Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00019
Ying Zhu, Cameron Detig, Steven Kane, Gary Lourie
Kinematic motion analysis is widely used in health-care, sports medicine, robotics, biomechanics, sports science, etc. Motion capture systems are essential for motion analysis. There are three types of motion capture systems: marker-based capture, vision-based capture, and volumetric capture. Marker-based motion capture systems can achieve fairly accurate results but attaching markers to a body is inconvenient and time-consuming. Vision-based, marker-less motion capture systems are more desirable because of their non-intrusiveness and flexibility. Volumetric capture is a newer and more advanced marker-less motion capture system that can reconstruct realistic, full-body, animated 3D character models. But volumetric capture has rarely been used for motion analysis because volumetric motion data presents new challenges. We propose a new method for conducting kinematic motion analysis using volumetric capture data. This method consists of a three-stage pipeline. First, the motion is captured by a volumetric capture system. Then the volumetric capture data is processed using the Iterative Closest Points (ICP) algorithm to generate virtual markers that track the motion. Third, the motion tracking data is imported into the biomechanical analysis tool OpenSim for kinematic motion analysis. Our motion analysis method enables users to apply numerical motion analysis to the skeleton model in OpenSim while also studying the full-body, animated 3D model from different angles. It has the potential to provide more detailed and in-depth motion analysis for areas such as healthcare, sports science, and biomechanics.
{"title":"Kinematic Motion Analysis with Volumetric Motion Capture","authors":"Ying Zhu, Cameron Detig, Steven Kane, Gary Lourie","doi":"10.1109/IV56949.2022.00019","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00019","url":null,"abstract":"Kinematic motion analysis is widely used in health-care, sports medicine, robotics, biomechanics, sports science, etc. Motion capture systems are essential for motion analysis. There are three types of motion capture systems: marker-based capture, vision-based capture, and volumetric capture. Marker-based motion capture systems can achieve fairly accurate results but attaching markers to a body is inconvenient and time-consuming. Vision-based, marker-less motion capture systems are more desirable because of their non-intrusiveness and flexibility. Volumetric capture is a newer and more advanced marker-less motion capture system that can reconstruct realistic, full-body, animated 3D character models. But volumetric capture has rarely been used for motion analysis because volumetric motion data presents new challenges. We propose a new method for conducting kinematic motion analysis using volumetric capture data. This method consists of a three-stage pipeline. First, the motion is captured by a volumetric capture system. Then the volumetric capture data is processed using the Iterative Closest Points (ICP) algorithm to generate virtual markers that track the motion. Third, the motion tracking data is imported into the biomechanical analysis tool OpenSim for kinematic motion analysis. Our motion analysis method enables users to apply numerical motion analysis to the skeleton model in OpenSim while also studying the full-body, animated 3D model from different angles. It has the potential to provide more detailed and in-depth motion analysis for areas such as healthcare, sports science, and biomechanics.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130618527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00018
Nuno Cid Martins, Bernardo Marques, Paulo Dias, B. Santos
Situated Visualization (SV), encompassing all the visualizations that change their appearance based on context, by considering the visualizations that are relevant to the physical context in which they are displayed [1], has been recognized as a method with potential in many situations, as is the case of supporting decision making [2]. Augmented and Mixed Reality (AR/MR) are well suited to assist in such scenarios, given its ability to display additional data regarding the real-world context and be supported by context-driven visualization techniques [3]. Though some perspectives on the SV model have been proposed, such as space, time, place, activity and community, an appropriate systematization, covering the main definitions and perspectives has yet to be established. Hence, there is an urge to obtain a more comprehensive description. The work presented in this paper characterizes the SV model, within the scope of AR/MR, shows a critical analysis of the existing knowledge, expanding the SV model and in turn hoping to elicit discussion within the research community.
{"title":"Augmenting the Reality of Situated Visualization","authors":"Nuno Cid Martins, Bernardo Marques, Paulo Dias, B. Santos","doi":"10.1109/IV56949.2022.00018","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00018","url":null,"abstract":"Situated Visualization (SV), encompassing all the visualizations that change their appearance based on context, by considering the visualizations that are relevant to the physical context in which they are displayed [1], has been recognized as a method with potential in many situations, as is the case of supporting decision making [2]. Augmented and Mixed Reality (AR/MR) are well suited to assist in such scenarios, given its ability to display additional data regarding the real-world context and be supported by context-driven visualization techniques [3]. Though some perspectives on the SV model have been proposed, such as space, time, place, activity and community, an appropriate systematization, covering the main definitions and perspectives has yet to be established. Hence, there is an urge to obtain a more comprehensive description. The work presented in this paper characterizes the SV model, within the scope of AR/MR, shows a critical analysis of the existing knowledge, expanding the SV model and in turn hoping to elicit discussion within the research community.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114358845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00038
Nicola Cerioli, Rupesh Vyas, M. Reeve, M. Masoodian
Although network visualizations are becoming increasingly common, designing such visualizations can be challenging due to the number of visual elements and non-linear relations that they need to display. The main design challenge faced is finding the right trade-off between providing a sufficient level of information detail while keeping the visual complexity of the visualization as low as possible. One way of overcoming this challenge is to rely on the use of mental models that are familiar to the users of network visualizations. In this paper, we propose the use of a mental interaction model similar to that of map visualizations - generally based on geographical maps - as the basis for visual design of network diagrams. We argue that such a mental model would foster a set of network interaction tasks that can be defined broadly as wayfinding. We present the process of wayfinding from a semiotic standpoint, and match its main key points to those of interaction tasks with network diagrams. As a case study for this analysis, we also present a prototype network diagram visualization tool, called Colocalization Network Explorer, which we have developed to support the exploration of the relationships between various diseases and the portion of the human genome that is potentially involved in their onset. Additionally, we describe how the design process has benefited from the adoption of the wayfinding mental model.
{"title":"Mapping the Colocalization Network: A Wayfinding Approach to Interacting with Complex Network Diagrams","authors":"Nicola Cerioli, Rupesh Vyas, M. Reeve, M. Masoodian","doi":"10.1109/IV56949.2022.00038","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00038","url":null,"abstract":"Although network visualizations are becoming increasingly common, designing such visualizations can be challenging due to the number of visual elements and non-linear relations that they need to display. The main design challenge faced is finding the right trade-off between providing a sufficient level of information detail while keeping the visual complexity of the visualization as low as possible. One way of overcoming this challenge is to rely on the use of mental models that are familiar to the users of network visualizations. In this paper, we propose the use of a mental interaction model similar to that of map visualizations - generally based on geographical maps - as the basis for visual design of network diagrams. We argue that such a mental model would foster a set of network interaction tasks that can be defined broadly as wayfinding. We present the process of wayfinding from a semiotic standpoint, and match its main key points to those of interaction tasks with network diagrams. As a case study for this analysis, we also present a prototype network diagram visualization tool, called Colocalization Network Explorer, which we have developed to support the exploration of the relationships between various diseases and the portion of the human genome that is potentially involved in their onset. Additionally, we describe how the design process has benefited from the adoption of the wayfinding mental model.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"57 13","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132738780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00077
Harshitha Ravindra, Jaya Sreevalsan-Nair
Population survey data is important for understanding the status of well-being along any dimensions, i.e., social, economic, political, health, etc. This data generates spatial point patterns which can be explored and analyzed using visualization. Given the spatial aspect of the data, there is a requirement of using cartographic maps, which are mostly limited to visualizing a single variable in most cases. Here, it is also important that the choice of visualizations also enable scale-aware analysis when zooming in and out of the maps, since the data is from the smaller political units and can be aggregated to larger political units. Thus, we explore the different visual compositions which use mathematical operators and the composite layouts for visualizing multiple outcome variables in survey data. The mathematical operators allow the use of univariate and bivariate data modeling and representation, and composite layouts of interest are juxtaposition and superimposed views. We demonstrate the inferences from visualizations using a case study on malnutrition in children under five in India. Our work shows that a visual composition of binary relationships represented in a visualization and a juxtaposed layout of such pairwise variables is effective in making inferences from the multivariate spatial point patterns in population data.
{"title":"Composition of Geospatial Visualizations for Scale-aware Views of Multiple Outcome Variables in Population Surveys","authors":"Harshitha Ravindra, Jaya Sreevalsan-Nair","doi":"10.1109/IV56949.2022.00077","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00077","url":null,"abstract":"Population survey data is important for understanding the status of well-being along any dimensions, i.e., social, economic, political, health, etc. This data generates spatial point patterns which can be explored and analyzed using visualization. Given the spatial aspect of the data, there is a requirement of using cartographic maps, which are mostly limited to visualizing a single variable in most cases. Here, it is also important that the choice of visualizations also enable scale-aware analysis when zooming in and out of the maps, since the data is from the smaller political units and can be aggregated to larger political units. Thus, we explore the different visual compositions which use mathematical operators and the composite layouts for visualizing multiple outcome variables in survey data. The mathematical operators allow the use of univariate and bivariate data modeling and representation, and composite layouts of interest are juxtaposition and superimposed views. We demonstrate the inferences from visualizations using a case study on malnutrition in children under five in India. Our work shows that a visual composition of binary relationships represented in a visualization and a juxtaposed layout of such pairwise variables is effective in making inferences from the multivariate spatial point patterns in population data.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131981649","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00026
A. Figueiras
We take a new approach to analyze what the general focus of Visualization research is, among the panoply of different topics and approaches. Due to the intrinsic characteristics of this kind of in-depth research, being often too time-consuming and difficult to carry, we resort to text mining techniques to streamline this analysis. This study was carried out by applying topic modeling for discovering the abstract topics that occur in visualization papers. The study used the vispubdata.org dataset as the reference to gather almost every paper presented, from 1990 to 2018, at the IEEE Visualization (VIS) set of conferences: InfoVis, SciVis, VAST, and Vis. We requested ten topics and assigned each one its ten most important and representative terms. With this analysis, we intend to envelop the current practices in the visualization research community.
{"title":"Visualization overview: Using modern text mining techniques to provide insight into visualization research practice","authors":"A. Figueiras","doi":"10.1109/IV56949.2022.00026","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00026","url":null,"abstract":"We take a new approach to analyze what the general focus of Visualization research is, among the panoply of different topics and approaches. Due to the intrinsic characteristics of this kind of in-depth research, being often too time-consuming and difficult to carry, we resort to text mining techniques to streamline this analysis. This study was carried out by applying topic modeling for discovering the abstract topics that occur in visualization papers. The study used the vispubdata.org dataset as the reference to gather almost every paper presented, from 1990 to 2018, at the IEEE Visualization (VIS) set of conferences: InfoVis, SciVis, VAST, and Vis. We requested ten topics and assigned each one its ten most important and representative terms. With this analysis, we intend to envelop the current practices in the visualization research community.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132313443","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00067
A. Afonso, J. Pires, Nuno Datia, Fernando Birra
With urban development in cities, shared bicycle systems are increasingly used as a way to avoid traffic caused by cars, promoting sustainable mobility and contributing for traffic and pollution reduction in urban areas. The imbalance in the availability of bicycles and docks at the stations of the systems makes it impossible to rent and return bicycles, making it necessary to redistribute them across the network. However, this process has flaws, mainly during rush hours. In this paper, we analyse data provided by the Lisbon City Council regarding their bike sharing system, which has the rebalancing operations' influence. Since the original data was contaminated with the rebalancing operations, an analysis was conducted in an attempt to remove this influence from the data. Following this analysis, a new dataset was created using only the trip data to enable model development for each station and predict the bicycle demand. The plateaus in the created dataset were then analysed to determine if they're due to lack of demand from costumers, or due to stations being full or empty.
{"title":"Bicycle Demand Prediction to Optimize the Rebalancing of a Bike Sharing System in Lisbon","authors":"A. Afonso, J. Pires, Nuno Datia, Fernando Birra","doi":"10.1109/IV56949.2022.00067","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00067","url":null,"abstract":"With urban development in cities, shared bicycle systems are increasingly used as a way to avoid traffic caused by cars, promoting sustainable mobility and contributing for traffic and pollution reduction in urban areas. The imbalance in the availability of bicycles and docks at the stations of the systems makes it impossible to rent and return bicycles, making it necessary to redistribute them across the network. However, this process has flaws, mainly during rush hours. In this paper, we analyse data provided by the Lisbon City Council regarding their bike sharing system, which has the rebalancing operations' influence. Since the original data was contaminated with the rebalancing operations, an analysis was conducted in an attempt to remove this influence from the data. Following this analysis, a new dataset was created using only the trip data to enable model development for each station and predict the bicycle demand. The plateaus in the created dataset were then analysed to determine if they're due to lack of demand from costumers, or due to stations being full or empty.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129291037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00080
A. Fradi, B. Louhichi, M. Mahjoub
Computer-aided design has been widely used in modern industry for several decades, resulting in the huge databases of 3D CAD models that specialist companies currently own. Therefore, developing a solution to retrieve a reusable 3D CAD model becomes a strategic need for companies specializing in the modern design and manufacturing industry. Recently, some research works have been launched with the aim of recognizing 3D CAD objects based on design similarity and reusability. In this context, the use of probabilistic graphical models for information retrieval was always of great importance, especially when the context is characterized by the large volume of data and the uncertainty of the result. In this paper, authors will present a new approach proposed for modeling 3D CAD objects into reusable subparts. This approach is based on the Hidden Markov Model (HMM). This model has shown improved accuracy and efficiency in recognizing reusable 3D CAD objects, compared to other previously proposed solutions.
{"title":"Retrieve reusable 3D CAD objects based on hidden Markov models (HMM)","authors":"A. Fradi, B. Louhichi, M. Mahjoub","doi":"10.1109/IV56949.2022.00080","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00080","url":null,"abstract":"Computer-aided design has been widely used in modern industry for several decades, resulting in the huge databases of 3D CAD models that specialist companies currently own. Therefore, developing a solution to retrieve a reusable 3D CAD model becomes a strategic need for companies specializing in the modern design and manufacturing industry. Recently, some research works have been launched with the aim of recognizing 3D CAD objects based on design similarity and reusability. In this context, the use of probabilistic graphical models for information retrieval was always of great importance, especially when the context is characterized by the large volume of data and the uncertainty of the result. In this paper, authors will present a new approach proposed for modeling 3D CAD objects into reusable subparts. This approach is based on the Hidden Markov Model (HMM). This model has shown improved accuracy and efficiency in recognizing reusable 3D CAD objects, compared to other previously proposed solutions.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115949832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00039
Akshay A. S. Rege
The aim of this paper is to inspire the development of Big Data interaction in a 3 dimensional form to make Big Data Visualization more immersive, intuitive, visually engaging and user friendly. This paper initially discusses the current approaches to Big Data interaction and their limitation therein. It then proceeds to review the latest trends and developments in the technology sphere to explore how Big Data interaction could be technologically enhanced. Following which, the paper articulates design guidelines that could be adopted in the design of 3 dimensional Big Data interaction, based on literature research. These guidelines contribute towards visual formatting, information organization and interaction design of Big Data, to make it more human centered. Through proposing the interaction design of Big Data in alignment with the natural orientation of human perception of the world, the paper intends to make the field of data science accessible to all. Lastly, the paper concludes with a discussion of future vision for Big Data interaction.
{"title":"Big Data in 3D: Design guidelines for an immersive 3 dimensional approach to Big Data interaction design","authors":"Akshay A. S. Rege","doi":"10.1109/IV56949.2022.00039","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00039","url":null,"abstract":"The aim of this paper is to inspire the development of Big Data interaction in a 3 dimensional form to make Big Data Visualization more immersive, intuitive, visually engaging and user friendly. This paper initially discusses the current approaches to Big Data interaction and their limitation therein. It then proceeds to review the latest trends and developments in the technology sphere to explore how Big Data interaction could be technologically enhanced. Following which, the paper articulates design guidelines that could be adopted in the design of 3 dimensional Big Data interaction, based on literature research. These guidelines contribute towards visual formatting, information organization and interaction design of Big Data, to make it more human centered. Through proposing the interaction design of Big Data in alignment with the natural orientation of human perception of the world, the paper intends to make the field of data science accessible to all. Lastly, the paper concludes with a discussion of future vision for Big Data interaction.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129397350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00049
Stefano Matsrostefano, F. Sciarrone
In recent years there has been an exponential growth of distance learning, provided by both public and private institutions. As a matter of fact, the number of students enrolled in courses delivered through the Network, has dramatically grown, also due to the COVID-19 pandemic, which has forced millions of people not to move. Consequently, more and more courses delivered in a remote modality have been attended by a huge number of people, producing an increasing number of Massive Open Online Courses (MOOC)s. These kind of courses are imposing new challenges for teachers, especially for monitoring and assessing the community learning processes. On the one hand, the learning assessment cannot be carried out based solely on closed-ended tests, while, on the other hand, teachers cannot evaluate thousands of open-answer assignments: they should have at their disposition a set of tools helping them monitor the community learning progress. This paper investigates the possibility of using some of the Source Code Embedding techniques, to give teachers useful information about their learners' programming styles in Massive Open Online Courses. We propose a method to visualize each student's program, included the teacher's one, as a point in a 2-D space, using the doc2vec embeddings technique. Thanks to this representation, teachers can identify in the 2-D space groups of students having similar programming styles and reason on them to start a suitable didactic feedback. Moreover, teachers can reason on the relationship between each point compared to their own point as well, considered as the truth programming style. A first experimentation using Python as the programming language is performed with encouraging results.
{"title":"Monitoring Programming Styles in Massive Open Online Courses Using Source Embedding","authors":"Stefano Matsrostefano, F. Sciarrone","doi":"10.1109/IV56949.2022.00049","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00049","url":null,"abstract":"In recent years there has been an exponential growth of distance learning, provided by both public and private institutions. As a matter of fact, the number of students enrolled in courses delivered through the Network, has dramatically grown, also due to the COVID-19 pandemic, which has forced millions of people not to move. Consequently, more and more courses delivered in a remote modality have been attended by a huge number of people, producing an increasing number of Massive Open Online Courses (MOOC)s. These kind of courses are imposing new challenges for teachers, especially for monitoring and assessing the community learning processes. On the one hand, the learning assessment cannot be carried out based solely on closed-ended tests, while, on the other hand, teachers cannot evaluate thousands of open-answer assignments: they should have at their disposition a set of tools helping them monitor the community learning progress. This paper investigates the possibility of using some of the Source Code Embedding techniques, to give teachers useful information about their learners' programming styles in Massive Open Online Courses. We propose a method to visualize each student's program, included the teacher's one, as a point in a 2-D space, using the doc2vec embeddings technique. Thanks to this representation, teachers can identify in the 2-D space groups of students having similar programming styles and reason on them to start a suitable didactic feedback. Moreover, teachers can reason on the relationship between each point compared to their own point as well, considered as the truth programming style. A first experimentation using Python as the programming language is performed with encouraging results.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"5 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129263819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-07-01DOI: 10.1109/IV56949.2022.00064
Chao Huang Lin, Razvan Andonie, A. Florea
Visual interpretation of Synthetic Aperture Radar (SAR) images plays an important role in remote sensing mainly because SAR images enable consistent monitoring in any lighting, weather, and cloud-cover conditions. An important application of SAR visualization is water detection. We introduce a Fully Convolutional Neural Network (FCN) Encoder to detect water in Sentinel-1 SAR images. Our FCN Encoder identifies water by the intensity of each pixel and also learns the spatial information of neighborhood pixels. We apply our method on standard benchmarks and real-world SAR images. The results are assessed both visually and from the point of view of classification accuracy. Compared with other classifiers, our FCN Encoder is more accurate. From visual inspection of the Seattle water detection result, the FCN Encoder produces a very clear (smooth) output. The results show that the FCN Encoder, trained with a harder dataset and hyperparameter optimization, improves significantly its generalization performance. In a real-world application, for the prediction phase, the FCN Encoder is about 40 times faster than a Convolutional Neural Network (CNN) with sliding window.
{"title":"Optimized Fully Convolutional Neural Network Encoder for Water Detection in SAR Images","authors":"Chao Huang Lin, Razvan Andonie, A. Florea","doi":"10.1109/IV56949.2022.00064","DOIUrl":"https://doi.org/10.1109/IV56949.2022.00064","url":null,"abstract":"Visual interpretation of Synthetic Aperture Radar (SAR) images plays an important role in remote sensing mainly because SAR images enable consistent monitoring in any lighting, weather, and cloud-cover conditions. An important application of SAR visualization is water detection. We introduce a Fully Convolutional Neural Network (FCN) Encoder to detect water in Sentinel-1 SAR images. Our FCN Encoder identifies water by the intensity of each pixel and also learns the spatial information of neighborhood pixels. We apply our method on standard benchmarks and real-world SAR images. The results are assessed both visually and from the point of view of classification accuracy. Compared with other classifiers, our FCN Encoder is more accurate. From visual inspection of the Seattle water detection result, the FCN Encoder produces a very clear (smooth) output. The results show that the FCN Encoder, trained with a harder dataset and hyperparameter optimization, improves significantly its generalization performance. In a real-world application, for the prediction phase, the FCN Encoder is about 40 times faster than a Convolutional Neural Network (CNN) with sliding window.","PeriodicalId":153161,"journal":{"name":"2022 26th International Conference Information Visualisation (IV)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130705186","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：