fuzzy clustering

[1] Corresponding Author Human activities, such as mining, constructing highways, and building infrastructures like dams and industrial facilities, have caused significant damage to many natural ecosystems. In addition to disrupting the balance of these ecosystems, some of these activities have led to considerable pollution. Traditional methods, such as geostatistics and geophysics, while helpful info helpful in identifying contaminated areas and measuring the extent of pollution, are often costly, time-consuming, and come with helpful in identifying areas and measuring the extent of pollution, are often expensive, time-consuming and come with various limitations. To address these limitations, remote sensing data can provide an effective solution. The foundation of remote sensing lies in the spectral frequencies or images captured through satellite or drone equipment. Remote sensing data processing methods for identifying the type and estimating the extent of soil contamination fall into three main categories: physical models, mathematical models, and physics-based mathematical models. Given the various challenges associated with remote sensing of pollution in mining areas and their surroundings and the limited research conducted—particularly in Iran—this study addresses a critical important important important necessary conducted undertaken—particularly in Iran—this study addresses the essential gap. Iran hosts numerous mining sites in or near critical environmental ecosystems, making pollution management in these areas a pressing issue. This research proposes a method combining fuzzy clustering and edge-based features to identify surface and physical soil contamination caused by mining activities and coal-washing waste from the eastern Alborz coal preparation plant. This approach uses Sentinel-2 satellite imagery at a 1:100,000 scale for the studied mining area. The study focuses on the eastern Alborz coal mining region in Semnan Province, Iran. This area lies 140 kilometers from the provincial capital, 25 kilometers northeast of Damghan, and 75 kilometers from Shahroud.

The complete knowledge of the cutting process and the performance of the sawing machine can help increase the efficiency and quality of the manufactured product.  During the field studies, 12 rock samples from two kinds of ornamental stones were collected and some major mechanical properties including uniaxial compressive strength (UCS), Mohs hardness (Mh), Schimazek’s F-abrasiveness factors (SF-a), and young modulus (YM) were measured. Also, Fuzzy C-means has been used as a soft computing technique in this study. All different studied rock samples are classified into 3, 4, and 5 classes. Then, the results of classification were compared with consumed energy values. Finally, it can be concluded that FCM could be a simple but efficient tool in the evaluation of the sawability of ornamental stone as one of the most important factors to estimation and prediction of production cost and productivity of processing plants.

The rock sawability and prediction of consumed energy is one of the most important factors in the estimation and prediction of production cost and productivity of processing plants. In this study, for laboratory tests, some rock blocks were collected from the studied quarries. Then, by using the fuzzy C-means clustering approached and considering laboratory results of rock samples, all of the rocks have been classified in 3, 4, and 5 separate clusters. The results clearly showed that the FCM algorithm was used as a reliable and efficient tool for classifying the ornamental stone.  

Nowadays, with the increasing growth of uncertain problems, the use of soft computing techniques with high ability in solving these kinds of problems has increased significantly. Assessment of the sawability of ornamental stone is the most important factor in the identification and prediction of production cost and productivity of processing plants. Given the unreliability of all experimental laboratory, one of the most important tasks in the sawability of ornamental stone’ classification is using a method with the highest possible accuracy. According to the importance of the issue, in this study, the Fuzzy C-means algorithm is used for the classification. Four important physical and mechanical characteristics of 12 rock samples are considered for the classification of sawability of ornamental stone from two kinds of ornamental stone, including hard and soft rock groups using Fuzzy C-means Optimization, including uniaxial compressive strength, Mohs hardness, Schmiazek F-abrasivity factor, and Young's modulus. Finally, in this study, the results of the classification are compared with consumed energy.

In this study employing Fuzzy C-means as soft computing technique and some major mechanical properties such as uniaxial compressive strength, Mohs hardness, Schmiazek F-abrasivity factor, and Young's modulus to evaluate the sawability of ornamental stone, 3 to 5 classes are considered. Generally, according to this research, the following remarks can be concluded: 1- The 12 rock samples from two kinds of ornamental stones, including hard and soft rock groups, are evaluated and tested. 2- A comparison was made between 3 different models (3 classes from 3 to 5 classes) with consumed energy of the sawing machine. The results show that all 12 rock samples are classified as very suitable. 3- In comparison to all classes, it can be concluded that FCM is a reliable technique for clustering the sawability of ornamental stone with highly acceptable degrees of robustness.