AI-driven aquaculture: A review of technological innovations and their sustainable impacts

Artificial Intelligence in Agriculture, Год журнала: 2025, Номер unknown

Опубликована: Фев. 1, 2025

Язык: Английский

---

A deep learning-based biomonitoring system for detecting water pollution using Caenorhabditis elegans swimming behaviors

Ecological Informatics, Год журнала: 2024, Номер 80, С. 102482 - 102482

Опубликована: Янв. 21, 2024

Caenorhabditis elegans is a representative organism whose DNA structure has been fully elucidated. It used as model for various analyses, including genetic functional analysis, individual behavioral and group analysis. Recently, it also studied an important bioindicator of water pollution. In previous studies, traditional machine learning methods, such the Hidden Markov Model (HMM), were to determine pollution identify pollutants based on differences in swimming behavior C. before after exposure chemicals. However, these models have low accuracy relatively high false-negative rate. This study proposes method detecting identifying types using Long Short-Term Memory (LSTM) model, deep suitable time-series data The activities each image frames are characterized by Branch Length Similarity (BLS) entropy profile. These BLS profiles converted into input vectors through additional preprocessing two clustering methods. We conduct experiments formaldehyde benzene at 0.1 mg/L each, with observation time intervals varying from 30 180 s. performance proposed compared that previously HMM approach variants LSTM models, Gated Recurrent Unit (GRU) Bidirectional (BiLSTM).

Язык: Английский

---

Drone imagery and deep learning for mapping the density of wild Pacific oysters to manage their expansion into protected areas

Ecological Informatics, Год журнала: 2024, Номер 82, С. 102708 - 102708

Опубликована: Июль 9, 2024

The recent expansion of wild Pacific oysters already had negative repercussions on sites in Europe and has raised further concerns over their potential harmful impact the balance biomes within protected areas. Monitoring colonisation, especially at early stages, become an urgent ecological issue. Current efforts to monitor rely "walk-over" surveys that are highly laborious often limited specific areas easy access. Remotely Piloted Aircraft Systems (RPAS), commonly known as drones, can provide effective tool for surveying complex terrains detect oysters. This study provides a novel workflow automated detection, counting mapping individual estimate density per square meter by using Convolutional Neural Networks (CNNs) applied drone imagery. Drone photos were collected low tides altitudes approximately 10 m across variety cases rocky shore mudflats scenarios. Using object we compared how different architectures including YOLOv5s, YOLOv5m, TPH-YOLOv5 FR-CNN performed detection surveyed We report precision our model 88% with difference performance 1% two sites. presented this work proposes use grid maps visualize towards management creation time series identify trends.

Язык: Английский

---

High Speed Small Item Production Line Tracking Using Computer Vision and Cloud Computing

TENCON 2021 - 2021 IEEE Region 10 Conference (TENCON), Год журнала: 2024, Номер unknown, С. 1215 - 1218

Опубликована: Дек. 1, 2024

Язык: Английский

---