Lessons and Challenges from Mining Retail E-Commerce Data

The architecture of Blue Martini Software's e-commerce suite has supported data collection, data transformation, and data mining since its inception. With clickstreams being collected at the application-server layer, high-level events being logged, and data automatically transformed into a data warehouse using meta-data, common problems plaguing data mining using weblogs (e.g., sessionization and conflating multi-sourced data) were obviated, thus allowing us to concentrate on actual data mining goals. The paper briefly reviews the architecture and discusses many lessons learned over the last four years and the challenges that still need to be addressed. The lessons and challenges are presented across two dimensions: business-level vs. technical, and throughout the data mining lifecycle stages of data collection, data warehouse construction, business intelligence, and deployment. The lessons and challenges are also widely applicable to data mining domains outside retail e-commerce.     

Evaluation of a multimode fiber optic low coherence interferometer for path length resolved Doppler measurements of diffuse light

The performance of a graded index multimode fiber optic low coherence Mach-Zehnder interferometer with phase modulation is analyzed. Investigated aspects were its ability to measure path length distributions and to perform path length resolved Doppler measurements of multiple scattered photons in a turbid suspension of particles undergoing Brownian and translational motion. The path length resolution of this instrument is compared with a system using single mode fibers for illumination and detection. The optical path lengths are determined from the zero order moment of the phase modulation peak in the power spectrum. The weighted first moment, which is equal to the average Doppler shift, shows a linear response for different mean flow velocities within the physiological range.     

Meta-cognitive RBF Network and its Projection Based Learning algorithm for classification problems

‘Meta-cognitive Radial Basis Function Network’ (McRBFN) and its ‘Projection Based Learning’ (PBL) algorithm for classification problems in sequential framework is proposed in this paper and is referred to as PBL-McRBFN. McRBFN is inspired by human meta-cognitive learning principles. McRBFN has two components, namely the cognitive component and the meta-cognitive component. The cognitive component is a single hidden layer radial basis function network with evolving architecture. In the cognitive component, the PBL algorithm computes the optimal output weights with least computational effort by finding analytical minima of the nonlinear energy function. The meta-cognitive component controls the learning process in the cognitive component by choosing the best learning strategy for the current sample and adapts the learning strategies by implementing self-regulation. In addition, sample overlapping conditions are considered for proper initialization of new hidden neurons, thus minimizes the misclassification. The interaction of cognitive component and meta-cognitive component address the what-to-learn, when-to-learn and how-to-learn human learning principles efficiently. The performance of the PBL-McRBFN is evaluated using a set of benchmark classification problems from UCI machine learning repository and two practical problems, viz., the acoustic emission signal classification and the mammogram for cancer classification. The statistical performance evaluation on these problems has proven the superior performance of PBL-McRBFN classifier over results reported in the literature.     

First and second law investigations of a new solar‐assisted thermodynamic cycle for triple effect refrigeration

This investigation is persuaded for the first and second law analyses of a new solar‐driven triple‐effect refrigeration cycle using Duratherm 600 oil (Duratherm Extended Life Fluid, NY, USA) as the heat transfer fluid is performed. The proposed cycle is an integration of ejector, absorption, and cascaded refrigeration cycles that could produce refrigeration output of different magnitude at different temperature simultaneously. Both exergy destruction and losses in each component and hence in the overall system are determined to identify the causes and locations of the thermodynamic imperfection. The effects of some influenced parameters such as hot oil outlet temperature, refrigerant turbine inlet pressure, and the evaporator temperature of ejector and cascaded refrigeration cycle have been observed on the first and second law performances. It is found that maximum irreversibility occurs in central receiver as 52.5% and the second largest irreversibility of 25% occurs in heliostat field. The second law efficiency of the solar driven triple effect refrigeration cycle is 2%, which is much lower than its first law efficiency of 11.5%. Analysis clearly shows that performance evaluation based on the first law analysis is inadequate and hence, more meaningful evaluation must be included in the second law analysis. Copyright © 2013 John Wiley & Sons, Ltd.     

An insight into spray pulsed reactor through mathematical modeling of catalytic dehydrogenation of cyclohexane

A mathematical model has been developed to study the impact of nozzle-catalyst distance and bulk gas temperature on the conversion and hydrogen evolution rate in a spray pulse reactor. The effects of reactor configuration and operating parameters on conversion and evolution rate were predicted with more than 90% accuracy. Reactor optimization and sensitivity analysis were carried out and an optimal design of nozzle-catalyst distance 5 cm and bulk gas temperature of 50 °C were proposed. The optimized design was predicted to increase the conversion from approximately 32–74%. The model could be in general used for designing any endothermic heterogeneous catalytic reaction in a spray pulse reactor.     

Morphological exploration of chemical vapor–deposited P-doped ZnO nanorods for efficient photoelectrochemical water splitting

Photoelectrochemical (PEC) water splitting is beneficial and has received attractive attention due to a greater potential to generate hydrogen and oxygen from water by using plentiful solar light to solve the problem of energy crisis. Various active semiconductor materials are used in PEC water splitting applications. Nevertheless, in past decades, most of the researchers suggested that titanium oxide (TiO₂) is the best photoanode for this type of applications. Now, Zinc oxide (ZnO) is considered a perfect substitution to TiO₂ due to its comparable energy band structure and superior photogenerated electron transfer rate. In this study, bare and phosphorous-doped ZnO nanorods were successfully developed on fluorine-doped tin oxide-coated glass (FTO) substrate by chemical vapor deposition. X-ray diffraction (XRD) pattern authenticated hexagonal structure formation with strong diffraction peak of (101), which showed that ZnO nanorods were perfectly developed along c axis. The optical and morphological properties were analyzed by UV–Vis and scanning electron microscopy images. The energy-dispersive X-ray spectra demonstrated that doping agent phosphorous was present in ZnO nanorods. The PEC properties of the developed ZnO nanorods were further investigated and obtained results suggested that a small amount of phosphorous-doped ZnO nanorods enhances their PEC performance.     

Antifungal activity of five different essential oils in vapour phase for the control of Colletotrichum gloeosporioides and Lasiodiplodia theobromae in vitro and on mango

Mango fruit has high commercial value; however, major postharvest losses are encountered throughout the supply chain due to postharvest diseases. These results lead to the search for natural fungicide for postharvest diseases control. The antifungal effects of five essential oils (thyme, clove, cinnamon, anise and vitex) were assessed by disc volatilisation method. Thyme oil vapours at 5 μL per Petriplate, and clove and cinnamon oil at 8 μL per Petriplate showed 100% growth inhibition of mango pathogens in vitro. GC/MS analysis of essential oil showed thymol (23.88), o‐cymol (23.88) and terpinolene (23.88) as the major constituents of thyme oil. Clove and cinnamon oils contain 3‐allyl‐2‐methoxyphenol (37.42%) and benzofuran 3‐methyl (17.97%), respectively. Thyme oil as a fumigant at 66.7 μL L^?1 showed a significant (P < 0.05) inhibition on postharvest pathogens of mango fruits stored at 25 °C for 6 days. Results of our study suggest the possibility of using thyme oil as an alternate natural fungicide to manage postharvest diseases in mango.     

Electricity demand supply analysis: Current status and future prospects for Maharashtra,India

The growth potential of any state is linked with infrastructure and electricity infrastructure is the most important parameter for economic growth. Maharashtra, a prominent state in India consumes 12 per cent of India's electricity. Maharashtra's power sector is facing the electricity deficit and shortage since early 2005. On the other hand, industrial and service sectors are rising in the state. The present paper discusses electricity situational analysis of the state. Electricity demand analysis has been presented and comparison of state electricity demand vis-à-vis Mumbai's demand (state capital) has been carried out for two years. Variation for monthly average demand for two years and load shedding have also been analyzed. Power supply situation analysis and analysis of major power suppliers have been carried out. The State Load Distribution Center data is used to depict the load variation for a typical day. Interventions needed to sustainably meet the growing demands are also discussed.     

Three-tier neural model for service provisioning over collaborative flying ad hoc networks

Neural Computing and Applications - Collaboration among different ad hoc networks allows the formation of efficient guided networks. One of the such collaborative networks is formed between aerial...