Recommender Systems for the Internet of Things: A Survey

Altulyan, May; Yao, Lina; Wang, Xianzhi; Huang, Chaoran; Kanhere, Salil S; Sheng, Quan Z

doi:10.48550/arxiv.2007.06758

Cited by 5 publications

(8 citation statements)

References 102 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Nearest Neighbors, Decision Trees, Ruled-based Classifiers, Bayesian Classifiers, Artificial Neural Networks, Support Vector Machines, and Association Rule Mining. As a result, choosing the right classifier for a specific recommendation task still requires a lot of exploration [ 24 , 45 , 46 , 48 ]. It also should be noted that it is necessary to start with the simplest ML approach during the experiments.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Product Quality Assessment in the Internet of Things: A Consumer-Oriented Approach

Naem

Koudil

Imam

2022

Sensors

View full text Add to dashboard Cite

This paper proposes a consumer-oriented approach to IoT product recommendations. It is designed to help new consumers choose high-quality IoT products that best meet their needs. We used hybrid techniques to implement the proposed approach. Experiments were also conducted to implement an intelligent IoT marketing system at the Rehab marketplace. The system has shown good results in its performance, usability, and user satisfaction. These results confirm the applicability and effectiveness of the approach in assessing and recommending IoT products.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Regarding the second aspect, the development of recommendation systems for IoT is a new arena that is attracting a number of researchers [ 24 ]. There are endeavors to implement IoTSRS in a variety of IoT domains but they face many challenges compared to traditional recommender systems.…”

Section: Related Workmentioning

confidence: 99%

Product Quality Assessment in the Internet of Things: A Consumer-Oriented Approach

Naem

Koudil

Imam

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…There are many algorithms for learning user's actions like deep learning, machine learning, collaborative filtering, content-based, knowledge-based and context-aware approach (that define the context related to the application by different users) [17]. Context-aware recommendations create better user experiences to improve performance in carrying out activities based on contexts such as location, identity, and actions of users and physical sensors on devices with applications [18], [19]. They are aware of actions, their attributes and possible activities that a user may perform by analyzing the user's behavior and nature of doing various actions [20], [21].…”

Section: Related Work To the Proposed Methodsmentioning

confidence: 99%

Context-aware recommender system for multi-user smart home

Sobhy

Mohamed

Keshk

et al. 2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">Smart home is one of the most important applications of the internet of things (IoT). Smart home makes life simpler, easier to control, saves energy based on user’s behavior and interaction with the home appliances. Many existing approaches have designed a smart home system using data mining algorithms. However, these approaches do not consider multiusers that exist in the same location and time (which needs a complex control). They also use centralized mining algorithm, then the system’s efficiency is reduced when datasets increase. Therefore, in this paper, we firstly build a context-aware recommender system that considers multi-user’s preferences and solves their conflicts by using unsupervised algorithms to deliver useful recommendation services. Secondly, we improve smart home’s responsive using parallel computing. The results reveal that the proposed method is better than existing approaches.</span>

show abstract

“…However, although they make full use of the computing resources of edge servers, which makes a great contribution to reducing network latency [9], they also generate a large amount of edge data, which aggravates the problem of information overload faced by the contemporary era, thus affecting the quality of various services and the user satisfaction [10]. Recommender systems can extract user preferences by using various user behaviors and application data generated on edge devices, so as to generate corresponding recommendations [11]. Unfortunately, the rapid growth of the number of users and the amount of related edge data makes data sparsity a challenging issue of the recommender systems [12][13][14], which severely deteriorates the recommendation performance.…”

Section: Introductionmentioning

confidence: 99%

Edge Data Based Trailer Inception Probabilistic Matrix Factorization for Context-Aware Movie Recommendation

Chen¹,

Li²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The rapid growth of edge data generated by mobile devices and applications deployed at the edge of the network has exacerbated the problem of information overload. As an effective way to alleviate information overload, recommender system can improve the quality of various services by adding application data generated by users on edge devices, such as visual and textual information, on the basis of sparse rating data. The visual information in the movie trailer is a significant part of the movie recommender system. However, due to the complexity of visual information extraction, data sparsity cannot be remarkably alleviated by merely using the rough visual features to improve the rating prediction accuracy. Fortunately, the convolutional neural network can be used to extract the visual features precisely. Therefore, the end-to-end neural image caption (NIC) model can be utilized to obtain the textual information describing the visual features of movie trailers. This paper proposes a trailer inception probabilistic matrix factorization model called Ti-PMF, which combines NIC, recurrent convolutional neural network, and probabilistic matrix factorization models as the rating prediction model. We implement the proposed Ti-PMF model with extensive experiments on three real-world datasets to validate its effectiveness. The experimental results illustrate that the proposed Ti-PMF outperforms the existing ones.

show abstract

Recommender Systems for the Internet of Things: A Survey

Cited by 5 publications

References 102 publications

Product Quality Assessment in the Internet of Things: A Consumer-Oriented Approach

Product Quality Assessment in the Internet of Things: A Consumer-Oriented Approach

Context-aware recommender system for multi-user smart home

Edge Data Based Trailer Inception Probabilistic Matrix Factorization for Context-Aware Movie Recommendation

Contact Info

Product

Resources

About