Smart Helmet-Based Proximity Warning System to Improve Occupational Safety on the Road Using Image Sensor and Artificial Intelligence.

Recently, collisions between equipment and workers occur frequently on the road in construction and surface mining sites. To prevent such accidents, we developed a smart helmet-based proximity warning system (PWS) that facilitates visual and tactile proximity warnings. In this system, a smart helmet comprising an Arduino Uno board and a camera module with built-in Wi-Fi was used to transmit images captured by the camera to a smartphone via Wi-Fi. When the image was analyzed through object detection and a heavy-duty truck or other vehicle was detected in an image, the smartphone transmitted a signal to the Arduino via Bluetooth and, when a signal was received, an LED strip with a three-color LED visually alerted the worker and the equipment operator. The performance of the system tested the recognition distance of the helmet according to the pixel size of the detected image in an outdoor environment. The proposed personal PWS can directly produce visual proximity warnings to both workers and operators enabling them to quickly identify and evacuate from dangerous situations.

Predicting the sorption efficiency of heavy metal based on the biochar characteristics, metal sources, and environmental conditions using various novel hybrid machine learning models.

Heavy metals in water and wastewater are taken into account as one of the most hazardous environmental issues that significantly impact human health. The use of biochar systems with different materials helped significantly remove heavy metals in the water, especially wastewater treatment systems. Nevertheless, heavy metal's sorption efficiency on the biochar systems is highly dependent on the biochar characteristics, metal sources, and environmental conditions. Therefore, this study implicates the feasibility of biochar systems in the heavy metal sorption in water/wastewater and the use of artificial intelligence (AI) models in investigating efficiency sorption of heavy metal on biochar. Accordingly, this work investigated and proposed 20 artificial intelligent models for forecasting the sorption efficiency of heavy metal onto biochar based on five machine learning algorithms and bagging technique (BA). Accordingly, support vector machine (SVM), random forest (RF), artificial neural network (ANN), M5Tree, and Gaussian process (GP) algorithms were used as the key algorithms for the aim of this study. Subsequently, the individual models were bagged with each other to generate new ensemble models. Finally, 20 intelligent models were developed and evaluated, including SVM, RF, M5Tree, GP, ANN, BA-SVM, BA-RF, BA-M5Tree, BA-GP, BA-ANN, SVM-RF, SVM-M5Tree, SVM-GP, SVM-ANN, RF-M5Tree, RF-GP, RF-ANN, M5Tree-GP, M5Tree-ANN, GP-ANN. Of those, the hybrid models (i.e., BA-SVM, BA-RF, BA-M5Tree, BA-GP, BA-ANN, SVM-RF, SVM-M5Tree, SVM-GP, SVM-ANN, RF-M5Tree, RF-GP, RF-ANN, M5Tree-GP, M5Tree-ANN, GP-ANN) are introduced as the novelty of this study for estimating the heavy metal's sorption efficiency on the biochar systems. Also, the biochar characteristics, metal sources, and environmental conditions were comprehensively assessed and used, and they are considered as a novelty of the study as well. For this aim, a dataset of sorption efficiency of heavy metal was collected and processed with 353 experimental tests. Various performance indexes were applied to evaluate the models, such as RMSE, R2, MAE, color intensity, Taylor diagram, box and whiskers plots. This study's findings revealed that AI models could predict heavy metal's sorption efficiency onto biochar with high reliability, and the efficiency of the ensemble models is higher than those of individual models. The results also reported that the SVM-ANN ensemble model is the most superior model among 20 developed models. The predictive model proposed that heavy metal's efficiency sorption on biochar can be accurately forecasted and early warning for the water pollution by heavy metal.

Application of a Drone Magnetometer System to Military Mine Detection in the Demilitarized Zone.

We propose a magnetometer system fitted on an unmanned aerial vehicle (UAV, or drone) and a data-processing method for detecting metal antipersonnel landmines (M16) in the demilitarized zone (DMZ) in Korea, which is an undeveloped natural environment. The performance of the laser altimeter was improved so that the drone could fly at a low and stable altitude, even in a natural environment with dust and bushes, and a magnetometer was installed on a pendulum to minimize the effects of magnetic noise and vibration from the drone. At a flight altitude of 1 m, the criterion for M16 is 5 nT. Simple low-pass filtering eliminates magnetic swing noise due to pendulum motion, and the moving average method eliminates changes related to the heading of the magnetometer. Magnetic exploration was conducted in an actual mine-removal area near the DMZ in Korea, with nine magnetic anomalies of more than 5 nT detected and a variety of metallic substances found within a 1-m radius of each detection site. The proposed UAV-based landmine detection system is expected to reduce risk to detection personnel and shorten the landmine-detection period by providing accurate scientific information about the detection area prior to military landmine-detection efforts.

Prediction of slope failure in open-pit mines using a novel hybrid artificial intelligence model based on decision tree and evolution algorithm.

In this study, the objective was to develop a new and highly-accurate artificial intelligence model for slope failure prediction in open-pit mines. For this purpose, the M5Rules algorithm was combined with a genetic algorithm (GA) in a novel hybrid technique, named M5Rules-GA model, for slope stability estimation and analysis and 450-slope observations in an open-pit mine in Vietnam were modeled using the Geo-Studio software based on essential parameters. The factor of safety was used as the model outcome. Artificial neural networks (ANN), support vector regression (SVR), and previously introduced models (such as FFA-SVR, ANN-PSO, ANN-ICA, ANN-GA, and ANN-ABC) were also developed for evaluating the proposed M5Rules-GA model. The evaluation of the model performance involved applying and computing the determination coefficient, variance account for, and root mean square error, as well as a general ranking and color scale. The results confirmed that the proposed M5Rules-GA model is a robust tool for analyzing slope stability. The other investigated models yielded less robust performance under the evaluation metrics.

Smart Glasses-Based Personnel Proximity Warning System for Improving Pedestrian Safety in Construction and Mining Sites.

A smart glasses-based wearable personnel proximity warning system (PWS) was developed for pedestrian safety in construction and mining sites. The smart glasses receive signals transmitted by Bluetooth beacons attached to heavy equipment or vehicles, with the proximity determined by the signal strength. A visual alert is displayed to the wearer when in close proximity. The media access control address of the Bluetooth beacon provides information on the approaching equipment or vehicle, which is displayed to the wearer so that they can respond appropriately. There was a detection distance of at least 10 m regardless of the direction the pedestrian was looking and the alert was successful in all 40 trials at ≥10 meters. The subjective workload was evaluated using the NASA task load index on ten subjects, either without a personal PWS, with a smartphone-based PWS, or with the smart glasses-based PWS. The mental, temporal, and physical stresses were lowest when using the smart glasses-based PWS. Smart glasses-based PWSs can improve work efficiency by freeing both hands of the pedestrians, and various functions can be supported through application development. Therefore, they are particularly useful for pedestrian safety in construction and mining sites.

Predicting Blast-Induced Ground Vibration in Open-Pit Mines Using Vibration Sensors and Support Vector Regression-Based Optimization Algorithms.

In this study, vibration sensors were used to measure blast-induced ground vibration (PPV). Different evolutionary algorithms were assessed for predicting PPV, including the particle swarm optimization (PSO) algorithm, genetic algorithm (GA), imperialist competitive algorithm (ICA), and artificial bee colony (ABC). These evolutionary algorithms were used to optimize the support vector regression (SVR) model. They were abbreviated as the PSO-SVR, GA-SVR, ICA-SVR, and ABC-SVR models. For each evolutionary algorithm, three forms of kernel function, linear (L), radial basis function (RBF), and polynomial (P), were investigated and developed. In total, 12 new hybrid models were developed for predicting PPV in this study, named ABC-SVR-P, ABC-SVR-L, ABC-SVR-RBF, PSO-SVR-P, PSO-SVR-L, PSO-SVR-RBF, ICA-SVR-P, ICA-SVR-L, ICA-SVR-RBF, GA-SVR-P, GA-SVR-L and GA-SVR-RBF. There were 125 blasting results gathered and analyzed at a limestone quarry in Vietnam. Statistical criteria like R2, RMSE, and MAE were used to compare and evaluate the developed models. Ranking and color intensity methods were also applied to enable a more complete evaluation. The results revealed that GA was the most dominant evolutionary algorithm for the current problem when combined with the SVR model. The RBF was confirmed as the best kernel function for the GA-SVR model. The GA-SVR-RBF model was proposed as the best technique for PPV estimation.

SIMPL: A Simplified Model-Based Program for the Analysis and Visualization of Groundwater Rebound in Abandoned Mines to Prevent Contamination of Water and Soils by Acid Mine Drainage.

Cessation of dewatering following underground mine closure typically results in groundwater rebound, because mine voids and surrounding strata undergo flooding up to the levels of the decant points, such as shafts and drifts. SIMPL (Simplified groundwater program In Mine workings using the Pipe equation and Lumped parameter model), a simplified lumped parameter model-based program for predicting groundwater levels in abandoned mines, is presented herein. The program comprises a simulation engine module, 3D visualization module, and graphical user interface, which aids data processing, analysis, and visualization of results. The 3D viewer facilitates effective visualization of the predicted groundwater level rebound phenomenon together with a topographic map, mine drift, goaf, and geological properties from borehole data. SIMPL is applied to data from the Dongwon coal mine and Dalsung copper mine in Korea, with strong similarities in simulated and observed results. By considering mine workings and interpond connections, SIMPL can thus be used to effectively analyze and visualize groundwater rebound. In addition, the predictions by SIMPL can be utilized to prevent the surrounding environment (water and soil) from being polluted by acid mine drainage.

An Overview of GIS-Based Modeling and Assessment of Mining-Induced Hazards: Soil, Water, and Forest.

In this study, current geographic information system (GIS)-based methods and their application for the modeling and assessment of mining-induced hazards were reviewed. Various types of mining-induced hazard, including soil contamination, soil erosion, water pollution, and deforestation were considered in the discussion of the strength and role of GIS as a viable problem-solving tool in relation to mining-induced hazards. The various types of mining-induced hazard were classified into two or three subtopics according to the steps involved in the reclamation procedure, or elements of the hazard of interest. Because GIS is appropriated for the handling of geospatial data in relation to mining-induced hazards, the application and feasibility of exploiting GIS-based modeling and assessment of mining-induced hazards within the mining industry could be expanded further.

Assessing Statistically Significant Heavy-Metal Concentrations in Abandoned Mine Areas via Hot Spot Analysis of Portable XRF Data.

To develop appropriate measures to prevent soil contamination in abandoned mining areas, an understanding of the spatial variation of the potentially toxic trace elements (PTEs) in the soil is necessary. For the purpose of effective soil sampling, this study uses hot spot analysis, which calculates a z-score based on the Getis-Ord Gi* statistic to identify a statistically significant hot spot sample. To constitute a statistically significant hot spot, a feature with a high value should also be surrounded by other features with high values. Using relatively cost- and time-effective portable X-ray fluorescence (PXRF) analysis, sufficient input data are acquired from the Busan abandoned mine and used for hot spot analysis. To calibrate the PXRF data, which have a relatively low accuracy, the PXRF analysis data are transformed using the inductively coupled plasma atomic emission spectrometry (ICP-AES) data. The transformed PXRF data of the Busan abandoned mine are classified into four groups according to their normalized content and z-scores: high content with a high z-score (HH), high content with a low z-score (HL), low content with a high z-score (LH), and low content with a low z-score (LL). The HL and LH cases may be due to measurement errors. Additional or complementary surveys are required for the areas surrounding these suspect samples or for significant hot spot areas. The soil sampling is conducted according to a four-phase procedure in which the hot spot analysis and proposed group classification method are employed to support the development of a sampling plan for the following phase. Overall, 30, 50, 80, and 100 samples are investigated and analyzed in phases 1-4, respectively. The method implemented in this case study may be utilized in the field for the assessment of statistically significant soil contamination and the identification of areas for which an additional survey is required.

A Rapid, Accurate, and Efficient Method to Map Heavy Metal-Contaminated Soils of Abandoned Mine Sites Using Converted Portable XRF Data and GIS.

The use of portable X-ray fluorescence (PXRF) and inductively coupled plasma atomic emission spectrometry (ICP-AES) increases the rapidity and accuracy of soil contamination mapping, respectively. In practice, it is often necessary to repeat the soil contamination assessment and mapping procedure several times during soil management within a limited budget. In this study, we have developed a rapid, inexpensive, and accurate soil contamination mapping method using a PXRF data and geostatistical spatial interpolation. To obtain a large quantity of high quality data for interpolation, in situ PXRF data analyzed at 40 points were transformed to converted PXRF data using the correlation between PXRF and ICP-AES data. The method was applied to an abandoned mine site in Korea to generate a soil contamination map for copper and was validated for investigation speed and prediction accuracy. As a result, regions that required soil remediation were identified. Our method significantly shortened the time required for mapping compared to the conventional mapping method and provided copper concentration estimates with high accuracy similar to those measured by ICP-AES. Therefore, our method is an effective way of mapping soil contamination if we consistently construct a database based on the correlation between PXRF and ICP-AES data.

Mapping Copper and Lead Concentrations at Abandoned Mine Areas Using Element Analysis Data from ICP-AES and Portable XRF Instruments: A Comparative Study.

Understanding spatial variation of potentially toxic trace elements (PTEs) in soil is necessary to identify the proper measures for preventing soil contamination at both operating and abandoned mining areas. Many studies have been conducted worldwide to explore the spatial variation of PTEs and to create soil contamination maps using geostatistical methods. However, they generally depend only on inductively coupled plasma atomic emission spectrometry (ICP-AES) analysis data, therefore such studies are limited by insufficient input data owing to the disadvantages of ICP-AES analysis such as its costly operation and lengthy period required for analysis. To overcome this limitation, this study used both ICP-AES and portable X-ray fluorescence (PXRF) analysis data, with relatively low accuracy, for mapping copper and lead concentrations at a section of the Busan abandoned mine in Korea and compared the prediction performances of four different approaches: the application of ordinary kriging to ICP-AES analysis data, PXRF analysis data, both ICP-AES and transformed PXRF analysis data by considering the correlation between the ICP-AES and PXRF analysis data, and co-kriging to both the ICP-AES (primary variable) and PXRF analysis data (secondary variable). Their results were compared using an independent validation data set. The results obtained in this case study showed that the application of ordinary kriging to both ICP-AES and transformed PXRF analysis data is the most accurate approach when considers the spatial distribution of copper and lead contaminants in the soil and the estimation errors at 11 sampling points for validation. Therefore, when generating soil contamination maps for an abandoned mine, it is beneficial to use the proposed approach that incorporates the advantageous aspects of both ICP-AES and PXRF analysis data.