Analysis of book sales prediction at Amazon marketplace in India: a machine learning approach

Information Systems and e-Business Management - Prediction of customer demand is an important part of Supply Chain Management, as it helps to avoid over or under production and reduces delivery...     

Use of Marine Waste Extract as a Nitrogen Source for Biological Sulfate Reduction: Development of a Suitable Alternative

Marine wastes extract (MWE), prepared from marine organic wastes, was used to develop an alternative nitrogen source for sulfate-reducing bacteria (SRB) in environments like acid mine drainage that are acidic in nature and contain high levels of sulfate and dissolved metals. The MWE contains 13.95 g L^?1 of nitrogen, and other micronutrients like K, Na, P, S, Ca, Fe, Mg, Mn, Zn, Co, Cu and Ni, and has a C/N ratio of 0.107. A modified SRB medium (MSRB) was developed by replacing the commercial nitrogen source of standard SRB growth medium with MWE. MSRB was compared with modified Postgate B, Postgate B, and Widdel and Pfennig media, which contained bactopeptone and NH₄Cl, as nitrogen sources. Results showed that the growth media could support a total microbial population of 2.8 × 10¹²–6.2 × 10¹² cells mL^?1 with 96, 80, 92.5, and 65 % SRB in MSRB, Postgate B, modified Postgate B, and Widdel and Pfennig media, respectively. The sulfate reduction efficiency was 97, 87, 72, and 68 % at reduction rates of 12.41, 11.10, 4.35, and 8.8 mg L^?1 h^?1, respectively, for the same media. We conclude that MWE could be a cost-effective substitute for commercially available nitrogen sources for SRB for large-scale treatment of sulfate-rich wastewater.     

Sliding mode control of quadruple tank process

The process investigated herein is the quadruple tank system that is stable only within a limited zone of operating parameters. The process model has been developed from fundamentals and tuned with experimental data. A controller design based on feedback linearization has been tested on this process model. Coupling feedback linearization with sliding mode algorithm provides robust control of the process and performs far superior to conventional PI control. A PC based controller interfaced to the experimental quadruple tank experimental set up has been used to implement this algorithm and test its performance. Inserting a ‘boundary layer’ around the sliding surface reduced the ‘chattering’ associated with sliding mode control. The implemented controller provides robust control and excellent set point tracking.     

Modeling the recrystallization process using inverse cellular automata and genetic algorithms: Studies using differential evolution

An inverse modeling approach was taken up in this work to model the process of recrystallization using cellular automata (CA). Using this method after formulating a CA model of recrystallization, differential evaluation (DE), a real-coded variant of genetic algorithms, was used to search for the value of nucleation rate, providing an acceptable matching between the theoretical and experimentally observed values of fraction-recrystallized (X). Initially, the inverse modeling was attempted with a simple CA strategy, in which each of the CA cells had an equal probability of becoming nucleated. DE searched for the value of the nucleation rate yielding the best results for single-crystal iron at 550 °C. A good match could not be simultaneously achieved this way for the early stages of recrystallization as well as for the later stages. To overcome this difficulty, the CA grid was divided into two zones, having lower and higher probabilities of nucleation. This resulted in good correspondence between the predicted and experimental values of X for the entire duration of recrystallization. The introduction of a distribution in the probability of nucleation made the model even closer to the actual process, in which the probability of nucleation is often nonuniform due to nonuniformity in dislocation density as well as the presence of grain/interface boundaries.     

Arsenic and other elements in hair, nails, and skin-scales of arsenic victims in West Bengal, India

For the first time, biological tissues (hair, nails, and skin-scales) of arsenic victims from an arsenic affected area of West Bengal (WB), India were analyzed for trace elements. Analysis was carried out by inductively coupled plasma-mass spectrometry (ICP-MS) for 10 elements (As, Se, Hg, Zn, Pb, Ni, Cd, Mn, Cu, and Fe). A microwave digester was used for digestion of the tissue samples. To validate the method, certified reference materials--human hair (GBW 07601) and bovine muscle (CRM 8414)--were analyzed for all elements. The W test was used to study the normal/log normal distribution for each element in the tissue samples. For hair (n=44) and nails (n=33), all elements show log-normal distribution. For skin-scale samples (n=11), data are not sufficient to provide the information about the trend. Geometric mean, standard error, and range for each element were presented and compared with literature values for other populations. This study reveals the higher levels of toxic elements As, Mn, Pb, and Ni in the tissue samples compared with available values in the literature. The elevated levels of these toxic metals in the tissues may be due to exposure of these elements through drinking water and food. The correlations of Mn and Ni with other essential elements, e.g. Fe, Cu, Zn, suggest that Mn and Ni may substitute for those elements in hair, nails, and skin-scales. However, correlation represents the relation between two elements only and does not take into consideration of the presence of other elements. Principle component analysis was applied to explain the behavior among the elements present in hair and nails. This study reveals that in the arsenic-affected areas of WB, the concentrations of other toxic elements in drinking water and foodstuff should be monitored to evaluate the arsenic poisoning.     

Prediction of an iron oxide concentration in the induction smelting process

Induction smelting process, ISP, is a direct smelting process in which self-fluxed composite pellets (made of iron ore, brown coal and lime) are melted in a single phase induction furnace in conjunction with top blown oxygen. A mass transfer model to predict the concentration of iron oxide, has been developed for this process. Transient mass balance equation with complex boundary conditions has been worked out by adopting a relatively new approach known as the cell model approach. These equations have been solved numerically using finite difference technique to obtain the iron oxide concentration profile in the induction smelting process. Numerical and experimental results obtained for the iron oxide concentration show a reasonable agreement with each other.     

Analyzing Fe–Zn system using molecular dynamics, evolutionary neural nets and multi-objective genetic algorithms

Failure behavior of Zn coated Fe is simulated through molecular dynamics (MD) and the energy absorbed at the onset of failure along with the corresponding strain of the Zn lattice are computed for different levels of applied shear rate, temperature and thickness. Data-driven models are constructed by feeding the MD results to an evolutionary neural network. The outputs of these neural networks are utilized to carry out a multi-objective optimization through genetic algorithms, where the best possible tradeoffs between two conflicting requirements, minimum deformation and maximum energy absorption at the onset of failure, are determined by constructing a Pareto frontier.     

Ineffectiveness and poor reliability of arsenic removal plants in West Bengal, India

In the recent past, arsenic contamination in groundwater has emerged as an epidemic in different Asian countries, such as Bangladesh, India, and China. Arsenic removal plants (ARP) are one possible option to provide arsenic-safe drinking water. This paper evaluates the efficiency of ARP projects in removing arsenic and iron from raw groundwater, on the basis of our 2-year-long study covering 18 ARPs from 11 manufacturers, both from home and abroad, installed in an arsenic affected area of West Bengal, India, known as the Technology Park Project (TP project). Immediately after installation of ARPs on August 29, 2001, the villagers began using filtered water for drinking and cooking, even though our first analysis on September 13, 2001 found that 10 of 13 ARPs failed to remove arsenic below the WHO provisional guideline value (10 microg/L), while six plants could not achieve the Indian Standard value (50 microg/L). The highest concentration of arsenic in filtered water was observed to be 364 microg/L. Our 2-year study showed that none of the ARPs could maintain arsenic in filtered water below the WHO provisional guideline value and only two could meet the Indian standard value (50 microg/L) throughout. Standard statistical techniques showed that ARPs from the same manufacturers were not equally efficient. Efficiency of the ARPs was evaluated on the basis of point and interval estimates of the proportion of failure. During the study period almost all the ARPs have undergone minor or major modifications to improve their performance, and after our study, 15 (78%) out of 18 ARPs were no longer in use. In this study, we also analyzed urine samples from villagers in the TP project area and found that 82% of the samples contained arsenic above the normal limit.