scholarly journals Enhancing Collaborative Filtering by User-User Covariance Matrix

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Yingyuan Xiao ◽  
Jingjing Shi ◽  
Wenguang Zheng ◽  
Hongya Wang ◽  
Ching-Hsien Hsu
Keyword(s):  
Collaborative Filtering ◽  
Covariance Matrix ◽  
Personalized Recommendation ◽  
Similarity Matrix ◽  
User Similarity ◽  
Filtering Method ◽  
The Past ◽  
Changing Trends ◽  
Over Time

The collaborative filtering (CF) approach is one of the most successful personalized recommendation methods so far, which is employed by the majority of personalized recommender systems to predict users’ preferences or interests. The basic idea of CF is that if users had the same interests in the past they will also have similar tastes in the future. In general, the traditional CF may suffer the following problems: (1) The recommendation quality of CF based system is greatly affected by the sparsity of data. (2) The traditional CF is relatively difficult to adapt the situation that users’ preferences always change over time. (3) CF based approaches are used to recommend similar items to a user ignoring the user’s demand for variety. In this paper, to solve the above problems we build a new user-user covariance matrix to replace the traditional CF’s user-user similarity matrix. Compared with the user-user similarity matrix, the user-user covariance matrix introduces the user-user covariance to finely describe the changing trends of users’ interests. Furthermore, we propose an enhancing collaborative filtering method based on the user-user covariance matrix. The experimental results show that the proposed method can significantly improve the diversity of recommendation results and ensure the good recommendation precision.

Research on Applying User-Based Collaborative Filtering Algorithms to Building Products Selection

2011 ◽  
Vol 339 ◽  
pp. 396-399
Author(s):  
Li Mei Sun ◽  
Fang Jun Luan ◽  
Tian Bo Liu
Keyword(s):  
Decision Support ◽  
Collaborative Filtering ◽  
Personalized Recommendation ◽  
Filtering Algorithms ◽  
Building Products ◽  
Filtering Method ◽  
Construction Products

Nowadays, there are lots of internet-based service platforms about construction products. The building products’ types are too many to select. This paper proposes an algorithm applying user-based collaborative filtering method to building products selection, which implements personalized recommendation with the help of group users’ experience. The algorithm provides decision support to relevant personnel and improves the efficiency and quality of building products selection.

Optimized Collaborative Filtering Recommendation Based on User’s Social Relationships

2014 ◽  
Vol 1044-1045 ◽  
pp. 1484-1488
Author(s):  
Yue Kun Fan ◽  
Xin Ye Li ◽  
Meng Meng Cao
Keyword(s):  
Collaborative Filtering ◽  
Social Relationships ◽  
Digital Libraries ◽  
Social Relationship ◽  
Nearest Neighbor ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Personalized Recommendation ◽  
Recommendation Algorithm

Currently collaborative filtering is widely used in e-commerce, digital libraries and other areas of personalized recommendation service system. Nearest-neighbor algorithm is the earliest proposed and the main collaborative filtering recommendation algorithm, but the data sparsity and cold-start problems seriously affect the recommendation quality. To solve these problems, A collaborative filtering recommendation algorithm based on users' social relationships is proposed. 0n the basis of traditional filtering recommendation technology, it combines with the interested objects of user's social relationship and takes the advantage of the tags to projects marked by users and their interested objects to improve the methods of recommendation. The experimental results of MAE ((Mean Absolute Error)) verify that this method can get better quality of recommendation.

scholarly journals A Triangular Personalized Recommendation Algorithm for Improving Diversity

2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Biao Cai ◽  
Xiaowang Yang ◽  
Yusheng Huang ◽  
Hongjun Li ◽  
Qiang Sang
Keyword(s):  
Collaborative Filtering ◽  
Information Overload ◽  
Personalized Recommendation ◽  
Recommendation Algorithm ◽  
Filtering Method ◽  
Online Databases ◽  
Recommendation Algorithms ◽  
Recommendation Accuracy ◽  
Third Dimension ◽  
Triangular Area

Recommendation systems are used when searching online databases. As such they are very important tools because they provide users with predictions of the outcomes of different potential choices and help users to avoid information overload. They can be used on e-commerce websites and have attracted considerable attention in the scientific community. To date, many personalized recommendation algorithms have aimed to improve recommendation accuracy from the perspective of vertex similarities, such as collaborative filtering and mass diffusion. However, diversity is also an important evaluation index in the recommendation algorithm. In order to study both the accuracy and diversity of a recommendation algorithm at the same time, this study introduced a “third dimension” to the commonly used user/product two-dimensional recommendation, and a recommendation algorithm is proposed that is based on a triangular area (TR algorithm). The proposed algorithm combines the Markov chain and collaborative filtering method to make recommendations for users by building a triangle model, making use of the triangulated area. Additionally, recommendation algorithms based on a triangulated area are parameter-free and are more suitable for applications in real environments. Furthermore, the experimental results showed that the TR algorithm had better performance on diversity and novelty for real datasets of MovieLens-100K and MovieLens-1M than did the other benchmark methods.

scholarly journals Communication-Based Book Recommendation in Computational Social Systems

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Long Zuo ◽  
Shuo Xiong ◽  
Xin Qi ◽  
Zheng Wen ◽  
Yiwen Tang
Keyword(s):  
Collaborative Filtering ◽  
Social System ◽  
Social Systems ◽  
Trust Model ◽  
Personalized Recommendation ◽  
Online Reading ◽  
Application Performance ◽  
User Similarity ◽  
Close Relationship ◽  
Collaborative Filtering Algorithm

This paper considers current personalized recommendation approaches based on computational social systems and then discusses their advantages and application environments. The most widely used recommendation algorithm, personalized advice based on collaborative filtering, is selected as the primary research focus. Some improvements in its application performance are analyzed. First, for the calculation of user similarity, the introduction of computational social system attributes can help to determine users’ neighbors more accurately. Second, computational social system strategies can be adopted to penalize popular items. Third, the network community, identity, and trust can be combined as there is a close relationship. Therefore, this paper proposes a new method that uses a computational social system, including a trust model based on community relationships, to improve the user similarity calculation accuracy to enhance personalized recommendation. Finally, the improved algorithm in this paper is tested on the online reading website dataset. The experimental results show that the enhanced collaborative filtering algorithm performs better than the traditional algorithm.

scholarly journals STREET ANTHROPOLOGY – A CULTURE OF MOBILITY

space&FORM ◽  
2021 ◽  
Vol 45 ◽  
pp. 109-136
Author(s):  
Marek Czyński ◽  
Keyword(s):  
Cultural Identity ◽  
Economic Capital ◽  
Urban Life ◽  
The Past ◽  
Balanced Approach ◽  
Spatial Policy ◽  
Characteristic Features ◽  
Over Time ◽  
Space Of Flows

The street anthropology is identical with the anthropology of urban life. In the past, a street was a place to socialize and, on equal footing with its architecture, it was part of the cultural identity of its inhabitants. The street reflects residents’ social, cultural and economic capital. Over time, mobility and communication accessibility have dominated the urban spatial policy. The contemporary street has become a "space of flows". The restoration of its original role requires a more balanced approach to cultural factors that determine the quality of life in a city. The article discusses characteristic features that determine patterns of mobility in modern streets.

scholarly journals Changing Trends in the Performance of Percutaneous Renal Biopsy from Nephrologist to Interventional Radiologist: A Single-Center Experience

2018 ◽  
Vol 48 (5) ◽  
pp. 326-329 ◽  
Author(s):  
Stephen M. Korbet ◽  
William L. Whittier ◽  
Roger A. Rodby
Keyword(s):  
Renal Biopsy ◽  
Practice Patterns ◽  
Medical Center ◽  
Percutaneous Renal Biopsy ◽  
The Past ◽  
Single Center Experience ◽  
Changing Trends ◽  
Time Burden ◽  
Universal Reason ◽  
Over Time

Background: Percutaneous renal biopsy of native kidneys (PRB) has been an integral part of the practice of nephrology. However, over the past 30 years, PRB has transitioned from a procedure performed only by nephrologists to interventional radiologists (IRs). We surveyed practicing nephrologists completing training in our program to determine the clinical practice patterns of PRB. Methods: The 78 fellows completing the nephrology program at Rush University Medical Center from June 1984 through June 2017 were successfully contacted and surveyed regarding their opinion on adequacy of their training and whether they performed PRB in practice and if not or no longer, why. To evaluate for differences in the performance of PRB over time, a comparison of 4 periods of fellowship completion (i.e., 1984–1990, 1991–2000, 2001–2010, 2011–2017) was performed. Results: All 78 nephrologists felt they had been adequately trained to perform PRB. PRB was performed by 45 (58%) nephrologists post-fellowship, but a significant decline was observed over the 4 periods of time from 1984 to 2017 (100 vs. 86 vs. 52 vs. 20%, p < 0.0001). The primary reason that 33 nephrologists did not perform PRB was that it was too time consuming and IR was available to perform PRB. Of the 71 nephrologists still in practice only 12 (17%) continue to perform PRB. A greater proportion of nephrologists completing training from 1984–1990 continue to perform PRB relative to those trained after 1990. The universal reason that nephrologists were no longer performing PRB was again an issue of time and the fact that IRs were available to perform PRB. Conclusion: We find that there has been a significant transition over time in the performance of PRB by a nephrologist to IR. The major reason for this is the time burden associated with PRB and the availability of IRs.

scholarly journals Deep Matrix Factorization Approach for Collaborative Filtering Recommender Systems

2020 ◽  
Vol 10 (14) ◽  
pp. 4926 ◽  
Author(s):  
Raúl Lara-Cabrera ◽  
Ángel González-Prieto ◽  
Fernando Ortega
Keyword(s):  
Collaborative Filtering ◽  
Recommender Systems ◽  
Matrix Factorization ◽  
Sources Of Information ◽  
Factorization Approach ◽  
Filtering Method ◽  
Layered Architecture ◽  
Fundamental Part ◽  
Many Sources

Providing useful information to the users by recommending highly demanded products and services is a fundamental part of the business of many top tier companies. Recommender Systems make use of many sources of information to provide users with accurate predictions and novel recommendations of items. Here we propose, DeepMF, a novel collaborative filtering method that combines the Deep Learning paradigm with Matrix Factorization (MF) to improve the quality of both predictions and recommendations made to the user. Specifically, DeepMF performs successive refinements of a MF model with a layered architecture that uses the acquired knowledge in a layer as input for subsequent layers. Experimental results showed that the quality of both the predictions and recommendations of DeepMF overcome the baselines.

Measuring the Improving Quality of Outpatient Care in Medical Oncology Practices in the United States

2013 ◽  
Vol 31 (11) ◽  
pp. 1471-1477 ◽  
Author(s):  
Michael N. Neuss ◽  
Jennifer L. Malin ◽  
Stephanie Chan ◽  
Pamela J. Kadlubek ◽  
John L. Adams ◽  
...  
Keyword(s):  
Clinical Information ◽  
The United States ◽  
Measuring Process ◽  
The Past ◽  
The Mean ◽  
Highly Correlated ◽  
American Society ◽  
Oncology Practice ◽  
Over Time

Purpose The American Society of Clinical Oncology Quality Oncology Practice Initiative (QOPI) has provided a method for measuring process-based practice quality since 2006. We sought to determine whether QOPI scores showed improvement in measured quality over time and, if change was demonstrated, which factors in either the measures or participants were associated with improvement. Methods The analysis included 156 practice groups from a larger group of 308 that submitted data from 2006 to 2010. One hundred fifty-two otherwise eligible practices were excluded, most commonly for insufficient data submission. A linear regression model that controlled for varied initial performance was used to estimate the effect of participation over time and evaluate participant and measure characteristics of improvement. Results Participants completed a mean of 5.06 (standard deviation, 1.94) rounds of data collection. Adjusted mean quality scores improved from 0.71 (95% CI, 0.42 to 0.91) to 0.85 (95% CI, 0.60 to 0.95). Overall odds ratio of improvement over time was 1.09 (P < .001). The greatest improvement was seen in measures that assessed newly introduced clinical information, in which the mean scores improved from 0.05 (95% CI, 0.01 to 0.17) to 0.69 (95% CI, 0.33 to 0.91; P < .001). Many measures showed no change over time. Conclusion Many US oncologists have participated in QOPI over the past 6 years. Participation over time was highly correlated with improvement in measured performance. Greater and faster improvement was seen in measures concerning newly introduced clinical information. Some measures showed no change despite opportunity for improvement.

A Novel Similarity Measure Based on Weighted Bipartite Network for Collaborative Filtering Recommendation

2012 ◽  
Vol 263-266 ◽  
pp. 1834-1837 ◽  
Author(s):  
Jian Xun Xia ◽  
Fei Wu ◽  
Chang Sheng Xie
Keyword(s):  
Collaborative Filtering ◽  
Pearson Correlation ◽  
Bipartite Network ◽  
Similarity Matrix ◽  
Data Set ◽  
User Similarity ◽  
Novel Approach ◽  
Weighted Matrix ◽  
Recommendation Algorithms ◽  
Recommendation Accuracy

This paper presents a novel approach to compute user similarity based on weighted bipartite network and resource allocation principle for collaborative filtering recommendation. The key is to calculate the asymmetric user weighted matrix and translate it into a symmetric user similarity matrix. We carry out extensive experiments over Movielens data set and demonstrate that the proposed approach can yield better recommendation accuracy and can partly to alleviate the trouble of sparseness. Compare with traditional collaborative filtering recommendation algorithms based on Pearson correlation similarity and adjusted cosine similarity, the proposed method can improve the average predication accuracy by 6.7% and 0.6% respectively.

scholarly journals UFlow 1.0: A Computer Model for Projections of Urban Sprawl

2020 ◽  
Author(s):  
André Koscianski
Keyword(s):  
Urban Sprawl ◽  
Data Availability ◽  
Complex Nature ◽  
Local Conditions ◽  
The Past ◽  
Reverse Mode ◽  
History Of ◽  
Over Time ◽  
Good Agreement

Abstract. Cities concentrate most of the world’s population and are the stage of difficult problems around logistics, economy, or quality of life, to enumerate just a few. As an object of research on itself, a urban agglomeration is difficult to characterize; it is both an ensemble of various disconnected heterogeneous elements, and the product of numerous actions and effects between those elements. Studies of the structure and the functioning of cities date back to one century ago, with an increased interest in the last decades on the phenomenon of expansion and all of its impacts. Models of city growth face the complex nature of this system and are approximative. Different representations seek to balance characteristics as data availability, level of detail of internal processes, or precision. The uflow model approaches the problem with the metaphor of an abstract field, which evolves over time and signals the conversion from empty to urban cells. The procedure for calibration adjusts parameters according to the history of the region under study, and is able to capture local conditions. The implementation takes advantage of parallel hardware, and the simulation can be performed in reverse mode, a feature that can be useful to verify the adaptation of the tool to a given scenario, or to compute approximations of the past state of a region. Tests confirmed the expected behaviour of the algorithms, and good agreement with actual data. The flexibility of the concept of intensity of urbanization is open to the integration of different data sources into the model, and the possibility of simulating their evolution over time.

Sign in / Sign up

Export Citation Format

Share Document