Monte Carlo Analytic Hierarchy Process (MAHP) approach to selection of optimum mining method

One of the most critical and complicated steps in mine design is a selection of suitable mining method based upon geological,geotechnical,geographical,safety and economical parameters.The aim of this study is developing a Monte Carlo simulation to selection the optimum mining method by using effective and major criteria and at the same time,taking subjective judgments of decision makers into consideration.Proposed approach is based on the combination of Monte Carlo simulation with conventional Analytic Hierarchy Process(AHP).Monte Carlo simulation is used to determine the confdence level of each alternative’s score,is calculated by AHP,with the respect to the variance of decision makers’opinion.The proposed method is applied for Jajarm Bauxite Mine in Iran and eventually the most appropriate mining methods for this mine are ranked.

Research on the Permeability Characteristics of Granite with Different Weathering Degrees before and after the Influence of Mining Method Construction

The influence of mining method tunnel construction on the groundwater environment is a very important and complex engineering environment problem, and the strong differential weathering of water-rich granite strata increases the difficulty of this problem. In this paper, the mineral composition and microstructure characteristics of granite with different weathering degrees before and after the influence of mining method were studied by in-situ and indoor seepage tests and theoretical calculation, and the impact of mining method tunneling on granite permeability was also analyzed. Calculation results revealed that the permeability coefficient of surrounding rock at 1.1 m away from excavation face increased 41.6 times as much as the original. The permeability coefficient of moderately and strongly weathered granite increased by 6.12 and 3.33 times, respectively and the permeability also increased. The variation of the permeability coefficient of fully weathered granite was the smallest, increasing by 1.67 times, which is due to mechanical excavation of a fully weathered layer on-site, and the disturbance was far less than that caused by blasting. The scale of the excavation damaged zone (EDZ) induced by mining method was determined by wave velocity test, which provides a basis for subsequent seepage field calculation and research.

Numerical Simulation of the Influence of Tunnel Construction by Mining Method on the Seepage Field in Weathered Granite Stratum

In actual space, considering the heterogeneity and anisotropy of rock and soil, the difference of hydrogeological conditions and the influence of tunnel excavation, tunnel seepage problem is a very complex three-dimensional seepage problem, which is very difficult to solve. The equivalent continuum model is one of the most commonly simplified models used in solving tunnel seepage problems. In this paper, the finite element software ABAQUS and the research results are used to establish a seepage numerical calculation model, study the influence of mining method construction on the seepage field in weathered granite, and clarify the influence of each stage of mining method construction on the groundwater environment. On this basis, the sensitivity of the seepage field to various factors such as natural environment, engineering geology and hydrogeology, tunnel construction and so on is analyzed, which provides a basis to establish the evaluation system of groundwater environment negative effect in weathered granite stratum by mining method tunnel construction.

Tacit Knowledge Mining:The Key Traditional Chinese Medical Inheritance

Traditional Chinese medicine(TCM)is a treasure of traditional Chinese culture and a gift to the world.TCM tacit knowledge refers to the knowledge and experiences formed in the process of learning and practice of TCM.The objective of this study is to discuss the importance of TCM tacit knowledge in the inheritance and education of TCM.As the essence of the TCM,TCM tacit knowledge has the characteristics of massive,complicated,relativistic,highly individualized,constantly innovative,the dependence of cultural background and the regional environment,as well as difficult to explicate.It exists in every aspect of the TCM theory and the process of dialectical treatment.Besides the traditional master‑apprentice,family‑based,school‑based,and inheritance and education methods,together with the inheritance based on the books,images,and network platforms,in the process of TCM modernization,a variety of modern theoretical models and computing techniques have also been used in the mining of the TCM tacit knowledge.In this study,we introduced the usage of SECI model,complexity adaptive system,latent variable model,and some of the data mining technologies in the TCM tacit knowledge mining.An accurate and efficient inheritance of TCM tacit knowledge is the key to maintain the vitality and innovative development of TCM.Under the reasonable application and combination of the traditional education methods,modern mining methods,and further the artificial intelligence,the explicit and inheritance of TCM tacit knowledge will get tremendous development,and it could extremely improve the efficiency and accuracy of the TCM inheritance and the TCM modernization.

Text Mining Analysis of Efficiency of the Continuously Implemented Gathering Type Action Plan for Male Elderly People Obtained

Aim: To clarify transformation of the participants’ consciousness for rebuilding the community and its factors from the discussion contents by actions for male elderly people in Town A in Fukushima prefecture. Design: This study was an action research. Method: The author verbalized discussion contents of the action conducted in 2018-2019 and analyzed them for each year by the text mining method. Results: The word appearance frequency was high in the order of “Person” and “Town A” in both years. One large word network was formed in 2018 and its topic was about what the participants feel in their life in Town A. Two large word networks were formed in 2019 and their topic was about the community participation including difficulty in motivating others such as how people who do not participate can feel like joining it.

Comparative evaluation of data mining methods in predicting the water vapor permeability of cement-based materials

Water vapor permeability of building materials is a crucial parameter for analysing and optimizing the hygrothermal performance of building envelopes and built environments.Its measurement is accurate but time-consuming,while data mining methods have the potential to predict water vapor permeability efficiently.In this study,six data mining methods—support vector regression(SVR),decision tree regression(DT),random forest regression(RF),K-nearest neighbor(KNN),multi-layer perceptron(MLP),and adaptive boosting regression(AdaBoost)—were compared to predict the water vapor permeability of cement-based materials.A total of 143 datasets of material properties were collected to build prediction models,and five materials were experimentally determined for model validation.The results show that RF has excellent generalization,stability,and precision.AdaBoost has great generalization and precision,only slightly inferior to the former,and its stability is excellent.DT has good precision and acceptable generalization,but its stability is poor.SVR and KNN have superior stability,but their generalization and precision are inadequate.MLP lacks generalization,and its stability and precision are unacceptable.In short,RF has the best comprehensive performance,demonstrated by a limited prediction deviation of 26.3%from the experimental results,better than AdaBoost(38.0%)and DT(38.3%)and far better than other remaining methods.It is also found that data mining methods provide better predictions when cement-based materials’water vapor permeability is high.

Applying data mining techniques to classify patients with suspected hepatitis C virus infection

Background Hepatitis C virus(HCV)has a high prevalence worldwide,and the progression of the disease can cause irreversible damage to severe liver damage or even death.Therefore,developing prediction models using machine learning techniques is beneficial.This study was conducted to classify suspected patients with HCV infection using different classification models.Methods The study was conducted using a dataset derived from the University of California,Irvine(UCI)Ma-chine Learning Repository.Since the HCV dataset was imbalanced,the synthetic minority oversampling technique(SMOTE)was applied to balance the dataset.After cleaning the dataset,it was divided into training and test data for developing six classification models.These six algorithms included the support vector machine(SVM),Gaus-sian Naïve Bayes(NB),decision tree(DT),random forest(RF),logistic regression(LR),and K-nearest neighbors(KNN)algorithm.The Python programming language was used to develop the classifiers.Receiver operating characteristic curve analysis and other metrics were used to evaluate the performance of the proposed models.Results After the evaluation of the models using different metrics,the RF classifier had the best performance among the six methods.The accuracy of the RF classifier was 97.29%.Accordingly,the area under the curve(AUC)for LR,KNN,DT,SVM,Gaussian NB,and RF models were 0.921,0.963,0.953,0.972,0.896,and 0.998,respectively,RF showing the best predictive performance.Conclusion Various machine learning techniques for classifying healthy and unhealthy patients were used in this study.Additionally,the developed models might identify the stage of HCV based on trained data.

Feature weighted clustering for user profiling

Personalization is the adaptation of the services to fit the user’s interests,characteristics and needs.The key to effective personalization is user profiling.Apart from traditional collaborative and content-based approaches,a number of classification and clustering algorithms have been used to classify user related information to create user profiles.However,they are not able to achieve accurate user profiles.In this paper,we present a new clustering algorithm,namely Multi-Dimensional Clustering(MDC),to determine user profiling.The MDC is a version of the Instance-Based Learner(IBL)algorithm that assigns weights to feature values and considers these weights for the clustering.Three feature weight methods are proposed for the MDC and,all three,have been tested and evaluated.Simulations were conducted with using two sets of user profile datasets,which are the training(includes 10,000 instances)and test(includes 1000 instances)datasets.These datasets reflect each user’s personal information,preferences and interests.Additional simulations and comparisons with existing weighted and non-weighted instance-based algorithms were carried out in order to demonstrate the performance of proposed algorithm.Experimental results using the user profile datasets demonstrate that the proposed algorithm has better clustering accuracy performance compared to other algorithms.This work is based on the doctoral thesis of the corresponding author.