Related references
Note: Only part of the references are listed.
Article
Automation & Control Systems
G. Reshma et al.
Summary: Intelligent automation in the healthcare sector is becoming more prevalent with the integration of AI techniques, assisting in better healthcare decision-making. Skin lesion segmentation and classification are crucial in intelligent systems for early and precise skin cancer diagnosis, despite challenges such as artifacts and variable lesion images. The presented IMLT-DL model incorporates various advanced techniques to achieve a high accuracy of 0.992 in skin lesion diagnosis.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2022)
Article
Automation & Control Systems
S. Neelakandan et al.
Summary: This paper proposes an Automated Word Embedding with Parameter Tuned Deep Learning (AWE-PTDL) model for focused web crawling. The model involves processes like pre-processing, word embedding, classification, and hyperparameter tuning to improve crawling performance.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2022)
Article
Environmental Sciences
Abdulmohsen Almalawi et al.
Summary: This paper utilizes artificial intelligence algorithms to forecast and monitor air quality, creating models for predicting the air quality of four distinct gases using Linear Regression, Support Vector Regression, and Gradient Boosted Decision Tree Ensembles. The AI models are evaluated based on performance measurements to choose the most accurate model for predicting air pollutants.
ENVIRONMENTAL RESEARCH
(2022)
Article
Environmental Sciences
Abdulmohsen Almalawi et al.
Summary: This paper proposes an arithmetic optimization algorithm (AOA) with a multi-head attention based bidirectional long short-term memory (MABLSTM) model for predicting the size fractionated airborne particle bound metals. The results show that this method can accurately predict the concentration of heavy metals and outperforms other methods.
Article
Environmental Sciences
Abdulmohsen Almalawi et al.
Summary: This article presents a novel RODL-HMSEP model based on biochar design, which can be used for predicting the adsorption performance of heavy metals in different biochar properties. By utilizing density clustering and deep belief network techniques, heavy metals can be efficiently removed from wastewater.
Review
Agricultural Engineering
Hao-nan Guo et al.
Summary: Conventional treatment and recycling methods of organic solid waste have inherent flaws, leading to increased attention on machine learning in this field. Research mainly focuses on municipal solid waste management, with artificial neural networks being the most widely used model.
BIORESOURCE TECHNOLOGY
(2021)
Article
Engineering, Environmental
Wei-Lung Mao et al.
Summary: This study discussed the application of an automatic classification robot based on image recognition in recycling tasks, optimizing the fully-connected layer of DenseNet121 to improve waste classification accuracy, and utilizing genetic algorithms for optimization. Results showed that the optimized DenseNet121 achieved a highest accuracy of 99.6% on TrashNet, outperforming other studies' CNNs.
RESOURCES CONSERVATION AND RECYCLING
(2021)
Review
Environmental Sciences
Merve Erkinay Ozdemir et al.
Summary: The increase in waste generation has significantly impacted human health, natural ecosystems, and ecological balance. Despite the rising recycling rates, challenges such as high expenses in waste separation persist. Machine learning plays a crucial role in improving waste recycling processes.
JOURNAL OF MATERIAL CYCLES AND WASTE MANAGEMENT
(2021)
Article
Engineering, Environmental
Cong Wang et al.
Summary: A proof-of-concept municipal waste management system utilizes deep learning and cloud computing for accurate waste classification at the beginning of garbage collection. IoT devices monitor waste amount and container status, enabling adaptive deployment and maintenance planning for successful waste management.
Review
Engineering, Environmental
Qiang Zhang et al.
Summary: This study introduces a waste classification model based on deep learning, which incorporates a self-monitoring module into the residual network model in order to enhance the representation capability of the feature map. The proposed model achieves a high accuracy in classifying recyclable waste images.
RESOURCES CONSERVATION AND RECYCLING
(2021)
Article
Computer Science, Artificial Intelligence
S. Neelakandan et al.
Summary: This paper proposes an efficient IoT-based traffic prediction system and traffic signal control system using OWENN algorithm and Intel 80,286 microprocessor for a smart city, which goes through phases of data collection, feature extraction, classification, optimized traffic values, and traffic signal control. The OWENN algorithm achieves high accuracy and outperforms existing models in traffic prediction and control.
Article
Engineering, Multidisciplinary
Mesut Togacar et al.
Article
Computer Science, Information Systems
Dimitris Ziouzios et al.
Article
Astronomy & Astrophysics
Dinesh Kumar et al.
MODERN PHYSICS LETTERS A
(2019)
Article
Computer Science, Hardware & Architecture
Peng Li et al.
Article
Green & Sustainable Science & Technology
V. Bisinella et al.
JOURNAL OF CLEANER PRODUCTION
(2017)
