The Present and Future Prospect of Artificial Intelligence in Mining Industry

* S.K. Singh
** Gopal Singh
* Head, Deptt. of Mining Engineering, BCP Bilaspur
** Asst. Prof., Deptt. of Mining Engineering, MATS University Raipur

Abstract: The mining operation uses traditional and conventional techniques to extract
minerals. Besides extracting minerals some other auxiliary operations are expedient to have
safe and economical process. Presently some mechanical and electronics equipments have been
used in this regard. Some softwares have also been developed to serve the purpose. But these
are not sufficient to meet the requirements of day by day changing scenario of introduction of
newer and advanced technology. To keep up with the new technology modernization and the
profit in shake of investors and stakeholders and importantly for the nation, and to ensure health
and safety mining industry needs to approve new-age autonomous technologies and intelligent
system in their field. Integration of Artificial Intelligence, Machine Learning, Internet of
Things (IoT) and Automation are the keys to the 4th revolution in mining industry. In this way
Artificial Intelligence can replace these technologies as the former is the simulation of human
intelligence processes by machines, especially computer systems. The present paer focuses on
the present and future of AI in mining industries. AI systems work by ingesting large amounts
of labelled training data, analyzing the data for correlations and patterns, and using these
patterns to make predictions about future states. The present era is of AI which can have wider
applicability in the various auxiliary operations associated with mining work. Owing to its
performance better than human beings its future prospect will be of better importance.

Keywords: Artificial Intelligence, Deep Learning, IoT in Mining, Machine Learning, Mining
Automation, Mining Industry

Introduction: Mining is considered as one of most required industries in 21st century as it is

the supplier of raw materials to other industries. Mining operations involve extraction of ores
and minerals of various kinds from the earth, which cannot be produced in laboratory or by
cultivation. Although being one of the most profitable sector mining industries is one of the
riskiest investments because of dangers associated with operations particularly at deeper
underground mines. Mining industries are continuously facing issues related to capitals,
infrastructure, health and safety and most importantly environmental and geological
consequences. Mining provides employment opportunities and performs a lead role of a
country’s economic development with systemic governance. In general, there are four basic
methods of mining:
(i) Surface Mining for shallow depth ore bodies, (ii) Underground mining for deep or deposits,
(iii) placer mining for extract valuable metals from sediments of beach or river beds, (iv) In-
situ mining, the method of recovering minerals from earth without extracting the mix of rocks
and ore to the surface for processing.
Artificial intelligence is the science of making machines that can think like humans. It can do
things that are considered "smart." AI technology can process large amounts of data in ways,
unlike humans. The goal for AI is to be able to do things such as recognize patterns, make
decisions, and judge like humans.
Artificial intelligence systems work by using any number of AI techniques.
Machine Learning: A machine learning (ML) algorithm is fed data by a computer and uses
statistical techniques to help it “learn” how to get progressively better at a task, without
necessarily having been programmed for that certain task. It uses historical data as input to
predict new output values.
Deep Learning: Deep learning is a type of machine learning that runs inputs through a
biologically inspired neural network architecture. The neural networks contain a number of
hidden layers through which the data is processed, allowing the machine to go “deep” in its
learning, making connections and weighting input for the best results.
Neural Networks: Neural networks are a series of algorithms and a subset of machine
learning that process data by mimicking the structure of the human brain. Each neural
network is composed of a group of attached neuron models, or nodes, which pass information
between each other.
Natural Language Processing: Natural language processing (NLP) is an area of artificial
intelligence concerned with giving machines the ability to interpret written and spoken
language in a similar manner as humans. NLP combines computer science, linguistics,
machine learning and deep learning concepts to help computers analyse unstructured text or
voice data and extract relevant information from it.
Computer Vision: Computer vision is a field of artificial intelligence in which machines
process raw images, videos and visual media, taking useful insights from them. Then deep
learning and convolutional neural networks are used to break down images into pixels and tag
them accordingly, which helps computers discern the difference between visual shapes and
patterns. Computer vision is used for image recognition, image classification and object
detection, and completes tasks like facial recognition and detection in self-driving cars.
Reasons for Adoptability of AI in Mining Industries and Operations:
In brief expected reasons to adopt AI are:
1. AI provides fast and accurate on-site decisions reducing the errors.
2. Using AI ensures consistent and radially efficient method for making accu-rate and quick
assessment of potential risks.
3. AI should manage and process large amount of data (big data) with speed, accuracy and
efficiency.
4. Boosting efficiency by increasing consistency and quality work that typically is subject to
human error.
5. Ensures improved health and safety measures.
6. Increased resource throughput.
7. In long run of efficient use, it can reduce the operation cost.
8. Better utilize the equipment, machines and vehicles.
9. Accelerating the shift to be more “process and continuity rather than people-oriented”.
10. Operation timing and product quality enhanced.
11. Reduce energy demand with increasing efficiency of whole operation.
12. Using neural network, the machine or software could learn the characteristics that the
operator is looking for.
13. AI enhanced automated system using integrated process control assists with significant
energy cost and production cost reduction.
AI and Automation in Mining:
• Open Pit Fleet Management System
Increase Haulage Efficiency using Intelligent Dispatch:
An intelligent Dispatch System allows mine Dispatchers to improve routing and run their
mine on auto-pilot. Advanced AI based algorithms use real time loading and haulage
performance data at each loading point to dynamically allocate Haul Trucks to Shovel/Front
Wheel Loaders so mines can:
Maximize tons hauled every shift
Minimize wait times at loading units
Decrease traffic congestion
Increase haulage efficiency
This results in a dramatic reduction of shovel and haul truck queuing time and increase in
Productivity and Overall Equipment Effectiveness.
GPS and Telematics based Automated Trip Cycle Analysis
Increase Situational Awareness and Operator Safety
Proximity Detection and Collision Avoidance
Streamline shift changes, re-fuelling and breaks
Manage Stockpiles
• Automated Drillers and Intelligent Drilling Systems:
Drilling and blasting are the two fundamental operations of every mining project. Holes are
drilled into any rock or hard surface to fill them with explosives. Blasting the explosives induce
cracks in inner geology of the hard surface or rock. Typically, a drill cycle involves tramming
hole, levelling jacks, drilling holes, cleaning and repeating the process. Instead of doing it all
manually, in the automated process the automated drill moves hole to hole following the pre-
fitted location coordinates (determined through GPS receivers or based upon any other spotting
technique). Sensors might help the machine to predict the environment and the rock type. The
whole orientation is also pre-programmed by facilitator.
Drones: Drones with highly efficient cameras could provide real time aerial footage and 3D
maps of the site. These data could be used to instantly estimate cumulative measurements, real-
time tracking and safe-guarding of equipments and employees’ locations and tracking safety-
environmental observances. Deploying drones not only ensures less cost for surveying but also
great accuracy and detailed survey. Using data from the drones selecting areas for stockpiling
and selecting potential exploration corridors are easy to determine.
• Inspecting Robots:
Remote-control, semi-automated or automated robots is likely to be used in various
application on a mining site. Underground mines have high roof fall or poisonous or
flammable gas related risks. Robots may be engaged into dangerous tasks rather than humans
on field or underground. Robot also could assist miners by adding light, vision, auditory and
vibration or gases sensing capabilities.
• Safety and Accident Analysis:
Mining is a risky and hazardous job. Monitoring the environment and other param-eters is a
proven way to analysis the accidents and ensure safety, but using AI, prediction of accidents
and safety factors would be easy and accurate.
• Environment Monitoring
Using IoT (Internet of Things) and AI, mine environment can be monitored in details. [21-24]
The whole system can check the environmental factors using IoT sensors, report after
computing the risk using A.I. algorithms and alert in form of alarm with LEDs and alarms in
case of emergency. Automatically underground environment fac-tors like different gas levels,
smoke, temperature, humidity, light, pressure, dust con-centration etc. Mines, especially
underground mines have many types of gases which could be poisonous for human beings and
could be flammable and dangerous. Naturally at first the gases (CH4, NO2, CO2, SO2, NH3,
smoke etc.), present at the mine might be measured using IoT sensors.
• Predict Dust Concentration:
Open cast or open pit mines cause a massive amount of dust and particulate matter emission in
open environment. Even in underground mines dust concentration level monitoring and
maintaining is an important challenge. ANN type complex intelligent systems can be designed
to predict dust particles [26] including particulate matters of different diameters concentration
near mine location using meteorological parameters (rainfall, temperature, wind speed, cloud
cover, dispersion factor etc.), geographical parameters (distance of receptor from the source
with respect to air directions) and emission rate (drilling, loading, conveying, hauling,
transporting, unloading etc.).
• Personal Tracking and Monitoring:
Miners’ job is undoubtedly risky. Tracking their positions and conditions around them is live
saving in practical cases. It would help to warn and take important steps quickly against any
type of possible risk on any worker.
• Roof Support Monitoring
Roof fall is the leading cause of coal miner injuries [30]. Analysing the data received from roof
support system of the mine using IoT sensors could be the key to predict hazards like roof fall,
water inrush, and release of hazardous gases from the walls etc. For developing a full working
roof support monitoring and hazard prediction the following type of data need to be collected:
[31]
1. Load on the legs (horizontal downward load)
2. Convergence of the sidewalls
3. Humidity (to predict water inrush)
4. Temperature
5. Gas Detection
Collecting these data using various sensors and equipments and using these data on pre-trained
ANN or machine learning network upcoming hazards could be detected. ML can easily predict
the roof support risk and requirements using experience from past data.
• Rock burst Prediction:
For high-stress mines rock burst is a severe disaster. Spontaneous and violent failure of rock
structure in high-stress mines is known as rock burst. Traditional rock burst techniques are
long-term predictions and short-term predictions.
During the project designing stage long term rock burst prediction is used to predict the risks
to operate on the specific site. Common machine learning and deep learning methods [35] that
show highest accuracy, are artificial neural network (ANN), distance discriminant analysis
(DDA), support vector machine (SVM), Bays discriminant analysis (BDA), Fisher linear
discriminant analysis (LDA) etc.
• Slope Stability Analysis:
Stability of mine dumps or stockpiles or open pit slopes is an important parameter of safety
and efficient working. To foresee accidents due to slope stability imbalance, modern miners
need to use machine learning approaches for achieving reliable and objective evaluation with
great accuracy. Proposed models of analysing slope stability depend upon discrete and
continuous functions and variables. Some tested [36] machine learning models are support
vector machine (SVM), FCM, K-means etc.
• Flyrock analysis and Blasting Pattern Analysis:
The most hazardous event as the consequence of blasting operations is flyrock. Imperfection
of blasting pattern design, blasting material or stemming are main reason of fly-rock, that could
endanger lives and equipments on site. Flyrock analysis is complex and uncertain. Various
parameters and unknown relations cause large inaccuracy in empirical models of flyrock
analysis. But some of the proposed and tested machine learning models already show high
accuracy to flyrock events [37-41]. As a result of improper blasting pattern undesirable
phenomena such as flyrock, poor fragmentation, back break, ground vibration etc. take place.
So, recognising right blast pattern is an important job for a mining engineer. ANN for
forecasting the peak-particle velocity for the blast-induced ground vibrations is studied by [42-
44].
 • Subsidence Risk Analysis:
Gradual downward shifting or sudden sinking of ground surface is termed as subsidence.
Construction of mines face many geo-mechanical uncertain challenges when it starts
production. Subsidence risk is one of them. Rock mass structure, rock energy density, rock
mass drainage, nearby aquifers etc. consider to be responsible factors for subsidence
construction in proposed machine learning models. Some tested machine learning models for
subsidence risk analysis include failure model and effect analysis (FMEA), fuzzy inference
system (FIS), ANNs, multilayer perceptron network (MLP). [48, 49]
• Ventilation:
Mine ventilation system consumes the most amount of energy in case of under-ground mines.
Ventilating system must work with highest capacity and efficiency, so the maintenance of
ventilation equipments also cost lots of capital.
AI enhanced smart ventilation system would have:
1. Smartly automated control airflow according to the workflow of the mine.
2. Air flow could be customized according to the need.
3. Associated environmental monitoring system would be a perk.
4. Fail-safe architecture to ensure ventilation in emergency.
5. Blast gas clearing facility associated with ventilation would make the opera-tion safer.
6. Must have an open architecture for easy and quick installing and repairing.
Smart ventilation system would help to (i) save energy cost and capital investment, (ii) make
smaller environmental and carbon footprint, (iii) ensures health and safety.
For example, Shyft Inc.9 have made an AI enhanced automated adjustable ventilation system
for mines with integrated process control assist, open architecture, fail-safe system and
environmental monitoring system.
Challenges to Implement AI in Mining Industry and Beyond:
Although application of AI and autonomous technologies in mining is almost decades old
(started with autonomous trucks), the pace of implementing is painfully sluggish. [101]
1. Implementing AI and autonomous system requires huge initial capital.
2. AI or autonomous technologies do not guarantee instant return for stakeholders.
3. Traditional mining industry has inadequate infrastructure.
4. In fear of losing jobs former workers and supervisors may resist the pace.
5. Industry culture is also resisting the pace as mining corporates still don’t sure about the
systemized approach to implement AI or automation in industry.
6. Even the AI researchers are not certain about the impact of AI on jobs, eco-nomics,
working relations, social system and societal makeup.
7. There is risk and uncertainty about unknown behaviours of AI and autono-mous systems.
8. It is still not clear about how AI could take group decisions on its own.
9. Functions of most of the AI or automated devices are too complex and need high
professional effort to implement.
10. For a well automated mine large number of connected devices will generate large amount
of data which will make computing and validating complexities for com-puters.
11. Many times getting regulatory approval is a serious issue.
12. For AI or automated mining industry lots of miners with traditional and ad-vanced tech-
skills are required.
13. Often poor testing data and methods are used for generating insights which lead to noise
and over-fitted models.
14. Most AI based technologies are considered as lab-based (not ready for mar-ket). So,
implementing them is considered risky for the industry.
15. Declining availability of high-grade ores and mineral resources impending large
investment is discouraging.
16. As mining industry is considered as a risky undertaking with investment volatility,
uncertain grades and variable mineral or ore prices, the industry always preferred proven
methods of operation to cut down the risk factor.
For correct implementation of AI in mining, industry needs to follow a series of well-defined
steps in designing new technologies and implementing them.
Conclusion:
According to the World Economic Forum the calculated investment on digital initiative would
be $420 billion in the next decade. Artificial intelligence is also going to save a lot of cash flow
and lives in the coming years in mining. “Mining is not everything but without mining
everything in nothing” (Max Planck). Mining sector plays a very important role in economic
development (neglecting the resource-curse hypothesis concept, which pretty much depend
upon the governance). So, with right governance and expect planning artificial intelligence is
undoubtedly going to be one of the keys to unlock the full potential of mineral extraction and
to ensure safety of workers. But the introduction of AI in mining sector may lead to
unemployment in the country like India where vast population resides because of loss of job in
mine working. So, a balance must be struct between human work and automated work in
mining industry to serve a better environment. The future may be a place of conflict as large
number of workers can lose their job. The mine planners will have to take reasonable steps to
avoid such type of unwanted situations.
References
1. Kurzweil, R.: The Law of Accelerating Returns. Kurzweil Accelerating In-telligence
(2001) https://doi.org/10.1007/978-3-662-05642-4_16
2. Wang, W., and Siau, K. (2019) Artificial Intelligence, Machine Learning, Automation,
Robotics, Future of Work, and Future of Humanity – A Review and Research Agenda. Journal
of Database Management, 30(1), 61–79.. doi:10.4018/JDM.2019010104
3. Press Release: (2014) Rio Tinto improves productivity through the world's largest fleet of
owned and operated autonomous trucks http://www.ri-otinto.com/media/media-releases-
237_10603.aspx Accessed 5th May 2020
4. Ali, S., Saiied, M.A., Mohammad, M.A., Mehmet, S.K.: (2016) Develop-ment of a multi-
layer perceptron artificial neural network model to determine haul trucks energy
consumption. International Journal of Mining Science and Technology, Volume 26, Issue 2,
Pages 285-293, ISSN 2095-2686 https://doi.org/10.1016/j.ijmst.2015.12.015
5. Caterpillar: (2017) Cat® command for hauling. https://www.cat.com/en_US/by-
industry/mining/surface-mining/surface-technology/command/command-for-hauling.html
Accessed 5th May 2020
6. Dyson, N.: (2017) BHP to double autonomous trucks at Jimblebar. Mining Magazine
https://www.miningmagazine.com/innovation/news/1331400/bhp-to-double-autonomous-
trucks-at-jimblebar
7. Press Release: (2014) Rio Tinto improves productivity through the world's largest fleet of
owned and operated autonomous trucks http://www.ri-otinto.com/media/media-releases-
237_10603.aspx Accessed 5th May 2020
8. Corporate Press Releases (Atlas Copco): (2016) Atlas Copco wins order for autonomous
mining in Australia. https://www.atlascopcogroup.com/en/me-dia/corporate-press-
releases/2016/20160620-order Accessed 5th May 2020
9. Crazier, R.: (2016) BHP Billiton hits go on autonomous drills
https://www.itnews.com.au/news/bhp-billiton-hits-go-on-autonomous-drills-421008 Accessed
5th May 2020
10. Hashmi K, Graham ID, Mills B (2000) Fuzzy logic based data selection for the drilling
process. J Mater Process Technol 108:55–61
11. Pendokhare DG, Quazi TZ (2012) Fuzzy Logic Based Drilling Control Pro-cess. Int J Sci
Eng Res 5:61–65
12. Ahamed NU, Yusof Z, Hamedon Z, Rabbi MF, Sikandar T, Palaniappan R, Ali MA,
Rahman SM, Sundaraj K (2016) Fuzzy logic controller design for intelligent drilling system.
In: 2016 IEEE international conference on auto-matic control and intelligent systems
(I2CACIS). IEEE, pp 208–213
13. Jang H, Topal E (2013) Optimizing overbreak prediction based on geological parameters
comparing multiple regression analysis and artificial neural net-work. Tunn Undergr Sp
Technol 38:161–169
14. Elkatatny S, Tariq Z, Mahmoud M (2016) Real time prediction of drilling fluid
rheological properties using Artificial Neural Networks visible mathe-matical model (white
box). J Pet Sci Eng 146:1202–1210
15. Lashari SZ, Takbiri-Borujeni A, Fathi E, Sun T, Rahmani R, Khazaeli M (2019) Drilling
performance monitoring and optimization: a data-driven ap-proach. J Pet Explor Prod
Technol 9:2747–2756
16. Ralston, J.C., Hargrave, O.C., Dunn, M.T.: (2017) Longwall automation: trends,
challenges and opportunities. International Journal of Mining Science and Technology
https://doi.org/10.1016/j.ijmst.2017.07.027
17. Prospects (BHP): (2017) How drones are changing mining. https://www.bhp.com/media-
and-insights/prospects/2017/04/how-drones-are-changing-mining/ Accessed 5th May 2020
18. Press release (thyssenkrupp): (2019) thyssenkrupp Industrial Solutions (Australia) are on
track to deliver the world’s largest rail mounted stackers and reclaimer on sched-ule for
BHP’s South Flank Project. https://www.thyssenkrupp.com/en/news-room/press-
releases/thyssenkrupp-industrial-solutions--australia--are-on-track-to-deliver-the-world-s-
largest-rail-mounted-stackers-and-reclaimer-on-schedule-for-bhp-s-south-flank-project--
18048.html Accessed 5th May 2020
19. Prospects (BHP): (2017)” Which technologies will boost mining safety and
productivity?” https://www.bhp.com/media-and-insights/pro-spects/2017/11/which-
technologies-will-boost-mining-safety-and-productiv-ity/ Accessed 5th May 2020
20. Iphar M, Cukurluoz AK (2018) Fuzzy risk assessment for mechanized un-derground coal
mines in Turkey. Int J Occup Saf Erg. https ://doi.org/10.1080/10803 548.2018.14268 04
21. Jo, B.W., Khan, R.M.A.: (2018) An Internet of Things System for Under-ground Mine Air
Quality Pollutant Prediction Based on Azure Machine Learning. Sensors DOI:
10.3390/s18040930
22. Reddy GP, Lakshmi MV: (2015) IoT in Mines for Safety and Efficient Monitoring.
International Journal of Advanced Research in Computer Engi-neering & Technology
(IJARCET) http://ijarcet.org/wp-content/up-loads/IJARCET-VOL-4-ISSUE-11-4232-
4236.pdf
23. Jo, B.W., Khan, R.M.A.: (2017) An Event Reporting and Early-Warning Safety System
Based on the Internet of Things for Underground Coal Mines: A Case Study. Applied
Sciences; https://www.mdpi.com/2076-3417/7/9/925/pdf
24. Gopal BVSP, Akash P, Sri PSGA: (2019) Design Of Iot Based Coal Mine Safety System
Using Nodemcu. International Journal of Innovative Technol-ogy and Exploring Engineering
(IJITEE) https://www.ijitee.org/wp-con-tent/uploads/papers/v8i6/F3812048619.pdf
25. News: (2019) IBM Helps Organizations Monitor Workers’ Safety with Wat-son IoT.
Construction Superintendent. https://consupt.com/2019/02/ibm-helps-organizations-monitor-
workers-safety-with-watson-iot/ Accessed 5th May 2020
26. Lal B, Tripathy, S.: (April 2012) Prediction of dust concentration in open cast coal mine
using artificial neural network. Atmospheric Pollution Re-search; DOI:
10.5094/APR.2012.023
27. Jo BW, Khan RMA: (2017) An Event Reporting and Early-Warning Safety System Based
on the Internet of Things for Underground Coal Mines: A Case Study. Applied Sciences;
https://www.mdpi.com/2076-3417/7/9/925/pdf
28. Hua J, Shen Z, Zhong S: (2015) We Can Track You If You Take the Metro: Tracking
Metro Riders Using Accelerometers on Smartphones. https://arxiv.org/abs/1505.05958
29. Sapiezynski, P., Stopczynski, A., Gatej, R., Lehmann, S.:(May 2015) Track-ing Human
Mobility using WiFi signals https://arxiv.org/abs/1505.06311
30. MSHA: (2017) Roof fall accidents decline, but remain leading cause of coal miner
injuries. (17-949-NAT). Arlington, VA: Mine Safety and Health Ad-ministration (MSHA).
31. Singh, A., Singh, U.K., Kumar, D.: (2018) IoT in Mining for Sensing, Moni-toring and
Prediction of Underground Mines Roof Support https://www.slideshare.net/iankits/iot-in-
mining-for-sensing-monitoring-and-prediction-of-underground-mines-roof-support
32. Vale (2018) Artificial Intelligence is expected to save $ 26 million for Vale in 2018.
http://saladeimprensa.vale.com/en/Paginas/Articles.aspx?r=Artifi-cial_Intelligence_is_ex-
pected_to_save_US26_million_for_Vale_in_2018&s=Innovation__Technology&rID=1063&
sID=4 Accessed 5th May 2020
33. Kimberley, M.: (2017) Deep Learning AI Pinpoints Mechanical Breakdowns by Listening
to Machines. https://thenewstack.io/deep-learning-ai-pinpoints-mechanical-breakdowns-
listening-machines/
34. Barbaschow, A.: (2018) Rio Tinto preparing for the Mine of the Future with automation.
https://www.zdnet.com/google-amp/article/rio-tinto-preparing-for-the-mine-of-the-future-
with-automation/ Accessed 5th May 2020
35. Yuanyuan, P., Apel, D.B., Liu, V., Mitri, H.: (2019) Machine learning meth-ods for
rockburst prediction-state-of-the-art review. International Journal of Mining Science and
Technology, 2019, ISSN 2095-2686 https://doi.org/10.1016/j.ijmst.2019.06.009
36. Zakaria, J.: (2016) Development of slope mass rating system using K-means and fuzzy c-
means clustering algorithms. International Journal of Mining Science and Technology,
Volume 26, Issue 6, 2016, Pages 959-966, ISSN 2095-2686
https://doi.org/10.1016/j.ijmst.2016.09.004
37. Khandelwal, M., Monjezi, M.: (2013) Prediction of flyrock in open pit blast-ing operation
using machine learning method. International Journal of Min-ing Science and Technology,
Volume 23, Issue 3, 2013, Pages 313-316, ISSN 2095-2686
https://doi.org/10.1016/j.ijmst.2013.05.005.
38. Bahrami A, Monjezi M, Goshtasbi K, Ghazvinian A (2011) Prediction of rock
fragmentation due to blasting using artificial neural network. Eng Com-put 27:177–181
39. Sayadi A, Monjezi M, Talebi N, Khandelwal M (2013) A comparative study on the
application of various artificial neural networks to simultaneous pre-diction of rock
fragmentation and backbreak. J Rock Mech Geotech Eng 5:318–324
40. Ebrahimi E, Monjezi M, Khalesi MR, Armaghani DJ (2016) Prediction and optimization
of back-break and rock fragmentation using an artificial neural network and a bee colony
algorithm. Bull Eng Geol Environ 75:27–36
41. Tiile RN (2018) Artificial neural network approach to predict blast-induced ground
vibration, airblast and rock fragmentation vibration, airblast and rock fragmentation. Missouri
University of Science and Technology
42. Zhongya Z, Xiaoguang J (2018) Prediction of peak velocity of blasting vi-bration based
on artificial neural network optimized by dimensionality re-duction of FA-MIV. In:
Mathematical Problems in Engineering.
43. Khandelwal M, Singh TN (2009) Prediction of blast-induced ground vibra-tion using
artificial neural network. Int J Rock Mech Min Sci 46:1214–1222
44. Khandelwal M, Kumar DL, Yellishetty M (2011) Application of soft compu-ting to
predict blast-induced ground vibration. Eng Comput 27:117–125
45. Yari, M., Monjezi, M. & Bagherpour, R: (2013) Selecting the most suitable blasting
pattern using AHP-TOPSIS method: Sungun copper mine. J Min Sci 49, 967–975
https://doi.org/10.1134/S1062739149060178
46. Zhou, J., Li, X., Mitri, H.S., Wang, S., Wei, W.: (2015) Identification of large-scale goaf
instability in underground mine using particle swarm opti-mization and support vector
machine. International Journal of Mining Sci-ence and Technology, Volume 23, Issue 5, 2013,
Pages 701-707, ISSN 2095-2686 https://doi.org/10.1016/j.ijmst.2013.08.014.
47. Shi, L., Qiu, M., Wei, W., Xu, D., Han, J.: (2014) Water inrush evaluation of coal seam
floor by integrating the water inrush coefficient and the infor-mation of water abundance.
International Journal of Mining Science and Technology, Volume 24, Issue 5, 2014, Pages
677-681, ISSN 2095-2686 https://doi.org/10.1016/j.ijmst.2014.03.028.
48. Hejmanowski, R., Witkowski, W.T: (2015) Suitability assessment of artifi-cial neural
network to approximate surface subsidence due to rock mass drainage. Journal of Sustainable
Mining,Volume 14, Issue 2,2015,Pages 101-107 https://doi.org/10.1016/j.jsm.2015.08.014
49. Rafie. M., Namin, F.S.: Prediction of subsidence risk by FMEA using artificial neural
network and fuzzy inference system. International Journal of Mining Science and
Technology, Volume 25, Issue 4, 2015, Pages 655-663, ISSN 2095-2686 (2015)
https://doi.org/10.1016/j.ijmst.2015.05.021.
50. Mel’nikov, N.N., Kalashnik, A.I., Kalashnik, N.A. et al (2018) Integrated Multi-Level
Geomonitoring of Natural-and-Technical Objects in the Mining Industry. J Min Sci 54, 535–
540 https://doi.org/10.1134/S1062739118043977
51. Hainsworth DW (1996) Dragline Automation. In: Australian coal association research
program project report, (C3007)
52. Dalal N, Triggs B (2005) Histograms of oriented gradients for human detec-tion. In: 2005
IEEE computer society conference on computer vision and pattern recognition (CVPR’05)
2005. IEEE, vol-1, pp 886–893
53. Azar RE, Dickinson S, McCabe B (2012) Server-customer interaction tracker: computer
vision–based system to estimate dirt-loading cycles. J Constr Eng Manag 139:785–794
54. Memarzadeh M, Golparvar-Fard M, Nieblesc JC (2013) Automated 2D de-tection of
construction equipment and workers from site video streams using histograms of oriented
gradients and colors. Autom Constr 32:24–37
55. Golparvar-Fard M, Heydarian A, Niebles JC (2013) Vision-based action recognition of
earthmoving equipment using spatio-temporal features and support vector machine
classifiers. Adv Eng Inform 27:652–663