Scholarlink

<p>In the aquaculture sector, accurate measurement of water pollution levels is vital for efficient monitoring of protecting aquatic life. Water contamination monitoring is essential for sustainable aquaculture and environmental management. In this paper, Comprehensive Analysis of Water Contamination in IoT-Enabled Aquaculture Systems using Advanced Quantum Optical Convolutional Neural Network Techniques for Enhanced Environmental Monitoring (WC-IoT-QOCNN-EM) is proposed. Initially, a total of 74,759 water quality records were collected from water quality dataset. Then, the data is pre-processed with the help of Unsharp Structure Guided Filtering (USGF) for replacing the missing values and normalizing the data. The pre-processed data is supplied to the Quantum Optical Convolutional Neural Network (QOCNN) for predicting the water contamination, which classifies contaminated and non-contaminated. Fractional-Order Water Flow Optimizer (FOWFO) is employed to maximize the hyperparameters of QOCNN. From the experimental results, it is evident that the WC-IoT-QOCNN-EM model achieves an accuracy of 99.21%, precision of 98.18% and F1-score of 99.20% on the test data. The WC-IoT-QOCNN-EM has improved the performance metrics compared to the traditional approaches. This confirms that the proposed approach is reliable, efficient and interpretable for the effective implementation of the intelligent IoT-based aquaculture systems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Comprehensive Analysis of Water Contamination in IoT-Enabled Aquaculture Systems Using Advanced Quantum Optical Convolutional Neural Network Techniques for Enhanced Environmental Monitoring

  • 期刊论文

  • 发表日期：

    2026年6月23日

查看全文
  • S Janarthanan,
  • S Shanthini Devi,
  • M Monica Dhana Ranjini,
  • Raghul G

摘要

In the aquaculture sector, accurate measurement of water pollution levels is vital for efficient monitoring of protecting aquatic life. Water contamination monitoring is essential for sustainable aquaculture and environmental management. In this paper, Comprehensive Analysis of Water Contamination in IoT-Enabled Aquaculture Systems using Advanced Quantum Optical Convolutional Neural Network Techniques for Enhanced Environmental Monitoring (WC-IoT-QOCNN-EM) is proposed. Initially, a total of 74,759 water quality records were collected from water quality dataset. Then, the data is pre-processed with the help of Unsharp Structure Guided Filtering (USGF) for replacing the missing values and normalizing the data. The pre-processed data is supplied to the Quantum Optical Convolutional Neural Network (QOCNN) for predicting the water contamination, which classifies contaminated and non-contaminated. Fractional-Order Water Flow Optimizer (FOWFO) is employed to maximize the hyperparameters of QOCNN. From the experimental results, it is evident that the WC-IoT-QOCNN-EM model achieves an accuracy of 99.21%, precision of 98.18% and F1-score of 99.20% on the test data. The WC-IoT-QOCNN-EM has improved the performance metrics compared to the traditional approaches. This confirms that the proposed approach is reliable, efficient and interpretable for the effective implementation of the intelligent IoT-based aquaculture systems.