Hybrid recommendation–based quality of service prediction for sensor services

Abstract

Wireless sensor networks are being the focus of several research application domains, and the concept of sensing-as-a-service is on the rise in wireless sensor networks. Large service repositories comprising more services and functionalities usually impose new challenges to users while identifying their preferred services and may incur higher costs. Thereby, service recommendation systems have become important and integral tools of service models to provide personalized products for consumers. However, many existing methods of sensor service recommendation focus only on service discovery. To this end, this article proposes a novel hybrid recommendation method, named new hybrid recommendation method. First, latent Dirichlet allocation model is used to compute the similarity of the latent topics of the services, and the user’s latent semantic themes are used to extract the potential interest services. Moreover, the relevance of neighbourhood services is considered, which can improve the accuracy of quality of service prediction. Experiments conducted on real datasets demonstrate that the proposed method is more accurate than the existing methods of service recommendation.

An efficient algorithm for link prediction based on local information: Considering the effect of node degree

“…38 There has been some research on learning-based prediction methods. 39 This includes feature-based classification in which a set of appropriate qualities from the network suitable for predictions are extracted, and probabilistic graph-based classification which assigned a node probability value to each node pair. Li and Chen, 40 in their work, offered a graph kernel-based learning algorithm that uses features like education, age, book title, and keywords to predict user-item links in a bipartite network.…”

Neighborhood-aware web service quality prediction using deep learning

“…CF has been widely used in various commercial recommendation systems [22,23]. Breese et al [24] proposed a user-based CF method.…”

Data-Driven Diffusion Recommendation in Online Social Networks for the Internet of People

“…Recommendation systems have been a popular research topic which has attracted attention worldwide [5,6]. Existing research on recommendation systems exploits emerging technologies such as, cloud computing [7], software engineering [8] and service-oriented computing [9], most of such approaches rely on QoS based strategies [9][10][11]. Major researches in recommendation algorithms can be divided into three main categories such as Collaborative Filtering (CF) [12], Content-Based Filtering [13], and Hybrid Recommendation approach [14].…”

“…To control the system from overspecializing on certain objects, collaborative filtering has been developed believing that similar users usually have similar interests. Furthermore, the hybrid recommendation method exploits the merits of both collaborative and contentbased approaches by combining them to avail personalized services to users, thereby overcoming the issues of cold start exists in many existing methods, and to achieve diversity in service recommendation [9]. However, balancing the emphasis given to the contents and collaboration whilst identifying services in the hybrid approach is still an open issue.…”