Security-Driven hybrid collaborative recommendation method for cloud-based iot services

Meng, Shunmei; Gao, Zijian; Li, Qianmu; Wang, Hao; Dai, Hong-Ning; Qi, Lianyong

doi:10.1016/j.cose.2020.101950

Cited by 21 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to transmission delay, recent blockchain configurations cannot be adjusted to a huge number of data per second [13]. This is indeed a critical gap for e-commerce recommender systems, like those used by social networking sites [37][38][39][40]. That needs to be prepared to accommodate huge following, billions of products, and individual needs that arrive in streaming sites, and provide recommendations in microseconds Furthermore, decentralized recommendation systems have indeed been formulated to overcome issues faced in classical recommendation systems with a centralized power (which operates as a secure connection with ultimate control over the recommender system) by distributing independence and control to subscribers.…”

Section: Limitations Of Blockchain Applicationmentioning

confidence: 99%

Blockchain-Based Recommendation System: A Review Focusing On Security Aspect

Anaam,

Haw,

Naveen

et al. 2023

AAIML

View full text Add to dashboard Cite

Recently, blockchain technology has caused considerable interest in academic research in the recommendation system domain. These records frequently contain encryption to achieve a comprehensive and reliable recommendation system. These records frequently contain encryption keys. Additionally, recommendation systems concerning suitable evaluation metrics are crucial to providing an accurate recommender system. Despite the attempts to address these issues through various strategies, very few researchers have considered a success in encrypting, especially in safeguarding the subscribers’ data. Currently, blockchain technology has drawn a lot of interest amongst several researchers, including in the area of recommendation system. To define these gaps, the current study aims to review the adoption of blockchain as one significant upside plan to increase data protection in recommendation systems. The systematic literature review (SLR) method was used to analyze publications from different electronic databases and documents of studies from 2019 to 2022. This research contributed to an in-depth comprehension of blockchain-based security techniques for recommending systems in addition to offering an overview of currently available blockchainbased programs within industries. The report emphasizes and examines significant facts and information about the blockchain depends security techniques for recommendation networks. Researchers highlight interest in a higher rate of security data and highlight noteworthy elements determined by an independent evaluation technique

show abstract

Section: Limitations Of Blockchain Applicationmentioning

confidence: 99%

Blockchain-Based Recommendation System: A Review Focusing On Security Aspect

Anaam,

Haw,

Naveen

et al. 2023

AAIML

View full text Add to dashboard Cite

show abstract

“…Existing artwork recommendation research mainly focuses on the recommendation of a single artwork to a potential user but neglects the more practical but complex recommendation scenarios in which the recommender system needs to return a set of artworks instead of a single artwork. In this situation, the quality of experience (QoE) of potential users is reduced considerably, especially when they need a group of related artworks (i.e., an artwork composition) instead of a single artwork [6][7][8][9] . For example, Fig.…”

Section: Introductionmentioning

confidence: 99%

Composite Recommendation of Artworks in E-Commerce Based on User Keyword-Driven Correlation Graph Search

Zhang,

Zhu,

Ahn

et al. 2024

Tsinghua Sci. Technol.

View full text Add to dashboard Cite

With the ever-increasing diversification of people's interests and preferences, artwork has become one of the most popular commodities or investment goods in E-commerce, and it increasingly attracts the attention of the public. Currently, many real-world or virtual artworks can be found in E-commerce, and finding a means to recommend them to appropriate users has become a significant task to alleviate the heavy burden on artwork selection decisions by users. Existing research mainly studies the problem of single-artwork recommendation while neglecting the more practical but more complex composite recommendation of artworks in E-commerce, which considerably influences the quality of experience of potential users, especially when they need to select a set of artworks instead of a single artwork. Inspired by this limitation, we put forward a novel composite recommendation approach to artworks by a user keyword-driven correlation graph search named ART com-rec . Through ART com-rec , the recommender system can output a set of artworks (e.g., an artwork composite solution) in E-commerce by considering the keywords typed by a user to indicate his or her personalized preferences. Finally, we validate the feasibility of the ART com-rec approach by a set of simulated experiments on a real-world PW dataset.

show abstract

“…On 15 March 2019, Xu et al proposed an algorithm for determining the independent degree between different classification sets that is based on Gaussian cores [9]. In 2020, Meng et al proposed a security-driven hybrid collaborative recommendation method for a cloud-based IoT service [10]. Even though a CF-based recommendation is simple to apply, it has a few favorable features, such as high computing costs for large user numbers and low accuracy in the existence of sparsity, as well as difficulty in explaining [11].…”

Section: Introductionmentioning

confidence: 99%

Variational Inference for a Recommendation System in IoT Networks Based on Stein’s Identity

et al. 2022

View full text Add to dashboard Cite

The recommendation services are critical for IoT since they provide interconnection between various devices and services. In order to make Internet searching convenient and useful, algorithms must be developed that overcome the shortcomings of existing online recommendation systems. Therefore, a novel Stein Variational Recommendation System algorithm (SVRS) is proposed, developed, implemented and tested in this paper in order to address the long-standing recommendation problem. With Stein’s identity, SVRS is able to calculate the feature vectors of users and ratings it has generated, as well as infer the preference for users who have not rated certain items. It has the advantages of low complexity, scalability, as well as providing insights into the formation of ratings. A set of experimental results revealed that SVRS performed better than other types of recommendation methods in root mean square error (RMSE) and mean absolute error (MAE).

show abstract

Security-Driven hybrid collaborative recommendation method for cloud-based iot services

Cited by 21 publications

References 49 publications

Blockchain-Based Recommendation System: A Review Focusing On Security Aspect

Blockchain-Based Recommendation System: A Review Focusing On Security Aspect

Composite Recommendation of Artworks in E-Commerce Based on User Keyword-Driven Correlation Graph Search

Variational Inference for a Recommendation System in IoT Networks Based on Stein’s Identity

Contact Info

Product

Resources

About