Classification of Gold-Bearing Particles Using Visual Cues and Cost-Sensitive Machine Learning

Horrocks, Tom; Wedge, Daniel; Holden, Eun‐Jung; Kovesi, Peter; Clarke, Nick; Vann, John

doi:10.1007/s11004-015-9597-7

Cited by 11 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in medical diagnosis, misclassifying a malignant tumor biopsy sample as benign is more severe than misclassifying a benign sample as malignant (Mazurowski et al, 2008, Park et al, 2011, Moon et al, 2012; in email spam detection, removing a non-spam email leads to more severe consequences than missing a spam email (Carreras andMarquez, 2001, Zhou et al, 2014); in political conflict prediction, missing a conflict has more critical consequences than vice versa (Beck et al, 2000, Cederman andWeidmann, 2017). In addition to these examples, asymmetric binary classification problems exist in geologic studies (Horrocks et al, 2015, Fernández-Gómez et al, 2017, fraud detection (Sahin et al, 2013, Bahnsen et al, 2013, and other medical diagnosis and prognosis problems (Artan et al, 2010, Ali et al, 2016.…”

Section: Introductionmentioning

confidence: 99%

Bridging Cost-sensitive and Neyman-Pearson Paradigms for Asymmetric Binary Classification

Li,

Tong,

2020

Preprint

View full text Add to dashboard Cite

Asymmetric binary classification problems, in which the type I and II errors have unequal severity, are ubiquitous in real-world applications. To handle such asymmetry, researchers have developed the cost-sensitive and Neyman-Pearson paradigms for training classifiers to control the more severe type of classification error, say the type I error. The cost-sensitive paradigm is widely used and has straightforward implementations that do not require sample splitting; however, it demands an explicit specification of the costs of the type I and II errors, and an open question is what specification can guarantee a high-probability control on the population type I error. In contrast, the Neyman-Pearson paradigm can train classifiers to achieve a high-probability control of the population type I error, but it relies on sample splitting that reduces the effective training sample size. Since the two paradigms have complementary strengths, it is reasonable to combine their strengths for classifier construction. In this work, we for the first time study the methodological connections between the two paradigms, and we develop the TUBE-CS algorithm to bridge the two paradigms from the perspective of controlling the population type I error.

show abstract

Section: Introductionmentioning

confidence: 99%

Bridging Cost-sensitive and Neyman-Pearson Paradigms for Asymmetric Binary Classification

Li,

Tong,

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Due to decreased sensor and storage cost and increase standardization and ease of use, more and more data are collected about the operation of industrial processes. In mining, in particular, information concerning the properties of material as it flows through the mining complex can be collected using near-infrared reflectance spectroscopy (Goetz et al 2009) or camera images (Chatterjee 2013;Horrocks et al 2015) in addition to the more traditional blasthole and in-fill drilling analysis. Material can also be better located thanks to the use of GPS devices on hauling equipment or RFID tags embedded in the material (La Rosa et al 2007).…”

Section: Introductionmentioning

confidence: 99%

“…2009) or camera images (Chatterjee 2013; Horrocks et al. 2015) in addition to the more traditional blasthole and in-fill drilling analysis. Material can also be better located thanks to the use of GPS devices on hauling equipment or RFID tags embedded in the material (La Rosa et al.…”

Section: Introductionmentioning

confidence: 99%

Responding to new information in a mining complex: fast mechanisms using machine learning

Păduraru

Dimitrakopoulos

2019

Mining Technology

View full text Add to dashboard Cite

As more and more data about mining complex operations are collected and stored, it becomes increasingly important for computer systems to help human operators make better, more informed decisions. This can be done indirectly, through improved visualization or prediction, or directly by suggesting decisions that respond to new information. This paper contributes to the direct approach by showing how state-of-the-art data-driven decision making can be used for optimizing material flows in a large mining complex. To this end, a combination of neural networks and policy gradient reinforcement learning is used for computing material destination decisions that automatically respond to new information. Results using a computational model of a large copper mining complex show that the proposed method significantly outperforms an optimized cut-off grade policy similar to the one currently used at the mine.

show abstract

“…Near-infrared reflectance spectroscopy placed on conveyor belts has been shown to provide accurate measurements of mineral concentration and other properties (Goetz et al 2009). Camera images can also be used for inferring various mineral properties using machine learning methods (Chatterjee 2013; Horrocks et al 2015). Fleet location data is increasingly collected thanks to the widespread use of GPS devices.…”

Section: Introductionmentioning

confidence: 99%

Adaptive policies for short-term material flow optimization in a mining complex

Păduraru

Dimitrakopoulos

2017

Mining Technology

View full text Add to dashboard Cite

With the advent of inexpensive sensors and digital storage, increasing amounts of data about a mining complex can be collected. This data can, in turn, be used to continuously adapt stochastic optimization models and short-term mining decision making, thus reducing and managing local uncertainty. Taking advantage of this uncertainty reduction requires new decisionmaking approaches, mechanisms, and optimization methods. This paper proposes the use of state-dependent policies, which encode recipes for responding to new information as it comes along. Focusing on short-term planning shows how to represent and optimize state-dependent policies for making adaptive destination decisions for materials mined and processed. Resulting policies can be applied across different short-term time scales, marking an important step towards simultaneously optimizing different time scales. An implementation of the proposed method at a copper-gold deposit shows that it can improve the utilization of processing streams, production and financial performance over simple heuristic approaches and practices.

show abstract

Classification of Gold-Bearing Particles Using Visual Cues and Cost-Sensitive Machine Learning

Cited by 11 publications

References 24 publications

Bridging Cost-sensitive and Neyman-Pearson Paradigms for Asymmetric Binary Classification

Bridging Cost-sensitive and Neyman-Pearson Paradigms for Asymmetric Binary Classification

Responding to new information in a mining complex: fast mechanisms using machine learning

Adaptive policies for short-term material flow optimization in a mining complex

Contact Info

Product

Resources

About