Context-Aware Collaborative Filtering Framework for Rating Prediction Based on Novel Similarity Estimation

Recommender systems are rapidly transforming the digital world into intelligent information hubs.The valuable context information associated with the users’prior transactions has played a vital role in determining the user preferences for items or rating prediction.It has been a hot research topic in collaborative filtering-based recommender systems for the last two decades.This paper presents a novel Context Based Rating Prediction(CBRP)model with a unique similarity scoring estimation method.The proposed algorithm computes a context score for each candidate user to construct a similarity pool for the given subject user-item pair and intuitively choose the highly influential users to forecast the item ratings.The context scoring strategy has an inherent capability to incorporate multiple conditional factors to filter down the most relevant recommendations.Compared with traditional similarity estimation methods,CBRP makes it possible for the full use of neighboring collaborators’choice on various conditions.We conduct experiments on three publicly available datasets to evaluate our proposed method with random user-item pairs and got considerable improvement in prediction accuracy over the standard evaluation measures.Also,we evaluate prediction accuracy for every user-item pair in the system and the results show that our proposed framework has outperformed existing methods.

Evaluation of Wheat Varietal Performance under Different Nitrogen Sources

Nitrogen fertilization plays a very important role for crop productivity. New developed wheat varieties need proper fertilization for improved crop productivity. The present study was carried out to quantify, the effects of nitrogen derived from urea and FYM on the four newly developed wheat varieties i.e. Siran-2009, Ata Habib, Janbaz-2009 and Pirsabak-2008 for yield improvement, quality and soil fertility status. The N treatments were control, 100% of the recommended nitrogen from urea as well as FYM, and 50% from each source. The experiment was carried out at New Developmental Farm, Khyber Pakhtunkhwa Agricultural University Peshawar Pakistan, during Rabi 2011-2012. Results of the data showed that Janbaz-2009 was more responsive to biological yield (11,011 kg·ha-1), grain yield (4339 kg·ha-1), and nitrogen use efficiency (14.8%), whereas Siran-2010 performed better for grain N contents (2.31%). Plots having both urea and FYM had improved biological yield (11,958 kg·ha-1), and grain yield (4901 kg·ha-1). Urea application had improved straw N contents (0.92%) in addition to Mix application of urea and FYM (0.93%). Mix application of both sources and sole FYM had higher grains N content (2.25%), whereas control plots in addition to mix application had improved nitrogen use efficiency (14.8%). Siran-2010 and Janbaz-2009 performed better in FYM and mix FYM and urea plots for most of the parameters. It was concluded from the experiment that Janbaz-2009 had improved yield and yield components, whereas Siran-2010 had improved the grain N content. Similarly, Mix application of FYM and urea had improved crop productivity, soil fertility and grains as well as straw N content. Thus wheat varieties Janbaz-2009 sown in mix FYM and urea is recommended for general cultivation in agro-climatic condition of Peshawar.