Article
Environmental Studies
Esteban Bravo-Lopez, Tomas Fernandez Del Castillo, Chester Sellers, Jorge Delgado-Garcia
Summary: In this research, Machine Learning (ML) methods were used to select the most important factors for evaluating the susceptibility to rotational landslides in the surrounding area of Cuenca, Ecuador. The results showed that ML methods can effectively predict landslide occurrence with high accuracy and highlight the importance of certain conditioning factors in landslide susceptibility.
Article
Computer Science, Artificial Intelligence
Mostafa Khojastehnazhand, Mozaffar Roostaei
Summary: This study used a machine vision system and texture feature extraction methods to classify seven varieties of wheat in the East Azerbaijan Province of Iran. By utilizing unsupervised and supervised methods, along with feature extraction, the different wheat varieties were identified with over 95% accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Diego Fernandez-Edreira, Jose Linares-Blanco, Carlos Fernandez-Lozano
Summary: Recent studies have shown that changes in microbiota balance can lead to various diseases, including diabetes, while Machine Learning techniques can identify complex patterns of data and extract intrinsic knowledge. The combination of mass sequencing techniques allows for the determination of an individual's metagenomic profile and the identification of microbial composition.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Feifei Liu, Zihao Huang, Tianrang Xie, Runze Hu, Bingbing Qi
Summary: This paper presents a novel approach in underwater image quality assessment by effectively combining low-level image properties with high-level semantic features, bridging the gap in achieving a comprehensive assessment of image quality.
Article
Environmental Sciences
Daniela Piacentini, Francesco Troiani, Davide Torre, Marco Menichetti
Summary: This study explores the spatial distribution of gravitational landforms along the rocky coast of Mt. San Bartolo, Italy, using a high-resolution DEM and LSQ analysis method. Results demonstrate that LSQ analysis can efficiently investigate gravitational slope processes in coastal areas.
Article
Computer Science, Information Systems
Yuexue Xu, Shengjia Zhang, Jinyu Li, Haiying Liu, Hongchun Zhu
Summary: This study utilized texture feature analysis method to classify typical landforms in southwest Tibet, and found that DWT texture feature can achieve higher classification accuracy.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2021)
Article
Computer Science, Information Systems
Weichan Zhong, Xiaojun Chen, Feiping Nie, Joshua Zhexue Huang
Summary: In this paper, a novel adaptive discriminant analysis method SADA is proposed for semi-supervised feature selection, which can effectively learn the similarity matrix and projection matrix during the process. Experimental results demonstrate the superior performance of SADA compared to other semi-supervised feature selection methods.
INFORMATION SCIENCES
(2021)
Article
Biochemical Research Methods
Fahimeh Motamedi, Horacio Perez-Sanchez, Alireza Mehridehnavi, Afshin Fassihi, Fahimeh Ghasemi
Summary: This article discusses two approaches for quantitative structure-activity prediction studies, focusing on identifying appropriate molecular descriptors and predicting the biological activities of designed compounds. The use of LASSO-random forest algorithm is shown to significantly improve output correlation, reduce implementation time and model complexity, while maintaining prediction accuracy.
Article
Computer Science, Artificial Intelligence
Haythem Ghazouani
Summary: Emotion recognition is a challenging problem in pattern recognition field, as it relies on the quality of face representation and lacks universal features to accurately capture all emotions. Combining multiple features to enhance recognition rate faces issues such as information redundancy and high dimensionality. A genetic programming framework called GP-FER is proposed in this work to address these challenges and has demonstrated superior performance on various facial expression datasets.
APPLIED SOFT COMPUTING
(2021)
Article
Multidisciplinary Sciences
Aijun Zhou, Nurbol Luktarhan, Zhuang Ai
Summary: This paper proposes a WebShell detection method based on the RNCA algorithm, which reduces the dimension of WebShell features through feature selection and constructs a stronger feature combination by fusing behavior sequence features and text static features to improve the recognition rate of WebShell.
Article
Computer Science, Artificial Intelligence
S. Eskandari, M. Seifaddini
Summary: This paper proposes a new approach for streaming feature selection by defining the redundancy analysis step as a binary optimization problem and adopting the binary bat algorithm to find the minimal informative subsets. Experimental studies show that this method outperforms other online and offline streaming feature selection methods in terms of classification accuracy.
PATTERN RECOGNITION
(2023)
Article
Transportation
Junxuan Zhao, Hao Xu, Zhihui Chen, Hongchao Liu
Summary: Accurate detection is crucial for enhancing the safety of vulnerable road users, and this study extends the application of infrastructure-based LiDAR to three major groups of users: pedestrians, cyclists, and wheelchair users. To address the challenges of detecting small-sized road users, a feature-based classification method combined with prior LiDAR trajectory information is proposed, resulting in significant improvement in road user classification performance. Experimental results show that classifiers with prior trajectory information achieve high recall rates, F1-scores, and AUC values for different traffic volumes and user categories.
JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Construction & Building Technology
Behzad Najafi, Monica Depalo, Fabio Rinaldi, Reza Arghandeh
Summary: The study focuses on extracting influential features from smart meter data to improve machine learning-based classification of non-residential buildings. Through advanced feature selection methods and a custom approach, the number of features needed for classification is reduced while accuracy is increased. By selecting and utilizing fewer features, the methodology simplifies feature extraction procedures and enhances interpretation of important features' influence.
ENERGY AND BUILDINGS
(2021)
Article
Engineering, Biomedical
Deepa Kumari, Pavan Kumar Reddy Yannam, Isha Nilesh Gohel, Mutyala Venkata Sai, Subhash Naidu, Yash Arora, B. S. A. S. Rajita, Subhrakanta Panda, Jabez Christopher
Summary: This paper proposes a novel hybrid feature extraction and selection method to classify mammograms into benign and malignant images. It compares combinations of existing feature extraction methods and selects the most relevant features using a hybrid feature selection approach. The performance of the classifiers is improved through hyperparameter tuning and pipeline optimization techniques. Experimental results show that the proposed framework achieves high accuracy, specificity, sensitivity, and F1-score on artificial neural networks.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Environmental Sciences
Mingliang Ma, Guobiao Yao, Jianping Guo, Kaixu Bai
Summary: The study reveals four typical variation patterns of surface ozone in China, with seasonal variation associated with UV radiation and meteorological factors, and long-term trends mainly influenced by ozone precursors and weather conditions. Furthermore, the increasing trend of ozone in North China is found to be related to the depletion of nitrogen dioxide and carbon monoxide, as well as the increase in volatile organic compounds.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2021)
Article
Environmental Sciences
Xianju Li, Xinwen Cheng, Weitao Chen, Gang Chen, Shengwei Liu
Article
Environmental Sciences
Weitao Chen, Yanxin Wang, Xianju Li, Yi Zou, Yiwei Liao, Juncang Yang
ENVIRONMENTAL EARTH SCIENCES
(2016)
Article
Environmental Sciences
Xianju Li, Weitao Chen, Xinwen Cheng, Lizhe Wang
Article
Environmental Sciences
Weitao Chen, Xianju Li, Haixia He, Lizhe Wang
Review
Environmental Sciences
Weitao Chen, Xianju Li, Haixia He, Lizhe Wang
Article
Environmental Sciences
Gang Chen, Song Chen, Xianju Li, Ping Zhou, Zhou Zhou
Article
Environmental Sciences
Weitao Chen, Xianju Li, Yanxin Wang, Shengwei Liu
ENVIRONMENTAL EARTH SCIENCES
(2013)
Article
Environmental Sciences
Weitao Chen, Xianju Li, Yanxin Wang, Gang Chen, Shengwei Liu
REMOTE SENSING OF ENVIRONMENT
(2014)
Article
Environmental Sciences
Xianju Li, Zhuang Tang, Weitao Chen, Lizhe Wang
Article
Chemistry, Analytical
Meng Li, Zhuang Tang, Wei Tong, Xianju Li, Weitao Chen, Lizhe Wang
Summary: A novel multi-level output-based deep belief network (DBN-ML) model was developed and applied for fine classification in an open-pit mine area of Wuhan City, enhancing model robustness through a multi-level output strategy and outperforming other models.
Article
Environmental Sciences
Mingjie Qian, Song Sun, Xianju Li
Summary: The study proposed a 3M-CNN model for fine land cover classification in complex landscapes using multimodal remote sensing data and multiscale kernel-based approach. Experimental results showed that the model achieved excellent overall accuracies on different satellite images and outperformed other comparative models, particularly in visual performance. Overall, the proposed process benefited the fine land cover classification of complex landscape areas.
Article
Environmental Sciences
Renxiang Guan, Zihao Li, Teng Li, Xianju Li, Jinzhong Yang, Weitao Chen
Summary: This study combines a clustering-based band selection method, residual networks, and capsule networks to create a deep model (ResCapsNet) that improves the classification accuracy of hyperspectral images (HSI) in heterogeneous environments. The model achieved the best performances compared to other methods, with good overall accuracies in two study areas.
Article
Green & Sustainable Science & Technology
Diya Zhang, Jiake Leng, Xianju Li, Wenxi He, Weitao Chen
Summary: A novel model is proposed in this study for the fine classification of land cover around complex mining areas. The experiments show that the proposed model outperforms other models and is beneficial for multimodal feature learning and complex landscape applications.
