Search

The inability to choose an excellent service recommended by a system simply because it is not available is common when people use service recommendation systems. Traditional research on recommendation systems has focused on the user profile, QoS(Quality of Service), and SLA (Service-Level Agreement). However, if the recommended resources are not immediately available, users will not hesitate to move on because they are not tolerant of long waiting times or waiting queues. In the long run, the frequent occurrence of such cases affects the users' perception of the recommendation system and even the recommended services offered, which is the major hindrance to improving the rate of conversion of the results of a recommendation system. This paper proposes a model to assess service availability based on user tolerance. The availability of a given service is calculated by using the waiting time for it as well as the varying tolerances that different people have to the waiting time. We carried out a controlled experiment on a representative population that helped obtain the representations of the user tolerance of different groups by using disordered multi-nomial classification-based logistic regression. Following this, the traditional queuing model is improved by using this representation to formulate a more personalized method to analyze service availability. The results of this analysis can also be used to improve the traditional recommendation algorithm. To prove the effectiveness of this modification, the authors conducted validation on the same controlled population as above through computational experiments. The results show that the SAAM (Service Availability Assessment Model Based on User Tolerance) can significantly reduce the rate of user loss and waiting times compared with the traditional queuing model, which does not consider user tolerance. [ABSTRACT FROM AUTHOR]

In recent years, the world has witnessed the increased maturity of service-oriented computing. The mashup, as one of the typical service-based applications, aggregates contents from more than one source into a single user interface. Facing the rapid growth of the number of web services, choosing appropriate web services for different mashup sources plays an important issue in mashup development, when, in particular, the new mashup is developed from the scratch. To solve this cold start problem when creating new mashups, we propose a web Service Recommendation approach for Mashup creation based on Graph network, called SRMG. SRMG makes service recommendation based on service characteristics and historical usage. It first leverages Bidirectional Encoder Representations from Transformers, to intelligently discover mashups with similar functionalities based on specifications. Afterward, it employs GraphGAN to obtain representation vectors for mashups and services based on historical usage, and further obtains mashup preferences for each service based on representation vectors. Finally, the new mashup's preference for target services is derived from the preference of existing mashups that are similar to it. The extensive experiments on real datasets from ProgrammableWeb demonstrate that SRMG is superior to the state-of-the-art ones. [ABSTRACT FROM AUTHOR]

The era of everythingasaservice led to an explosion of services with similar functionalities on the internet. Quickly obtaining a high-quality service has become a research focus in the field of service recommendation. Studies show that quality of service (QoS) predictions are an effective way to discover services with high quality. However, sparse data and performance fluctuation challenge the accuracy and robustness of QoS prediction. To solve these two challenges, this paper proposes a location-based deep factorization machine model, namely LDFM, by employing information entropy and location projection of users and services. Particularly, our LDFM can be decomposed into three phases: i) extending a raw QoS dataset without introducing additional information, where LDFM projects the existing users (services) in the direction of their position vectors to increase the number of users (services) as well as the number of records that users invoke services; ii) mining a sufficient number of potential features behind the behaviors of users who invoke services, where LDFM employs a factorization machine to extract potential features of breadth with low dimensions (i.e., one and two dimensions) and utilizes deep learning to seek potential depth features with high dimensions; and iii) weighting extracted features within various dimensions, where LDFM employs information entropy to strengthen the positive effects of valid features while reducing the negative impacts generated by biased features. Our experimental results (including t-test analyses) show that our proposed LDFM always performs well under different user-service matrix densities and performs better than existing start-of-the-art methods in terms of the accuracy and robustness of QoS predictions. [ABSTRACT FROM AUTHOR]

During the recent years, several new Information and Communication Technology solutions have been developed in order to meet the increasing needs of elderly with cognitive impairments and support their autonomous living. Most of these solutions follow a human-centred paradigm that aims to provide users with personalised services according to their needs by also ensuring their safety with mechanisms that can automatically trigger appropriate actions in situations where there may be a risk for an elderly. The present paper presents a hybrid matchmaking approach that uses efficiently both a rule-based and a statistical matchmaker in order to (a) propose ambient assisted living services to the end-users, based on their role, status and context of use and (b) identify and resolve problematic cases by automatically selecting the most proper set of services to be called in a single or combined manner. [ABSTRACT FROM AUTHOR]

The rise of high-quality cloud services has made service recommendation a crucial research question. Quality of Service (QoS) is widely adopted to characterize the performance of services invoked by users. For this purpose, the QoS prediction of services constitutes a decisive tool to allow end-users to optimally choose high-quality cloud services aligned with their needs. The fact is that users only consume a few of the broad range of existing services. Thereby, perform a high-accurate service recommendation becomes a challenging task. To tackle the aforementioned challenges, we propose a data sparsity resilient service recommendation approach that aims to predict relevant services in a sustainable manner for end-users. Indeed, our method performs both a QoS prediction of the current time interval using a flexible matrix factorization technique and a QoS prediction of the future time interval using a time series forecasting method based on an AutoRegressive Integrated Moving Average (ARIMA) model. The service recommendation in our approach is based on a couple of criteria ensuring in a lasting way, the appropriateness of the services returned to the active user. The experiments are conducted on a real-world dataset and demonstrate the effectiveness of our method compared to the competing recommendation methods. [ABSTRACT FROM AUTHOR]

With the proliferation of smartphones and an increasing number of services provisioned by clouds, mobile edge computing (MEC) is emerging as a complementary technology of cloud computing. It could provide cloud resources and services by local mobile edge servers, which are normally nearby users. However, a significant challenge is aroused in MEC because of the mobility of users. User trajectory prediction technologies could be used to cope with this issue, which has already played important roles in service recommendation systems with MEC. Unfortunately, little attention and work have been given in service recommendation systems considering users mobility. Thus, in this paper, we propose a mobility-aware personalized service recommendation (MPSR) approach based on user trajectory and quality of service (QoS) predictions. In the proposed method, users trajectory is firstly discovered by a hybrid long-short memory network. Then, given users trajectories, service QoS is predicted, considering the similarity of different users and different edge servers. Finally, services are recommended by a center trajectory strategy through MPSR. Experimental results on a real dataset show that our proposed approach can outperform the traditional recommendation approaches in terms of accuracy in mobile edge computing. [ABSTRACT FROM AUTHOR]

Due to technological advancement, cloud computing is an inevitable form of computing these days and is considered a boon to mid-scale industries. As the usage of cloud computing increases day-by-day, the service deployment improves every single day, which paves the way for security threats as well. Finding trustworthy service is a highly challenging problem, which may lead to time consumption or end with inappropriate services. Due to this problem, end user needs trust based appropriate service with minimum time consumption and the service should be reliable too. Hence, a cloud service recommendation system is the current need of the cloud environment. From a pool of available cloud services, the proposed system can recommend the time conserving reliable trustworthy services. This work attempts to keep this as the goal and presents a cloud service recommendation system using clustering based trust degree computation algorithm. Trust measures are deliberating to compute the trust degree (TD) for each dynamic service, which is computed for every time and the historical information is maintained as well. Since the trust agent clustered the services in automated fashion, to isolates the most trustworthy services from all the available clustered cloud services and efficiently allocates services to the end user using trustworthy service allocation algorithm. Process of service search and recommendation needs minimum time consumption. Registering service with trust agent (TA) provides most reliable trust worthy services. The performance of this recommendation system is evaluated in terms of precision, recall, F-measure and time consumption rates. The average F-measure rate of the proposed work is computed by varying the count of users from 200 to 300 and the average F-measure rate is 91.85% with minimal time consumption than the existing approaches. [ABSTRACT FROM AUTHOR]

Owing to the rapid proliferation of service technologies in cross-enterprise manufacturing collaborations, manufacturing service composition (MSC) has attracted much attention from both academia and industries. However, the existing service composition is often constructed by the combination of off-line and on-line services, quality of service (QoS) attributes are not appropriate for satisfying the specific demands of MSC. Moreover, there are very few historical QoS invocations of manufacturing service, leading to difficulty in recommending appropriate service composition to a target user. In order to find the personalized MSC mode from a complex service network more accurately, we combine combinatorial optimization with collaborative filtering in this paper to figure out two questions: (1) how to construct a QoS description model of manufacturing service composition; (2) how to enhance the effectiveness of personalized QoS-aware service composition recommendations. First, the new QoS model of MSC is proposed by considering both traditional characteristics (e.g. availability, performance and reliability), variability of service composition and enterprise dimensional QoS attributes. Second, the service combination optimization is constructed based on combinatorial optimization method. Third, the collaborative filtering is employed to calculate the missing QoS values of the candidate manufacturing services. Finally, with both available objective functions and predicted QoS values, optimal service composition recommendation can be generated by using combinatorial optimization model with QoS constraints. [ABSTRACT FROM AUTHOR]

With the rapid development of cloud manufacturing (CMfg), quality-of-service (QoS) prediction becomes increasingly important in CMfg service platform because it turns out to be impractical to acquire all service QoS values. In this paper, we present a neighbourhood enhanced matrix factorization approach to predict missing QoS values. We first systematically consider geographical information, sample set diversity computation and platform context to extend basic Pearson Correlation Coefficient (PCC) similarity and extract neighbourhood information. Then, we integrate neighbourhood information into matrix factorization (MF) and make prediction of missing values. Compared with existing methods, the proposed method has the following new features: (1) entropy information is adopted to derive personal weights for different users or services when computing PCC similarity; (2) location information and sample set similarity are considered to enhance PCC similarity; (3) topology information is introduced to address data sparsity issue; (4) neighbourhood information is incorporated with MF to improve prediction accuracy. We conduct an experiment on a real-world dataset which includes web service invocations from 339 service users on 5825 services to verify the feasibility and efficiency of our method. [ABSTRACT FROM AUTHOR]

Service recommendation aims to help users to find the most suitable Web services based on their quality of service (QoS) preferences instead of searching through extensive volume of Web services using search engine manually. Accurate unknown QoS rating prediction is one of the key challenges in the analysis of service recommendation. Collaborative filtering (CF) is a well-known recommendation method that estimates missing ratings by employing a set of similar users to the active user. The core idea of CF consists of picking out an appropriate set of users and using them in the rating prediction process. However, the majority of existing CF methods are not well-designed for Web service QoS prediction as they ignore the implicit but important characteristic of Web service QoS data that fluctuate in big-range. In other words, through analysis of real-world QoS datasets, we observed that QoS ratings vary widely and they are highly skewed with large variances, as two main facts, which dramatically degrade the accuracy of CF methods in QoS prediction. Towards this problem, in this paper, we propose a big-range aware collaborative filtering approach dubbed BRACF to predict Web service QoS ratings accurately. Specifically, since big-range of QoS data can lead to similarity exaggeration, we design a simple yet effective similarity model which considers the influence of big-range among users' QoS data for accurately characterizing the similarity between users. Moreover, the similarity model is seamlessly incorporated into CF model for identifying similar neighbor using Top-K strategy and then it generates QoS predictions by combining bias information. Through extensive experiments on two public real-world Web service QoS for datasets, as response time and throughput, we show that BRACF significantly outperforms state-of-the-art CF methods. We believe that this work demonstrates the potential impact of big range data for the accurate QoS prediction. [ABSTRACT FROM AUTHOR]

Along with the popularity of intelligent services and mobile services, service recommendation has become a key task, especially the task based on quality-of-service (QoS) in edge computing environment. Most existing service recommendation methods have some serious defects, and cannot be directly adopted in edge computing environment. For example, most of existing methods cannot learn deep features of users or services, but in edge computing environment, there are a variety of devices with different configurations and different functions, and it is necessary to learn deep features behind those complex devices. In order to fully utilize hidden features, this paper proposes a new matrix factorization (MF) model with deep features learning, which integrates a convolutional neural network (CNN). The proposed mode is named Joint CNN-MF (JCM). JCM is capable of using the learned deep latent features of neighbors to infer the features of a user or a service. Meanwhile, to improve the accuracy of neighbors selection, the proposed model contains a novel similarity computation method. CNN learns the neighbors features, forms a feature matrix and infers the features of the target user or target service. We conducted experiments on a real-world service dataset under a batch of cases of data densities, to reflect the complex invocation cases in edge computing environment. The experimental results verify that compared to counterpart methods, our method can consistently achieve higher QoS prediction results. [ABSTRACT FROM AUTHOR]

Internet of things (IoT) which has become widespread in various fields leads to a great variety in the provision of services to users. This variety in IoT services in turn pose challenges for users regarding their selections of appropriate services. Appropriate and proper service selection results in a better user satisfaction. In this regard, recommender systems (RS) are developed which help users to choose among various IoT services. Each user has his own characteristics in terms of profile and previous service selection, thus, customized methods should be proposed based on each user's own characteristics and service interests. In this paper, for an IoT environment, which includes a large number of objects, services and users, some service RSs are proposed. In the proposed RSs, user profiles and previous users' activities (in terms of service usage) are used based on which a binary decision tree has been made. The created decision tree is used for user classification in terms of their profile and service interest. The output of each RS is then ranked and combined using ensemble learning techniques, which improve the accuracy and efficiency of the recommendations. The result of ensemble learning is thus customized according to each user profile and service interest. The proposed RS is evaluated on a collected dataset and results confirm the high efficiency of the method presented in this research. [ABSTRACT FROM AUTHOR]

The strong integration of technology in the physical world caused the emergence of smart environments. These environments are supposed to improve the quality of life of their users by providing them with customized services when needed and adapting to their changing needs. The dynamics of the users, the huge number of available services and the strong collaboration between the stakeholders, make traditional service-oriented approaches incapable of providing relevant services to the users in these environments. To deal with these issues, we propose a recommendation-based system for service composition targeting smart environments. The proposed system is able to capture the situation of the users through the analysis of their context information, which in turn allows the system to capture their requirements and select the appropriate service models to satisfy their needs. Then, based on the invocation log, the system implements two recommendation policies. First, it selects the best services in terms of QoS that satisfy the captured requirements. Second, the system recommends new tasks to be integrated in existing service models. The conducted experiments show the efficiency and effectiveness of the recommendation policies proposed. To illustrate the workings of the proposed system, we present a case study called SMARTROAD pertaining to the transport domain and road security. [ABSTRACT FROM AUTHOR]

Quality of service (QoS)-based web service selection has been studied in the service computing community for some time. However, characteristics of the input dataset that is going to be processed by the web service are not usually considered in the selection process, even though they might have impact on QoS values of the service, e.g. latency on processing a bigger dataset is higher than that on a smaller dataset, one service takes longer time to process a certain dataset than another service. To address this issue, in this work, we take into consideration the dataset features in the QoS-based service recommendation process and we focus on data mining services because their QoS values could be highly dependent on dataset features. We propose two approaches for data mining service recommendations and compare their performances. In the first approach, we use a meta-learning algorithm to incorporate dataset features in the recommendation process and study the use of different machine learning algorithms (both classification models and regression models) as meta-learners in recommending data mining services for the given dataset. We also investigate the impact of the number of dataset features on the performance of the meta-learners. In the second approach, we propose a novel technique of using factor analysis for web service recommendation. We use decomposition technique to identify latent features of the input dataset and then recommend services by exploiting these latent variables. Our proposed approach of web service recommendation based on latent features was shown to be a more robust model with an accuracy of 85% compared to meta-feature-based recommendation. [ABSTRACT FROM AUTHOR]

Collaborative filtering (CF) is a technique commonly used for personalized recommendation and Web service quality-of-service (QoS) prediction. However, CF is vulnerable to shilling attackers who inject fake user profiles into the system. In this paper, we first present the shilling attack problem on CF-based QoS recommender systems for Web services. Then, a robust CF recommendation approach is proposed from a user similarity perspective to enhance the resistance of the recommender systems to the shilling attack. In the approach, the generally used similarity measures are analyzed, and the DegSim (the degree of similarities with top k neighbors) with those measures is selected for grouping and weighting the users. Then, the weights are used to calculate the service similarities/differences and predictions.We analyzed and evaluated our algorithms using WS-DREAM and Movielens datasets. The experimental results demonstrate that shilling attacks influence the prediction of QoS values, and our proposed features and algorithms achieve a higher degree of robustness against shilling attacks than the typical CF algorithms. [ABSTRACT FROM AUTHOR]

Objective: Children and families enrolled in early childhood systems of care (SOC) present with various psychological and behavioral risk factors that may inhibit healthy development. Within a SOC, wraparound services are designed to increase families' access to numerous child-serving sectors in order to target those risk factors. This study examined whether child and family risk factors at enrollment in an early childhood SOC predicted dosage, service recommendation, and usage of recommended services. Method: Participants were 144 children ranging in age from 1.38 to 5.89 years and their caregivers. Families completed measures of child and caregiver functioning prior to participation in the SOC. Service recommendation and usage were measured at intake and three months, respectively. We used multiple regression analysis to examine the relationship between risk factors and dosage of services received. Logistic regression analyses identified the relationships between risk factors and service recommendation and usage according to specific service types within the SOC. Results: Children with greater behavior problems received more services overall (R2 = .103, β = .243, p = .033). Child risk factors predicted recommendation for child welfare (trauma exposure:  OR = 1.352, p = .052) and mental health services (behavior problems: OR = 1.061, p = .034; trauma exposure: OR = 1.316, p = .046), whereas families with substance use issues were less likely to be recommended for mental health services (OR = .229, p = .017). Conclusions: Findings highlight opportunities for improved service provision and service-level decision making in early childhood SOCs. [ABSTRACT FROM AUTHOR]

Socialized recommender system recommends reliable healthcare services for users. Ratings are predicted on the healthcare services by merging recommendations given by users who has social relations with the active users. However, existing works did not consider the influence of distrust between users. They recommend items only based on the trust relations between users. We therefore propose a novel deep learning-based socialized healthcare service recommender model, which recommends healthcare services with recommendations given by recommenders with both trust relations and distrust relations with the active users. The influences of recommenders, considering both the node information and the structure information, are merged via the deep learning model. Experimental results show that the proposed model outperforms the existing works on prediction accuracy and prediction coverage simultaneously, even for cold start users or users with very sparse trust relations. It is also computational less expensive. [ABSTRACT FROM AUTHOR]

Existing approaches, such as semantic content-based or Collaborative Filtering-based recommendations, fail to exploit social aspects of services because services lack social relationships and do not consider social influence. In this paper, we propose a methodology for connecting distributed services in a global social service network (GSSN) to facilitate discovering internal social relationship for social influence-aware service recommendation. First, we propose a novel platform for constructing a GSSN by linking distributed services with social links based on quality of social link. We then propose a flexible model of the effective awareness of social influence, which provides a quantitative measure of the strength of influence between services. Next, a novel social influence-aware service recommendation approach is proposed based on GSSN using internal social relationship among services. The experimental results demonstrated that our new approach can solve the service recommendation problem with a low usage threshold and high accuracy, where the user preferences are exploited by a recommend-as-you-go method. [ABSTRACT FROM AUTHOR]

How to discover the trustworthy services is a challenge for potential users because of the deficiency of usage experiences and the information overload of QoE (quality of experience) evaluations from consumers. Aiming to the limitations of traditional interval numbers in measuring the trustworthiness of service, this paper proposed a novel service recommendation approach using the interval numbers of four parameters (INF) for potential users. In this approach, a trustworthiness cloud model was established to identify the eigenvalue of INF via backward cloud generator, and a new formula of INF possibility degree based on geometrical analysis was presented to ensure the high calculation precision. In order to select the highly valuable QoE evaluations, the similarity of client-side feature between potential user and consumers was calculated, and the multi-attributes trustworthiness values were aggregated into INF by the fuzzy analytic hierarchy process method. On the basis of ranking INF, the sort values of trustworthiness of candidate services were obtained, and the trustworthy services were chosen to recommend to potential user. The experiments based on a realworld dataset showed that it can improve the recommendation accuracy of trustworthy services compared to other approaches, which contributes to solving cold start and information overload problem in service recommendation. [ABSTRACT FROM AUTHOR]

The cloud computing has been growing over the past few years, and service providers are creating an intense competitive world of business. This proliferation makes it hard for new users to select a proper service among a large amount of service candidates. A novel user preferences-aware recommendation approach for trustworthy services is presented. For describing the requirements of new users in different application scenarios, user preferences are identified by usage preference, trust preference and cost preference. According to the similarity analysis of usage preference between consumers and new users, the candidates are selected, and these data about service trust provided by them are calculated as the fuzzy comprehensive evaluations. In accordance with the trust and cost preferences of new users, the dynamic fuzzy clusters are generated based on the fuzzy similarity computation. Then, the most suitable services can be selected to recommend to new users. The experiments show that this approach is effective and feasible, and can improve the quality of services recommendation meeting the requirements of new users in different scenario. [ABSTRACT FROM AUTHOR]

Context-aware recommender systems have been widely investigated in both academia and industry because they can make recommendations based on a user's current context (e.g., location, time). However, most existing context-aware techniques only use contextual information at the item level when modeling users' preferences, i.e., contextual information that correlates with users' overall evaluations of items such as ratings. Few studies have attempted to detect more fine-grained contextual preferences at the level of item aspects (e.g., a hotel's 'location', 'food quality', and 'service'). In this study, we use contextual weighting strategies to derive users' aspect-level context-dependent preferences from user-generated textual reviews. The inferred context-dependent preferences are then combined with users' context-independent preferences that are also inferred from reviews to reflect their stable requirements over time. To automatically incorporate both types of user preferences into the recommendation process, we propose a linear-regression-based algorithm that uses a stochastic gradient descent learning procedure. We tested the proposed recommendation algorithm with two real-life service datasets (one with hotel review data and the other with restaurant review data) and compared its contribution with three previously suggested approaches: one that does not consider contextual information; one that uses contextual information to pre-filter rating data before applying the recommendation algorithm; and one that generates recommendations according to users' aspect-level contextual preferences. The experiment results demonstrate that our approach outperforms the others in terms of recommendation accuracy. [ABSTRACT FROM AUTHOR]

The elastic computing power and the pay-as-you-go model of the cloud offer an attractive platform to deploy software as a service applications. The large number of applications expected to heavily take advantage of the cloud will result in an explosive growth of various cloud services. As many cloud services may compete to offer similar functionalities, it is desirable to consider user preferences on the nonfunctional service properties (aka, quality of service, or QoS) when delivering cloud services to the end users. Unfortunately, current approaches primarily rely on the descriptions from the cloud service providers or expert-provided rankings, which are completely orthogonal to the open and distributed nature of the cloud. We present a novel framework (referred to as CloudRec) that exploits a user-centric strategy to achieve personalized QoS assessment of cloud services. CloudRec integrates a novel community-based QoS assessment model with an iterative algorithm to accurately discover a set of homogenous user and service communities from scarce and large-scale QoS data. The communities can serve as a bridge to relate users and services and hence provide an effective means to estimate the QoS of unknown cloud services. The effectiveness of the proposed framework is demonstrated through a rigorous theoretical analysis and an extensive empirical study on real QoS data. [ABSTRACT FROM AUTHOR]

Finding and recommending suitable services for mobile devices are increasingly important due to the popularity of mobile Internet. While recent research has attempted to use role-based approaches to recommend services, role discovery is still an ongoing research topic. Using role-based approaches, popular mobile services can be recommended to other members in the same role group in a context- dependent manner. This paper proposes several role mining algorithms, to suit different application requirements, that automatically group users according to their interests and habits dynamically. Most importantly, we propose an online role mining algorithm that can discover role patterns efficiently and incrementally. Finally, we present a complete, question-based framework that can efficiently perform role mining for context-aware service recommendation in a mobile environment-where a device may not be always connected to the server and/or scalability of the role mining algorithm running on the server is critical. [ABSTRACT FROM AUTHOR]

The vision of pervasive environments is being realized more than ever with the proliferation of services and computing resources located in our surrounding environments. Identifying those services that deserve the attention of the user is becoming an increasingly-challenging task. In this paper, we present an adaptive multi-criteria decision making mechanism for recommending relevant services to the mobile user. In this context, ' Relevance' is determined based on a user-centric approach that combines both the reputation of the service, the user's current context, the user's profile, as well as a record of the history of recommendations. Our decision making mechanism is adaptive in the sense that it is able to cope with users' contexts that are changing and drifts in the users' interests, while it simultaneously can track the reputations of services, and suppress repetitive notifications based on the history of the recommendations. The paper also includes some brief but comprehensive results concerning the task of tracking service reputations by analyzing and comprehending Word-of-Mouth communications, as well as by suppressing repetitive notifications. We believe that our architecture presents a significant contribution towards realizing intelligent and personalized service provisioning in pervasive environments. [ABSTRACT FROM AUTHOR]

Based on the methods of acquaintance cache and group-based intelligent forwarding of service recommendations, a novel group-based active service (GAS) protocol for migrating workflows was proposed. This protocol did not require service requesters to discover services or resources. The semantic acquaintance knowledge representation was exploited to describe service groups and this semantic information was used to recommend service to respective clients. The experimental results show that the new protocol proposed offers better performance than other protocols in terms of first-response-time, success-scope and ratio of success-packet-number to total-packet-number. When the number of service request packet is 20, the first-response-time of GAS protocol is only 5.1 s, which is significantly lower than that of other protocols. The success-scope of GAS protocol is 49.1%, showing that GAS protocol can effectively improve the reliability of mobile transactions. And the ratio of success-packet-number to total-packet-number of GAS protocol is up to 0.080, which is obviously higher than that of other protocols. [ABSTRACT FROM AUTHOR]

In the age of big data, service recommendation has provided an effective manner to filter valuable information from massive data. Generally, by observing the past service invocation records (Boolean values) distributed across different cloud platforms, a recommender system can infer personalized preferences of a user and recommend him/her new services to gain more profits. However, the historical service invocation records are a kind of private information for users. Therefore, how to protect sensitive user data distributed across multiple cloud platforms is becoming a necessity for successful service recommendations. Additionally, the historical service invocation records often update with time, which call for an efficient and scalable service recommendation method. In view of these challenges, we introduce the multi-probe Simhash technique in information retrieval domain into the recommendation process and further put forward a privacy-preserving recommendation method based on historical service invocation records. At last, we design several experiments on the real-world service quality data in set WS-DREAM. Experimental results show the feasibility of the proposal in terms of producing accurate recommended results while protecting users' private information contained in historical service invocation records. [ABSTRACT FROM AUTHOR]