Introduction

Latent factor (LF) models are highly effective in extracting useful knowledge from High-Dimensional and Sparse (HiDS) matrices which are commonly seen in various industrial applications. An LF model usually adopts iterative optimizers, which may consume many iterations to achieve a local optima, resulting in considerable time cost. Hence, how to accelerate the training process of an LF model becomes a highly significant issue. To address it, this work innovatively proposes a randomized latent factor (RLF) model. It incorporates the principle of randomized learning techniques for neural networks into the LF analysis on HiDS matrices to alleviate the computational burden greatly. It also extends the standard learning process for randomized neural networks in context of LF analysis to make the resulting model represent an HiDS matrix correctly. Experimental results on three HiDS matrices from industrial applications demonstrate that compared with state-of-the-art LF models, RLF is able to achieve significantly higher computational efficiency and comparable prediction accuracy for missing data. More importantly, it provides a novel, effective, and efficient approach to LF analysis on HiDS matrices.

Non-negative latent factor (NLF) models well represent high-dimensional and sparse (HiDS) matrices filled with non-negative data, which are frequently encountered in industrial applications like recommender systems. However, current NLF models mostly adopt Euclidean distance in their objective function, which represents a special case of a β-divergence function. Hence, it is highly desired to design a β-divergence-based NLF ( β-NLF) model that uses a β-divergence function, and investigate its performance in recommender systems as β varies. To do so, we first model β-NLF's learning objective with a β-divergence function. Subsequently, we deduce a general single latent factor-dependent, non-negative and multiplicative update scheme for β-NLF, and then design an efficient β-NLF algorithm. The experimental results on HiDS matrices from industrial applications indicate that by carefully choosing the value of β, β-NLF outperforms an NLF model with Euclidean distance in terms of accuracy for missing data prediction without increasing computational time. The research outcomes show the necessity of using an optimal β-divergence function in order to achieve the best performance of an NLF model on HiDS matrices. Hence, the proposed model has both theoretical and application significance.

Latent factor (LF) model is an effective method for extracting useful knowledge from high-dimensional and sparse (HiDS) data generated by various industrial applications. Parallelized stochastic gradient descent (SGD) is widely used in building a parallelized LF model for handling large-scale HiDS data, but parallelized SGD suffers from slow convergence and considerable time cost. To address this issue, this study incorporates the principle of momentum into parallelized SGD, where momentum decay coefficient and learning rate are adjusted dynamically, and proposes a momentum-incorporated fast parallelized SGD (MFSGD) method to discover latent patterns from large-scale HiDS data. The experiments on two datasets show that the proposed MFSGD method outperforms state-of-the-art parallel SGD methods in terms of computational efficiency.

Wireless industrial sensor networks are wireless sensor networks which have been adapted to industrial applications. Most techniques for wireless sensor networks can be applied to wireless industrial sensor networks. However, for industrial applications of wireless industrial sensor networks, new requirements such as real-time, reliable delivery need to be considered. In this paper, we propose EARQ, which is a novel routing protocol for wireless industrial sensor networks. It provides real-time, reliable delivery of a packet, while considering energy awareness. In EARQ, a node estimates the energy cost, delay and reliability of a path to the sink node, based only on information from neighboring nodes. Then, it calculates the probability of selecting a path, using the estimates. When packet forwarding is required, it randomly selects the next node. A path with lower energy cost is likely to be selected, because the probability is inversely proportional to the energy cost to the sink node. To achieve real-time delivery, only paths that may deliver a packet in time are selected. To achieve reliability, it may send a redundant packet via an alternate path, but only if it is a source of a packet. Experimental results show that EARQ is suitable for industrial applications, due to its capability for energy efficient, real-time, reliable communications.

Latent factor analysis (LFA) is highly efficient in knowledge discovery from high-dimensional and sparse (HiDS) matrices frequently encountered in big data and web service related applications. A stochastic gradient descent (SGD) algorithm is commonly adopted as a learning algorithm for LFA owing to its high efficiency. However, its sequential nature makes it less scalable when processing large-scale data. Although an alternating SGD algorithm decouples an LFA process to achieve parallelization, its performance relies on its hyper-parameter selection that is highly expensive to tune. To address it, this paper presents three adaptive alternating SGD algorithms, thus leading to three Parallel Adaptive LFA (PAL) models for LFA on large-scale HiDS matrices. Experimental studies on HiDS matrices from industrial service applications show that the proposed PAL models perform significantly better than existing ones in terms of both convergence rate and computational efficiency, as well as achieve competitive prediction accuracy for missing data.

Nowadays, short video feed has attracted billions of mobile users all around the world to interact with content effortlessly, yielding an explosive growth of short video commerce. Typically, users watch full-screen short videos of a few seconds one-by-one in a watch-list generated by recommender systems, skipping those they are not interested in. However, the recommender system at the cloud makes a user-interest-specific decision mostly based on the users' behavior data collected within the application itself (e.g., users' view history), without examining the lower-layer network and communication statistics. When the playback choked due to the limited network bandwidth, the user will probably skip the video, leading to a waste of bandwidth and degradation of the user's quality of experience (QoE). Meanwhile, the excessive number of user requests to video contents raises a heavy computational load and communication cost for the recommender system at the cloud to determine which videos to be recommended and delivered to each user in a real-time manner. The advance of edge computing provides a promising avenue of deploying edge nodes with caches (e.g., household devices) beyond cloud and edge servers, such that the recommender system in the cloud can place popular video contents closer to client users, and meanwhile the contents are delivered to client users with good network condition. In this paper, we propose CFP, a cross-layer recommender system for short video streaming with fine-grained preloading technique at the network edge. CFP jointly optimizes the recommendation effect of the video application and the content preloading efficiency under various network conditions at the network edge. CFP takes a two-stage approach: the cloud server first seeks to perform edge-wise instead of user-interest-specific recommendation with neural collaborative filtering recommender, preloading a list of candidate videos to edge nodes, and each edge node, deploying the GRU with attention, then delivers the proper video contents to the client user device according to the user's preference. Trace-driven emulations demonstrate the efficiency of the proposed CFP scheme.

With the success of wireless technologies and the number of wireless devices increasing, the wireless coverage footprint expands and removes the needs of wired networks for industrial applications. Wireless industrial sensor networks (WISNs) are a type of wireless sensor networks (WSNs), which dedicate to industrial applications. The WISNs bring several advantages over traditional wired industrial networks for detection and control, include flexibility, scalability, remote maintenance, and rapid deployment. However, some technical issues and routing design principles need to be noticed in terms of the stringent requirements of industrial applications. In this paper, we firstly introduce the characteristics and some routing issues of WISNs. Then we discuss existing routing protocols for WISNs and analysis their performances. Finally, we outline several future research directions.

Social online learning is gaining prominence with the emergence of social media and networks. In the presence of recommendation systems, the learner has access to several educational contents and elements proposed according to his interaction, profile, dynamics and other parameters. Our proposal revolves around an intelligent recommender system for generating recommendations in social learning environments, in particular social networks, based on the learner's activities, falling into the category of hybrid recommender systems and integrating the concept of community detection in the generation of recommendations. The proposed global approach is composed of several recommender systems: the correlation and co-occurrence based recommender system aims at measuring the degree of connectivity between learners' activities in order to generate relevant recommendations in the light of learners' implicit feedback, the community detection based recommender system through friendships. This system is an important part of our overall approach as it combines the hybrid recommendation system with the community detection based on friendship links between learners and the recommendation system based on the degree of interactivity of learners with the available learning objects. This system also consists in detecting communities, which group learners with similar preferences and orientations. The results obtained prove the potential of combining the two notions of connectivity and the integration of community detection based on several indicators to produce more relevant recommendations, while offering recommendations by group of learners by applying the concept of continuous improvement.KeywordsSocial learningRecommender systemCorrelationCo-occurrenceFriendshipInteractionCommunity detection

A location-based orientation-aware recommender system using IoT smart devices and Social Networks

Recommender system is the system which, by using automated information filtering technology, recommends products or services to the customers who are likely to be interested in. Those systems are widely used in many different Web retailers such as Amazon.com, Netfix.com, and CDNow.com. Various recommender systems have been developed. Among them, Collaborative Filtering (CF) has been known as the most successful and commonly used approach. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. However, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting in advance whether the performance of CF recommender system is acceptable or not is practically important and needed. In this study, we propose a decision making guideline which helps decide whether CF is adoptable for a given application with certain transaction data characteristics. Several previous studies reported that sparsity, gray sheep, cold-start, coverage, and serendipity could affect the performance of CF, but the theoretical and empirical justification of such factors is lacking. Recently there are many studies paying attention to Social Network Analysis (SNA) as a method to analyze social relationships among people. SNA is a method to measure and visualize the linkage structure and status focusing on interaction among objects within communication group. CF analyzes the similarity among previous ratings or purchases of each customer, finds the relationships among the customers who have similarities, and then uses the relationships for recommendations. Thus CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. Under the assumption that SNA could facilitate an exploration of the topological properties of the network structure that are implicit in transaction data for CF recommendations, we focus on density, clustering coefficient, and centralization which are ones of the most commonly used measures to capture topological properties of the social network structure. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. We explore how these SNA measures affect the performance of CF performance and how they interact to each other. Our experiments used sales transaction data from H department store, one of the well?known department stores in Korea. Total 396 data set were sampled to construct various types of social networks. The dependant variable measuring process consists of three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used UCINET 6.0 for SNA. The experiments conducted the 3-way ANOVA which employs three SNA measures as dependant variables, and the recommendation accuracy measured by F1-measure as an independent variable. The experiments report that 1) each of three SNA measures affects the recommendation accuracy, 2) the density's effect to the performance overrides those of clustering coefficient and centralization (i.e., CF adoption is not a good decision if the density is low), and 3) however though the density is low, the performance of CF is comparatively good when the clustering coefficient is low. We expect that these experiment results help firms decide whether CF recommender system is adoptable for their business domain with certain transaction data characteristics.

With the rapid increase of countries population worldwide, crowd management is becoming more and more important issue all over the world. The importance of location determination is even becoming more critical especially during the events with large numbers of people that is approximated in millions such as in Pilgrimage and Umra events. Nowadays, there are many new technologies including wireless sensor networks and mobile cloud computing that can be utilized to provide useful applications and services. Pilgrimage (Al-Hajj) and Umra are the largest gathering events for the Muslims in the holy city Makkah from all over the world. Individuals who want to perform pilgrimage or Umra rituals should do specific worship tasks in specific locations and time periods. Every year more than three million Muslims come to Makkah to perform Pilgrimage during Al-Hajj months and more than 13 million Muslims perform Umra in a calendar year. This situation requires secure and safe management for these crowds. In this research, we developed a mobile application that provides dynamic interactive maps to facilitate and assist the performance of pilgrimage and Umra. After the visitor specify the desired destination in and around Makkah, the application detects his/her GPS location and generates dynamic interactive map giving the best path to reach the desired destination. The path determination is based on the crowdedness percentage values which are derived from wireless sensor network that cover the area. So, the lowest-cost path is provided to the user from his current location to the desired destination. The generated best path is viewed as an interactive map. Also, there is audio description for this path to help elder people. Our application is compatible with Android and iOS operating systems. We followed the Software Engineering design principles including the Unified Modeling Language standards during the application development process. Many demos and experiments were performed to test the functionality and performance of the application.

The geographical location and tourist features of St. Petersburg require a specialized web service for owners and tenants of river transport, aggregating all the information necessary for them. Currently, such information is available in various news sources, web portals and groups in social networks. The work presents a prototype of a service for small river transport users. Information needs and functional and requirements for it were identified during in-depth interviews with stakeholders of the project. The web service database is implemented in the PostgreSQL DBMS with the PostGIS extension. The work presents the structure of the service, which includes 10 pages, describes its main sections, such as current regulatory documents, news, interactive maps, reference information, as well as technical information about ships and restrictions on their movement due to technical characteristics. During its development, an analysis of existing solutions related to each section was carried out. During the "Maps" section development, an analysis of existing web tools for displaying interactive maps and the selection of the best solutions was carried out. Using the Google Maps designer, interactive maps were created for the web service being developed. The first of them is a map of the city's water bodies, containing such layers as: floating gas stations, lighthouses, customs, checkpoint and Ministry of Emergencies, private yacht clubs and marinas, berths and quayes, bridges, etc. The interactive weather map allows the user to get acquainted with the weather conditions, as well as their 5-day forecast. One of the priority functional requirements of the web service, called stakeholders, was the determination of water barriers and bridges that were inappropriate in the size of the vessel. The "Your Ship" section of the developed prototype web service offers a solution to meet this requirement. The developed web service is one of the favorable incentives for the development of the water tourism sphere and the use of river transport in St. Petersburg.

User-side Quality-of-Service (QoS) data are vital for efficient cloud service selection, while available QoS data in real applications are commonly described by a high-dimensional and Sparse (HiDS) matrix due to a) increasing users and services, and b) the impossibility of observing the full invoking mapping among users and services. A latent factor analysis (LFA) model has proven to be efficient in performing representation learning on such an HiDS QoS matrix. However, existing LFA models commonly adopt a first-order optimizer that cannot makes it approach the second-order stationary point of the learning objective, thereby resulting in accuracy loss. Aiming at addressing this issue, this study proposes to incorporate a Generalized Nesterov's Acceleration (GNA) method in to a Hessian-vector algorithm for LFA, thereby establishing a GNA-incorporated Hessian-vector-based LFA (GNHL) model with two-fold ideas: a) adopting the principle of a Hessian-vector method to acquire a proper Newton step efficiently, and b) incorporating a GNA method into its linear search for accelerating its convergence rate. Experimental results on six real QoS datasets demonstrate that a GNHL model outperforms state-of-the-art LFA models in generating highly accurate predictions for missing QoS data with low computational burden.

Advances in Web 2.0 technologies have led to unstructured information overload in the complex and multidimensional datasets that originate in social networks. This overload can diminish the quality of web-related services such as recommender systems in the social web and can overwhelm users with irrelevant information. Such overload indicates the need to design and develop efficient and accurate information management and retrieval systems in social networks and anticipate recommendations in the semantic context of user interest. Community detection in social networks can help identify higher-order structures that unveil insight into networks and their functional organization and reduce irrelevant information received by the user. In this study, the application of community detection in online social networks is investigated within the framework of topic discovery-based user link identification and is consequently used to uncover implicit user communities (ad hoc communities). In the proposed approach, we use a graph-based information extraction technique that provides for a personalized information retrieval (recommender) system. We hypothesize that the ad hoc communities of users sharing similar interests embedded in a folksonomy-based social network can be identified by overlapping tag clusters in the tag concept hierarchy. Our methodology incorporates the novel information extraction techniques of topic modeling for topic extraction (feature extraction), user profile modeling for user profile extraction, and community extraction from the social graph, modeled in a framework to derive relevant ad hoc user communities of social interest from folksonomy data. Our experimental results demonstrate an accuracy of 70–98 % in community detection using data obtained from CiteULike®.

Cloud computing provides a way to deliver a variety of services through the internet. These services mainly include servers, storage, computing, networks, and so on. Cloud computing has brought massive changes to the way resources and data can be managed. Hence, many organizations and individuals are adopting cloud technology for storing their data and are accessing different resources from the cloud. The only concern for large-scale adoption of the cloud is the security issue. It will be always challenging to select a trustworthy cloud service among the large pool of available services. In this chapter, a trust-based cloud service selection mechanism is proposed. The proposed method computes the trustworthiness of cloud service by considering its performance and recommendations. Also, a method to compute trust values for the cloud users on basis of behaviour and recommendation is proposed. Wireless sensor networks (WSNs) consist of sensor nodes that monitor the surrounding environment and collect a large amount of data. In this chapter, an integrated framework for WSNs and cloud computing is proposed so that the data is stored efficiently in the cloud and accessed by trustworthy users and services. The major contribution of the chapter is to integrate machine learning techniques with the traditional trust model to improve the performance of trust evaluation. The fuzzy-c means algorithm is applied to compute the trust levels for cloud services and cloud users. The results show that the proposed method performs better than the existing relevant techniques.