Dynamic User Preferences Research Articles

Recommending Mobile Services with Trustworthy QoS and Dynamic User Preferences via FAHP and Ordinal Utility Function

Due to ubiquitous Internet connectivity, widely available cloud services, and popular mobile devices, mobile networks have become service delivery and consumption platforms for many industries worldwide. To recommend optimal mobile Web services with trustworthy Quality-of-Service (QoS) and dynamic user preferences, this paper proposes a novel service recommendation model based on Fuzzy Analytic Hierarchy Process (FAHP) and ordinal utility function. First, a Multi-QoS vector is defined, and to take into account the trustworthiness of QoS, the fidelity of QoS is modeled as one component of the Multi-QoS vector. Then, a fuzzy hierarchy including dual attributes of QoS (objective attribute and subjective evaluation) is established to fully consider the objective and subjective attributes’ impact on optimal service recommendation. Furthermore, a FAHP-based weighting mode is developed, in which the resolution ratio of weight can be adjusted dynamically by decision-maker according to user preferences. Finally, the optimal service is obtained through the calculation of ordinal utility function of candidate service. Experimental results and method comparison illuminate the feasibility and efficiency of the proposed model.

Dynamic User Preference Parameters Selection and Energy Consumption Optimization for Smart Homes Using Deep Extreme Learning Machine and Bat Algorithm

The advancements in electronic devices have increased the demand for the internet of things (IoT) based smart homes, where the connecting devices are growing at a rapid pace. Connected electronic devices are more common in smart buildings, smart cities, smart grids, and smart homes. The advancements in smart grid technologies have enabled to monitor every moment of energy consumption in smart buildings. The issue with smart devices is more energy consumption as compared to ordinary buildings. Due to smart cities and smart homes' growth rates, the demand for efficient resource management is also growing day by day. Energy is a vital resource, and its production cost is very high. Due to that, scientists and researchers are working on optimizing energy usage, especially in smart cities, besides providing a comfortable environment. The central focus of this paper is on energy consumption optimization in smart buildings or smart homes. For the comfort index (thermal, visual, and air quality), we have used three parameters, i.e., Temperature (°F), illumination (lx), and CO2 (ppm). The major problem with the previous methods in the literature is the static user parameters (Temperature, illumination, and CO2); when they (parameters) are assigned at the beginning, they cannot be changed. In this paper, the Alpha Beta filter has been used to predict the indoor Temperature, illumination, and air quality and remove noise from the data. We applied a deep extreme learning machine approach to predict the user parameters. We have used the Bat algorithm and fuzzy logic to optimize energy consumption and comfort index management. The predicted user parameters have improved the system's overall performance in terms of ease of use of smart systems, energy consumption, and comfort index management. The comfort index after optimization remained near to 1, which proves the significance of the system. After optimization, the power consumption also reduced and stayed around the maximum of 15-18wh.

Recurrent Poisson Factorization for Temporal Recommendation

Poisson Factorization (PF) is the gold standard framework for recommendation systems with implicit feedback whose variants show state-of-the-art performance on real-world recommendation tasks. However, they do not explicitly take into account the temporal behavior of users which is essential to recommend the right item to the right user at the right time. In this paper, we introduce Recurrent Poisson Factorization (RPF) framework that generalizes the classical PF methods by utilizing a Poisson process for modeling the implicit feedback. RPF treats time as a natural constituent of the model, and takes important factors for recommendation into consideration to provide a rich family of time-sensitive factorization models. They include Hierarchical RPF that captures the consumption heterogeneity among users and items, Dynamic RPF that handles dynamic user preferences and item specifications, Social RPF that models the social-aspect of product adoption, Item-Item RPF that considers the inter-item correlations, and eXtended Item-Item RPF that utilizes items’ metadata to better infer the correlation among engagement patterns of users with items. We also develop an efficient variational algorithm for approximate inference that scales up to massive datasets. We demonstrate RPF's superior performance over many state-of-the-art methods on synthetic dataset, and wide variety of large scale real-world datasets.

Dynamic attention-based explainable recommendation with textual and visual fusion

Explainable recommendation, which provides explanations about why an item is recommended, has attracted growing attention in both research and industry communities. However, most existing explainable recommendation methods cannot provide multi-model explanations consisting of both textual and visual modalities or adaptive explanations tailored for the user’s dynamic preference, potentially leading to the degradation of customers’ satisfaction, confidence and trust for the recommender system. On the technical side, Recurrent Neural Network (RNN) has become the most prevalent technique to model dynamic user preferences. Benefit from the natural characteristics of RNN, the hidden state is a combination of long-term dependency and short-term interest to some degrees. But it works like a black-box and the monotonic temporal dependency of RNN is not sufficient to capture the user’s short-term interest.In this paper, to deal with the above issues, we propose a novel Attentive Recurrent Neural Network (Ante-RNN) with textual and visual fusion for the dynamic explainable recommendation. Specifically, our model jointly learns image representations with textual alignment and text representations with topical attention mechanism in a parallel way. Then a novel dynamic contextual attention mechanism is incorporated into Ante-RNN for modelling the complicated correlations among recent items and strengthening the user’s short-term interests. By combining the full latent visual-semantic alignments and a hybrid attention mechanism including topical and contextual attentions, Ante-RNN makes the recommendation process more transparent and explainable. Extensive experimental results on two real world datasets demonstrate the superior performance and explainability of our model.

About time

PurposeThe purpose of this paper seeks to develop a motivation-based complementary framework for temporally dynamic user preferences to facilitate optimal timing in web personalisation. It also aims to highlight the benefits of considering user motivation when addressing issues in temporal dynamics.Design/methodology/approachThrough theory, a complementary framework and propositions for motivation-based temporal dynamics for further testing are created. The framework is validated by feeding back findings, whereas some of the propositions are validated through an experiment.FindingsThe suggested framework distinguishes two ways (identifying/learning and shifting) of using a motive-based approach to temporal dynamics in web personalisation. The suggested outcomes include enhanced timing in matching current preferences and improved conversion. Validation measures predominantly support both the framework and the tested propositions. The theoretical basis for the approach paves a path towards refined psychological user models; however, currently on a complementary level.Research limitations/implicationsWhile the framework is validated through feeding back findings, and some of the propositions are validated through basic experimentation, further empirical testing is required.Practical implicationsA generalised approach for complementing personalisation procedures with motivation-based temporal dynamics is offered, with implications for both user modelling and preference matching.Originality/valueThis paper offers novel insights to web personalisation by considering the in-depth effects of user motivation.

도로 교통망에 대한 사용자의 선호도 변화를 반영한 경로 추천

도로 교통망에 대한 사용자의 선호도 변화를 반영한 경로 추천

Dynamic user preference based group vertical handoffs in heterogeneous wireless networks: a non-cooperative game approach

When a group of Mobile Users (MUs) equipped with multi-mode or multi-home terminals, like passengers on board a bus or a train or a car, moves from one wireless network (WN) to another WN within a heterogeneous wireless network (HWN) environment, request vertical handoffs simultaneously, a group vertical handoff (GVHO) occurs. In literature, the prevailing research work is mainly concerned for forced GVHO with network aspects like signal strength and bandwidth etc. while in reality the user initiated GVHO with the user aspects like price, power consumption and velocity etc. along with their respective user preferences is more important for performing vertical handoffs in HWNs. In user initiated GVHO, selection of the mutually best WN-MU pair which can maximise network revenue of constituent WN as well as user satisfaction of MU in a group while minimising the simultaneous selection of a WN by multiple MU of the group is a challenging problem. This paper proposes a GVHO decision model based on non-cooperative game which utilizes multiple handoff decision attributes and their respective user preferences calculated dynamically on real-time basis as the game strategies to select the best available WNs by group MUs at NASH equilibrium for vertical handoffs. The performance of the proposed model is evaluated in terms of number of GVHOs, price of anarchy and price of stability for both group of MUs and WNs. The simulation results show that the proposed model results in minimum number of GVHOs as compared to existing GVHO models and maximisation of user satisfaction and network revenue.

Semantic Approach for Multifarious Ranked Novelty and Diversity in News Recommendations

Information overload on web creates lots of inconvenience for end users to unearth requisite information which instigate the demand of personalized recommendations. Recommender systems strive to attain just accuracy in recommendations based on the history of user preferences, resulting in over specialized recommendations. This leads to gradual loss of user’s interest in the system. These approaches also fail to recommend other products in long list which could be of user interest but user is not aware of. This in-turn leads to sparse user profiles.In dynamic domains, novelty and diversity in coverage can handle over specialization problem. To bring useful novelty and diversity, it is proposed to semantically expand the user preferences. For this purpose our designed multi level ontology is used with linkages among concepts, entities and properties, carrying different weights. Ontology is also enriched with different relations from online semantic lexicon and annotated with additional information about entities from open and linked external knowledge source.For relevant accurate recommendations in highly dynamic domains, we propose semantic approach to implicitly capture individual user preferences in separate profiles. One profile is to capture short term dynamic interests with temporal effects and another is to capture long term static interests. Semantic profiling helps to handle preferences in manageable number of news categories which are arranged hierarchically. It also helps to handle synonymy and polysemy problems, reducing ambiguity in profiling. An additional important step of outlier analysis and rectification is proposed to handle the effects of sudden unexpected temporary drifts in dynamic user preferences. This focused analysis helps to maintain correct ranking of user preferences which is generally overlooked. The rectified ranking of user interests is fetched for semantic expansion of user preferences, to bring correct ranking in diversity and novelty.Proposed approach semantically brings reasonable multifarious novelty and diversity by analyzing different features of item. Testing is based on live data gathered from RSS feeds of popular news providers for trustworthiness. Transparency is achieved by presenting new recommendations in separate sections along with explicit trace path options, based on difference in approaches. Transparency assists end user in making decision. User’s interests in diverse and novel recommendations are updated in their individual profiles, resulting in reduction of sparsity.

Dynamic User Preference Based Network Selection for Vertical Handoff in Heterogeneous Wireless Networks

In Heterogeneous Wireless Networks (HWN), seamless Vertical Handoff (VHO) to the best available network is significant in providing Quality of Experience to the Mobile Users. The selection of best available network is based on multiple contrasting handoff decision attributes along with their respective User Preferences. In literature, the user preferences used in various network selection techniques are pre-fixed i.e. static and arbitrary without any standard theoretical basis. This paper proposes a method to moderate these static user preferences on real time basis according to the current value of respective handoff decision attributes, to make them dynamic and realistic. The effect of Dynamic User Preferences on network selection for vertical handoff, is evaluated with the prominent Multi Attribute Decision Making (MADM) methods like Simple Additive Weighting, Multiplicative Exponential Weighting, Technique of Order Preference Similarity to Ideal Solution, and Grey Relational Analysis. Simulations are performed using both static user preference weights from the user and proposed dynamic user preference weights. The result of simulations shows that the number of vertical handoffs, needs to complete an application by a mobile user, using dynamic user preference weights is less in comparison to using static user preference weights for all considered MADM methods. This proves the effectiveness of the proposed dynamic user preferences in network selections to perform VHOs in HWNs.

An Index Structure for Efficiently Handling Dynamic User Preferences and Multidimensional Data

An Index Structure for Efficiently Handling Dynamic User Preferences and Multidimensional Data

An Index Structure for Efficiently Handling Dynamic User Preferences and Multidimensional Data

An Index Structure for Efficiently Handling Dynamic User Preferences and Multidimensional Data

A Novel Hybrid Similarity Calculation Model

This paper addresses the problems of similarity calculation in the traditional recommendation algorithms of nearest neighbor collaborative filtering, especially the failure in describing dynamic user preference. Proceeding from the perspective of solving the problem of user interest drift, a new hybrid similarity calculation model is proposed in this paper. This model consists of two parts, on the one hand the model uses the function fitting to describe users’ rating behaviors and their rating preferences, and on the other hand it employs the Random Forest algorithm to take user attribute features into account. Furthermore, the paper combines the two parts to build a new hybrid similarity calculation model for user recommendation. Experimental results show that, for data sets of different size, the model’s prediction precision is higher than the traditional recommendation algorithms.

Collaborative filtering with facial expressions for online video recommendation

Online video recommender systems help users find videos suitable for their preferences. However, they have difficulty in identifying dynamic user preferences. In this study, we propose a new recommendation procedure using changes of users’ facial expressions captured every moment. Facial expressions portray the users’ actual emotions about videos. We can utilize them to discover dynamic user preferences. Further, because the proposed procedure does not rely on historical rating or purchase records, it properly addresses the new user problem, that is, the difficulty in recommending products to users whose past rating or purchase records are not available. To validate the recommendation procedure, we conducted experiments with footwear commercial videos. Experiment results show that the proposed procedure outperforms benchmark systems including a random recommendation, an average rating approach, and a typical collaborative filtering approach for recommendation to both new and existing users. From the results, we conclude that facial expressions are a viable element in recommendation.

English

A design of reading recommendation method based on user preference for online learning namely, RM-UP is proposed. The aim of this study is to design an online learning recommendation system to support automatic information extract, dynamic user preference analysis and conduct an accurate recommendation of reading materials to relevant users.

Exploiting User Preference for Online Learning in Web Content Optimization Systems

Web portal services have become an important medium to deliver digital content (e.g. news, advertisements, etc.) to Web users in a timely fashion. To attract more users to various content modules on the Web portal, it is necessary to design a recommender system that can effectively achieve Web portal content optimization by automatically estimating content item attractiveness and relevance to user interests. The state-of-the-art online learning methodology adapts dedicated pointwise models to independently estimate the attractiveness score for each candidate content item. Although such pointwise models can be easily adapted for online recommendation, there still remain a few critical problems. First, this pointwise methodology fails to use invaluable user preferences between content items. Moreover, the performance of pointwise models decreases drastically when facing the problem of sparse learning samples. To address these problems, we propose exploring a new dynamic pairwise learning methodology for Web portal content optimization in which we exploit dynamic user preferences extracted based on users' actions on portal services to compute the attractiveness scores of content items. In this article, we introduce two specific pairwise learning algorithms, a straightforward graph-based algorithm and a formalized Bayesian modeling one. Experiments on large-scale data from a commercial Web portal demonstrate the significant improvement of pairwise methodologies over the baseline pointwise models. Further analysis illustrates that our new pairwise learning approaches can benefit personalized recommendation more than pointwise models, since the data sparsity is more critical for personalized content optimization.

A thermal preference scale for personalized comfort profile identification via participatory sensing

Thermal comfort is the main driving factor in determining heating, ventilation and air conditioning (HVAC) systems' operational settings. Current building management systems (BMS) operate according to conservatively defined and standardized settings. Many dynamic environmental and human related variables affect occupant thermal comfort in buildings, calling for flexibility in HVAC operations by integrating dynamic user preferences. This paper builds on the vision that a participatory sensing based approach could be used for integrating user thermal comfort preferences into the operational logic of HVAC systems on a real time and continuous basis. The paper emphasizes on participatory sensing requirements for improving human data acquisition by proposing a thermal comfort preference scale. Several guiding features, which could potentially improve the users' expressions of thermal comfort preferences, were evaluated. Interface usability evaluation methods, including think aloud usability assessment studies and task execution surveys, were used in order to assess the proposed alternatives. Moreover, a field experiment was conducted to explore the driving factors, which affect users' thermal preference vote, for determining HVAC control parameters. The results showed that the proposed sensation scale outperforms a five-level ASHRAE like scale and the addition of the guiding features helps increase the consistency between users' expectations and their votes. The results of the field study showed that the ambient temperature is the most effective factor on users' votes. Consequently, HVAC set points for temperature could be used as a control parameter for personalized thermal comfort without any need for retrofitting HVAC system components.

Ant-based service selection framework for a smart home monitoring environment

Selecting ambient media services in a smart home monitoring environment is challenging. Services in such an environment should be ubiquitous, adaptive, and robust with respect to access and delivery. Many different techniques exist for selecting services in smart environments, for example, dynamic programming, genetic algorithms, and fuzzy logic. However, existing approaches to service selection fail to address the dynamic nature of the services and the requirement of considering the user context and user satisfaction. We address this issue by proposing an ant-inspired service selection framework based on dynamic user preferences and satisfaction. This ant-inspired approach is robust to failures and adaptive to dynamic context. The proposed framework enables different categories of residents (e.g., elderly people, fathers with children, mothers, and so on) to access various media services in such a way that their experiences are optimized with regard to their surrounding environment. Experimental results demonstrate the viability of the proposed framework.

Resource collaboration system based on dynamic user preference and context

In a ubiquitous computing environment, service composition and collaboration among heterogeneous resources are required, thus, an infrastructure that supports these requirements is an essential factor in seamless service delivery. In this environment, users hope to get a variety of customized services by using only an individual mobile device. But the resource of the mobile device has limitations such as tiny display screens, limited input, less powerful processors, and limited storage. Moreover each user situation is different and user preferences are also various. Therefore it is one of new issues to provide a customized service for a user through resource collaboration based on various user preference and situation. To solve this issue, this paper proposes a resource collaboration system which infers customized resources for composing a user required service and collaborative with selected resources. For our collaboration system, this paper proposes the method to infer resources based on the context and user preferences including dynamic change of the preference. This paper also shows a reasonable execution environment for the proposed system through the performance evaluation in server-client and peer-to-peer environments.

A novel model of adaptation decision-taking engine in multimedia adaptation

In heterogeneous environments, universal multimedia access (UMA) is proposed to provide multimedia content services. Multimedia adaptation is one of technologies to perform UMA, in which adaptation decision-taking engine (ADTE) is a key component. Though there are many models of ADTE existing, it needs to be reconsidered for personalized content services. In this paper, a novel model of ADTE is proposed based on decision tree termed adaptation decision tree (ADT) in which adaptation decision is viewed as sequence decision: modality decision and format decision. Correspondingly, user preferences are divided into two types: user modality preferences and user format preferences. By utilizing user preferences, the ADT model is built up. Before making decision, an optimal multimedia variation set ( OMVS) with respect to user modality preferences is constructed and any element here is with the shortest distance to user format preferences for every modality. Therefore, adaptation decision can be executed by letting the element in OMVS travel along the ADT one by one. Finally, the first element that reaches the leaf with the logical value true is the decision result, or the one with the smallest value in distance is the decision variation if no elements get to proper leaf. Quantitative analysis and experimental simulation prove that the model is effective and efficient to cope with adaptation decision in multimedia adaptation especially in dynamic user preferences and resource-limited cases.

Wireless broadband applications: the teleservice model and adaptive QoS provisioning

This article presents a teleservice model for wireless broadband applications based on an adaptive QoS paradigm. According to this, a multimedia broadband application is considered as a set of hierarchically ordered adaptable media streams, which accept varying degrees of network-level guarantees, depending on dynamic resource changes and user preferences. Some algorithms that match the proposed paradigm are designed for call and mobility management. Their performance is analyzed in a mobile multitier cellular system, including the satellite component.