Data Visualization Research Articles

Do Beliefs About Intelligence Drive Engagement in Online Learning?

This study investigates the relationship between students’ beliefs about intelligence (fixed vs. growth mindset) and their engagement and behaviour in an online learning platform. The data was collected from 28 students enrolled in COMP90082 – Software Project subject at The University of Melbourne. Students’ beliefs about intelligence were measured through a survey administered during the first week, while their online learning behaviours were captured through clickstream data from the learning management system. The study adopted a two-fold approach: first, students’ learning strategies were identified through cluster analysis of their online session duration. By examining over 41,000 learning actions —such as accessing course materials, participating in discussions, and completing assignments— three distinct learning strategies emerged: “light”, “light-intensive”, and “intensive.” Subsequently, the relationship between these learning strategies and students’ beliefs about intelligence was examined using data visualisation techniques, chi-square tests, and logistic regression models. The findings revealed that students with a growth mindset were more likely to adopt intensive and engaged learning approaches within the online platform. Conversely, those with a fixed mindset tended to exhibit lower engagement levels and less intensive learning strategies. The study may contribute to the growing literature on the psychology of online learning and highlight the potential for tailoring instructional interventions and platform design to foster a growth mindset, thereby enhancing student engagement and academic success in digital learning environments.

Autonomous UAV Chasing with Monocular Vision: A Learning-Based Approach

In recent years, unmanned aerial vehicles (UAVs) have shown significant potential across diverse applications, drawing attention from both academia and industry. In specific scenarios, UAVs are expected to achieve formation flying without relying on communication or external assistance. In this context, our work focuses on the classic leader-follower formation and presents a learning-based UAV chasing control method that enables a quadrotor UAV to autonomously chase a highly maneuverable fixed-wing UAV. The proposed method utilizes a neural network called Vision Follow Net (VFNet), which integrates monocular visual data with the UAV’s flight state information. Utilizing a multi-head self-attention mechanism, VFNet aggregates data over a time window to predict the waypoints for the chasing flight. The quadrotor’s yaw angle is controlled by calculating the line-of-sight (LOS) angle to the target, ensuring that the target remains within the onboard camera’s field of view during the flight. A simulation flight system is developed and used for neural network training and validation. Experimental results indicate that the quadrotor maintains stable chasing performance through various maneuvers of the fixed-wing UAV and can sustain formation over long durations. Our research explores the use of end-to-end neural networks for UAV formation flying, spanning from perception to control.

Visual and Radar Data Fusion: Complementary or Alternative Sensors in Intelligent Driving Systems

This article explores the role and advantages and disadvantages of visual and radar data fusion in intelligent driving systems. With the rapid development of intelligent driving technology, the comprehensive perception of the environment by car perception systems has become crucial, usually requiring the combination of low, medium, and high-precision sensors. Visual sensors perform excellently in acquiring high-resolution images and recognizing detailed information, while radar sensors have higher stability and penetration in harsh weather conditions. Due to the limitations of a single sensor in complex driving environments, data fusion has become a key strategy for improving the performance of perception systems. By comparing different perception schemes and application scenarios, this article analyzes the actual effects and potential advantages of visual and radar data fusion, revealing its important role in intelligent driving technology. Fusion technology can compensate for the shortcomings of various sensors, and improve the accuracy and reliability of environmental perception, but still faces challenges in data synchronization, algorithm selection, and real-time performance. This article aims to provide valuable insights for the development of future intelligent driving technology.

BIG DATA AND STATISTICAL APPLICATIONS

In recent years, modern developments in computer and cloud technologies have led to a significant increase in the quantity and speed of generated and stored information. This increase in the amount of information has introduced a new concept into our lives called "Big Data". Big Data offers significant advantages, especially for governments and businesses, in making informed decisions about their futures. However, the magnitude and diversity of this emerging data also bring about some challenges. Traditional database systems have been inadequate in processing these data formats, necessitating the need for new tools and techniques to overcome this challenge. Today, a wide range of techniques and technologies have been developed to collect, process, analyze, and visualize “Big Data”. These techniques and technologies encompass and draw upon various fields such as statistics, computer science, applied mathematics, and economics. Keywords: big data, visualization of data, structured data, big data technologies, big data techniques.

A comparative study on the use of spatiotemporal maps for teaching data visualization in a hybrid learning context

ABSTRACT Data visualization is a complex matter and so is teaching it in the context of engineering and data science. Even more challenging is teaching in a midst of once in a century pandemic. In this paper, we show the results of a workshop conducted with second-year students on a university degree in data science, which took place in the context of pandemic restrictions in a hybrid learning environment. About half of the students were in the classroom and the other half at home. They learned to use STMaps, a tool developed in the scope of the SILKNOW project. We transferred research outcomes to the classroom; similarly, the results of evaluating the tool were transferred to the project. But more importantly, we found insights that the learning process of students that were online was not the same quality as of those that were physically in the classroom. While both groups performed well in terms of correctly fulfilling the tasks proposed during the workshop, the students at home were less motivated and perceived the tasks more cumbersome to achieve. From a research perspective, this activity was perceived as very useful, and similar activities are being planned for each academic year.

A review of advances in image recognition models: From K-NN to Vision Transformer

Abstract. In the digital age, visual data are everywhere. Image recognition has become a vital branch of artificial intelligence and is used in a wide range of fields. From medical diagnostics to autonomous vehicles, its impact is profound and far-reaching. This review visits the significant advancements in the field of image recognition, summarizes and analyzes the progress from traditional methods like K-Nearest Neighbors (K-NN) to newer models like Vision Transformer. This paper analyzes image recognition models like AlexNet, GoogLeNet, ResNet, and Vision Transformer, with the principles, strengths, weaknesses, and the significance of these models to deep learning fields, along with their applications in image recognition tasks. These models not only push the boundaries of image recognition but also find extensive applications across various domains. In the future, image recognition can continue to develop with larger and better datasets, increased computing power, and more advanced network structures.

The Frontier Exploration and Application Prospect of Data Science

Abstract. In the era of information explosion, data floods in like a relentless tide, shaping peoples world every minute and second. Data science, the most prominent discipline of our time, wields unprecedented power to propel the development of industries across the board, serving as a bridge that connects the past with the future, granting insights into the present, and predicting trends. This article delves into the allure of data science, unveiling how it has become the key to unlocking the future world. Furthermore, this review explores in detail the core concepts, key technologies, and broad applications of data science. Through in-depth research on data acquisition, processing, analysis, and visualization, it reveals the innovative applications and significant impacts of data science in multiple fields such as business intelligence, healthcare, and financial technology. At the same time, the future trends and challenges of data science are prospectively analyzed, which provides a valuable reference for further promoting the research and practice in this field.

Enhancing environmental modeling and 3D point cloud construction for unmanned vehicles using laser SLAM and stereo vision with Convolutional Neural Networks

Abstract. This research presents an innovative SLAM algorithm that integrates Convolutional Neural Networks (CNNs) with LIDAR and stereo vision to significantly enhance the accuracy of environmental modeling and the construction of dense 3D point cloud maps in complex and dynamic surroundings. By processing pre-recorded video data and employing advanced image segmentation techniques, this study achieves a deep fusion of visual and geometric data, resulting in highly detailed and precise 3D representations of the environment. The experimental results demonstrate that this approach effectively detects and excludes dynamic objects, thereby significantly improving the overall quality, robustness, and reliability of the constructed maps. This work represents a substantial advancement in SLAM technology, particularly in its capability to model and capture intricate environmental details under varying conditions, making it a powerful tool for precise environmental mapping.

Exploring the influence of body movements on spatial perception in landscape and interior design

This study investigates the influence of body movements on spatial perception in both landscape and interior design environments, focusing on how physical interactions shape spatial understanding beyond visual perception alone. Grounded in the theory of embodied cognition, the research examines how gait, posture, and movement dynamics affect spatial awareness. The study captures detailed data on movement patterns and visual engagement across different spatial contexts using a combination of real-world observations and Virtual Reality (VR) simulations, motion-tracking systems, wearable sensors, and eye-tracking technology. A total of 157 participants, aged 20 to 65, navigated both outdoor landscapes and indoor environments, with key variables such as surface materials, spatial layout, and lighting conditions manipulated to assess their effects on spatial perception. The study measured gait speed, step frequency, path deviations, time to destination, visual attention, and subjective ratings of perceived openness, ease of movement, and emotional response. Key findings include that surface materials significantly influenced gait speed and step frequency. For example, participants walking on concrete had a significantly faster gait speed (mean difference = 0.5220, p = 0.001) than those walking on gravel. In terms of spatial layout, the two-way Analysis of variance (ANOVA) results showed that winding paths led to more path deviations (F-statistic = 350.00, p = 3.19 × 10−8) and longer times to destination (F-statistic = 1744.00, p = 2.39 ´ 10−11) compared to straight paths. The environment type (landscape vs. interior) also significantly affected navigation, with landscape participants showing a more significant deviation from direct paths (F-statistic = 19.60, p = 2.37 × 10−3). Visual engagement data, analyzed through a chi-square test, indicated that vertical elements like walls approached significance in attracting visual attention (Chi-square = 2.88, p = 0.0896), while other elements like trees and benches had less impact. The Wilcoxon signed-rank test results showed significant differences between real-world and VR experiences in perceived openness (W-statistic = 0.0, p = 0.001953), ease of movement (W-statistic = 0.0, p = 0.001953), and comfort (W-statistic = 0.0, p = 0.001953), highlighting VR’s limitations in replicating the full embodied experience of physical spaces.

Mapping the Landscape of Biomechanics Research in Stroke Neurorehabilitation: A Bibliometric Perspective

Background/Objectives: The incorporation of biomechanics into stroke neurorehabilitation may serve to strengthen the effectiveness of rehabilitation strategies by increasing our understanding of human movement and recovery processes. The present bibliometric analysis of biomechanics research in stroke neurorehabilitation is conducted with the objectives of identifying influential studies, key trends, and emerging research areas that would inform future research and clinical practice. Methods: A comprehensive bibliometric analysis was performed using documents retrieved from the Scopus database on 6 August 2024. The analysis included performance metrics such as publication counts and citation analysis, as well as science mapping techniques, including co-authorship, bibliographic coupling, co-citation, and keyword co-occurrence analyses. Data visualization tools such as VOSviewer and Power BI were utilized to map the bibliometric networks and trends. Results: An overabundance of recent work has yielded substantial advancements in the application of brain–computer interfaces to electroencephalography and functional neuroimaging during stroke neurorehabilitation., which translate neural activity into control signals for external devices and provide critical insights into the biomechanics of motor recovery by enabling precise tracking and feedback of movement during rehabilitation. A sampling of the most impactful contributors and influential publications identified two leading countries of contribution: the United States and China. Three prominent research topic clusters were also noted: biomechanical evaluation and movement analysis, neurorehabilitation and robotics, and motor recovery and functional rehabilitation. Conclusions: The findings underscore the growing integration of advanced technologies such as robotics, neuroimaging, and virtual reality into neurorehabilitation practices. These innovations are poised to enhance the precision and effectiveness of therapeutic interventions. Future research should focus on the long-term impacts of these technologies and the development of accessible, cost-effective tools for clinical use. The integration of multidisciplinary approaches will be crucial in optimizing patient outcomes and improving the quality of life for stroke survivors.

The role of social media data in enhancing B2B omni-channel marketing efforts in small businesses

PurposeThis paper explores the role of social media data in enhancing business-to-business (B2B) omni-channel marketing (OCM) efforts in small businesses. B2B marketing strategy is explored through the lens of each business’s marketing manager’s insights. A novel social media data visualisation tool for B2B marketing campaign development is presented, adding contextualisation to OCM activities.Design/methodology/approachThis exploratory study uses the qualitative interview method to consider the research question: what role does social media data play in enhancing B2B marketing efforts across the omni-channel in small businesses? The paper presents the findings of 25 in-depth interviews with small business marketing managers from a range of B2B industries, guided by a literature-informed interview template. Insights are developed using an open coding approach via traditional pen and paper methods, underpinned by thematic analysis.FindingsSmall business marketing managers recognise the importance of social media data in enhancing B2B OCM efforts in their organisations. They acknowledge online marketing channels as paths to enhanced brand awareness and relationship building and recognise social media’s growing influence on B2B customers’ decision-making processes. There is a dichotomy between the professed importance of social media data and its use among some small business marketing managers in their B2B OCM efforts. Others are capturing these data and integrating it with other data resources, thereby embedding social media data as a strategic resource within their business. Findings indicate that it is only in these small businesses that OCM strategy is evolving to meet B2B customer expectations of an integrated OCM experience, informed by social media data, across all channels and touchpoints.Research limitations/implicationsThis work is of particular interest to marketing managers within small businesses seeking to improve their B2B marketing efforts across the omni-channel. It is of value to all B2B enterprises, given the rate of advancement of the B2B social media marketing landscape.Originality/valueRecognised as an emerging area, research relating to B2B OCM is limited. This paper provides empirical data on OCM efforts in small businesses from a B2B perspective and considers the role of social media data in enhancing marketing efforts across the omni-channel. Underpinned by social network theory and based on insights gleaned from fieldwork, a social media data visualisation tool is presented, the first of its kind in this sphere.

Biomedical Engineering Literature: Advanced Reading Skills for Research and Practice

Medical engineering is a field of study that combines biological and medical sciences with engineering to develop improved healthcare technologies. It is imperative that you possess a deep understanding of both the material and the technical language used in this rapidly advancing field in order to effectively grasp key topics and navigate the rapidly expanding literature. This paper examines the future of the biomedical engineering profession through the lens of advanced reading strategies. It starts with the assertion that biomedical engineering literature presents three challenges: the level of density is technical, the area is interdisciplinary, and the growth of knowledge is exponential. In the view of the above challenges, the paper discusses various advanced reading skills in relation to biomedical engineers. These skills include the ability to critically read scientific texts, both at a fast pace for an overview and in detail for deeper understanding, to identify key ideas and methodologies relevant to the field, and to assess the validity of scientific claims and data representations. The paper also aims at pointing out how separate elements like the use of systematic reviews, of meta-analysis, of data visualization tools that complement reading, help the researcher in the process of managing gathered information from various sources. This paper describes teaching these skills for both academic and professional practice, with examples of how improved reading competencies can enhance research quality and contribute to innovations in medical technologies, tissue engineering, and clinical trials. Furthermore, the paper aims to discuss the future trends due to the increasing incorporation of continuous learning for addressing the challenges posed by novel technologies including artificial intelligence and nanotechnology that define the future of biomedical engineering. biomedical engineering students require the acquisition of higher order reading skills in preparation for information reading: national and international publications in the engineering profession, policy and technology in support of health care delivery systems, product development, and other purposes. The ideas stated and demonstrated in this paper should be practical to both beginning scholars and veteran professionals in the biomedical engineering field as well as useful for seminar and workshop participants in seminars and workshops on biomedical engineering literature.

Clustering in point processes on linear networks using nearest neighbour volumes

This study introduces a novel method specifically designed to detect clusters of points within linear networks. This method extends a classification approach used for point processes in spatial contexts. Unlike traditional methods that operate on planar spaces, our approach adapts to the unique geometric challenges of linear networks, where classical properties of point processes are altered, and intuitive data visualisation becomes more complex. Our method utilises the distribution of the Kth nearest neighbour volumes, extending planar-based clustering techniques to identify regions of increased point density within a network. This approach is particularly effective for distinguishing overlapping Poisson processes within the same linear network. We demonstrate the practical utility of our method through applications to road traffic accident data from two Colombian cities, Bogota and Medellin. Our results reveal distinct clusters of high-density points in road segments where severe traffic accidents (resulting in injuries or fatalities) are most likely to occur, highlighting areas of increased risk. These clusters were primarily located on major arterial roads with high traffic volumes. In contrast, low-density points corresponded to areas with fewer accidents, likely due to lower traffic flow or other mitigating factors. Our findings provide valuable insights for urban planning and road safety management.

A Comprehensive Comparative Study of Intuitive Physics Modeling in Machine Learning Trained with Cartoon and Realistic Data

Abstract. This study delves into the influence of training data typesspecifically cartoon versus realistic visual datasetson the development of intuitive physics modeling in machine learning. Intuitive physics, the inherent human ability to understand and predict the physical properties and dynamics of objects, presents a significant challenge for current AI systems to replicate accurately. Leveraging YOLOv5, a cutting-edge object detection model, this research systematically evaluates the cognitive understanding and performance of AI models trained on distinct types of visual data. The findings reveal that the visual complexity inherent in the training datasets plays a crucial role in shaping the model's ability to generalize and accurately perform intuitive physics tasks. Models trained on cartoon datasets exhibited different learning patterns and generalization capabilities compared to those trained on realistic data, providing valuable insights into the role of data representation in AI training. This research offers both theoretical advancements in understanding AI's cognitive limitations and practical guidance for designing AI systems that can interact with the physical world more effectively. Ultimately, the study contributes to bridging the gap between human cognition and machine learning, pushing the boundaries of what AI can achieve in modeling complex, real-world phenomena.

Mixed reality applications in upper extremity surgery: the future is now.

Mixed reality refers to the integration of virtual reality into the real-world environment. This digital content can be interacted with in real time. The emergence of mixed reality technology has been made possible by the introduction of head-mounted displays, which are being utilized across multiple surgical specialties. In upper extremity surgery, mixed reality has widespread applications in trauma, corrective surgery, arthroplasty, arthroscopy, and oncology. Preoperatively, mixed reality allows for complex 3D planning. Intraoperatively, surgeons can access this 3D data in a sterile environment. While in its infant stages, mixed reality is likely to become a powerful tool for intraoperative guidance and navigation. Mixed reality can change the paradigm of communication, as it allows the sharing of visual data from the surgeon's perspective, enabling remote assistance and participation.

Nudging with Narrative Visualization: Communicating to a Young Adult Audience in the Pandemic

Effective narrative visualization communicates information by integrating story-telling and data visualization in a comprehensible, compelling manner. The compelling aspect of effective narrative visualization consequentially results in the potential to shift the attitude of an audience. However, there is much to understand about how narrative visualization can best be designed to influence target audiences. This paper focuses on an empirical experiment where we examined the effects of two communication strategies - anthropomorphism and personal identification - on a young adult audience. In particular, we wanted to understand which strategy, when integrated into narrative visualization, can nudge a specific audience's attitude towards greater consideration in the context of the COVID-19 pandemic. Our results indicated that the personal identification communication strategy was the most successful in nudging participants. This study contributes a better grasp of how technologies such as narrative visualization, using different communication strategies, can deliver more targeted messaging.

Dandy walker syndrome: A bibliometric analysis of the most 100 cited articles

Introduction: Dandy-Walker Syndrome (DWS), a complex neurodevelopmental disorder, has intrigued clinicians and researchers since its description by physicians Walter Dandy and Arthur Walker. Despite its recognition for nearly a century, understanding its etiology, pathogenesis, and clinical manifestations remains elusive. This bibliometric analysis aims to elucidate influential academic works on DWS. Methods: In January 2024, we conducted a Scopus search for articles on DWS and identified the top 100 referenced publications. The Harzing Publish or Perish search engine was utilized with relevant terms, including “Dandy-Walker,” “Dandy-Walker Syndrome,” and “Dandy-Walker Malformation.” Data from Scopus, including publication details and citation counts, were compiled and organized using Microsoft Excel. Statistical analysis and data visualization were performed using Python, with Pandas, Matplotlib, Seaborn, and NetworkX libraries employed for this purpose. Results: The bibliometric analysis of DWS research revealed key insights. Significant research output was noted in the 2000-2009 and 1990-1999 decades. The cumulative citations totaled 6,059, with an average of 2.60 citations per year per article. Leading authors included W B Dobyns, Kathleen J Millen, and G Pilu. Institutions such as the University of California and Harvard Medical School were prominent, with the United States being the predominant contributor. Major journals like the American Journal of Medical Genetics played significant roles. Conclusion: This bibliometric study summarizes the most-cited articles on DWS, providing light on the field and its seminal works that have shaped both present-day clinical treatment and the trajectory of future research.

Data Visualization of Student Academic Performance Analysis

Understanding and enhancing student academic performance has become increasingly crucial, yet educators often face data overload, making identifying and prioritizing factors influencing student performance difficult. This study seeks to create a comprehensive system for visualizing and analysing student academic performance. The research follows the waterfall model, with clearly defined phases to ensure an organized and complete development process. The study's main objectives include determining the requirements and techniques to analyse student academic performance and developing and designing a data visualization dashboard using Microsoft Power BI. The final phase consists of evaluating of the student performance dashboard using the Technology Acceptance Model (TAM). A total of 35 respondents was randomly chosen for evaluation and hands-on sessions. The dimensions encompassed Perceived Ease of Use, Perceived Usefulness, Attitude towards Using, and Behavioural Intention. The Attitude of Using received the highest mean score of 4.39, closely followed by Behavioural Intention with a score of 4.38. The results indicate that the participants have a high level of satisfaction with using the dashboard, considering it advantageous and indicating a desire for future implementation. Finally, the project exhibits potential for further advancement, encompassing predictive analytics and tailored learning recommendations, aiming to provide even more precise and actionable insights into student performance.

Convolutional-free Malware Image Classification using Self-attention Mechanisms

Malware analysis is a critical aspect of cybersecurity, aiming to identify and differentiate malicious software from benign programmes to protect computer systems from security threats. Despite advancements in cybersecurity measures, malware continues to pose significant risks in cyberspace, necessitating accurate and rapid analysis methods. This paper introduces an innovative approach to malware classification using image analysis, involving three key phases: converting operation codes into RGB image data, employing a Generative Adversarial Network (GAN) for synthetic oversampling, and utilising a simplified Vision Transformer (ViT)-based classifier for image analysis. The method enhances feature richness and explainability through visual imagery data and addresses imbalanced classification using GAN-based oversampling techniques. The proposed framework combines the strengths of convolutional autoencoders, hybrid classifiers, and adapted ViT models to achieve a balance between accuracy and computational efficiency. As shown in the experiments, our convolutional-free approach possesses excellent accuracy and precision compared with convolutional models and outperforms CNN models on two datasets, thanks to the multi-head attention mechanism. On the Big2015 dataset, our model outperforms other CNN models with an accuracy of 0.8369 and an AUC of 0.9791. Specifically, our model reaches an accuracy of 0.9697 and an F1 score of 0.9702 on MALIMG, which is extraordinary.

Growth of a Tessellation: Geometric rules for the Development of Stingray Skeletal Patterns.

The skeletons of sharks and rays, fashioned from cartilage, and armored by a veneer of mineralized tiles (tesserae) present a mathematical challenge: How can the continuous covering be maintained as the skeleton expands? This study, using microCT and custom visual data analyses of growing stingray skeletons, systematically examines tessellation patterns and morphologies of the many thousand interacting tesserae covering the hyomandibula (a skeletal element critical to feeding), over a two-fold developmental change in hyomandibula length. The number of tesserae remains surprisingly constant, even as the hyomandibula expands isometrically, with all hyomandibulae displaying self-similar distributions of tesserae shapes/sizes. Although the distribution of tesserae geometries largely agrees with the rules for polyhedra tiling of complex surfaces-dominated by hexagons and a minor fraction of pentagons and heptagons, but very few other polygons-the agreement with Euler's classic mathematical laws is not perfect. Contrary to the assumed uniform growth rate (which is shown would create geometric incompatibilities), larger tesserae grow faster to accommodate skeletal expansion. It is hypothesized that this local regulation of global system complexity is driven by tension (from cartilaginous core expansion) in the fibers connecting tesserae, with strain-responsive cells orchestrating local mineral apposition.