Comprehensive Environmental Monitoring System for Industrial and Mining Enterprises Using Multimodal Deep Learning and CLIP Model

Addressing the challenges of limited accuracy in anomaly detection within comprehensive environmental monitoring of industrial and mining enterprises, and the constraints posed by singular data modalities, this study proposes an integration of a multimodal Long Short-Term Memory (LSTM) model with th...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuqin Wang, Na Cheng, Yan Hu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10852209/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832575585492140032
author Shuqin Wang
Na Cheng
Yan Hu
author_facet Shuqin Wang
Na Cheng
Yan Hu
author_sort Shuqin Wang
collection DOAJ
description Addressing the challenges of limited accuracy in anomaly detection within comprehensive environmental monitoring of industrial and mining enterprises, and the constraints posed by singular data modalities, this study proposes an integration of a multimodal Long Short-Term Memory (LSTM) model with the Contrastive Language-Image Pretraining (CLIP) model. The initial phase employs ResNet within the CLIP model for extracting image features, and a Transformer for encoding text features. Subsequently, feature vectors obtained from monitoring images and text are fused using a rudimentary concatenation method to generate a joint embedding representation. Principal Component Analysis (PCA) is then applied to diminish the dimensionality of the amalgamated features derived from environmental monitoring images, descriptive texts, and sensor data collected by industrial and mining enterprises. Finally, a multimodal LSTM model is leveraged to detect anomalies in the monitoring data by capturing long-term dependencies within time series information. The model was trained and evaluated using real-time data from a coal mining enterprise’s environmental monitoring system spanning March to September 2023. Results reveal that the multimodal LSTM-CLIP model achieved an anomaly detection accuracy of 0.98 in environmental monitoring, marking a 0.10 improvement over the unimodal LSTM model, with a response time of merely 110.25 milliseconds. These findings underscore the efficacy of the multimodal LSTM-CLIP model in integrating multimodal information, thereby significantly enhancing the accuracy of anomaly detection and the speed of environmental anomaly warnings, ultimately ensuring the safety of industrial and mining enterprises.
format Article
id doaj-art-604e1c12587c4187ab845aeed96477d7
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-604e1c12587c4187ab845aeed96477d72025-01-31T23:05:16ZengIEEEIEEE Access2169-35362025-01-0113199641997810.1109/ACCESS.2025.353353710852209Comprehensive Environmental Monitoring System for Industrial and Mining Enterprises Using Multimodal Deep Learning and CLIP ModelShuqin Wang0Na Cheng1Yan Hu2https://orcid.org/0009-0003-0823-8056School of Computer Engineering, Anhui Wenda University of Information Engineering, Hefei, ChinaSchool of Computer Engineering, Anhui Wenda University of Information Engineering, Hefei, ChinaSchool of Computer Engineering, Anhui Wenda University of Information Engineering, Hefei, ChinaAddressing the challenges of limited accuracy in anomaly detection within comprehensive environmental monitoring of industrial and mining enterprises, and the constraints posed by singular data modalities, this study proposes an integration of a multimodal Long Short-Term Memory (LSTM) model with the Contrastive Language-Image Pretraining (CLIP) model. The initial phase employs ResNet within the CLIP model for extracting image features, and a Transformer for encoding text features. Subsequently, feature vectors obtained from monitoring images and text are fused using a rudimentary concatenation method to generate a joint embedding representation. Principal Component Analysis (PCA) is then applied to diminish the dimensionality of the amalgamated features derived from environmental monitoring images, descriptive texts, and sensor data collected by industrial and mining enterprises. Finally, a multimodal LSTM model is leveraged to detect anomalies in the monitoring data by capturing long-term dependencies within time series information. The model was trained and evaluated using real-time data from a coal mining enterprise’s environmental monitoring system spanning March to September 2023. Results reveal that the multimodal LSTM-CLIP model achieved an anomaly detection accuracy of 0.98 in environmental monitoring, marking a 0.10 improvement over the unimodal LSTM model, with a response time of merely 110.25 milliseconds. These findings underscore the efficacy of the multimodal LSTM-CLIP model in integrating multimodal information, thereby significantly enhancing the accuracy of anomaly detection and the speed of environmental anomaly warnings, ultimately ensuring the safety of industrial and mining enterprises.https://ieeexplore.ieee.org/document/10852209/Industrial and mining enterprisesintegrated environmental monitoring systemmultimodal LSTM modelCLIP modelanomaly detection accuracy
spellingShingle Shuqin Wang
Na Cheng
Yan Hu
Comprehensive Environmental Monitoring System for Industrial and Mining Enterprises Using Multimodal Deep Learning and CLIP Model
IEEE Access
Industrial and mining enterprises
integrated environmental monitoring system
multimodal LSTM model
CLIP model
anomaly detection accuracy
title Comprehensive Environmental Monitoring System for Industrial and Mining Enterprises Using Multimodal Deep Learning and CLIP Model
title_full Comprehensive Environmental Monitoring System for Industrial and Mining Enterprises Using Multimodal Deep Learning and CLIP Model
title_fullStr Comprehensive Environmental Monitoring System for Industrial and Mining Enterprises Using Multimodal Deep Learning and CLIP Model
title_full_unstemmed Comprehensive Environmental Monitoring System for Industrial and Mining Enterprises Using Multimodal Deep Learning and CLIP Model
title_short Comprehensive Environmental Monitoring System for Industrial and Mining Enterprises Using Multimodal Deep Learning and CLIP Model
title_sort comprehensive environmental monitoring system for industrial and mining enterprises using multimodal deep learning and clip model
topic Industrial and mining enterprises
integrated environmental monitoring system
multimodal LSTM model
CLIP model
anomaly detection accuracy
url https://ieeexplore.ieee.org/document/10852209/
work_keys_str_mv AT shuqinwang comprehensiveenvironmentalmonitoringsystemforindustrialandminingenterprisesusingmultimodaldeeplearningandclipmodel
AT nacheng comprehensiveenvironmentalmonitoringsystemforindustrialandminingenterprisesusingmultimodaldeeplearningandclipmodel
AT yanhu comprehensiveenvironmentalmonitoringsystemforindustrialandminingenterprisesusingmultimodaldeeplearningandclipmodel