Thesis (M.S.)--University of Wisconsin--Madison, 1965. / eContent provider-neutral record in process. Description based on print version record. Bibliography: l. 67-70.

No description available.

Underground mines are the source of 33% of US coal production and 60% of worldwide coal production. Room-and-pillar mining with continuous miners has been the most common production system used in these mines since the 1960s. The introduction of continuous miners mechanized the underground coal mining industry triggering a period of sustained growth in mine productivity; however, productivity peaked at the turn of the century and has been in decline for a decade. Research on productivity in underground coal mines began at Southern Illinois University Carbondale in 2000 and led to development of a deterministic spreadsheet model for evaluating continuous miner production systems. As with other production models, this model uses a heuristic approach to define the fundamental input parameter known as a cut sequence. This dissertation presents a dynamic programming algorithm to supplant that trial-and-error practice of determining and evaluating room-and-pillar mining sequences. Dynamic programming has been used in mining to optimize multi-stage processes where production parameters are stage-specific; however, this is the inaugural attempt at considering parameters that are specific to paths between stages. The objective of the algorithm is to maximize continuous miner utilization for true production when coal is actually being loaded into haulage units. This is accomplished with an optimal value function designed to minimize cut-cycle time. In addition to loading time, cut-cycle time also includes change-out and place change times. The reasonableness of the methodology was validated by modeling an actual mining sequence and comparing results with time study and production report data collected from a cooperating mine over a two-week time period in which more than 300 cuts were mined. The validation effort also inspired some fine-tuning adjustments to the algorithm. In a case study application of the dynamic programming algorithm, a seven-day "optimal mining sequence" was identified for three crosscuts of advance on an eleven-entry super-section developing a main entry system for a new mine in southern Illinois. Productivity improvements attributable to the optimal sequence were marginal but the case study application reconfirmed the reasonableness of the methodology.

This dissertation thesis describes an advanced method of knowledge discovery in databases (KDD), implemented in system LISp-Miner. The goal is to show the possibilities of coordinated use of analytical tools and complex procedures GUHA in this system. The thesis uses methodology CRISP-DM, which is firstly described and work is proceeded using this methodology in the following sections. The author firstly introduces readers domain area and then the data itself, which are processed to the analysis needs. Analytical questions that are answered at, are drawn from the literature, which is focused on domain area. The work should be used as a guide to LISp-Miner users, using analytical tools and procedures GUHA is therefore described the easiest way to understand.

This diploma thesis introduces three different methods of creating a neural network binary classifier for the purpose of automated weather prediction with attribute pre-selection using association rules and correlation patters mining by the LISp-Miner system. First part of the thesis consists of collection of theoretical knowledge enabling the creation of such predictive model, whereas the second part describes the creation of the model itself using the CRISP-DM methodology. Final part of the thesis analyses the performance of created classifiers and concludes the proposed methods and their possible benefits over training the network without attribute pre-selection.

The aim of this thesis is to analyze the real data from the restaurant sector in the center of Prague, prove assumptions based on existing knowledge and explore hidden relations. The database management system MySQL was used for the initial transformation of the original data structure. The data after the transformation were converted into a form that it was possible to manipulate with it using the procedure LMDataSource of the system LISp-Miner. The analysis of association of relations were used for the procedure 4ft-Miner of the system LISp-Miner. The MySQL database system was used for the frequency analysis to obtain results, and Microsoft Word and Excel were used to interpret the results. Some of the assumptions in the research were found proven. Furthermore, an interesting combination of relations was discovered. The output of this work allows the owner of the data to use some of the data analysis results for the optimization of internal processes. In addition, this study points out other possible ways to analyze these data.

In past years, great attention has been paid to evolutionary algorithms and they have been utilized in wide range of industries including data mining field, which nowadays presents a highly demanded product for many commercial institutions. Both mentioned topics are combined in this work. Main thesis subject is testing of new Reverse-Miner module, which can generate data with hidden properties using evolutionary algorithms while using also other modules of LISp-Miner system, commonly used for the purposes of data mining. Main goal lies in generation of two databases by the module in such way so they would meet explicitly set requirements. Other goals are also set within the thesis in the form of understanding the domain necessary for subsequent modeling. The result of the practical part of the thesis is represented not only by two successfully generated databases, but also by description of steps, methods and techniques used. The common recommendations for data preparation by module Reverse-Miner are later summarized, based on experience with modeling. Previous thesis outputs are furthermore contemplating the conclusion of analysis of technical means used for generation and they also provide several suggestions for possible future extensions.

Detta examensarbete omfattar generering samt vidareutveckling av koncept av en infästning för ett muckhanteringssystem på en tunnelborrningsmaskin. Maskinen, som går under arbetsnamnet Mobile miner, utvecklas av Atlas Copco tillsammans med bland andra konsultföretaget Svea Teknik AB. Examensarbetet genomförs parallellt med slutskedet av det verkliga utvecklingsprojektet och kan eventuellt komma att inkluderas. Examensarbetet har föregåtts av utvecklingen av tunnelborrningsmaskinen och dess främre muckhanteringssystem som består av en ramp (apron) och en kedjetransportör. Systemets uppgift är att samla upp och transportera bort den bergskross (muck) som genereras vid själva borringreppet. Infästningen delas upp i en främre och en bakre infästning på grund av systemets storlek, samt för att uppfylla systemets fördefinierade rörlighetskrav. En kravspecifikation upprättas, baserad på en bakgrundsstudie, för generering av flertalet infästningskoncept medan endast ett koncept för en främre infästning vidareutvecklas efter konceptval med Pughs matris.Vidareutvecklingen resulterade i en främre infästning med två lastkännande överbelastningsskydd, placerade under apron, tillsammans med två skenstyrningar för vertikal positionering av apron. Överbelastningsskydden mäter med hjälp av hydraulcylindrar den last som angriper aprons front och är konstruerade för att lösa ut vid en specificerad överlast varpå maskinens rörelser stoppas. Detta för att skydda apron från haveri.Den främre infästningen är utformad för att möjliggöra enkel montering och demontering av det främre muckhanteringssystemet i samband med service. Kopplingarna mellan det främre muckhanteringssystemet och maskinen är konstruerade med låsningar vars montering och demontering kan genomföras med hög personsäkerhet. Totalvikten för den främre infästningens delkomponenter är ca 800 kg under vidareutvecklingsfasen.Den vidareutvecklade främre infästningen uppfyller de krav och önskemål i kravspecifikationen som var möjliga att verifieras med CAD och FEM-analys. / This master’s thesis includes generation and further development of concept for a muck handling system mount on a tunnel boring machine. The machine, with the working title Mobile miner, is developed by Atlas Copco together with the technical consultant firm Svea Teknik AB among others. The master’s thesis is conducted in parallel with the finalizing of the actual development project with a chance of being included. The master’s thesis is preceded by the development of the tunnel boring machine and its frontal muck handling system that consists of a ramp (apron) and a chain conveyor. The task of the system is to gather and transport the crushed rock (muck) that is generated during the tunnel boring process. The mount is divided into a frontal- and a rear mount due to the size of the system and due to the movement criteria’s for the system. A specification of requirements is generated, preceded by a literature study, several concepts are generated while only one concept of a frontal mount is further developed. The concept of a frontal mount to be further developed is chosen using Pugh’s matrix.The development process resulted in a frontal mount with two load sensing systems, placed beneath the apron, together with two rail guides used to adjust the vertical position of the apron. The load sensing system measures the load acting on the front of the apron using hydraulic cylinders that signals the machine to stop all its movements when exposed to a specified overload. This is to protect the apron from breaking down.The frontal mount is designed to allow easy mounting and dismounting of the frontal muck handling system during service. The connections between the frontal muck handling system and the machine are designed with locking mechanisms that can be mounted and dismounted with high personal safety. The total weight of the components for the frontal mount is about 800 kg during the further development phase.The frontal mount fulfills the requirements and requests stated in the specification of requirements possible to verify using CAD and FEM-analysis.

The presented work "An Empirical Comparison of Commercial Data Mining Tools" deals with data mining tools from world's leading software providers of statistical solutions. The aim of this work is to compare commercial packages IBM SPSS Modeler and SAS Enterprise Miner in terms of their specification and utility considering a chosen set of evaluation criteria. I would like to achieve the appointed goal by a detailed analysis of selected features of the surveyed software packages as well as by their application on real data. The comparison is founded on 29 component criteria which reflect user's requirements regarding functionality, usability and flexibility of the system. The pivotal part of the comparative process is based on an application of the surveyed data mining tools on data concerning meningoencephalitis. Results predestinate evaluation of their performance while analyzing small and large data. Quality of developed data models and duration of their derivation are stated in reference to the use of six comparable data mining techniques for classification. Small data more likely comply with IBM SPSS Modeler. Although it produces slightly less accurate models, their development times are much shorter. Increasing the amount of data changes the situation in favor of competition. SAS Enterprise Miner manages better results while analyzing large data. Considerably more accurate models are accompanied by slightly shorter times of their development. Functionality of the surveyed data mining tools is comparable, whereas their usability and flexibility differentiate. IBM SPSS Modeler offers apparently better usability and learnability. Users of SAS Enterprise Miner have a slightly more flexible data mining tool at hand.

In 2006, Congress passed the MINER Act requiring mine operators to submit an emergency response plan that included post-accident communications and tracking systems to MSHA within three years of the Act. These systems were required to be designed for maximum survivability after a catastrophic event, such as a fire or explosion, and to be permissible (meets MSHA criteria for explosion-proof). At that time, no commercially available systems existed that met these standards. Several companies undertook developing new, or enhancing existing, technologies to meet these requirements. This research presents the results of a study that was conducted to determine the present day types of systems being used, along with their average annual worker hours, coal production, number of mechanized mining units, and type of communications and tracking systems installed. Furthermore, 10 mines were visited to obtain detailed information related to the various technologies. It was found the most influential parameters on system selection include MSHA district, mining method, and number of underground workers.