scholarly journals EBCR: Empirical Bayes concordance ratio method to improve similarity measurement in memory-based collaborative filtering

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0255929
Author(s):  
Yu Du ◽  
Nicolas Sutton-Charani ◽  
Sylvie Ranwez ◽  
Vincent Ranwez
Keyword(s):  
Collaborative Filtering ◽  
Prediction Accuracy ◽  
Empirical Bayes ◽  
Similarity Measures ◽  
Ratio Method ◽  
Bayes Inference ◽  
Benchmark Datasets ◽  
Large Product ◽  
Accuracy Performance ◽  
Selection Of

Recommender systems aim to provide users with a selection of items, based on predicting their preferences for items they have not yet rated, thus helping them filter out irrelevant ones from a large product catalogue. Collaborative filtering is a widely used mechanism to predict a particular user’s interest in a given item, based on feedback from neighbour users with similar tastes. The way the user’s neighbourhood is identified has a significant impact on prediction accuracy. Most methods estimate user proximity from ratings they assigned to co-rated items, regardless of their number. This paper introduces a similarity adjustment taking into account the number of co-ratings. The proposed method is based on a concordance ratio representing the probability that two users share the same taste for a new item. The probabilities are further adjusted by using the Empirical Bayes inference method before being used to weight similarities. The proposed approach improves existing similarity measures without increasing time complexity and the adjustment can be combined with all existing similarity measures. Experiments conducted on benchmark datasets confirmed that the proposed method systematically improved the recommender system’s prediction accuracy performance for all considered similarity measures.

scholarly journals AgreeRelTrust—a Simple Implicit Trust Inference Model for Memory-Based Collaborative Filtering Recommendation Systems

Electronics ◽  
2019 ◽  
Vol 8 (4) ◽  
pp. 427 ◽  
Author(s):  
Zahir ◽  
Yuan ◽  
Moniz
Keyword(s):  
Collaborative Filtering ◽  
Prediction Accuracy ◽  
Computational Cost ◽  
Recommendation Systems ◽  
Similarity Measures ◽  
Extraction Methods ◽  
Common Interest ◽  
Trust Relationship ◽  
Public Data ◽  
Implicit Trust

Recommendation systems alleviate the problem of information overload by helping users find information relevant to their preference. Memory-based recommender systems use correlation-based similarity to measure the common interest among users. The trust between users is often used to address the issues associated with correlation-based similarity measures. However, in most applications, the trust relationships between users are not available. A popular method to extract the implicit trust relationship between users employs prediction accuracy. This method has several problems such as high computational cost and data sparsity. In this paper, addressing the problems associated with prediction accuracy-based trust extraction methods, we proposed a novel trust-based method called AgreeRelTrust. Unlike accuracy-based methods, this method does not require the calculation of initial prediction and the trust relationship is more meaningful. The collective agreements between any two users and their relative activities are fused to obtain the trust relationship. To evaluate the usefulness of our method, we applied it to three public data sets and compared the prediction accuracy with well-known collaborative filtering methods. The experimental results show our method has large improvements over the other methods.

scholarly journals Enhanced K-Means Clustering Algorithm Using Collaborative Filtering Approach

2017 ◽  
Vol 10 (2) ◽  
pp. 474-479
Author(s):  
Ankush Saklecha ◽  
Jagdish Raikwal
Keyword(s):  
Collaborative Filtering ◽  
Clustering Algorithm ◽  
Clustering Algorithms ◽  
Clustering Approach ◽  
Improving Accuracy ◽  
Accuracy Performance ◽  
Number Of Iterations ◽  
Filtering Approach ◽  
Selection Of

Clustering is well-known unsupervised learning method. In clustering a set of essentials is separated into uniform groups.K-means is one of the most popular partition based clustering algorithms in the area of research. But in the original K-means the quality of the resulting clusters mostly depends on the selection of initial centroids, so number of iterations is increase and take more time because of that it is computationally expensive. There are so many methods have been proposed for improving accuracy, performance and efficiency of the k-means clustering algorithm. This paper proposed enhanced K-Means Clustering approach in addition to Collaborative filtering approach to recommend quality content to its users. This research would help those users who have to scroll through pages of results to find important content.

Application of the turbidity ratio method in the spherical particle size determination in the range m ∈ and α ∈

1979 ◽  
Vol 44 (7) ◽  
pp. 2064-2078 ◽  
Author(s):  
Blahoslav Sedláček ◽  
Břetislav Verner ◽  
Miroslav Bárta ◽  
Karel Zimmermann
Keyword(s):  
Refractive Index ◽  
Spherical Particle ◽  
Ratio Method ◽  
Refractive Indices ◽  
Relative Refractive Index ◽  
Particle Size Determination ◽  
The Individual ◽  
The Given ◽  
Turbidity Ratio ◽  
Selection Of

Basic scattering functions were used in a novel calculation of the turbidity ratios for particles having the relative refractive index m = 1.001, 1.005 (0.005) 1.315 and the size α = 0.05 (0.05) 6.00 (0.10) 15.00 (0.50) 70.00 (1.00) 100, where α = πL/λ, L is the diameter of the spherical particle, λ = Λ/μ1 is the wavelength of light in a medium with the refractive index μ1 and Λ is the wavelength of light in vacuo. The data are tabulated for the wavelength λ = 546.1/μw = 409.357 nm, where μw is the refractive index of water. A procedure has been suggested how to extend the applicability of Tables to various refractive indices of the medium and to various turbidity ratios τa/τb obtained with the individual pairs of wavelengths λa and λb. The selection of these pairs is bound to the sequence condition λa = λ0χa and λb = λ0χb, in which b-a = δ = 1, 2, 3; a = -2, -1, 0, 1, 2, ..., b = a + δ = -1, 0, 1, 2, ...; λ0 = λa=0 = 326.675 nm; χ = 546.1 : 435.8 = 1.2531 is the quotient of the given sequence.

scholarly journals Efficient Graph Collaborative Filtering via Contrastive Learning

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4666
Author(s):  
Zhiqiang Pan ◽  
Honghui Chen
Keyword(s):  
Collaborative Filtering ◽  
State Of The Art ◽  
Representation Learning ◽  
First Order ◽  
Satisfactory Performance ◽  
Potential Applications ◽  
Benchmark Datasets ◽  
Bayesian Personalized Ranking ◽  
Graph Neural Networks ◽  
Training Efficiency

Collaborative filtering (CF) aims to make recommendations for users by detecting user’s preference from the historical user–item interactions. Existing graph neural networks (GNN) based methods achieve satisfactory performance by exploiting the high-order connectivity between users and items, however they suffer from the poor training efficiency problem and easily introduce bias for information propagation. Moreover, the widely applied Bayesian personalized ranking (BPR) loss is insufficient to provide supervision signals for training due to the extremely sparse observed interactions. To deal with the above issues, we propose the Efficient Graph Collaborative Filtering (EGCF) method. Specifically, EGCF adopts merely one-layer graph convolution to model the collaborative signal for users and items from the first-order neighbors in the user–item interactions. Moreover, we introduce contrastive learning to enhance the representation learning of users and items by deriving the self-supervisions, which is jointly trained with the supervised learning. Extensive experiments are conducted on two benchmark datasets, i.e., Yelp2018 and Amazon-book, and the experimental results demonstrate that EGCF can achieve the state-of-the-art performance in terms of Recall and normalized discounted cumulative gain (NDCG), especially on ranking the target items at right positions. In addition, EGCF shows obvious advantages in the training efficiency compared with the competitive baselines, making it practicable for potential applications.

scholarly journals Genomic Prediction and Indirect Selection for Grain Yield in US Pacific Northwest Winter Wheat Using Spectral Reflectance Indices from High-Throughput Phenotyping

2019 ◽  
Vol 21 (1) ◽  
pp. 165 ◽  
Author(s):  
Dennis N. Lozada ◽  
Jayfred V. Godoy ◽  
Brian P. Ward ◽  
Arron H. Carter
Keyword(s):  
Winter Wheat ◽  
Pacific Northwest ◽  
Prediction Accuracy ◽  
Indirect Selection ◽  
Yield Potential ◽  
High Yield ◽  
High Throughput Phenotyping ◽  
Reflectance Indices ◽  
Selection Of ◽  
High Yield Potential

Secondary traits from high-throughput phenotyping could be used to select for complex target traits to accelerate plant breeding and increase genetic gains. This study aimed to evaluate the potential of using spectral reflectance indices (SRI) for indirect selection of winter-wheat lines with high yield potential and to assess the effects of including secondary traits on the prediction accuracy for yield. A total of five SRIs were measured in a diversity panel, and F5 and doubled haploid wheat breeding populations planted between 2015 and 2018 in Lind and Pullman, WA. The winter-wheat panels were genotyped with 11,089 genotyping-by-sequencing derived markers. Spectral traits showed moderate to high phenotypic and genetic correlations, indicating their potential for indirect selection of lines with high yield potential. Inclusion of correlated spectral traits in genomic prediction models resulted in significant (p < 0.001) improvement in prediction accuracy for yield. Relatedness between training and test populations and heritability were among the principal factors affecting accuracy. Our results demonstrate the potential of using spectral indices as proxy measurements for selecting lines with increased yield potential and for improving prediction accuracy to increase genetic gains for complex traits in US Pacific Northwest winter wheat.

scholarly journals Empirical Bayes Inference for the Parameter of Power Distribution Based on Ranked Set Sampling

2015 ◽  
Vol 2015 ◽  
pp. 1-5
Author(s):  
Naiyi Li ◽  
Yuan Li ◽  
Yongming Li ◽  
Yang Liu
Keyword(s):  
Power Distribution ◽  
Empirical Bayes ◽  
Ranked Set Sampling ◽  
Bayes Inference ◽  
Bayes Test

This research is based on ranked set sampling. Through the analysis and proof, the empirical Bayes test rule and asymptotical property for the parameter of power distribution are obtained.

scholarly journals Water-use dynamics of an alien-invaded riparian forest within the Mediterranean climate zone of the Western Cape, South Africa

2017 ◽  
Vol 21 (9) ◽  
pp. 4551-4562 ◽  
Author(s):  
Bruce C. Scott-Shaw ◽  
Colin S. Everson ◽  
Alistair D. Clulow
Keyword(s):  
South Africa ◽  
Water Use ◽  
Sap Flow ◽  
Riparian Forest ◽  
Riparian Forests ◽  
Ratio Method ◽  
Natural State ◽  
Indigenous Species ◽  
Western Cape ◽  
Selection Of

Abstract. In South Africa, the invasion of riparian forests by alien trees has the potential to affect the country's limited water resources. Tree water-use measurements have therefore become an important component of recent hydrological studies. It is difficult for South African government initiatives, such as the Working for Water (WfW) alien clearing program, to justify alien tree removal and implement rehabilitation unless hydrological benefits are known. Consequently, water use within a riparian forest along the Buffeljags River in the Western Cape of South Africa was monitored over a 3-year period. The site consisted of an indigenous stand of Western Cape afrotemperate forest adjacent to a large stand of introduced Acacia mearnsii. The heat ratio method of the heat pulse velocity sap flow technique was used to measure the sap flow of a selection of indigenous species in the indigenous stand, a selection of A. mearnsii trees in the alien stand and two clusters of indigenous species within the alien stand. The indigenous trees in the alien stand at Buffeljags River showed significant intraspecific differences in the daily sap flow rates varying from 15 to 32 L day−1 in summer (sap flow being directly proportional to tree size). In winter (June), this was reduced to only 7 L day−1 when limited energy was available to drive the transpiration process. The water use in the A. mearnsii trees showed peaks in transpiration during the months of March 2012, September 2012 and February 2013. These periods had high average temperatures, rainfall and high daily vapor pressure deficits (VPDs – average of 1.26 kPa). The average daily sap flow ranged from 25 to 35 L in summer and approximately 10 L in the winter. The combined accumulated daily sap flow per year for the three Vepris lanceolata and three A. mearnsii trees was 5700 and 9200 L, respectively, clearly demonstrating the higher water use of the introduced Acacia trees during the winter months. After spatially upscaling the findings, it was concluded that, annually, the alien stand used nearly 6 times more water per unit area than the indigenous stand (585 mm a−1 compared to 101 mm a−1). This finding indicates that there would be a gain in groundwater recharge and/or streamflow if the alien species are removed from riparian forests and rehabilitated back to their natural state.

scholarly journals Oscillatory Biomedical Signals: Frontiers in Mathematical Models and Statistical Analysis

2021 ◽  
Vol 7 ◽  
Author(s):  
Hau-Tieng Wu ◽  
Tze Leung Lai ◽  
Gabriel G. Haddad ◽  
Alysson Muotri
Keyword(s):  
Statistical Analysis ◽  
Empirical Bayes ◽  
Network Formation ◽  
Markov Models ◽  
Hidden Markov ◽  
Biomedical Signals ◽  
Time Frequency ◽  
Bayes Inference ◽  
Cardiorespiratory Patterns ◽  
Parameter Estimators

Herein we describe new frontiers in mathematical modeling and statistical analysis of oscillatory biomedical signals, motivated by our recent studies of network formation in the human brain during the early stages of life and studies forty years ago on cardiorespiratory patterns during sleep in infants and animal models. The frontiers involve new nonlinear-type time–frequency analysis of signals with multiple oscillatory components, and efficient particle filters for joint state and parameter estimators together with uncertainty quantification in hidden Markov models and empirical Bayes inference.

Sign in / Sign up

Export Citation Format

Share Document