Search Results (5,390)

Feature selection (FS) constitutes a critical stage within the realms of machine learning and data mining, with the objective of eliminating irrelevant features while guaranteeing model accuracy. Nevertheless, in datasets featuring a multitude of features, choosing the optimal feature poses a significant challenge. This study presents an enhanced Sand Cat Swarm Optimization algorithm (MSCSO) to improve the feature selection process, augmenting the algorithm’s global search capacity and convergence rate via multiple innovative strategies. Specifically, this study devised logistic chaotic mapping and lens imaging reverse learning approaches for population initialization to enhance population diversity; balanced global exploration and local development capabilities through nonlinear parameter processing; and introduced a Weibull flight strategy and triangular parade strategy to optimize individual position updates. Additionally, the Gaussian–Cauchy mutation strategy was employed to improve the algorithm’s ability to overcome local optima. The experimental results demonstrate that MSCSO performs well on 65.2% of the test functions in the CEC2005 benchmark test; on the 15 datasets of UCI, MSCSO achieved the best average fitness in 93.3% of the datasets and achieved the fewest feature selections in 86.7% of the datasets while attaining the best average accuracy across 100% of the datasets, significantly outperforming other comparative algorithms. Full article

The detection and monitoring of mining-induced seismicity are essential for understanding the mechanisms behind earthquakes and mitigating seismic hazards. However, traditional underground seismic monitoring networks for mining-induced seismicity are challenging to install and operate, which has limited their widespread application. In recent years, an alternative approach has emerged: utilizing dense seismic arrays at the surface to monitor mining-induced seismicity. This paper proposes a rapid and efficient data processing scheme for the detection and monitoring of mining-induced seismicity based on the surface dense array. The proposed workflow includes machine learning-based phase picking and P-wave first-motion-polarity picking, followed by rapid phase association, precise earthquake location, and template matching for detecting small earthquakes to enhance the completeness of the earthquake catalog. Additionally, it also provides focal mechanism solutions for larger mining-induced events. We applied this workflow to the continuous waveform data from 90 seismic stations over a period of 27 days around the Dongchuan Copper Mine, Yunnan Province, China. Our results yielded 1536 high-quality earthquake locations and two focal mechanism solutions for larger events. By analyzing the spatiotemporal distribution of these events, we are able to investigate the mechanisms of the induced seismic clusters near the Shijiangjun and Lanniping deposits. Our findings highlight the excellent monitoring capability and application potential of the workflow based on machine learning and template matching compared with conventional techniques. Full article

The Silesian Upland in southern Poland is known as a place where subsidence processes induced by mining activities occur in an area of nearly 1500 square kilometres, with many water bodies that formed in subsidence basins. This study concerned the dynamics of changes in the occurrence, boundaries and area of water bodies in subsidence basins (using orthoimagery from 1996 to 2023), as well as the assessment of the factors underlying the morphogenetic and hydrogenetic transformations of these basins. Within the subsidence basins covered by the study, water bodies occupied a total area that changed from 9.22 hectares in 1996 to 48.43 hectares in 2003, with a maximum of 52.30 hectares in 2009. The obtained figures testify to the extremely dynamic changes taking place in subsidence basins, which are unprecedented within such short time intervals in the case of other morphogenetic types of lakes and anthropogenic water bodies (for instance, from 1996 to 2003, the basin of the Brantka water body in Bytom underwent a more than two-fold change in its area, with R_A values in the range of 54.4% to 131.9). A reflection of the dynamics of short-term changes in the water bodies in question in the period from 1996 to 2023 is the increase in the water area of the three studied water bodies, which was projected by linear regression to range from 0.09 hectares/year to 0.56 hectares/year. The area change trends, as determined by polynomial regression, suggest a slight decrease in the water table within the last few years, as well as within the next few years, for each of the studied basins. Full article

The present article is devoted to the issue of studying the patterns of displacement of superincumbent rock over panels of a mine obtained using advanced seismic technologies, allowing for the study of the boundaries of caving zones in the depths of rock mass. A seismic exploration has been performed in local areas of Zhomart mine responsible for the development of Zhaman-Aybat cuprous sandstone deposits in Central Kazakhstan at the stage of repeated mining with pulling of previously non-mined ore pillars and superincumbent rock caving. A 2D field seismic exploration has been accomplished, totaling to 8000-line m of seismic lines using seismic shot point. The survey depth varied from 455 m to 625 m. The state-of-the-art technologies of kinematic and dynamic analysis of wavefield have been widely used during data processing and interpretation targeted at identifying anomalies associated with the structural heterogeneity of the pays and rock mass, engaging modern algorithms and mathematical apparatuses of specialized geodata processing systems. The above effort resulted in new data regarding the location and morphology of the reflectors, characterizing geological heterogeneity of the section, zones of smooth rock displacement, and displacement of strata with significant disturbance of the rocks overlying mined-out productive pay. The potential of the application of modern 2D seismic exploration to studying an underworked zone with altered physical and mechanical properties located over an ore deposit has been assessed. The novelty and practical significance of the research lies in the determination of the boundaries of zones of displacement and superincumbent rock caving over the panels obtained using state-of-the-art technologies of seismic exploration. The deliverables may be used to improve the process of recognizing specific types of technogenic heterogeneities in the rock mass, impacting the efficiency and safety of subsurface ore mining, both for localization and mining monitoring. Full article

The rapid desorption of gas in coal is an important cause of gas over-limit and outbursts. In order to explain the causes of coal and gas outbursts induced by vibration, this paper studies the gas desorption experiments of tectonic coal with different particle sizes and different adsorption equilibrium pressures under 0~50 Hz vibration. High-pressure mercury intrusion experiments were used to measure the changes in pore volume and specific surface area of tectonic coal before and after vibration, revealing the control of pore structure changes on the initial desorption capacity of gas. Additionally, from the perspective of energy transformation during coal and gas outbursts, the effect of vibration on the process of coal and gas outbursts in tectonic coal was analyzed. The results showed that tectonic coal has strong initial desorption capacity, desorbing 29.58% to 54.51% of the ultimate desorption volume within 10 min. Vibration with frequencies of 0~50 Hz increased both the gas desorption ratios and desorption volume as the frequency increased. The initial desorption rate also increased with the vibration frequency, and vibration can enhance the initial desorption capacity of tectonic coal and delay the attenuation of desorption rate. Vibration affected the changes in the initial gas desorption rate and desorption rate attenuation coefficient by increasing the pore volume and specific surface area, with the changes in macropores and mesopores primarily affecting the initial desorption rate and 0~10 min desorption ratios, while the changes in micropores and minipores mainly influenced the attenuation rate of the desorption rate. Vibration increased the free gas expansion energy of tectonic coal as the frequency increased. During the incubation and triggering processes of coal and gas outbursts, vibration has been observed to accelerate the fragmentation and destabilisation of the coal body, while simultaneously increasing the gas expansion energy to a point where it reaches the threshold energy necessary for coal transportation, thus inducing and triggering the coal and gas protrusion. The study results elucidate, from an energy perspective, the underlying mechanisms that facilitate the occurrence of coal and gas outbursts, providing theoretical guidance for coal and gas outburst prevention and mine safety production. Full article

In coal mining operations, methane explosions constitute a severe safety risk, endangering miners’ lives and causing substantial economic losses, which, in turn, weaken the production efficiency and economic benefits of the mining industry and hinder the sustainable development of the industry. To address this challenge, this article explores the application of decoupling network-based methods in methane explosion simulation, aiming to optimize underground mine ventilation system design through scientific means and enhance safety protection for miners. We used the one-dimensional finite difference method (FDM) software Flowmaster to simulate the propagation process of shock waves from a gas explosion source in complex underground tunnel networks, covering a wide range of scenarios from laboratory-scale parallel network samples to full-scale experimental mine settings. During the simulation, we traced the pressure loss in the propagation of the shock wave in detail, taking into account the effects of pipeline friction, shock losses caused by bends and obstacles, T-joint branching connections, and cross-sectional changes. The results of these two case studies were presented, leading to the following insights: (1) geometric variations within airway networks exert a relatively minor influence on overpressure; (2) the positioning of the vent positively contributes to attenuation effects; (3) rarefaction waves propagate over greater distances than compression waves; and (4) oscillatory phenomena were detected in the conduits connecting to the surface. This research introduces a computationally efficient method for predicting methane explosions in complex underground ventilation networks, offering reasonable engineering accuracy. These research results provide valuable references for the safe design of underground mine ventilation systems, which can help to create a safer and more efficient mining environment and effectively protect the lives of miners. Full article

During the process of mining underground coal, the coal emits a large amount of methane into the mining space, which may lead to methane accumulation and exceed explosion safety limits When the methane encounters a fire source, a methane explosion may occur. The forceful impact caused by a methane explosion in an underground roadway can cause serious damage to the roadway structures and even lead to the collapse of the ventilation system. At the same time, the explosion impact may result in the death of workers and cause physical injury to the surviving workers. Therefore, it is necessary to study the damage effect and injury range of methane explosions. On the basis of the damage criteria and damage characteristics of methane explosions, according to the overpressure distribution of shock waves in the propagation process of a methane explosion, the explosion hazard range is divided into four ranges (from inside to outside): death range, serious injury range, minor injury range, and safety range. Four injury degrees of shock wave overpressure to personal body (slight, medium, serious injury, death), and seven damage degrees of overpressure to structures are also analyzed. The thresholds of their damage (destruction) are determined. On this basis, an experimental system and numerical simulation are constructed to measure damage characteristics, the overpressure value, and the range distance of a methane explosion with different initial explosion intensities. According to the experimental and numerical results, the attenuation formula of a methane explosion shock wave in the propagation process is derived. The research results show that the overpressure and impulse of shock waves are selected as the damage criteria for comprehensive evaluation, and the overpressure criterion is suitable of determining the injury (failure) range over long distances. The four injury ranges are in line with the actual situation and are reasonable. The injury degree also conforms to the medical results, which can be used to guide the injury degree of mine methane explosions. The injury range caused by methane explosions with different initial explosion intensities is reasonable and is basically consistent with the on-site situation. The derived attenuation formula and calculated safety distance are in good agreement with the experimental and numerical results. The research results can provide guidance and help in the escape, rescue, and protection of coal mine underground person. Full article

The complexities inherent in drug development are multi-faceted and often hamper accuracy, speed and efficiency, thereby limiting success. This review explores how recent developments in machine learning (ML) are significantly impacting target-based drug discovery, particularly in small-molecule approaches. The Simplified Molecular Input Line Entry System (SMILES), which translates a chemical compound’s three-dimensional structure into a string of symbols, is now widely used in drug design, mining, and repurposing. Utilizing ML and natural language processing techniques, SMILES has revolutionized lead identification, high-throughput screening and virtual screening. ML models enhance the accuracy of predicting binding affinity and selectivity, reducing the need for extensive experimental screening. Additionally, deep learning, with its strengths in analyzing spatial and sequential data through convolutional neural networks (CNNs) and recurrent neural networks (RNNs), shows promise for virtual screening, target identification, and de novo drug design. Fragment-based approaches also benefit from ML algorithms and techniques like generative adversarial networks (GANs), which predict fragment properties and binding affinities, aiding in hit selection and design optimization. Structure-based drug design, which relies on high-resolution protein structures, leverages ML models for accurate predictions of binding interactions. While challenges such as interpretability and data quality remain, ML’s transformative impact accelerates target-based drug discovery, increasing efficiency and innovation. Its potential to deliver new and improved treatments for various diseases is significant. Full article

This study comprehensively assessed carbon dioxide emissions over a span of two decades, from 2000 to 2020, with the decomposition and decoupling analyses considering multiple influence factors across both short-term and long-term dimensions. The results revealed great fluctuations in the decoupling analysis index (DAI) for subjected sectors such as natural resource processing, electricity, gas, water, textiles, machinery, and electronics manufacturing. Of note, significantly changed sectoral DAIs were observed in urban traffic and transportation, logistics warehousing, and the postal industry within Anhui Province. In contrast, the DAIs of other sectors and social services exhibited a weak decoupling state in Anhui Province. The industrial sectors responsible for mining and textiles and the energy structure encompassing electricity, gas, and water emerged as the primary contributors to carbon dioxide emissions. Additionally, the efficiency of the socio-economic development (EDE) was identified as the principal driver of carbon dioxide emissions during the observed period, while the energy consumption intensity (ECI) served as the putative crucial inhibiting factor. The two-dimensional decoupling of carbon dioxide emissions attributable to the EDE demonstrated a gradual transition from industrial sectors to buildings and tertiary industries from 2000 to 2020. In the future, the interaction between urban carbon dioxide emissions and the socio-economic landscape should be optimized to foster integrated social sustainable development in Anhui Province. Full article

In order to solve the problem of gas overrun in the fully mechanized caving face and the upper corner of high gas and extra-thick coal seam, the fracture and caving process of the roof in the goaf is analyzed and studied by using the relevant theories of fracture mechanics and seepage mechanics. The mathematical model of fracture and caving of the immediate roof and main roof in the goaf is established. Combined with ANSYS Fluent 6.3.26, the seepage process of gas in coal and rock accumulation in the goaf under different ventilation modes is simulated. The distribution law of gas concentration in the goaf is obtained, and the application scope of different ventilation modes is determined. In addition, the influence of the tail roadway application and the wind speed size on the gas concentration in the goaf and the upper corner of the fully mechanized caving face is also explored. The results show that, affected by wind speed and rock porosity, along the strike of the goaf, about 30 m near the working face, the gas concentration is low and growth is slow. In the range of 30~160 m, the gas concentration increases rapidly and reaches a higher value. After 160 m, the gas concentration tends to be stable. Along with the tendency of the working face, the gas concentration in the goaf increases gradually from the inlet side to the return side, and the gas concentration increases noticeably near the return air roadway. Along the vertical direction of the goaf, the gas concentration gradually increases, and the concentration of the fracture zone basically reaches 100%. Different ventilation modes have different application scopes. The U-type ventilation mode is suitable for the scenario of less desorption gas in the coal seam, while U + I and U + L-type ventilation modes are suitable for the scenario of more desorption gas in coal seam or higher mining intensity. The application of the tail roadway can reduce the gas concentration in the upper corner to a certain extent, but it has limited influence on the overall gas concentration distribution in the goaf. In addition, when the wind speed of the working face should be controlled at 2.0~3.5 m/s, it is more conducive to the discharge of gas, the method of reducing the gas concentration in the upper corner by increasing the wind speed of the working face is more suitable for the case where the absolute gas emission of the fully mechanized caving face is low, and the effect is limited when the absolute gas emission is high. The above conclusions provide a reference for solving the problem of gas overrun in the goaf and the upper corner of a fully mechanized caving face. Full article

The Dongzhongla deposit is a skarn-type lead–zinc ore deposit located in the eastern segment of the Gangdese metallogenic belt, situated in the Xizang province, China. The high-altitude mountainous terrain of the region poses significant challenges to ground-based exploration. To facilitate more accurate mineral exploration in the deposit and its surrounding area, a high-resolution airborne magnetic survey was conducted over the mining area and its periphery. The airborne magnetic data were processed using derivative and Euler deconvolution methods, yielding results that reflect the geological structural features of the study area. By integrating the geological characteristics of the ore deposit, we inferred that the areas of magnetic anomaly extensions and the peripheries of other magnetic anomalies are favorable zones for mineralization, providing positive leads for further mineral exploration. Full article

This paper provides an overview of the impacts of mining-related environmental liabilities on humans, soils, sediments, surface water and groundwater across various mining districts in Zacatecas, Mexico. An analysis has been carried out on the areas of the state most affected by the presence of potentially toxic elements (PTEs) such as arsenic, lead, cadmium, copper, chromium and zinc, identifying priority areas for environmental assessment and remediation. Likewise, a review of the concentrations of PTEs reported in different environmental matrices of the state’s mining areas with the presence of environmental liabilities was carried out, most of which exceed the maximum permissible limits established by Mexican and international regulations, generating an environmental risk for the populations near these districts due to their potential incorporation into the food chain. Additionally, this study explores research focused on the biostabilization of PTEs using microorganisms with specific metabolic activities. Phytoremediation is presented as a viable tool for the stabilization and elimination of PTEs, in which endemic plants from arid–semi-arid climates have shown favorable results in terms of the phytostabilization and phytoextraction processes of the PTEs present in mining waste. Full article

Weighted k-nearest neighbor (WKNN)-based Wi-Fi fingerprinting is popular in indoor location-based services due to its ease of implementation and low computational cost. KNN-based methods rely on distance metrics to select the nearest neighbors. However, traditional metrics often fail to capture the complexity of indoor environments and have limitations in identifying non-linear relationships. To address these issues, we propose a novel WKNN-based Wi-Fi fingerprinting method that incorporates distance metric learning. In the offline phase, our method utilizes a Siamese network with a triplet loss function to learn a meaningful distance metric from training fingerprints (FPs). This process employs a unique triplet mining strategy to handle the inherent noise in FPs. Subsequently, in the online phase, the learned metric is used to calculate the embedding distance, followed by a signal-space distance filtering step to optimally select neighbors and estimate the user’s location. The filtering step mitigates issues from an overfitted distance metric influenced by hard triplets, which could lead to incorrect neighbor selection. We evaluate the proposed method on three benchmark datasets, UJIIndoorLoc, Tampere, and UTSIndoorLoc, and compare it with four WKNN models. The results show a mean positioning error reduction of 3.55% on UJIIndoorLoc, 16.21% on Tampere, and 16.49% on UTSIndoorLoc, demonstrating enhanced positioning accuracy. Full article

Resource-oriented cities are faced with the problems of the decline of traditional industries, exhaustion of resources, and wastage of space. Faced with these problems, urban renewal has become an important role and is widely used in the reuse of old and abandoned spaces. As a historical witness of the industrial revolution and urbanization process, coal mine industrial heritage not only has the value of material heritage but also carries rich historical and cultural information. However, with the adjustment of industrial structure, much coal mine industrial heritage has gradually lost its original production function and become neglected idle space in cities, and industrial buildings and equipment in these spaces have been abandoned or dismantled. The study takes the Wangfeng Mine site in Jiaozuo City, Henan Province as an example, combined with the urban development history and current situation of Jiaozuo city, it discusses the remodeling strategy of industrial heritage space from the perspective of urban renewal. Firstly, through case analysis, historical data sorting, and field research, the study integrated the historical development context of the Jiaozuo coal mine site and its impact on the urban spatial pattern, secondly, discussed the practical problems in the reuse process of industrial sites, and finally proposed specific spatial remodeling strategies based on the conjugation theory. This included determining how to deal with the three pairs of conjugated relations between protection and development, function and ecology, and history and modernity so as to make the spatial remodeling strategy of industrial sites more scientific and sustainable. To promote the sustainable and healthy development of urban industrial heritage space. Full article

There are currently more than 30 underground mines operating in Poland. These are mines extracting hard coal, salt, and metal ores. Each of these plants has its own specifics for operation, but all operate under the same regulations. The basic principle is to ensure the safety of the crew and equipment. The progressive mechanization and automation of the mining process results in the installation of power electronic converters in the networks of mining plants, which significantly deteriorate the quality of the power in the plant supply networks. In addition, the constant reconfiguration of these networks related to the progress of the work can affect the safety conditions of the plant. This article describes problems occurring at one underground mining plant that are related to the structure of the power grid. Failures and interruptions in the production process were the result of poor power quality. They directly translated into increased production costs and significantly affected the safety level of the workforce, which could result in further consequences, not only in the financial sphere. The article also addresses the issue of existing legal regulations, the provisions of which may be insufficient in assessing the current state of power quality in mining plants. Full article