Recommender systems provide personalized service support to users by learning their previous behaviors and predicting their current preferences for particular products. Artificial intelligence (AI), particularly computational intelligence and machine learning methods and algorithms, has been naturally applied in the development of recommender systems to improve prediction accuracy and solve data sparsity and cold start problems. This position paper systematically discusses the basic methodologies and prevailing techniques in recommender systems and how AI can effectively improve the technological development and application of recommender systems. The paper not only reviews cutting-edge theoretical and practical contributions, but also identifies current research issues and indicates new research directions. It carefully surveys various issues related to recommender systems that use AI, and also reviews the improvements made to these systems through the use of such AI approaches as fuzzy techniques, transfer learning, genetic algorithms, evolutionary algorithms, neural networks and deep learning, and active learning. The observations in this paper will directly support researchers and professionals to better understand current developments and new directions in the field of recommender systems using AI.
The vessel monitoring data provide important information for people to understand the vessel dynamic status in real time and make appropriate decisions in vessel management and operations. However, some of the essential data may be incomplete or unavailable. In order to recover or predict the missing information and best exploit the vessels monitoring data, this paper combines statistical analysis, data mining and neural network methods to propose a multi-task analysis and modelling framework for multi-source monitoring data of inland vessels. Specifically, an advanced neural network, Long Short-Term Memory (LSTM) was tailored and employed to tackle three important tasks, including vessel trajectory repair, engine speed modelling and fuel consumption prediction. The developed models have been validated using the real-life vessel monitoring data and shown to outperform some other widely used modelling methods. In addition, statistics and data technologies were employed for data extraction, classification and cleaning, and an algorithm was designed for identification of the vessel navigational state.
Since the transfer learning can employ knowledge in relative domains to help the learning tasks in current target domain, compared with the traditional learning it shows the advantages of reducing the learning cost and improving the learning efficiency. Focused on the situation that sample data from the transfer source domain and the target domain have similar distribution, an instance transfer learning method based on multisource dynamic TrAdaBoost is proposed in this paper. In this method, knowledge from multiple source domains is used well to avoid negative transfer; furthermore, the information that is conducive to target task learning is obtained to train candidate classifiers. The theoretical analysis suggests that the proposed algorithm improves the capability that weight entropy drifts from source to target instances by means of adding the dynamic factor, and the classification effectiveness is better than single source transfer. Finally, experimental results show that the proposed algorithm has higher classification accuracy.
A practical probabilistic data association filter is proposed for tracking multiple targets in clutter. The number of joint data association events increases combinatorially with the number of measurements and the number of targets, which may become computationally impractical for even small numbers of closely located targets in real target-tracking applications in heavily cluttered environments. In this paper, a Markov chain model is proposed to generate a set of feasible joint events (FJEs) for multiple target tracking that is used to approximate the multi-target data association probabilities and the probabilities of target existence of joint integrated probabilistic data association (JIPDA). A Markov chain with the transition probabilities obtained from the integrated probabilistic data association (IPDA) for single-target tracking is designed to generate a random sequence composed of the predetermined number of FJEs without incurring additional computational cost. The FJEs generated are adjusted for the multi-target tracking environment. A computationally tractable set of these random sequences is utilized to evaluate the track-to-measurement association probabilities such that the computational burden is substantially reduced compared to the JIPDA algorithm. By a series of simulations, the track confirmation rates and target retention statistics of the proposed algorithm are compared with the other existing algorithms including JIPDA to show the effectiveness of the proposed algorithm.
The recommender systems provide users with what they prefer and filter unnecessary information. In the fierce marketing environment, it is crucial to recommend items to users in an early stage to keep user's interests and loyalty. With the fast product renewal, classical recommendation methods such as collaborative filtering cannot handle the cold-start item problem. In many real-world applications, content information of items or users is available and can be used to assist recommendation. Besides, user may interact with the items in different behaviors such as view, click or subscribe. How to use the complex content information and multiple user behaviors are real problems that are not well solved in applications. In this paper, we propose a content-based recommender system to deal with the practical problem. Boosting tree model also added to the system to avoid potential Spam. We applied our developed method to real-estate application to recommend new property which just landed into the market to users. Experimental results with three data subsets and three recommendation scenarios demonstrate that the proposed method can outperform the baseline on recommendation accuracy. The results indicate that our method can effectively reduce potential Spam to users, so that user experience will be improved.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.