Prediction of retail sales of footwear using feedforward and recurrent neural networks

Fluctuation of sales over time is one of the major problems faced by most of the industries. To alleviate this problem management tries to base their plans on forecast of sales pattern, which are mostly adhoc and rarely provides solid foundation for the plans. This study makes an attempt to solve this problem by taking a neural network approach, at the process of sales of footwear, and arriving at an optimum neural network model. The algorithms used for developing such model through neural network are both feedforward and recurrent Elman network. The data used in this work are the weekly sales of footwear and the information about the seasonality of sales process. While solving the problem, the focus is on forecasting of weekly retail sales as per the requirement of management. This work would reduce the uncertainty existing in the short-term/middle term planning of sales and distribution logistics of footwear over different time horizons across the entire supply chain of footwear business.     

A novel microfluidic switch for pH control using Chitosan based hydrogels

We report a novel pH-sensitive hydrogel based micro-valve for metered flow that has applications in a laboratory made “Intelligent valving system”. The hydrogel solution was prepared through Chitosan and poly vinyl alcohol in acetic acid and crystallized using gluteraldehyde as the crosslinking agent in the form of thin wafers and it was found to be very sensitive to pH changes. The pore structure of hydrogel was investigated through Field Emission Scanning Electron Microscopy and thin wafers of the gel were physically placed inside PDMS microchannels. Flow metering in these channels was observed by controlled expansion of the hydrogel plug till complete valving was realized. This valving device was further precisely characterized with micro Particle Image Velocimetry using a solution containing fluorescent polymeric micro beads. The principle advantage of this hydrogel device is the smaller range of pH (varying between pH 3 and 7) over which the valving response is observed.     

A Novel Neurofilament Light Chain ELISA Validated in Patients with Alzheimer’s Disease,Frontotemporal Dementia,and Subjective Cognitive Decline,and the Evaluation of Candidate Proteins for Immunoassay Calibration

Neurofilament light chain (Nf-L) is a well-known biomarker for axonal damage; however, the corresponding circulating Nf-L analyte in cerebrospinal fluid (CSF) is poorly characterized. We therefore isolated new monoclonal antibodies against synthetic peptides, and these monoclonals were characterized for their specificity on brain-specific intermediate filament proteins. Two highly specific antibodies, ADx206 and ADx209, were analytically validated for CSF applications according to well-established criteria. Interestingly, using three different sources of purified Nf-L proteins, a significant impact on interpolated concentrations was observed. With a lower limit of analytical sensitivity of 100 pg/mL using bovine Nf-L as the calibrator, we were able to quantify the Nf-L analyte in each sample, and these Nf-L concentrations were highly correlated to the Uman diagnostics assay (Spearman rho = 0.97, p < 0.001). In the clinical diagnostic groups, the new Nf-L ELISA could discriminate patients with Alzheimer’s disease (AD, n = 20) from those with frontotemporal lobe dementia (FTD, n = 20) and control samples with subjective cognitive decline (SCD, n = 20). Henceforth, this novel Nf-L ELISA with well-defined specificity and epitopes can be used to enhance our understanding of harmonizing the use of Nf-L as a clinically relevant marker for neurodegeneration in CSF.     

A Gravitational Search Algorithm Based Static VAR Compensator Switching Function Optimization Technique for Minimum Harmonic Injection

Switching function optimization for minimum source harmonic injection for a static VAR compensator is presented. The static VAR compensator is configured with a fixed capacitor and insulated-gate bipolar transistor controlled reactor. The switching function is optimized for minimum source harmonic injection considering the desired fundamental voltage across load terminals. A gravitational search algorithm is employed for this purpose. It is observed that the proposed switching scheme with two different switching angles per half-cycle provides lower source harmonic injection compared to conventional switching, hence improving the source current harmonics. The switching angles are computed off-line using the gravitational search algorithm for varying modulation indices considering the minimum total harmonic distortion of the reactor voltage. The switching angles are stored in a processor as a function of the modulation index for on-line application using a piecewise mixed model approximation technique for low memory usage. It is observed that the proposed switching improves the source current total harmonic distortion on an average of 4 to 5% over most of the operating range compared to conventional switching without optimization. Various simulation and experimental results are presented on different loads to validate the proposed concept.     

Multi-Objective Approach for Reconfiguration of Distribution Systems with Distributed Generations

This paper presents a fuzzy multi-objective based heuristic algorithm for network reconfiguration of distribution systems considering distributed generations (DGs). The objectives of reduction of real power loss, branch current carrying capacity limit, maximum and minimum voltage constraints, and feeder load balancing are considered for performance enhancement of the distribution system. Since these objectives are non-commensurable and difficult to solve simultaneously using conventional approaches, they are converted into fuzzy domain and a fuzzy multi-objective function is formulated. A sensitivity analysis based on voltage profile improvement and real power loss reduction is used for obtaining optimal locations of DGs and genetic algorithm is used for optimal sizing of DGs. The proposed reconfiguration algorithm is implemented in two stages, initially in the first stage without incorporating DGs and in the second stage incorporating DGs for obtaining an optimal distribution system network reconfiguration. The advantage of the proposed method is demonstrated through a seventy node four feeders and a sixteen node three feeders distribution systems.     

Exploration of photoreduction ability of reduced graphene oxide–cadmium sulphide hetero-nanostructures and their intensified activities against harmful microbes

Journal of Materials Science - Fabrication of effective photocatalyst using semiconductors and graphene or reduced graphene oxide has been regarded as one of the most promising task to attenuate...