Visual Analysis Method Research Articles

Diagnosing Ensemble Few-Shot Classifiers.

The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes and make improvements. To tackle this issue, we propose a visual analysis method, FSLDiagnotor. Given a set of base learners and a collection of samples with a few shots, we consider two problems: 1) finding a subset of base learners that well predict the sample collections; and 2) replacing the low-quality shots with more representative ones to adequately represent the sample collections. We formulate both problems as sparse subset selection and develop two selection algorithms to recommend appropriate learners and shots, respectively. A matrix visualization and a scatterplot are combined to explain the recommended learners and shots in context and facilitate users in adjusting them. Based on the adjustment, the algorithm updates the recommendation results for another round of improvement. Two case studies are conducted to demonstrate that FSLDiagnotor helps build a few-shot classifier efficiently and increases the accuracy by 12% and 21%, respectively.

The Importance of Classifying the Traditional Mosulian Ornaments in Enhancing the Conservation Process

Ornaments are effective interior design elements, which enhance the identity and heritage value of heritage buildings. The Mosulian ornaments represent the mixture of the culture and architectural, which are produced by Mosulian marble ‘Farish’. After the war in 2017, there was a dramatic disappearance of the original types of Mosulian ornament because of the non-oriented restoration and conservation process. UNESCO and the government sector suffered from the availability of information to find a guideline to be used in the restoration and conservation process. However, the shortage of documentations led to the disappearance of valuable ornaments, especially after investing the new technology in producing the ornaments in the conservation processes. The study aims to classify the Mosulian ornaments in terms of shape, material, and position, to construct a platform and data set of the Mosulian ornaments. The study applied a qualitative approach using observation and visual analysis methods to observe the results of the analysis with a checklist form. The results indicated that Mosulian architecture is rich in ornamental elements, floral ornaments are used in the greatest ratio than geometric, while animal shapes are rarely used. The principle of repetition in two and four steps is the main principle used in generating process. The classification of ornament can enhance the heritage value of the buildings, designers and developers can rely on this classification to design and reuse the ornament.

Materialne dziedzictwo kulturowe polsko-niemieckiego obszaru przygranicznego – geneza, stan i perspektywy. Studium przypadku Ziemi Lubuskiej

The article is part of the current scientific considerations on material cultural heritage from the perspective of historical geography. This approach means focusing on the historical dimension of the contemporary world and on identifying the influence of the former spatial organization of a given area on its current features. The main goal of the article is to analyze the present condition of the most important elements of the immovable material cultural heritage of the Polish-German border area, focusing on the case study of Lubusz Land. This analysis is preceded by a discussion of the origins and typical features of individual heritage elements in the research area, and concludes with an attempt to define the perspectives for these components in terms of their social perception, protection and role in the development of contemporary spatial structures and the preservation of their historic character. The research in the scope specified above was carried out with the use of the methodological apparatus of history and socio-economic geography, including the philological, genetic and retrogressive methods as well as visual field analysis, mathematical and statistical methods and the cartographic presentation of phenomena. The conducted analysis allowed the formulation of conclusions about the quantitative and structural richness of the cultural heritage in the Polish-German border area, which in the genetic aspect is primarily related to the period of domination of German culture in the past centuries. However, the physical condition of this heritage is actually critical due to the impact of economic, legal and property, and institutional factors as well as those related to awareness that were liberated as a result of the collapse of the German state in its shape before 1945, the events of World War II, and radical political, social and economic changes in the post-war period. The post-socialist systemic transformation, initiated in Poland and East Germany in 1990, did not bring about any fundamental positive changes regarding the determinants and factors shaping the fate of the immovable material cultural heritage of the Polish-German border area. This conclusion applies especially to the eastern (Polish) part of this area. Negative tendencies are continued.

Prediction and visualization analysis of drilling energy consumption based on mechanism and data hybrid drive

To obtain an accurate and reliable energy consumption (EC) prediction model, and to quantify the relationship between drilling power, EC, and energy efficiency. An EC prediction model and multi-angle visualization analysis method driven by mechanism and data are proposed. Firstly, the power and energy models of each stage of the drilling rig are established through detailed power flow theory. Additionally, based on the deviation between the actual EC results and the theoretical mechanism model calculation results, a least squares support vector machine (LSSVM) data compensation model is established, and the LSSVM model parameters are optimized by the improved whale optimization algorithm; after that, multi-angle visualization analysis of energy parameters was performed by drilling power histogram, energy efficiency ring diagram, energy sequence diagram, and energy bubble diagram. Finally, the experiment of curb drilling shows that the prediction error of the hybrid drive model is 2.44%. Compared with the prediction results of the mechanism model and the data-driven model, the average prediction error is reduced by 0.76% and 2.25%, which verifies the high efficiency of the hybrid-driven model. Also, through the multi-angle visualization analysis of energy parameters, the drilling energy saving is 2127.4 kJ, and the energy efficiency is improved by 26.71%.

PRRGNVis: Multi-Level Visual Analysis of Comparison for Predicted Results of Recurrent Geometric Network

The structure of a protein determines its function, and the advancement of machine learning has led to the rapid development of protein structure prediction. Protein structure comparison is crucial for inferring the evolutionary relationship of proteins, drug discovery, and protein design. In this paper, we propose a multi-level visual analysis method to improve the protein structure comparison between predicted and actual structures. Our method takes the predicted results of the Recurrent Geometric Network (RGN) as the main research object and is mainly designed following three levels of protein structure visualization on RGN. Firstly, at the prediction accuracy level of the RGN, we use the Global Distance Test—Total Score (GDT_TS) as the evaluation standard, then compare it with distance-based root mean square deviation (dRMSD) and Template Modeling Score (TM-Score) to analyze the prediction characteristics of the RGN. Secondly, the distance deviation, torsion angle, and other attributes are used to analyze the difference between the predicted structure and the actual structure at the structural similarity level. Next, at the structural stability level, the Ramachandran Plot and PictorialBar combine to be improved to detect the quality of the predicted structure and analyze whether the amino acid residues conform to the theoretical configuration. Finally, we interactively analyze the characteristics of the RGN with the above visualization effects and give reasons and reasonable suggestions. By case studies, we demonstrate that our method is effective and can also be used to analyze other predictive network results.

New methods for analysing diachronic suffix competition across registers

AbstractThis paper tracks stylistic variation in the use of two roughly synonymous suffixes, the Romance -ityand the native -ness, during the Early Modern English period. We seek to verify from a statistical viewpoint the claims ofRodríguez-Puente (2020), who reports on a decrease of -nessin favour of -ityin registers representative of the speech-written and formal-informal continua at that time. To this end, we develop new methods of statistical and visual analysis that enable diachronic comparisons of competing processes across subcorpora, building upon an earlier method bySäily and Suomela (2009). Our results confirm that -itygained ground first in written registers and then spread towards speech-related registers, and we are able to time this change more accurately thanks to a novel periodisation. We also provide strong statistical support indicating that the proportion of -itywas significantly higher in legal registers than in other registers.

Bibliometric analysis of research trends of physical activity intervention for autism spectrum disorders.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by social impairment, restricted interests, and repetitive stereotyped behaviors. At present, its pathogenesis has not been fully understood. Various methods are used for clinical treatment and intervention, among which physical activity (PA) intervention also has an obvious effect. This study has used bibliometric methods and visual analysis methods to analyze 885 studies of PA intervention in ASD from 2003 to 2022 in the Web of Science (WoS) database in order to provide theoretical support for the follow-up research on the effect of PA with ASD. The main findings of this study are as follows. First, the literature on PA interventions in ASD research showed a growing trend. The leading institution in this field is the University of Delaware, forming a core group of authors represented by authors such as Sean Healy and Carol Curtin et al. Second, the research focus of this research area mainly includes PA interventions for children and adolescents with ASD. PA can improve symptoms such as stereotyped behaviors and motor function in patients with ASD as well as can reduce childhood obesity rates and improve quality of life. Third, skill, youth, prevalence, and meta-analysis systematic reviews were found. It is the long-term concern and focus of researchers. In conclusion, the current research is only a short-term analysis, and it is not possible to verify the long-term effect; thus, future data analysis should evaluate and explore the long-term effects of PA interventions on ASD including cohort and longitudinal study types focused on the rehabilitation of patients with ASD. Moreover, testing the sustainability of benefits for children with ASD and constructing a multidimensional exercise integrated intervention model are the main directions for future research in this field.

Research on Classroom Emotion Recognition Algorithm Based on Visual Emotion Classification.

In this paper, we construct a classroom emotion recognition algorithm by classifying visual emotions for improving the quality of classroom teaching. We assign weights to the training images through an attention mechanism network and then add a designed loss function so that it can focus on the feature parts of face images that are not obscured and can characterize the target emotion, thus improving the accuracy of facial emotion recognition under obscuration. Analyze the salient expression features of classroom students and establish a classification criteria and criteria library. The videos of classroom students' facial expressions are collected, a multi-task convolutional neural network (MTCNN) is used for face detection and image segmentation, and the ones with better feature morphology are selected to build a standard database. A visual motion analysis method with the fusion of overall and local features of the image is proposed. To validate the effectiveness of the designed MTCNN model, two mainstream classification networks, VGG16 and ResNet18, were tested and compared with MTCNN by training on RAF-DB, masked dataset, and the classroom dataset constructed in this paper, and the final accuracy after training was 78.26% and 75.03% for ResNet18 and VGG16, respectively. The results show that the MTCNN proposed in this paper has a better recognition effect. The test results of the loss function also show that it can effectively improve the recognition accuracy, and the MTCNN model has an accuracy of 93.53% for recognizing students' facial emotions. Finally, the dataset is extended with the training method of expression features, and the experimental study shows that the method performs well and can carry out recognition effectively.

PNMAVis: Visual Analysis Tool of Protein Normal Mode for Understanding Cavity Dynamics

Molecular cavities play a critical role in our understanding of molecular phenomena. Recently, a number of works on the visual analysis of protein cavity dynamics have been developed to allow experts and users to interactively research dynamic cavity data. However, previous explorations are limited to studying cavity-lining amino acids and they lack a consideration of the impact of the key amino acids, which are far away from the cavity but have an important impact on the cavity. When studying protein amino acids, biochemists use normal mode decomposition to analyze protein changes on a time scale. However, the high-dimensional parameter space generated via decomposition is too large to be analyzed in detail. We present a novel approach that combines cavity characterization and normal mode analysis (NMA) for cavity dynamics analysis to reduce and explore this vast space through interactive visualization. PNMAVis can analyze whether direct factors (cavity-lining amino acids) or indirect factors (key amino acids) affect cavity changes, through multiple linked 2D and 3D views. The visual analysis method we proposed is based on close cooperation with domain experts, aiming to meet their needs to explore the relationship between cavity stability and cavity-lining amino acids fluctuations and key amino acids fluctuations as much as possible, and also to help domain experts identify potential allosteric residues. The effectiveness of our new method is demonstrated by the case study conducted by cooperative protein experts on a biological field case and an open normal mode data set.

“Do not deceive me anymore!” interpretation through model design and visualization for instagram counterfeit seller account detection

Counterfeit goods sold online have amounted to $330 billion in losses worldwide. Of these, luxury brand losses account for $30.3 billion. The social and economic effects of counterfeit goods have become more severe with the shift of counterfeit sales channels to social networking services (SNSs) since the first decade of the 2000s when these networks became active. In particular, the number of counterfeit sellers on Instagram increased by more than 171% in 2019. This study endeavors to detect counterfeit seller accounts in the SNS environment through a deep learning method that implements an algorithm to differentiate legitimate and counterfeit seller accounts. We designed a model to classify counterfeit seller accounts and general accounts using image and textual data collected from Instagram. As a result, the proposed model obtained a final account detection accuracy of 100% and demonstrated the possibility of use as a counterfeit seller account detector. Moreover, the elements that influenced the results and the parts that the model focused on were identified using a visual analysis method to improve the interpretation capability of the algorithm and explain the results. The difference between human and machine judgments was analyzed based on the visualization.

A uncertainty visual analytics approach for bus travel time

Bus travel time is uncertain due to the dynamic change in the environment. Passenger analyzing bus travel time uncertainty has significant implications for understanding bus running errors and reducing travel risks. To quantify the uncertainty of the bus travel time prediction model, a visual analysis method about the bus travel time uncertainty is proposed in this paper, which can intuitively obtain uncertain information of bus travel time through visual graphs. Firstly, a Bayesian encoder–decoder deep neural network (BEDDNN) model is proposed to predict the bus travel time. The BEDDNN model outputs results with distributional properties to calculate the prediction model uncertainty degree and provide the estimation of the bus travel time uncertainty. Second, an interactive uncertainty visualization system is developed to analyze the time uncertainty associated with bus stations and lines. The prediction model and the visualization model are organically combined to better demonstrate the prediction results and uncertainties. Finally, the model evaluation results based on actual bus data illustrate the effectiveness of the model. The results of the case study and user evaluation show that the visualization system in this paper has a positive impact on the effectiveness of conveying uncertain information and on user perception and decision making.

Visual analysis method of foundation pit monitoring information based on BIM platform

In order to visually express the safety monitoring information of foundation pits and underground engineering, realize the efficient management of massive dynamic safety monitoring information during the construction of foundation pits and underground engineering, as well as assist safety analysis, a building information model (BIM)-based Foundation pit and underground engineering dynamic safety monitoring information integration and network visualization method is proposed in the article. Firstly, the research builds a three-dimensional BIM model of foundation pit engineering based on the analysis of the element composition of the three-dimensional virtual scene of the foundation pit and underground engineering. Then, apply the method of key field mapping to establish the dynamic coupling between the BIM model and the safety monitoring information. Finally, the research realizes the virtual display of the construction process based on the three-dimensional visualization function of BIM technology. Furthermore, combined with the actual situation, the corresponding system is developed and applied in a certain project, which realized the visual integration of dynamic information of engineering safety monitoring and BIM under the network environment, and provided a support platform for the safety analysis of foundation pits and underground engineering.

Innovative methods and tools for obtaining pre-forecast information in the socio-economic processes research

By using the phase analysis algorithm mechanism and the visualization and data analysis methods, the authors clearly show the resulting synergistic effect from the complex socio-economic processes research in the context of the triad results: the initial time series, a number of its increments and aggregated data. The article is devoted to the adaptation of mathematical methods of nonlinear dynamics and the description of the tool for obtaining pre-forecast information about complex economic processes, in particular, the phase analysis algorithm testing in the research of the time series of the tourist flow to the Dombai ski village of the Karachay-Cherkess Republic. Phase analysis is the method for studying local fluctuations in a time series that are asymmetric, irregular, and have an unstable period.

DOSE OPTIMIZATION WITH mAs REDUCTION OF 15% USING COMPUTED RADIOGRAPHY ON RADIOGRAPHIC EXAMINATIONS PELVIC AP PROJECTION

Background: Routine pelvic radiograph examination commonly performed in diagnostic radiology services is a pelvic examination of anteroposterior projection (AP). This results in direct exposure to ionizing radiation to the internal organs in the lower abdomen, especially the reproductive organs. Purpose: Optimizing the dosage of AP projection pelvic radiographs. Method: Research is conducted quantitatively and used experimental approach with an analysis of 15% mAs reduction from the standard mAs value on AP projection pelvic examination on radiation dose and image quality using anthropomorphic phantoms. The radiation dose analysis uses the exposure index indicator. In contrast, the image quality uses the Visual Grading Analysis method, then it was continued with the Kappa Cohens test to determine the level of agreement between 2 respondents. Result: The exposure factor with the mAs value reduced by 15% from the standard exposure factor on the AP projection pelvic radiography affected the decrease in the value exposure index. The EI value generated from the optimization exposure factor shows a decrease to 300 EI, which means the dose produced is only half of the standard exposure factor dose but still produces an acceptable image, as evidenced by the VGA score. As an assessment of image quality. In this study, there was no significant difference with range VGA scores 1,7. Besides that, the test had the Kappa Cohens level of agreement with a value of 0.5-0.8. Conclusion: All images resulting from the 15% mAs value reduction variation can be used as a diagnostic assessment.

Visualization Assisted Approach to Anomaly and Attack Detection in Water Treatment Systems

The specificity of the water treatment field, associated with water transmission, distribution and accounting, as well as the need to use automation and intelligent tools for various information solutions and security tools, have resulted in the development of integrated approaches and practical solutions regarding various aspects of the functioning of such systems. The research problem lies in the insecurity of water treatment systems and their susceptibility to malicious influences from the side of potential intruders trying to compromise the functioning. To obtain initial data needed for assessing the states of a water treatment system, the authors have developed a case study presenting a combination of a physical model and a software simulator. The methodology proposed in the article includes combining methods of machine learning and visual data analysis to improve the detection of attacks and anomalies in water treatment systems. The selection of the methods and tuning of their modes and parameters made it possible to build a mechanism for efficient detection of attacks in data from sensors with accuracy values above 0.95 for each class of attack and mixed data. In addition, Change_Measure metric parameters were selected to ensure the detection of attacks and anomalies by using visual data analysis. The combined method allows identifying points when the functioning of the system changes, which could be used as a trigger to start resource-intensive procedures of manual and/or machine-assisted checking of the system state on the basis of the available machine learning models that involve processing big data arrays.

A survey of visual analytics in urban area

AbstractNowadays, the population has been overgrowing due to urbanization, yielding many severe problems in the urban area, including traffic congestion, unbalanced distribution of urban hotspots, air pollution and so on. Due to the uncertainty of the urban environment, it always needs to integrate experts' domain knowledge into solving these issues. In recent years, the visual analytics method has been widely used to assist domain experts in solving urban problems with its intuitiveness, interactivity and interpretability. In this survey, we first introduce the background of urban computing, present the motivation of visual analytics in the urban area and point out the characteristics of visual analytics methods. Second, we introduce the most frequently used urban data, analyse the main properties and provide an overview on how to use these data. Thereafter, we propose our taxonomy for visual analytics in the urban area and illustrate the taxonomy. The taxonomy provides four levels for visual analytics on urban data from a new perspective based on the four stages in data mining. Four levels from our taxonomy include: descriptive analytics, diagnostic analytics, predictive analytics and prescriptive analytics. Finally, we conclude this survey by discussing the limitations of the existing related works and the challenges to visual analytics in the urban area.

Personality and safety behavior: An analysis of worldwide research on road and traffic safety leading to organizational and policy implications

This study presents a comprehensive systematic review of worldwide research on the relationship between personality and safety behaviors in context of road and traffic safety to identify key areas, current global trends, and suggest future research direction towards understanding nuances of personality as predictor of accident involvement and risk-taking behaviors. Using bibliometric and visual analysis methods, we examine a sample of 613 studies extracted from the Scopus database based on a search query string with rigorous inclusion and exclusion criteria. Keyword co-occurrence analysis shows five clusters representing focal areas studied by scholars in the field globally which are then classified into central, niche, and emergent themes using the strategic diagram. Further, using citation analysis, co-citation analysis and bibliographic coupling, we highlight the intellectual structure of the knowledge domain and identify potential future areas for research. The results indicate that the research field is yet to be fully developed and more research is warranted towards wider personality traits and subtypes, using different structures of personality, employing longitudinal designs and behavioral methods, and expending insights from personality research for accident prevention and to develop and predict directives for self-driving vehicles. The study concludes by presenting implications for organizations and policymakers.

From researchers to academic entrepreneurs: a diachronic analysis of the visual representation of academics in university annual reports

Influenced by the global neoliberalization of higher education, academic entrepreneurialism has become a new paradigm of university development and has brought about profound changes in various types of university discourse. Against this backdrop, this study investigates the transformations in the visual depiction of academics in the annual reports of six major universities in Hong Kong during the past two decades. Drawing on critical visual analysis, the study shows that the communicative purposes of the images have shifted from reporting the research process to promoting research outcomes. The visual identities of academics have shown clear transformations of becoming increasingly individualized, entrepreneurial and self-promotional. With a higher degree of social interaction and closer social distance with viewers, they are playing an increasingly important role in building public relations. The study enriches the social analysis of neoliberalization as a process through the quantitative and diachronic lens. It demonstrates how a visual analytical method applied to the critical analysis of identity construction and university discourse can provide an explicit understanding of the visual manifestations of neoliberalism in higher education and its diachronic change.

GEMvis: a visual analysis method for the comparison and refinement of graph embedding models

GEMvis: a visual analysis method for the comparison and refinement of graph embedding models

The role of cartographic culture in the development of cognitive, scientific, communicative and creative human activity

The article is devoted to the study of the role of cartographic culture in the development of cognitive, scientific, communicative and creative human activity. Geographical maps are considered as a phenomenon of world culture and their significant role in many spheres of human life and activity is highlighted. The concept of cartographic culture is revealed. The research is based on literary, cartographic sources, materials of museum expositions and modern cartographic exhibitions, a collection of maps of the authors' personal archive, significant experience in teaching cartographic and geographical disciplines at university and school. The methods of visual and system-structural analysis, comparison, historical and logical are used in the research. The scientific novelty of the research consists in the systematization and generalization of multiple diverse information characterizing the manifestations of cartographic culture, the conditions of its formation, the components of this culture, in proving by examples the importance of cartographic culture in the life of a modern person. The main conclusions of the study: cartographic culture encompasses the ability of a person to understand, know, read maps; have a developed cartographic thinking and a formed cartographic worldview; an idea of the richness and diversity of cartographic works; the ability to create at least at an elementary level thematic cartographic schemes, perceive and recreate cartographic images. The main component of cartographic culture is mastering the language of geographical maps as one of the most important means of communication, having great cognitive, ideological, ideological significance, having visibility, accessibility, information capacity, understandable at the international level.