A machine learning approach for predicting human shortest path task performance
Finding a shortest path for a given pair of vertices in a graph drawing is one of the fundamental tasks for qualitative evaluation of graph drawings. In this paper, we present the first machine learning approach to predict human shortest path task performance, including accuracy, response time, and...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | Visual Informatics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2468502X22000183 |
| _version_ | 1811309784689803264 |
|---|---|
| author | Shijun Cai Seok-Hee Hong Xiaobo Xia Tongliang Liu Weidong Huang |
| author_facet | Shijun Cai Seok-Hee Hong Xiaobo Xia Tongliang Liu Weidong Huang |
| author_sort | Shijun Cai |
| collection | DOAJ |
| description | Finding a shortest path for a given pair of vertices in a graph drawing is one of the fundamental tasks for qualitative evaluation of graph drawings. In this paper, we present the first machine learning approach to predict human shortest path task performance, including accuracy, response time, and mental effort.To predict the shortest path task performance, we utilize correlated quality metrics and the ground truth data from the shortest path experiments. Specifically, we introduce path faithfulness metrics and show strong correlations with the shortest path task performance. Moreover, to mitigate the problem of insufficient ground truth training data, we use the transfer learning method to pre-train our deep model, exploiting the correlated quality metrics.Experimental results using the ground truth human shortest path experiment data show that our models can successfully predict the shortest path task performance. In particular, model MSP achieves an MSE (i.e., test mean square error) of 0.7243 (i.e., data range from −17.27 to 1.81) for prediction. |
| first_indexed | 2024-04-13T09:48:12Z |
| format | Article |
| id | doaj.art-12041c84764c45b2a967ae23c41d09bc |
| institution | Directory Open Access Journal |
| issn | 2468-502X |
| language | English |
| last_indexed | 2024-04-13T09:48:12Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Visual Informatics |
| spelling | doaj.art-12041c84764c45b2a967ae23c41d09bc2022-12-22T02:51:40ZengElsevierVisual Informatics2468-502X2022-06-01625061A machine learning approach for predicting human shortest path task performanceShijun Cai0Seok-Hee Hong1Xiaobo Xia2Tongliang Liu3Weidong Huang4University of Sydney, Australia; Corresponding author.University of Sydney, AustraliaUniversity of Sydney, AustraliaUniversity of Sydney, AustraliaUniversity of Technology Sydney, AustraliaFinding a shortest path for a given pair of vertices in a graph drawing is one of the fundamental tasks for qualitative evaluation of graph drawings. In this paper, we present the first machine learning approach to predict human shortest path task performance, including accuracy, response time, and mental effort.To predict the shortest path task performance, we utilize correlated quality metrics and the ground truth data from the shortest path experiments. Specifically, we introduce path faithfulness metrics and show strong correlations with the shortest path task performance. Moreover, to mitigate the problem of insufficient ground truth training data, we use the transfer learning method to pre-train our deep model, exploiting the correlated quality metrics.Experimental results using the ground truth human shortest path experiment data show that our models can successfully predict the shortest path task performance. In particular, model MSP achieves an MSE (i.e., test mean square error) of 0.7243 (i.e., data range from −17.27 to 1.81) for prediction.http://www.sciencedirect.com/science/article/pii/S2468502X22000183Graph drawingMachine learningShortest path taskQuality metrics |
| spellingShingle | Shijun Cai Seok-Hee Hong Xiaobo Xia Tongliang Liu Weidong Huang A machine learning approach for predicting human shortest path task performance Visual Informatics Graph drawing Machine learning Shortest path task Quality metrics |
| title | A machine learning approach for predicting human shortest path task performance |
| title_full | A machine learning approach for predicting human shortest path task performance |
| title_fullStr | A machine learning approach for predicting human shortest path task performance |
| title_full_unstemmed | A machine learning approach for predicting human shortest path task performance |
| title_short | A machine learning approach for predicting human shortest path task performance |
| title_sort | machine learning approach for predicting human shortest path task performance |
| topic | Graph drawing Machine learning Shortest path task Quality metrics |
| url | http://www.sciencedirect.com/science/article/pii/S2468502X22000183 |
| work_keys_str_mv | AT shijuncai amachinelearningapproachforpredictinghumanshortestpathtaskperformance AT seokheehong amachinelearningapproachforpredictinghumanshortestpathtaskperformance AT xiaoboxia amachinelearningapproachforpredictinghumanshortestpathtaskperformance AT tongliangliu amachinelearningapproachforpredictinghumanshortestpathtaskperformance AT weidonghuang amachinelearningapproachforpredictinghumanshortestpathtaskperformance AT shijuncai machinelearningapproachforpredictinghumanshortestpathtaskperformance AT seokheehong machinelearningapproachforpredictinghumanshortestpathtaskperformance AT xiaoboxia machinelearningapproachforpredictinghumanshortestpathtaskperformance AT tongliangliu machinelearningapproachforpredictinghumanshortestpathtaskperformance AT weidonghuang machinelearningapproachforpredictinghumanshortestpathtaskperformance |