Hybrid Matrix Factorization Research Articles

AutoMF: A hybrid matrix factorization model with deep learning to select anti-viral drugs for Covid-19

In the wake of the novel Covid-19 disease pandemic, the global economy has been affected and health crises are widespread. The disease is still incurable, and no effective treatment exists for it. During the Covid-19 crisis, drug repurposing has proven to be an effective treatment strategy. Drug repositioning is an approach to finding effective drugs for treating new diseases by discovering new efficacy of existing drugs. Studies on drug-virus association can reveal new efficacy. The antiviral drug repositioning problem is defined here as a matrix completion problem in which antiviral drugs go down the rows, while viruses go down the columns. We propose a hybrid model called AutoMF that identifies new drug–virus association. This new hybrid model aims to develop a matrix factorization model with deep learning and use it to predict drug-virus associations for repositioning drugs. In our model, a heterogeneous drug–virus network is used, which combines drug–virus associations, drug-drug similarity matrix, and virus-virus similarity matrix. Matrix factorization can extract latent factors from the drug-virus associations. The sparse nature of the associations may prevent the latent factors from being very effective. To solve this problem, deep learning is used to learn effective latent representations from similarity matrices to incorporate with MF to enhance their latent factor priors. Our model outperforms several recent approaches in comparison to benchmarking tests performed on the DVA dataset. In our approach, we identify antiviral drugs currently being tested in clinical trials or those used currently to treat patients.

DVO + LCLMF: A web service recommendation mechanism with QoS privacy preservation

AbstractQoS‐aware based web service recommendation is one of the crucial solutions to help users find high‐quality web services. To accurately predict the QoS values of candidate services, it is usually required to collect historical QoS data of users (QoS data for short). If these collected QoS data are improperly processed, QoS data privacy may be threatened. However, how to accurately predict the QoS values of candidate services while protecting QoS data privacy has not been well studied. In response to the situation, we propose a hybrid web service recommendation mechanism, which is divided into three parts. In the first part, the QoS data privacy preservation algorithm, which called DVO, is proposed based on keeping the cosine similarity of QoS data unchanged, that is, to realize the confusion of QoS data while ensuring the availability of QoS data remains unchanged. In the second part, a hybrid matrix factorization model based on location information and service features, which called LCLMF, is proposed to improve the accuracy of QoS values prediction. According to DVO and LCLMF, the DVO + LCLMF is designed in the third part, which can accurately predict QoS values while protecting QoS data privacy. The experimental results show that DVO + LCLMF can accurately predict the QoS values of candidate services on the basis of attaining QoS data privacy protection.

Hybrid matrix factorization recommendation algorithm based on item similarity

In order to solve the problem of sparse data in matrix factorization recommendation algorithm, a hybrid matrix factorization recommendation algorithm based on item similarity is proposed. First of all, Worde2vec is used to mine the content information of items in user’s comment data to get the content similarity of items; secondly, the attribute similarity of items is calculated according to the attribute information of items; then, the content similarity and attribute similarity are fused to get the final item similarity; finally, the similarity of item is integrated into the objective function of matrix factorization algorithm. The experimental results show that the hybrid recommendation algorithm has higher accuracy, recall and coverage than the traditional matrix factorization recommendation algorithm.

A hybrid matrix factorization technique to free the watermarking scheme from false positive and negative problems

Optimization techniques are used in watermarking algorithms to balance the trade-off between the two mutually conflicting parameters-imperceptibility and robustness. Differential Evolution (DE) with Rotational Cross over (RCO), namely DE-RCO, is employed in the proposed algorithm to improve the convergence of optimization. The DE-RCO provides a watermarking scheme with the highest robustness preserving the transparency. The watermark encoding and decoding carried in the transform domain with a hybrid combination of Schur Factorization (SF) and Singular Value Decomposition (SVD). Two-fold security provided with the Digital Signature (DS) generation and B-test. The DS is concealed in the watermarked image for authentication purpose of freeing the algorithm from the false-positive problem. When the signature passed through the insecure channel, it may corrupt and lead to the failure of the A-test, even the correct watermark given at the extraction leading to the false-negative problem. B-test is conducted to free the algorithm from a false negative problem. An enhanced authentication framework designed and implemented to make the algorithm free from the false-positive and false-negative issues using DS and the hash generated by Gaussian Hermite Moments (GHMs). The experimental results compared with the related existing watermarking schemes demonstrate that the proposed scheme exhibit strong robustness to attacks, invisible and highly secure against false-positive and false-negative problems.

Recommender system for modelling subject combination in Ugandan senior secondary schools

Subject combinations at A-level in Ugandan Senior Secondary Schools have made or marred the future career of many prospective students, many students have ended up doing courses they had not planned to do because they made wrong choices at their A-level. This recommender system offers the decision-making process for students based on their subject performance coupled with interest, passion, skills and talents to enable them make right choices. It is person-centred and there are three (3) main actors: the student (who are interested in making appropriate career choice), the documents (which contains available information about interest and passion, skills and talents and subject performances) and access metrics (which aids the student of A-level in extracting knowledge from available resources). A hybrid matrix factorization model using ANFIS and R were used to represents students and subjects as linear combinations derived from their characteristics and interactions, this is combined with rule-based model to offer a unified approach of presenting any student with a list of subjects that will lead to prospective career choices. This offer higher predictive accuracy in career choice matchmaking and overcoming challenges of parental influence, peer influence and others while expanding opportunities of career guidance in Uganda.

A Hybrid Matrix Factorization Method with Isolation Forest for Recommendation System

Matrix Factorization (MF), which is a traditional Collaborative Filtering (CF) technology, has been widely used in recommendation system. MF model relies on exiting user-item ratings, which maybe contains some noise because of intrusion attack, error of log system or mistake of artificial data. In order to detect these data noises and enhances the rating prediction accuracy, we propose a new method, a hybrid matrix factorization technique with Isolation Forest (IForest), which is shown to be highly effective in detecting anomalies with extremely high efficiency. IForest detects anomalies by builds an ensemble of iTrees for a given data set, then anomalies are those instances which have short average path lengths on the iTrees. Extensive experiment results on movieslens (1M) datasets show that our hybrid model outperforms other methods in effectively utilizing side information and achieves performance improvement.

From Reputation Perspective: A Hybrid Matrix Factorization for QoS Prediction in Location-Aware Mobile Service Recommendation System

With the great development of mobile services, the Quality of Services (QoS) becomes an essential factor to meet end users’ personalized requirement on the nonfunctional performance of mobile services. However, most of the QoS values in real cases are unattainable because a service user would only invoke some specific mobile services. Therefore, how to predict the missing QoS values and recommend high-quality services to end users becomes a significant challenge in mobile service recommendation research. Previous QoS prediction researches demonstrate that the nonfunctional performance of mobile services is closely related to users’ location information. However, most location-aware QoS prediction methods ignore the premise that the obtainable QoS values observed by different users in same location region would probably be untrustworthy, which will lead to inaccurate and unreliable prediction results. To make credible location-aware QoS prediction, we propose a hybrid matrix factorization method integrated location and reputation information (LRMF) to predict the unattainable QoS values. Our approach firstly cluster users into different locational region based on their geographical distribution, and then we compute users’ reputation to identify untrustworthy users in every locational region. Finally, the unknown QoS values can be predicted by integrating locational cluster information and users’ reputation into a hybrid matrix factorization model. Comprehensive experiments are conducted on a public QoS dataset which contains sufficient real-world service invocation records. The evaluation results indicate that our LRMF method can effectively reduce the impact of unreliable users on QoS prediction and make credible mobile service recommendation.

IDoctor: Personalized and professionalized medical recommendations based on hybrid matrix factorization

Nowadays, crowd-sourced review websites provide decision support for various aspects of daily life, including shopping, local services, healthcare, etc. However, one of the most important challenges for existing healthcare review websites is the lack of personalized and professionalized guidelines for users to choose medical services. In this paper, we develop a novel healthcare recommendation system called iDoctor, which is based on hybrid matrix factorization methods. iDoctor differs from previous work in the following aspects: (1) emotional offset of user reviews can be unveiled by sentiment analysis and be utilized to revise original user ratings; (2) user preference and doctor feature are extracted by Latent Dirichlet Allocation and incorporated into conventional matrix factorization. We compare iDoctor with previous healthcare recommendation methods using real datasets. The experimental results show that iDoctor provides a higher predication rating and increases the accuracy of healthcare recommendation significantly.