Detecting anomalies from liquid transfer videos in automated laboratory setting
In this work, we address the problem of detecting anomalies in a certain laboratory automation setting. At first, we collect video images of liquid transfer in automated laboratory experiments. We mimic the real-world challenges of developing an anomaly detection model by considering two points. Fir...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Molecular Biosciences |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmolb.2023.1147514/full |
| _version_ | 1797833604263313408 |
|---|---|
| author | Najibul Haque Sarker Zaber Abdul Hakim Ali Dabouei Mostofa Rafid Uddin Zachary Freyberg Andy MacWilliams Joshua Kangas Min Xu |
| author_facet | Najibul Haque Sarker Zaber Abdul Hakim Ali Dabouei Mostofa Rafid Uddin Zachary Freyberg Andy MacWilliams Joshua Kangas Min Xu |
| author_sort | Najibul Haque Sarker |
| collection | DOAJ |
| description | In this work, we address the problem of detecting anomalies in a certain laboratory automation setting. At first, we collect video images of liquid transfer in automated laboratory experiments. We mimic the real-world challenges of developing an anomaly detection model by considering two points. First, the size of the collected dataset is set to be relatively small compared to large-scale video datasets. Second, the dataset has a class imbalance problem where the majority of the collected videos are from abnormal events. Consequently, the existing learning-based video anomaly detection methods do not perform well. To this end, we develop a practical human-engineered feature extraction method to detect anomalies from the liquid transfer video images. Our simple yet effective method outperforms state-of-the-art anomaly detection methods with a notable margin. In particular, the proposed method provides 19% and 76% average improvement in AUC and Equal Error Rate, respectively. Our method also quantifies the anomalies and provides significant benefits for deployment in the real-world experimental setting. |
| first_indexed | 2024-04-09T14:25:48Z |
| format | Article |
| id | doaj.art-205aa24d6bc94c7f902cd8a172f72e1b |
| institution | Directory Open Access Journal |
| issn | 2296-889X |
| language | English |
| last_indexed | 2024-04-09T14:25:48Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Molecular Biosciences |
| spelling | doaj.art-205aa24d6bc94c7f902cd8a172f72e1b2023-05-04T04:24:54ZengFrontiers Media S.A.Frontiers in Molecular Biosciences2296-889X2023-05-011010.3389/fmolb.2023.11475141147514Detecting anomalies from liquid transfer videos in automated laboratory settingNajibul Haque Sarker0Zaber Abdul Hakim1Ali Dabouei2Mostofa Rafid Uddin3Zachary Freyberg4Andy MacWilliams5Joshua Kangas6Min Xu7Computer Science and Engineering Department, Bangladesh University of Engineering and Technology, Dhaka, BangladeshComputer Science and Engineering Department, Bangladesh University of Engineering and Technology, Dhaka, BangladeshComputational Biology Department, Carnegie Mellon University, Pittsburgh, PA, United StatesComputational Biology Department, Carnegie Mellon University, Pittsburgh, PA, United StatesDepartment of Psychiatry, University of Pittsburgh, Pittsburgh, PA, United StatesComputational Biology Department, Carnegie Mellon University, Pittsburgh, PA, United StatesComputational Biology Department, Carnegie Mellon University, Pittsburgh, PA, United StatesComputational Biology Department, Carnegie Mellon University, Pittsburgh, PA, United StatesIn this work, we address the problem of detecting anomalies in a certain laboratory automation setting. At first, we collect video images of liquid transfer in automated laboratory experiments. We mimic the real-world challenges of developing an anomaly detection model by considering two points. First, the size of the collected dataset is set to be relatively small compared to large-scale video datasets. Second, the dataset has a class imbalance problem where the majority of the collected videos are from abnormal events. Consequently, the existing learning-based video anomaly detection methods do not perform well. To this end, we develop a practical human-engineered feature extraction method to detect anomalies from the liquid transfer video images. Our simple yet effective method outperforms state-of-the-art anomaly detection methods with a notable margin. In particular, the proposed method provides 19% and 76% average improvement in AUC and Equal Error Rate, respectively. Our method also quantifies the anomalies and provides significant benefits for deployment in the real-world experimental setting.https://www.frontiersin.org/articles/10.3389/fmolb.2023.1147514/fulllab automationvideo anomaly detectionaction recognitionmachine learningfeature extraction |
| spellingShingle | Najibul Haque Sarker Zaber Abdul Hakim Ali Dabouei Mostofa Rafid Uddin Zachary Freyberg Andy MacWilliams Joshua Kangas Min Xu Detecting anomalies from liquid transfer videos in automated laboratory setting Frontiers in Molecular Biosciences lab automation video anomaly detection action recognition machine learning feature extraction |
| title | Detecting anomalies from liquid transfer videos in automated laboratory setting |
| title_full | Detecting anomalies from liquid transfer videos in automated laboratory setting |
| title_fullStr | Detecting anomalies from liquid transfer videos in automated laboratory setting |
| title_full_unstemmed | Detecting anomalies from liquid transfer videos in automated laboratory setting |
| title_short | Detecting anomalies from liquid transfer videos in automated laboratory setting |
| title_sort | detecting anomalies from liquid transfer videos in automated laboratory setting |
| topic | lab automation video anomaly detection action recognition machine learning feature extraction |
| url | https://www.frontiersin.org/articles/10.3389/fmolb.2023.1147514/full |
| work_keys_str_mv | AT najibulhaquesarker detectinganomaliesfromliquidtransfervideosinautomatedlaboratorysetting AT zaberabdulhakim detectinganomaliesfromliquidtransfervideosinautomatedlaboratorysetting AT alidabouei detectinganomaliesfromliquidtransfervideosinautomatedlaboratorysetting AT mostofarafiduddin detectinganomaliesfromliquidtransfervideosinautomatedlaboratorysetting AT zacharyfreyberg detectinganomaliesfromliquidtransfervideosinautomatedlaboratorysetting AT andymacwilliams detectinganomaliesfromliquidtransfervideosinautomatedlaboratorysetting AT joshuakangas detectinganomaliesfromliquidtransfervideosinautomatedlaboratorysetting AT minxu detectinganomaliesfromliquidtransfervideosinautomatedlaboratorysetting |