The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Collaborative filtering is widely used in recommender systems. When training data are extremely sparse, neighbor selection methods work ineffectively. To address this issue, this paper proposes a distributed representation model that represents users as low-dimensional vectors for neighbor selection by considering the chronological order of users' ratings. Experiments show that the proposed method...
One of the most important and challenging problems in recommendation systems is that of modeling temporal behavior. Typically, modeling temporal behavior increases the cost of parameter inference and estimation. Along with it, it also poses the constraint of requiring a large amount of data for reliably learning the parameters of the model. Therefore, it is often difficult to model temporal behavior...
Personalized recommendations can effectively solve the data explosion problem in network. Most existing works utilize rating information to reduce the score prediction error, e.g. MAE; however, users prefer a list of top-k items and minimizing MAE does not always result in better top-k item lists. Meanwhile, because of data sparse problem, social connections among users play an increasingly important...
We propose a novel personalized recommendation model for social network users based on location computing. The novelty of our model is that we deal with the location based recommendation by combing logistic regression with collaborative filtering method. The logistic regression is used to train the weights of items' features, i.e., the recommendation sort list. On the other hand, the collaborative...
Rating prediction is a key task of e-commerce recommendation mechanisms. Recent studies in social recommendation enhance the performance of rating predictors by taking advantage of user relationships. However, these prediction approaches mostly rely on user personal information which is a privacy threat. In this paper, we present dTrust, a simple social recommendation approach that avoids using user...
E-learning is a modality of education that has been growing all over the world. However, in computing and engineering education programs, the frequent use of graphical representations creates obstacles to the inclusion of visually impaired learners. Besides, many of the strategies and tools used in traditional lectures are not appropriated in e-learning lectures because of the distance among participants...
Filtering recommendation system is always key and hot point in electronic commerce research; to obtain recommendation result with high accuracy, performance, universality and strong adaptation, improve recommended efficiency and veracity of collaborative filtering recommendation system and provide more personalized recommendation service for users, a kind of collaborative filtering recommendation...
We are witnessing a rising role of mobile computing and social networks to perform all sorts of tasks. This way, social networks like Twitter or Telegram are used for leisure, and they frequently serve as a discussion media for work-related activities. In this paper, we propose taking advantage of social networks to enable the collaborative creation of models by groups of users. The process is assisted...
Personalized e-learning systems are mainly structured based on two basic models: domain model and user model. When considering personalization in a collaborative environment with user-generated content via Web 2.0 technologies, the task of generating the models is very challenging. This paper presents an approach to extract information related to the domain model and user model for the purpose of...
This paper presents an application of the formal method to model and verifies the communication and control for a fleet of collaborative autonomous underwater vehicles (AUV) named as Eco-Dolphin. The fleet includes YellowDolphin, BlueDolphin, and RedDolphin, which are designed to collect environmental data and provide surveillance services in littoral water. The system architecture of the fleet is...
Modelling is a crucial step for analyzing the data. Graph is an important modelling technique for some areas especially if the data has some kind of relation between each other like complex networks. There are plenty of study in complex network area which uses graphs as a modelling tool. Collaboration networks are a kind of complex evolving networks. Also community detection and evaluation is an important...
Domain-specific languages (DSLs) are small languages tailored to a certain application area, like logistics, web application testing or smart city planning. Traditionally, the use of DSLs has been limited to a static setting in desktop or web editors. However, in this paper, we claim that DSLs can be central components of mobile collaborative applications. In our vision, graphical DSLs can be extended...
The collaborative recommendation mechanism is beneficial for the subject in an open network to find efficiently enough referrers who directly interacted with the object and obtain their trust data. The uncertainty analysis to the collected trust data selects the reliable trust data of trustworthy referrers, and then calculates the statistical trust value on certain reliability for any object. After...
Recommendation systems employed on the Internet aim to serve users by recommending items which will likely be of interest to them. The recommendation problem could be cast as either a rating estimation problem which aims to predict as accurately as possible for a user the rating values of items which are yet unrated by that user, or as a ranking problem which aims to find the top-k ranked items that...
Modeling of data is an important step in process of interpreting the data and to understand the desired situation more clearly. The topic of social network structures is one of the highly studied subject and modeling is very important for social network mining. One of the modeling tools for such structures is Graphs. Graphs have been used for modeling and visualization tool of many structures such...
With the wide adoption of the Internet, organizations establish collaborative networks to execute Collaborative Business Processes (CBPs). Current approaches of Process-Aware Information Systems (PAISs) to implement and execute CBPs have shortcomings: high costs and complexity of IT infrastructure to deploy the PAISs; poor support for autonomy, decentralization, global view of message exchange and...
The single teaching mode will do harm to students' interest in learning for some reasons. This study presents a novel hybrid teaching method that integrating Massive Online Open Course (MOOC) and Small Private Online Course (SPOC) into the physical classroom on fundamentals of computer courses in college. Firstly, the authors present a framework of problem-driven learning methods for fundamentals...
The large-scale construction of MOOC curriculum is an opportunity and a challenge to the teaching mode reform of university computer in ordinary colleges and universities. This paper first analyzes the urgency of the “basic requirement” proposed teaching content reform to promote the needs of MOOC courses in ordinary colleges and universities; Second, leveraging the elite, build MOOC courses in collaboration...
Recommender systems are becoming the crystal ball of the Internet because they can anticipate what the users may want, even before the users know they want it. However, the machine-learning algorithms typically involved in the training of such systems can be computationally expensive, and often may require several days for retraining. Here, we present a distributed approach for load-balancing the...
Sparse Linear Method (SLIM) recommendation algorithm is developed for Top-N recommender system, which has better performance than existing algorithms. However, the limitation of the algorithm is that only the similarity between items evaluated by at least one user can be calculated. In this paper, we propose a method based on similar user set to improve the performance of SLIM algorithm. We calculate...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.