Nowadays, scholar recommender systems often recommend academic papers based on users’ personalized retrieval demands. Typically, a recommender system analyzes the keywords typed by a user and then returns his or her preferred papers, in an efficient and economic manner. In practice, one paper often contains partial keywords that a user is interested in. Therefore, the recommender system needs to return the user a set of papers that collectively covers all the queried keywords. However, existing recommender systems only use the exact keyword matching technique for recommendation decisions, while neglecting the correlation relationships among different papers. As a consequence, it may output a set of papers from multiple disciplines that are different from the user’s real research field. In view of this shortcoming, we propose a keyword-driven and popularity-aware paper recommendation approach based on an undirected paper citation graph, named PR_keyword+pop. At last, we conduct large-scale experiments on the real-life Hep-Th dataset to further demonstrate the usefulness and feasibility of PR_keyword+pop. Experimental results prove the advantages of PR_keyword+pop in searching for a set of satisfactory papers compared with other competitive approaches.

The gradual prevalence of Internet of Things (IoT) and wireless communication technologies has enabled the wide adoption of various smart devices (e.g., smart watches) in provisioning the healthcare services to massive users. Besides monitoring the real-time health signals or conditions of users, smart devices can also record a series of sport-related user information such as user location information at a certain time point. The location sequence information is valuable to cluster the users who share the similar sport preferences or habits and therefore, is also playing a key role in providing wireless healthcare services to these users. However, the user location information is often sensitive to certain wireless users as they decline to reveal their daily sport behavior patterns to others. In this situation, a natural challenge is raised in securing the sensitive user location information while mining the users’ daily sport behavior patterns and provisioning better healthcare services to the users. Considering this challenge, we take advantage of the well-known SimHash technique to protect users’ location privacy while clustering the users who share similar sport preferences or habits for better healthcare services. At last, we validate the feasibility of the proposal through a set of simulated experiments conducted on a real-world dataset. Reported results demonstrate that our solution performs better than the other two competitive ones while securing user location information.

With the wide popularity of various sport items and the continuous prosperity of sport business, player transfer events are becoming more and more frequent, which gives birth to a big player transfer market with attractive attentions of spectators. However, for the purposes of business competition or concerns of privacy disclosure, the multiple parties involved in an identical player transfer event are often reluctant to release the concrete transfer fees of a player as the transfer fee is always sensitive enough for the player himself or herself as well as the involved multiple sport clubs. The hidden player transfer fees block the fair and transparent sport business trades and cheat prospective spectators to some extent, which decreases the spectator trust towards player market value and finally, lowers the spectators' satisfaction towards sport business. In this situation, it is becoming a necessity to develop a trusted player transfer evaluation method supported by all the parties involved in player transfer events. Inspired by this challenging task, a trusted player transfer evaluation method with privacy protection is put forward in this paper, which is mainly based on Locality-Sensitive Hashing (LSH) and Blockchain technologies and named TPTE _LSH+B . At last, a series of simulated experiments are deployed to validate the feasibility of our proposed TPTE _LSH+B algorithm. Experimental results report that TPTE _LSH+B has a good evaluation performance with competitive approaches.

With the ever-increasing popularity of sports and health ideas, people are paying more attentions to gaining high-quality healthy life through various taking various sport items or exercises. Through observing and analyzing the past sport exercise score records, we can cluster the players into different categories, each of which share the same or similar sport preferences or performances. However, the sport exercise score records are often massive and often stored in different cloud platforms, which raise a big difficulty for time-efficient player clustering. Furthermore, the sport exercise score records are a kind of privacy for most players; therefore, it is often not rational or legal to release these sensitive data to the public for similar player clustering purpose. Considering the above two issues, we use SimHash, a kind of privacy-aware approximate neighbor search technique, for similar player clustering by analyzing the sport exercise score records distributed across different cloud platforms. Thus, we can realize privacy-aware similar player clustering through SimHash. At last, we provide a set of experiments to validate the advantages of our proposed privacy-aware similar player clustering algorithm. Reported experimental results show the effectiveness of our proposal in remedying the big data volume and privacy concerns in player clustering based on sport exercise score records.

With the emergence of the "unmanned" field, unmanned supermarket software has entered consumers’ lives in line with the pace of development of the times. Nowadays, developers of unmanned supermarket software often tend to create feature-rich consumer mashup applications by invoking a variety of Web APIs (Application Programming Interfaces) in order to save time and costs. The number of APIs available on edge servers has significantly increased with the rise of mobile edge computing. To cope with the continuous growth in API volume and the increasing diversity of API functions in API sharing communities (e.g., ProgrammableWeb.com), lightweight recommendation techniques have been employed to assist consumer mashup developers in finding their desired Web APIs from a vast pool of candidates. However, during the data processing in edge computing, traditional Web API recommendation approaches often prioritize the accuracy of recommended APIs, neglecting the potential privacy risks associated with disclosure. This significantly reduces the willingness and incentive of consumer mashup developers to share API information, such as historical edge mashup-API invocation records. To address this issue, we propose a privacy-preserving Web API recommendation approach, WARecITQ, based on Iterative Quantification (ITQ). Specifically, we convert the sensitive mashup-API invocation records into less-sensitive mashup indices using Iterative Quantization hash coding. We then utilize these less-sensitive mashup indices as the primary decision-making criteria for Web API recommendations, thereby achieving the goal of completing top-k API recommendations. Lastly, we crawled a real-world dataset of mashup-API invocation records from ProgrammableWeb.com and conducted a series of experiments on the dataset to evaluate performance. The results of the experiments demonstrate the superiority of our WARecITQ approach in multiple performance metrics compared to other related approaches, while ensuring consumer mashup developer privacy.