Microbial Aspects of Environmentally Benign Iron Ore

Many types of micro-organisms inhabit iron ore deposits contributing to biogenic formation and conversion of iron oxides and associated minerals. Bacteria such as Paenibacillus polymyxa arc capable of significantly altering the surface chemical behaviour of iron ore minerals such as haematite, alumina, calcite and silica. Differing mineral surface affinities of bacterial cells and metabolic products such as proteins and polysaccharides can be utilised to induce their flotation or flocculation. Mineral-specific bioreagents such as proteins are generated when bacteria are grown in the presence of haematite, alumina, calcite and silica. Alumina-grown bacterial cells and proteins separated from such cells were found to be capable of separating alumina from haematite. Biodegradation of iron ore flotation collectors such as amines and oleates can be effectively utilised to achieve environmental control in iron ore processing mills.

MULTI-INSTRUMENT DETECTION IN POLYPHONIC MUSIC USING GAUSSIAN MIXTURE BASED FACTORIAL HMM

We formulate the problem of detecting the constituent instruments in a polyphonic music piece as a joint decoding problem. From monophonic data, parametric Gaussian Mixture Hidden Markov Models (GM-HMM) are obtained for each instrument. We propose a method to use the above models in a factorial framework, termed as Factorial GM-HMM (F-GM-HMM). The states are jointly inferred to explain the evolution of each instrument in the mixture observation sequence. The dependencies are decoupled using variational inference technique. We show that the joint time evolution of all instruments' states can be captured using F-GM-HMM. We compare performance of proposed method with that of Student's-t mixture model (tMM) and GM-HMM in an existing latent variable framework. Experiments on two to five polyphony with 8 instrument models trained on the RWC dataset, tested on RWC and TRIOS datasets show that F-GM-HMM gives an advantage over the other considered models in segments containing co-occurring instruments.