Influenza-like symptom prediction by analyzing self-reported health status and human mobility behaviors

Fenglong Ma, Shiran Zhong, Jing Gao, Ling Bian

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Human mobility behaviors are of great importance to predict influenza-like symptoms. However, most existing studies focus on analyzing population-level outcomes instead of individual-level. One challenge for individual-level influenza symptom prediction is a shortage of a sufficiently large dataset that contains individual health status as well as the mobility behavior information at the same time. Besides, the quality of the collected data is not high enough, due to the carelessness and low variation of reporting behaviors. Also, the number of individuals with influenza symptom onset is much smaller than that of ones without symptoms, i.e., the imbalanced data problem. These challenges further increase the difficulty of accurately predicting influenza-like symptoms. To address these challenges, in this paper, we propose a novel and powerful selective ensemble support vector machines (SESVM). The proposed SESVM can select the best basic SVM classifier by running on the randomly split sub training sets, which consist of the positive samples and the split negative ones. By randomly splitting the dataset multiple times, we can obtain many predictions by each best basic SVM classifier. SESVM finally aggregates all the predictions together to produce the final results. We conduct Experiments on a new longitudinal individual self-reported weekly survey dataset with mobility behaviors, and the results show that the proposed SESVM outperforms all the existing approaches for the influenza symptom prediction task.

Original languageEnglish (US)
Title of host publicationACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics
PublisherAssociation for Computing Machinery, Inc
Pages233-242
Number of pages10
ISBN (Electronic)9781450366663
DOIs
StatePublished - Sep 4 2019
Event10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2019 - Niagara Falls, United States
Duration: Sep 7 2019Sep 10 2019

Publication series

NameACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

Conference

Conference10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2019
CountryUnited States
CityNiagara Falls
Period9/7/199/10/19

Fingerprint

Human Influenza
Health Status
Support vector machines
Health
Classifiers
Running
Support Vector Machine
Experiments
Population
Datasets

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Software
  • Biomedical Engineering
  • Health Informatics

Cite this

Ma, F., Zhong, S., Gao, J., & Bian, L. (2019). Influenza-like symptom prediction by analyzing self-reported health status and human mobility behaviors. In ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics (pp. 233-242). (ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics). Association for Computing Machinery, Inc. https://doi.org/10.1145/3307339.3342141
Ma, Fenglong ; Zhong, Shiran ; Gao, Jing ; Bian, Ling. / Influenza-like symptom prediction by analyzing self-reported health status and human mobility behaviors. ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. Association for Computing Machinery, Inc, 2019. pp. 233-242 (ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics).
@inproceedings{11658bd6e0964d01acaac192f1387835,
title = "Influenza-like symptom prediction by analyzing self-reported health status and human mobility behaviors",
abstract = "Human mobility behaviors are of great importance to predict influenza-like symptoms. However, most existing studies focus on analyzing population-level outcomes instead of individual-level. One challenge for individual-level influenza symptom prediction is a shortage of a sufficiently large dataset that contains individual health status as well as the mobility behavior information at the same time. Besides, the quality of the collected data is not high enough, due to the carelessness and low variation of reporting behaviors. Also, the number of individuals with influenza symptom onset is much smaller than that of ones without symptoms, i.e., the imbalanced data problem. These challenges further increase the difficulty of accurately predicting influenza-like symptoms. To address these challenges, in this paper, we propose a novel and powerful selective ensemble support vector machines (SESVM). The proposed SESVM can select the best basic SVM classifier by running on the randomly split sub training sets, which consist of the positive samples and the split negative ones. By randomly splitting the dataset multiple times, we can obtain many predictions by each best basic SVM classifier. SESVM finally aggregates all the predictions together to produce the final results. We conduct Experiments on a new longitudinal individual self-reported weekly survey dataset with mobility behaviors, and the results show that the proposed SESVM outperforms all the existing approaches for the influenza symptom prediction task.",
author = "Fenglong Ma and Shiran Zhong and Jing Gao and Ling Bian",
year = "2019",
month = "9",
day = "4",
doi = "10.1145/3307339.3342141",
language = "English (US)",
series = "ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics",
publisher = "Association for Computing Machinery, Inc",
pages = "233--242",
booktitle = "ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics",

}

Ma, F, Zhong, S, Gao, J & Bian, L 2019, Influenza-like symptom prediction by analyzing self-reported health status and human mobility behaviors. in ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, Association for Computing Machinery, Inc, pp. 233-242, 10th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics, ACM-BCB 2019, Niagara Falls, United States, 9/7/19. https://doi.org/10.1145/3307339.3342141

Influenza-like symptom prediction by analyzing self-reported health status and human mobility behaviors. / Ma, Fenglong; Zhong, Shiran; Gao, Jing; Bian, Ling.

ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. Association for Computing Machinery, Inc, 2019. p. 233-242 (ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Influenza-like symptom prediction by analyzing self-reported health status and human mobility behaviors

AU - Ma, Fenglong

AU - Zhong, Shiran

AU - Gao, Jing

AU - Bian, Ling

PY - 2019/9/4

Y1 - 2019/9/4

N2 - Human mobility behaviors are of great importance to predict influenza-like symptoms. However, most existing studies focus on analyzing population-level outcomes instead of individual-level. One challenge for individual-level influenza symptom prediction is a shortage of a sufficiently large dataset that contains individual health status as well as the mobility behavior information at the same time. Besides, the quality of the collected data is not high enough, due to the carelessness and low variation of reporting behaviors. Also, the number of individuals with influenza symptom onset is much smaller than that of ones without symptoms, i.e., the imbalanced data problem. These challenges further increase the difficulty of accurately predicting influenza-like symptoms. To address these challenges, in this paper, we propose a novel and powerful selective ensemble support vector machines (SESVM). The proposed SESVM can select the best basic SVM classifier by running on the randomly split sub training sets, which consist of the positive samples and the split negative ones. By randomly splitting the dataset multiple times, we can obtain many predictions by each best basic SVM classifier. SESVM finally aggregates all the predictions together to produce the final results. We conduct Experiments on a new longitudinal individual self-reported weekly survey dataset with mobility behaviors, and the results show that the proposed SESVM outperforms all the existing approaches for the influenza symptom prediction task.

AB - Human mobility behaviors are of great importance to predict influenza-like symptoms. However, most existing studies focus on analyzing population-level outcomes instead of individual-level. One challenge for individual-level influenza symptom prediction is a shortage of a sufficiently large dataset that contains individual health status as well as the mobility behavior information at the same time. Besides, the quality of the collected data is not high enough, due to the carelessness and low variation of reporting behaviors. Also, the number of individuals with influenza symptom onset is much smaller than that of ones without symptoms, i.e., the imbalanced data problem. These challenges further increase the difficulty of accurately predicting influenza-like symptoms. To address these challenges, in this paper, we propose a novel and powerful selective ensemble support vector machines (SESVM). The proposed SESVM can select the best basic SVM classifier by running on the randomly split sub training sets, which consist of the positive samples and the split negative ones. By randomly splitting the dataset multiple times, we can obtain many predictions by each best basic SVM classifier. SESVM finally aggregates all the predictions together to produce the final results. We conduct Experiments on a new longitudinal individual self-reported weekly survey dataset with mobility behaviors, and the results show that the proposed SESVM outperforms all the existing approaches for the influenza symptom prediction task.

UR - http://www.scopus.com/inward/record.url?scp=85073150830&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073150830&partnerID=8YFLogxK

U2 - 10.1145/3307339.3342141

DO - 10.1145/3307339.3342141

M3 - Conference contribution

AN - SCOPUS:85073150830

T3 - ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

SP - 233

EP - 242

BT - ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics

PB - Association for Computing Machinery, Inc

ER -

Ma F, Zhong S, Gao J, Bian L. Influenza-like symptom prediction by analyzing self-reported health status and human mobility behaviors. In ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. Association for Computing Machinery, Inc. 2019. p. 233-242. (ACM-BCB 2019 - Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics). https://doi.org/10.1145/3307339.3342141