This study employs fuzzy regression and fuzzy multivariate clustering techniques to analyze arsenic-polluted water samples originating from acid rock drainage in waste rock dumps. The research focuses on understanding the complex relationships between variables associated with arsenic contamination, such as water arsenic concentration, pH levels, and soil characteristics. To this end, fuzzy regression models were developed to estimate the relationships between water arsenic concentration and independent variables, thus, incorporating the inherent uncertainties into the analysis. Furthermore, multivariate fuzzy k-means clustering analysis facilitated the identification of fuzzy-based clusters within the dataset, providing insights into spatial patterns and potential sources of arsenic pollution. The pairwise comparisons indicated the strongest correlation of 0.62 between soil total arsenic and pH, while the weakest correlation of 0.13 was observed between soil-soluble arsenic and soil iron, providing valuable insights into their relationships and impact on water arsenic levels. The associated uncertainties in the relationships among the variables were determined based on the degree of belongingness of each data point to various fuzzy sets. Three distinct clusters emerged from the analysis: Cluster 1 comprised Points 5, 6, and 7; Cluster 2 included Points 1, 2, 3, 4, 8, and 9; and Cluster 3 consisted of Points 10, 11, 12, and 13. The findings enhance our understanding of the factors influencing arsenic contamination to provide an effective mitigation strategy in acid rock drainage scenarios. This research also demonstrates the applicability and effectiveness of fuzzy regression and fuzzy multivariate clustering in the analysis of arsenic-polluted water samples.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jhazmat.2023.133250 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Statistical and data visualization techniques to study the role of one-electron in the energy of neutral and charged clusters of Na.
Sci Rep
January 2025
Department of Physics, Faculty of Science, Fasa University, Fasa, 74616-86131, Iran.
In this work, we explored the role of a single electron in the energy of neutral and charged clusters of using data visualization and statistical techniques as a new insight. Initially, we studied the effects of one electron, time, and temperature on energy using multiple linear regression analysis with dummy variables, and the results demonstrated that all three predictors significantly affected the energy. Time had a positive impact (direct ratio effect) on the energy of , and and a negative impact (inverse ratio effect) on the energy of while temperature had a positive effect on the energy of all three sodium clusters.
View Article and Find Full Text PDFBreast Tumor Detection and Diagnosis Using an Improved Faster R-CNN in DCE-MRI.
Bioengineering (Basel)
December 2024
School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou 510006, China.
AI-based breast cancer detection can improve the sensitivity and specificity of detection, especially for small lesions, which has clinical value in realizing early detection and treatment so as to reduce mortality. The two-stage detection network performs well; however, it adopts an imprecise ROI during classification, which can easily include surrounding tumor tissues. Additionally, fuzzy noise is a significant contributor to false positives.
View Article and Find Full Text PDFEEG Signals Classification Related to Visual Objects Using Long Short-Term Memory Network and Nonlinear Interval Type-2 Fuzzy Regression.
Brain Topogr
January 2025
Department of Biomedical Engineering, Amirkabir University of Technology, Tehran, Iran.
By gaining insights into how brain activity is encoded and decoded, we enhance our understanding of brain function. This study introduces a method for classifying EEG signals related to visual objects, employing a combination of an LSTM network and nonlinear interval type-2 fuzzy regression (NIT2FR). Here, ResNet is utilized for feature extraction from images, the LSTM network for feature extraction from EEG signals, and NIT2FR for mapping image features to EEG signal features.
View Article and Find Full Text PDFClimate change impact on water treatment plants: analysis of chlorophyll-a levels and process performance.
Environ Sci Pollut Res Int
January 2025
Department of Environmental Health Engineering, School of Public Health, Mazandaran University of Medical Sciences, Sari, Iran.
Climate change significantly impacts the risk of eutrophication and, consequently, chlorophyll-a (Chl-a) concentrations. Understanding the impact of water flows is a crucial first step in developing insights into future patterns of change and associated risks. In this study, the Statistical DownScaling Model (SDSM)-a widely used daily downscaling method-is implemented to produce downscaled local climate variables, which serve as input for simulating future hydro-climate conditions using a hydrological model.
View Article and Find Full Text PDFIncident duration prediction through integration of uncertainty and risk factor evaluation: A San Francisco incidents case study.
PLoS One
January 2025
Department of Industrial Engineering, Sharif University of Technology, Tehran, Iran.
Predicting incident duration and understanding incident types are essential in traffic management for resource optimization and disruption minimization. Precise predictions enable the efficient deployment of response teams and strategic traffic rerouting, leading to reduced congestion and enhanced safety. Furthermore, an in-depth understanding of incident types helps in implementing preventive measures and formulating strategies to alleviate their influence on road networks.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!