Figure - available from: Mathematical Problems in Engineering
This content is subject to copyright. Terms and conditions apply.
Source publication
The fast developing social network is a double-edged sword. It remains a serious problem to provide users with excellent mobile social network services as well as protecting privacy data. Most popular social applications utilize behavior of users to build connection with people having similar behavior, thus improving user experience. However, many...
Similar publications
Data mining is a technique that explores the necessary data is extracted from large data sets. Privacy protection of data mining is about hiding the sensitive information or identity of breach security or without losing data usability. Sensitive data contains confidential information about individuals, businesses, and governments who must not agree...
Citations
... In [81], Gong et al. propose an improved locality-sensitive hashing-based service recommendation method to protect users; privacy over multiple quality dimensions during the distributed mobile network. In [82], Jiang et al. propose a secure friend recommender system without exposing the actual user behavior but the anonymous data to protect privacy data. The anonymous data is from Chinese ISP recording the user browsing behavior. ...
Under the explosive growth of information available on the Web, recommender systems have been used as an effective technology to filter useless information and attempt to recommend the most useful items. The proliferation of smart phones, smart wearable devices and other Internet of Thing (IoT) devices has gradually driven many novel emerging services which are latency-sensitive and computation-intensive with a higher quality-of-service. Under such circumstances, the data sources contain four key characteristics (i.e., sparsity, heterogeneity, mobility, volatility). The conventional recommender systems based on cloud computing are incapable of digging the information of user demands. Mobile edge computing is a novel computing paradigm via pushing computation/storage resource from the remote cloud servers to the network edge servers to provide more intelligent and personalized service. This paper comprehensively reviews the state of the art literature on the convergence of recommender systems and edge computing, and identify the future directions along this dimension. This paper can provide an array of new perspectives on the convergence for researchers, practitioners, and tap into the richness of this interdisciplinary research area.
... The exclusive features of smart mobile devices, such as the ability to provide services to mobile users wherever and whenever they need it (i.e., ubiquity) has enabled MRSs to collect data related to users' transportation means, health, income, mood, location etc. [33]. An MRS collects such information from inbuilt sensors in mobile devices [16,36], installed mobile apps on users' mobile devices [11], call logs, contacts, emails stored in mobile devices [2,49], and users' web browsing histories [17,46]. Although collecting such data enables MRSs to construct better user profiles and provide accurate recommendations, it also violates users' privacy. ...
... In addition to collecting the data from users, MRSs also collect data about the users from mobile apps [11,23,36], in-built sensors [3,6,16,20,34,42,44,47], applications running on mobile devices such as emails or chat messages [2,7], and past records [17,18,35,46]. ...
... Kim et al. [18] proposed an MRS named buying-net that collects information related to items the customer purchased, the prices of the items, and its brand value to construct a user profile. Jiang et al. [17] also use web-browsing history to create user profiles. The MRS collects users' behavior information from their web-browsing records and utilizes a K-nearest neighbors (KNN) classification algorithm to classify users. ...
A mobile recommender (or recommendation) system (MRS) is a type of recommendation system that generates recommendations for mobile users in a mobile Internet environment. An MRS collects users’ information through users’ mobile devices via inbuilt sensors, installed mobile apps, running applications, past records etc. Although collecting such data enables MRSs to construct better user profiles and provide accurate recommendations, it also infringes users’ privacy. This study intends to provide a comprehensive review of privacy concerns associated with data collection in MRSs. This study makes three important contributions. First, it synthesizes the literature on sources of data collection in MRSs. Second, it provides insights into privacy concerns associated with data collection in MRSs. Third, it offers insights into how these privacy issues can be addressed.
... Abnormal/irregular symptom-based [49][50][51] To detect and analyze unknown and zero-day attacks (i) To detect abnormal behavior, this technique collects and integrates logs, which are generated in the system, and analyzes the correlated information (ii) In particular, this is required for detecting infected systems, with unknown new malicious code, and it helps to determine whether transmitted traffic is normal or abnormal (i) In case of security system, if the system does not process information in real time, the system gets exposed to security threats (ii) It is technically difficult to collect and analyze correlation for high-capacity and high-speed traffic from network attack scenarios. This also motivated the need for a common solution which can handle both the identification of zeroday attacks as well as reliable communication during such possibilities. ...
“Internet of Things” (IoT) bridges the communication barrier between the computing entities by forming a network between them. With a common solution for control and management of IoT devices, these networks are prone to all types of computing threats. Such networks may experience threats which are launched by exploitation of vulnerabilities that are left unhandled during the testing phases. These are often termed as “zero-day” vulnerabilities, and their conversion into a network attack is named as “zero-day” attack. These attacks can affect the IoT devices by exploiting the defense perimeter of the network. The existing solutions are capable of detecting such attacks but do not facilitate communication, which affects the performance of the network. In this paper, a consensus framework is proposed for mitigation of zero-day attacks in IoT networks. The proposed approach uses context behavior of IoT devices as a detection mechanism followed by alert message protocol and critical data sharing protocol for reliable communication during attack mitigation. The numerical analysis suggests that the proposed approach can serve the purpose of detection and elimination of zero-day attacks in IoT network without compromising its performance.
... As is frequently the case, there is more than one geodesic between a given pair of vertices. In this situation, a clever solution is to give each geodesic equal weight such that the weights add to unity [12,[26][27][28]. Newman [4] put forward another method assuming that the route of information spreading through is some kind of random walk. ...
We come up with a punishment in the form of exponential decay for the number of vertices that a path passes through, which is able to reconcile the contradictory effects of geodesic length and edge weights. This core thought is the key to handling three typical applications; that is, given an information demander, he may be faced with the following problems: choosing optimal route to contact the single supplier, picking out the best supplier between multiple candidates, and calculating his point centrality, which involves indirect connections. Accordingly, three concrete solutions in one logic thread are proposed. Firstly, by adding a constraint to Dijkstra algorithm, we limit our candidates for optimal route to the sample space of geodesics. Secondly, we come up with a unified standard for the comparison between adjacent and nonadjacent vertices. Through punishment in the form of exponential decay, the attenuation effect caused by the number of vertices that a path passes through has been offset. Then the adjacent vertices and punished nonadjacent vertices can be compared directly. At last, an unprecedented centrality index, quasi-closeness, is ready to come out, with direct and indirect connections being summed up.
The personalized recommender system has become a research hotspot in the field of artificial intelligence (AI) because it can effectively deal with information overload. Cold start and data sparsity are two major challenges for smart recommender systems. This paper proposes an optimized recommender algorithm based on statistics and preference model that is able to solve the problems of data sparsity and cold start by means of statistics. Taking the film scoring system as the test object, the Gaussian model is established for the video type preference. The results show that the optimized algorithm can better deal with cold start and data sparsity, and achieve more accurate prediction recommender score.
With the development of Internet, various social network service (SNS) platforms appeared, such as Facebook, twitter, Flickr, Sina microblog, and so on. Friend recommendation is the key issue for the SNS which can enhance the interactivity among SNS users.A novel recommendation algorithm is proposed in this paper, it applies time line to compute the interactions among target user and his/her recommended friends firstly, which predicts the intimacy trend and fits intimacy with interactive information at different time slots; then a Latent Dirichlet Allocation (LDA) model is used to generate subjects and judge the subject similarities between target user and recommended friends, at last, the two parts have been combined by an information entropy method which adjust the weight information dynastically during the friend recommendation process. Compared with collaborative filtering recommendation algorithm and LDA method, the experimental results proved that the proposed algorithm has got better performance.
