Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning
The use of bivalve mollusks as bioindicators in automated monitoring systems can provide real-time detection of emergency situations associated with the pollution of aquatic environments. The behavioral reactions of <i>Unio pictorum</i> (Linnaeus, 1758) were employed in the development o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2687 |
| _version_ | 1797614312897904640 |
|---|---|
| author | Aleksandr N. Grekov Aleksey A. Kabanov Elena V. Vyshkvarkova Valeriy V. Trusevich |
| author_facet | Aleksandr N. Grekov Aleksey A. Kabanov Elena V. Vyshkvarkova Valeriy V. Trusevich |
| author_sort | Aleksandr N. Grekov |
| collection | DOAJ |
| description | The use of bivalve mollusks as bioindicators in automated monitoring systems can provide real-time detection of emergency situations associated with the pollution of aquatic environments. The behavioral reactions of <i>Unio pictorum</i> (Linnaeus, 1758) were employed in the development of a comprehensive automated monitoring system for aquatic environments by the authors. The study used experimental data obtained by an automated system from the Chernaya River in the Sevastopol region of the Crimean Peninsula. Four traditional unsupervised machine learning techniques were implemented to detect emergency signals in the activity of bivalves: elliptic envelope, isolation forest (iForest), one-class support vector machine (SVM), and local outlier factor (LOF). The results showed that the use of the elliptic envelope, iForest, and LOF methods with proper hyperparameter tuning can detect anomalies in mollusk activity data without false alarms, with an F1 score of 1. A comparison of anomaly detection times revealed that the iForest method is the most efficient. These findings demonstrate the potential of using bivalve mollusks as bioindicators in automated monitoring systems for the early detection of pollution in aquatic environments. |
| first_indexed | 2024-03-11T07:10:38Z |
| format | Article |
| id | doaj.art-9ba1435e464f473981f59cc884892753 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:10:38Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9ba1435e464f473981f59cc8848927532023-11-17T08:38:18ZengMDPI AGSensors1424-82202023-03-01235268710.3390/s23052687Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine LearningAleksandr N. Grekov0Aleksey A. Kabanov1Elena V. Vyshkvarkova2Valeriy V. Trusevich3Institute of Natural and Technical Systems, 299011 Sevastopol, RussiaDepartment of Informatics and Control in Technical Systems, Sevastopol State University, 299053 Sevastopol, RussiaInstitute of Natural and Technical Systems, 299011 Sevastopol, RussiaInstitute of Natural and Technical Systems, 299011 Sevastopol, RussiaThe use of bivalve mollusks as bioindicators in automated monitoring systems can provide real-time detection of emergency situations associated with the pollution of aquatic environments. The behavioral reactions of <i>Unio pictorum</i> (Linnaeus, 1758) were employed in the development of a comprehensive automated monitoring system for aquatic environments by the authors. The study used experimental data obtained by an automated system from the Chernaya River in the Sevastopol region of the Crimean Peninsula. Four traditional unsupervised machine learning techniques were implemented to detect emergency signals in the activity of bivalves: elliptic envelope, isolation forest (iForest), one-class support vector machine (SVM), and local outlier factor (LOF). The results showed that the use of the elliptic envelope, iForest, and LOF methods with proper hyperparameter tuning can detect anomalies in mollusk activity data without false alarms, with an F1 score of 1. A comparison of anomaly detection times revealed that the iForest method is the most efficient. These findings demonstrate the potential of using bivalve mollusks as bioindicators in automated monitoring systems for the early detection of pollution in aquatic environments.https://www.mdpi.com/1424-8220/23/5/2687anomaly detectionmachine learningbiological early warning systemsmussels |
| spellingShingle | Aleksandr N. Grekov Aleksey A. Kabanov Elena V. Vyshkvarkova Valeriy V. Trusevich Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning Sensors anomaly detection machine learning biological early warning systems mussels |
| title | Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning |
| title_full | Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning |
| title_fullStr | Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning |
| title_full_unstemmed | Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning |
| title_short | Anomaly Detection in Biological Early Warning Systems Using Unsupervised Machine Learning |
| title_sort | anomaly detection in biological early warning systems using unsupervised machine learning |
| topic | anomaly detection machine learning biological early warning systems mussels |
| url | https://www.mdpi.com/1424-8220/23/5/2687 |
| work_keys_str_mv | AT aleksandrngrekov anomalydetectioninbiologicalearlywarningsystemsusingunsupervisedmachinelearning AT alekseyakabanov anomalydetectioninbiologicalearlywarningsystemsusingunsupervisedmachinelearning AT elenavvyshkvarkova anomalydetectioninbiologicalearlywarningsystemsusingunsupervisedmachinelearning AT valeriyvtrusevich anomalydetectioninbiologicalearlywarningsystemsusingunsupervisedmachinelearning |