cover as well as the effects of human activities on ecosystems. Space-time modelling of ecosystems in an environmental digital library is essential for visualizing past, present, and future impacts of changes occurring within such landscapes (e.g., shift in land use practices). In this paper, we describe three novel features, spa- tio-temporal indexing, visualization, and geostatistical genre, for the environmental digital library, Environmental Visualization and Geographic Enterprise System (ENVISAGE), currently in progress at the University of Florida.

Interactive multigraph visualization and exploration with a two-phase strategy

While it is very reasonable to use a multigraph consisting of multiple edges between vertices to represent various relationships, the multigraph has not drawn much attention in research. To visualize such a multigraph, a clear layout representing a global structure is of great importance, and interactive visual analysis which allows the multiple edges to be adjusted in appropriate ways for detailed presentation is also essential. A novel interactive two-phase approach to visualizing and exploring multigraph is proposed. The approach consists of two phases： the first phase improves the previous popular works on force-directed methods to produce a brief drawing for the aggregation graph of the input multigraph, while the second phase proposes two interactive strategies, the magnifier model and the thematic-oriented subgraph model. The former highlights the internal details of an aggregation edge which is selected interactively by user, and draws the details in a magnifying view by cubic Bezier curves; the latter highlights only the thematic subgraph consisting of the selected multiple edges that the user concerns. The efficiency of the proposed approach is demonstrated with a real-world multigraph dataset and how it is used effectively is discussed for various potential applications.

Analytic provenance for criminal intelligence analysis

In criminal intelligence domain where solution discovery is often serendipitous,it demands techniques to provide transparent evidences of top-down and bottom-up analytical processes of analysts while sifting through or transforming sourced data to provide plausible explanation of the fact.Management and tracing of such security sensitive analytical information flow originated from tightly coupled visualizations into visual analytic system for criminal intelligence that triggers huge amount of analytical information on a single click,involves design and development challenges.In this research paper,we have introduced a system called"PROV"to capture,visualize and utilize analytical information named as analytic provenance by considering such challenges.A video demonstrating its features is available online at https://streamable.com/r8mlx.Prior to develop this system for criminal intelligence analysis,we conducted a systematic research to outline the requirements and technical challenges.We gathered such information from real police intelligence analysts through multiple sessions who are the end users of a large heterogeneous event-driven modular Analyst’s User Interface(AUI)of the project VALCRI(Visual Analytics for Sensemaking in Criminal Intelligence),developed by using visual analytic technique.We have proposed a semantic analytic state composition technique to trigger new insight by schematizing captured reasoning states.To evaluate the system we carried out few subjective feedback sessions with the end-users of the project and found very positive feedback.We also have tested our event triggered analytic state capturing protocol with an external geospatial and temporal crime analysis system and found that our proposed technique works generically for both small and large complex visual analytic systems.

Analytical Tools and Strategic Approach to Detect Poor Quality Medicines, Identify Unknown Components, and Timely Alerts for Appropriate Measures: Case Study of Antimalarial Medicines

Nowadays, the circulation of poor quality medicines is becoming an alarming worldwide phenomenon with serious public health and socio-economic concerns. The situation is particularly critical in developing countries where drug quality assurance and regulatory systems for drug manufacturing, importation, distribution and sales are weak. A sustained vigilance on poor quality medicines that regroup counterfeit/falsified, substandard and degraded medicines is therefore required to ensure patient safety and genuine medicines integrity. A case situation is illustrated including a strategic approach and analytical tools that were found useful to detect poor quality medicines, identify unknown components, and timely alerts for appropriate measures against the spread of those harmful products. Several suspected medicines randomly sampled in several strategic Rwandan areas were firstly check-controlled by means of visual inspection and then applying several analytical techniques from simple to more complex ones. The following medicines were studied: quinine sulfate tablets, artemisinin-based combination tablets, and artesunate powders for injection. Taking into account the pharmaceutical forms and the chemical characteristics, the following tests were applied: uniformity of mass, friability, disintegration, fluorescence, identification and assay. They were followed by more complex analytical techniques that allowed more comprehension of abnormal findings among which the presence of a wrong active pharmaceutical ingredient in quinine sulfate tablets which is mainly discussed in this paper to illustrate a strategic approach and various analytical tools that can be used in detecting and identifying unknown component in poor quality medicines.

Ontology-Driven Analytic Models for Pension Management and Decision Support System

Ontology-Driven Analytic Models for Pension Management are sophisticated approaches that integrate the principles of ontology and analytics to optimize the management and decision-making processes within pension systems. While Ontology-Driven Analytic Models offer significant benefits for pension management, there are also challenges associated with implementing and utilizing the models. Developing a comprehensive and accurate ontology for pension management requires a deep understanding of the domain, including regulatory frameworks, investment strategies, retirement planning, and integration of data from heterogenous sources. Integrating these data into a cohesive ontology can be challenging. This research work leverages on semantic ontology as an approach for structured representation of knowledge about concepts and their relationships, and applies it to analyze and optimize decision support for pension management. The proposed ontology presents a formal and explicit specification of concepts (classes), their attributes, and the relationships between them and provides a shared and standardized understanding of the domain;enabling precise communication and knowledge representation for decision-support. The ontology deploys computational frameworks and analytic models to assess and evaluate data, generate insights, predict future pension fund performance as well as assess risk exposure. The research adopts the Reasoner, SPARQL query and OWL Visualizer executed over Java IDE for modelling the ontology-driven analytics. The approach encapsulated and integrated semantic ontologies with analytical models to enhance the accuracy, contextuality, and comprehensiveness of analyses and decisions within pension systems.

A Visual Analysis and Prediction System for Infectious Diseases Based on Improved SIR Model

To effectively track the impact of population migration between regions on the spread of infectious diseases, this paper proposes a visualized analysis and prediction system of infectious diseases based on the improved SIR model. The research contents including: using the multi graph link interaction mode, visualizing the space-time distribution and development trend of infectious diseases;The LightGBM model is used to track the changes of infection rate and recovery rate, and the Mi/Mo SIR model is constructed according to the initial data of different populations;Mi/Mo SIR model is used to predict infectious diseases in combination with visual panel, providing users with tools to analyze and explain the space-time characteristics and potential laws of infectious diseases. The study found that the closure of cities and the restriction of personnel mobility were necessary and effective, and the system provided an important basis for the prediction and early warning of infectious diseases.

基于CiteSpace的智能纺织服装产品研究进展

为揭示智能纺织服装的研究现状、热点和趋势,以CNKI数据库和WOS数据库中2012—2022年的相关文献为研究对象,采用CiteSpace可视化分析软件绘制知识图谱,分析智能纺织服装产品在国家、机构、作者方面的分布现状及合作情况,对研究热点和前沿趋势进行梳理。结果表明,2012—2022年,CNKI数据库发文量稳步上升,WOS数据库发文量快速增长且中国学者发文量较多;CNKI数据库研究合作强度较低且以东华大学和江南大学为主体;WOS数据库合作关系密切,研究集中度和合作强度大;CNKI数据库研究方向更注重应用和设计模式,WOS数据库则更注重电子元件制造和智能纤维与面料的开发;健康检测、变色肌理、仿生设计、生物材料、可穿戴应变等是目前智能纺织服装领域的前沿热点,电子元件制造、智能纤维及面料智能化研究是未来智能纺织服装领域研究的热点及趋势。

基于表征学习的时空态势可视分析方法

时空态势描述了大量运动对象在一段时间内的空间位置变化过程,分析和寻找时空态势对大量实际应用都具有重要意义.针对海量的数据和无法避免的数据缺失为分析时空态势带来的问题,提出一种从大规模时空数据中寻找代表性时空态势的表征学习的方法.首先,基于Denoising Autoencoder框架实现一个时空态势表征模型,将每个时空态势编码为一个紧凑的表征向量,向量之间的距离体现了时空态势之间的特征差异,通过向编码器添加噪声并让解码器还原未带噪声的原始态势,提高表征模型在数据缺失条件下的鲁棒性;然后提出一种可视摘要算法,以一个精简的小图标直观地显示连续时空态势的整体运动特征,进一步构造了一个时空态势投影,供用户快速地找到数据集中代表性的时空态势.基于纽约出租车数据集和芝加哥犯罪数据集,采用自相似和交叉相似的指标与既有相似性方法对比,实验结果表明,所提出的表征模型在大数据量、高缺失率条件下的准确性和鲁棒性,并具有较高的执行效率;用户实验包括选择和排序任务,结果表明,所提方法找到的代表性的时空态势与用户的主观认知更加一致.

基于SAPAD-AHP的视障者医院导盲机器人设计研究

为解决视障者就医困难等问题,采用SAPAD-AHP方法对视障者医院导盲机器人设计进行研究。首先,采用访谈、观察和体验等方法,对视障者就医过程和痛点进行记录。其次,通过SAPAD模型对视障者就医行为进行研究,建立其“行为―对象―意义”的映射关系,并对意义进行聚类分析,得到一般意义簇。最后,结合AHP法进行权重分析,算出每个意义簇的权重,通过排序得到核心意义簇。通过“核心意义簇―对象”的映射,得到视障者的核心需求,对核心需求进行分析与拆解,得到真正需求,从而完善视障者导盲机器人设计研究。