Anomaly Detection on Univariate Sensing Time Series Data for Smart Aquaculture Using K-Means, Isolation Forest, and Local Outlier Factor

Petkovski, Aleksandar; Shehu, Visar

doi:10.1109/meco58584.2023.10154991

Cited by 3 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unsupervised learning techniques, including K-means clustering, are employed for soil type classification and anomaly detection [159]. K-means clustering partitions datasets into distinct clusters based on similarity, facilitating the identification of soil variability within fields or anomalous conditions requiring attention.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

“…Maintaining soil health and managing nutrient levels are fundamental aspects of sustainable agriculture [109,115]. The trend of soil degradation and nutrient loss due to intensive farming practices, erosion, and deforestation is alarming [115,159]. There are significant knowledge gaps about the long-term impacts of soil degradation on ecosystem services, biodiversity, and human health [159].…”

Section: Soil Health and Nutrient Managementmentioning

confidence: 99%

“…The trend of soil degradation and nutrient loss due to intensive farming practices, erosion, and deforestation is alarming [115,159]. There are significant knowledge gaps about the long-term impacts of soil degradation on ecosystem services, biodiversity, and human health [159]. Research efforts should prioritize ecosystem-based approaches to soil health management, integrating agroecological principles and indigenous knowledge systems.…”

Section: Soil Health and Nutrient Managementmentioning

confidence: 99%

“…Furthermore, Ref. [159] utilizes time series data for anomaly detection in smart aquaculture systems, identifying irregularities in water quality parameters to prevent fish disease outbreaks and improve farm productivity.…”

Section: Time Series Datamentioning

confidence: 99%

“…Water quality monitoring [216] Time Series Data Sequential data points ordered over Anomaly detection [159] time, such as weather or Soil parameter prediction [180,217] environmental observations. Pest incidence forecast [143] Animal disease detection [218] Scalar Data Single numerical values, Smart greenhouse farming [94] representing a single quantity or attribute.…”

Section: Kind Of Data Description Usage Examplesmentioning

confidence: 99%

See 4 more Smart Citations

IoT Solutions with Artificial Intelligence Technologies for Precision Agriculture: Definitions, Applications, Challenges, and Opportunities

Senoo,

Anggraini,

Kumi

et al. 2024

Electronics

View full text Add to dashboard Cite

The global agricultural sector confronts significant obstacles such as population growth, climate change, and natural disasters, which negatively impact food production and pose a threat to food security. In response to these challenges, the integration of IoT and AI technologies emerges as a promising solution, facilitating data-driven decision-making, optimizing resource allocation, and enhancing monitoring and control systems in agricultural operations to address these challenges and promote sustainable farming practices. This study examines the intersection of IoT and AI in precision agriculture (PA), aiming to provide a comprehensive understanding of their combined impact and mutually reinforcing relationship. Employing a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, we explore the synergies and transformative potential of integrating IoT and AI in agricultural systems. The review also aims to identify present trends, challenges, and opportunities in utilizing IoT and AI in agricultural systems. Diverse forms of agricultural practices are scrutinized to discern the applications of IoT and AI systems. Through a critical analysis of existing literature, this study contributes to a deeper understanding of how the integration of IoT and AI technologies can revolutionize PA, resulting in improved efficiency, sustainability, and productivity in the agricultural sector.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

Section: Soil Health and Nutrient Managementmentioning

confidence: 99%

Section: Soil Health and Nutrient Managementmentioning

confidence: 99%

Section: Time Series Datamentioning

confidence: 99%

Section: Kind Of Data Description Usage Examplesmentioning

confidence: 99%

See 3 more Smart Citations

IoT Solutions with Artificial Intelligence Technologies for Precision Agriculture: Definitions, Applications, Challenges, and Opportunities

Senoo,

Anggraini,

Kumi

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

An Intelligent LoRaWAN-Based IoT Device for Monitoring and Control Solutions in Smart Farming Through Anomaly Detection Integrated With Unsupervised Machine Learning

Fahaad Alumfareh,

Humayun,

Ahmad

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Anomaly Detection on Univariate Sensing Time Series Data for Smart Aquaculture Using Deep Learning

Petkovski

Shehu

2023

SEEU Review

Self Cite

View full text Add to dashboard Cite

Aquaculture plays a significant role in both economic development and food production. Maintaining an ecological environment with good water quality is essential to ensure the production efficiency and quality of aquaculture. Effective management of water quality can prevent abnormal conditions and contribute significantly to food security. Detecting anomalies in the aquaculture environment is crucial to ensure that the environment is maintained correctly to meet healthy and proper requirements for fish farming. This article focuses on the use of deep learning techniques to detect anomalies in water quality data in the aquaculture environment. Four deep learning anomaly detection techniques, including Autoencoder, Variational Autoencoder, Long-Short Term Memory Autoencoder, and Spectral-Residual Convolutional Neural Network, were analysed using multiple real-world sensor datasets collected from IoT aquaculture systems. Extensive experiments were conducted for temperature, dissolved oxygen, and pH parameters, and the evaluation analysis revealed that the Long-Short Term Memory Autoencoder anomaly detection method showed promising results in detecting anomalies for the temperature and oxygen datasets, while the Spectral-Residual Convolutional Neural Network demonstrated the best performance on the pH datasets.

show abstract

Anomaly Detection on Univariate Sensing Time Series Data for Smart Aquaculture Using K-Means, Isolation Forest, and Local Outlier Factor

Cited by 3 publications

References 12 publications

IoT Solutions with Artificial Intelligence Technologies for Precision Agriculture: Definitions, Applications, Challenges, and Opportunities

IoT Solutions with Artificial Intelligence Technologies for Precision Agriculture: Definitions, Applications, Challenges, and Opportunities

An Intelligent LoRaWAN-Based IoT Device for Monitoring and Control Solutions in Smart Farming Through Anomaly Detection Integrated With Unsupervised Machine Learning

Anomaly Detection on Univariate Sensing Time Series Data for Smart Aquaculture Using Deep Learning

Contact Info

Product

Resources

About