Mobile Recommendation Research Articles

THE PERSONALIZATION AND PREDICTION INNOVATION OF MOBILE RECOMMENDER SYSTEMS

With the advent of the Internet, the ability to retrieve and use information has become ubiquitous, but the amount of information available has also grown exponentially. This information growth has caused information overload for users trying to sift through the information to find the best options that will meet their needs, thus recommendation systems were developed. The current recommendation systems are rudimentary in function and are basically able to provide suggestions for similar products, local restaurants and hotels, or point-of-interest locations. The future of the recommendation systems, including mobility, will be able to take user behavior and contextual information to make better and more precise suggestions. The new system will be able to protect the user’s privacy and personal information along with seamlessly communicating with each other through standardization. This paper will provide current literature research along with the problems and probable solutions to the mobile recommender systems industry.

Techniques for cold-starting context-aware mobile recommender systems for tourism

Novel research works in recommender systems have illustrated the benefits of exploiting contextual information, such as the time and location of a suggested place of interest, in order to better predict the user ratings and produce more relevant recommendations. But, when deploying a context-aware system one must put in place techniques for operating in the cold-start phase, i.e., when no or few ratings are available for the items listed in the system catalogue and it is therefore hard to predict the missing ratings and compose relevant recommendations. This problem has not been directly tackled in previous research. Hence, in order to address it, we have designed and implemented several novel algorithmic components and interface elements in a fully operational points of interest (POI) mobile recommender system (STS). In particular, in this article we illustrate the benefits brought by using the user personality and active learning techniques. We have developed two extended versions of the matrix factorisationalgorithmtoidentifywhatitemstheuserscouldandshouldrateandtocomposepersonalisedrecommendations.While context-aware recommender systems have been mostly evaluated offline, a testing scenario that suffers from many limitations, in our analysis we evaluate the proposed system in live user studies where the graphical user interface and the full interaction design play a major role. We have measured the system effectiveness in terms of several metrics such as: the quality and quantity of acquired ratings-in-context, the recommendation accuracy (MAE), the system precision, the perceived recommendation quality, the user choice satisfaction, and the system usability. The obtained results confirm that the proposed techniques can effectively overcome the identified cold-start problem.

Reflections on US Policies Regarding ‘Effective Regulation and Discipline’ and Foreign Lawyer Mobility: Has the Time Come to Talk About the Elephant in the Room?

The ABA has adopted four model policies that address, in one way or another, the issue of foreign lawyer mobility. These policies are the ABA Model Foreign Legal Consultant Rule, which is commonly known as the FLC rule, the ABA Model Rule for Temporary Practice by Foreign Lawyers, which is commonly known as the FIFO rule, ABA Model Rule of Professional Conduct 5.5, which permits foreign lawyers to serve as in-house counsel, and the ABA Model Rule on Pro Hac Vice Admission. All four of the ABA’s foreign lawyer mobility recommendations include a requirement that the mobile foreign lawyer is “subject to effective regulation and discipline by a duly constituted professional body or a public authority.” In other words, these rules set forth requirements regarding the nature of the regulatory system in the foreign lawyer’s home jurisdiction. A number of U.S. states have included this requirement in their foreign lawyer mobility provisions, but a number have not. (Some countries have a somewhat comparable provision in their foreign lawyer mobility rules, but other countries do not.) Although the ABA model rules and a number of state rules include this requirement, neither the ABA Model Rules nor any of the state rules have defined what it means for a foreign lawyer to come from a system with “effective regulation and discipline.” Nor is there any evidence that this requirement has been enforced in those states that have included this requirement. This article suggests that the “effective regulation and discipline” requirement has been an elephant in the room that no one has been willing to talk about. The article argues that the time has come to confront this issue head-on. It asserts that either efforts should be undertaken to define and enforce this requirement or that the requirement should be abandoned. The article reviews two “threshold” issues that jurisdictions might want to consider when deciding whether to adopt or retain an “effective regulation and discipline” requirement. It also identifies resources that might be consulted for “benchmarking” purposes if and when U.S. regulators decide to add “meat to the bones” by defining and enforcing the “effective regulation and discipline” requirement found in foreign lawyer mobility provisions.

A FRAMEWORK FOR INTEGRATED MOBILE CONTENT RECOMMENDATION

Content filtering in a mobile recommendation system plays a vital role in providing solution to help mobile device users obtain their desire content. However, mobile content recommendation systems have problems and limitations related to cold start and sparsity. These problems can be viewed as a user’s first time connection to a mobile recommendation system and initial rating of the content in an early stage of the system. Hence, to obtain personalized content for mobile user, mobile content filtering is needed. This paper proposes a framework for integrated mobile content recommendation. The framework makes use of classification and adaptive association rule techniques to build an integrated model. The results demonstrate that the proposed framework outperforms related techniques. This can address the problem of sparsity for mobile content recommendation systems. To cite this document: Worapat Paireekreng, Kok Wai Wong, and Chun Che Fung, "A framework for integrated mobile content recommendation", International Journal of Electronic Commerce Studies, Vol.4, No.2, pp. 185-202, 2013. Permanent link to this document: http://dx.doi.org/10.7903/ijecs.1038

Mobile application to provide personalized sightseeing tours

Tourist recommendation systems have been growing over the last few years, mainly because of the use of mobile devices to obtain user context. This work discusses some of the most relevant systems on the field and presents PSiS Mobile, which is a mobile recommendation and planning application designed to support a tourist during his vacations. It provides recommendations about points of interest to visit based on tourist preferences and on user and sight context. Also, it suggests a visit planning which can be dynamically adapted based on current user and sight context. This tool works also like a journey dairy since it records the tourist moves and tasks to help him remember how the trip was like. To conclude, some field experiences will be presented.

RECOGNIZING TRANSPORTATION MODE ON MOBILE PHONE USING PROBABILITY FUSION OF EXTREME LEARNING MACHINES

As one important clue to understand people's behavior and life pattern, transportation mode (such as walking, bicycling, taking bus, driving, taking light-rail or subway, etc.) information has already widely used in mobile recommendation, route planning, social networking and health caring. This paper proposes a transportation mode recognition method using probability fusion of extreme learning machines (ELMs). Two ELM classification models are trained to recognize accelerometer data and Global Positioning System (GPS) data, respectively. Fuzzy output vectors of these two ELMs are transformed into probability vectors and fused to determine the final result. Experimental results verify that the proposed method is effective and can obtain higher recognition accuracy than traditional fusion methods.

An intelligent mobile location-aware book recommendation system that enhances problem-based learning in libraries

Despite rapid and continued adoption of mobile devices, few learning modes integrate with mobile technologies and libraries' environments as innovative learning modes that emphasize the key roles of libraries in facilitating learning. In addition, some education experts have claimed that transmitting knowledge to learners is not the only educational goal, as cultivating problem-solving skills is also essential. By integrating the problem-based learning (PBL) model with book resources in libraries, one can identify the advantages of libraries in supporting e-Learning, resulting in innovative and valuable research. Therefore, this study presents a novel intelligent mobile location-aware book recommendation system (IMLBRS) with map-based guidance to support cooperative PBL in a real-library environment. Using map navigation and book recommendation functionalities, learners can search for books associated with problem-solving with increased ease and efficiency, thereby helping learners increase their PBL performance in a library environment. Experimental results reveal that learning performance during PBL supported by the proposed IMLBRS for book searches is superior to learning performance during PBL supported by the online public access catalogue (OPAC). Experimental results also show that the proposed system facilitates better learning performance for learners with a field-dependent learning style than for learners with a field-independent learning style. Moreover, the proposed system facilitates learner contemplation, cooperative learning, and library user education as learners interact with a real-library environment and peers during cooperative PBL.

Travel Recommendation by Mining People Attributes and Travel Group Types From Community-Contributed Photos

Leveraging community-contributed data (e.g., blogs, GPS logs, and geo-tagged photos) for personalized recommendation is one of the active research problems since there are rich contexts and human activities in such explosively growing data. In this work, we focus on personalized travel recommendation and show promising applications by leveraging the freely available community-contributed photos. We propose to conduct personalized travel recommendation by further considering specific user profiles or attributes (e.g., gender, age, race) as well as travel group types (e.g., family, friends, couple). Instead of mining photo logs only, we exploit the automatically detected people attributes and travel group types in the photo contents. By information-theoretic measures, we demonstrate that such detected user profiles are informative and effective for travel recommendation-especially providing a promising aspect for personalization. We effectively mine the demographics of individual and group travelers for different locations (or landmarks) and their travel paths. A probabilistic Bayesian learning framework which further entails mobile recommendation on the spot is introduced as well. We experiment on more than 10 million photos collected from 19 major cities worldwide and conduct the extensive investigation of profiling activities in communities according to temporal and spatial information. Note that the photos in the paper attribute to various Flickr users under the Creative Commons License. The experiments confirm that people attributes of individuals and groups are promising and orthogonal to prior works using travel logs only and can further improve prior travel recommendation methods especially for difficult predictions by further leveraging user contexts via mobile devices.

The influence of national culture on the attitude towards mobile recommender systems

This study aimed to identify factors that influence user attitudes towards mobile recommender systems and to examine how these factors interact with cultural values to affect attitudes towards this technology. Based on the theory of reasoned action, belief factors for mobile recommender systems are identified in three dimensions: functional, contextual, and social. Hypotheses explaining different impacts of cultural values on the factors affecting attitudes were also proposed. The research model was tested based on data collected in China, South Korea, and the United Kingdom. Findings indicate that functional and social factors have significant impacts on user attitudes towards mobile recommender systems. The relationships between belief factors and attitudes are moderated by two cultural values: collectivism and uncertainty avoidance. The theoretical and practical implications of applying theory of reasoned action and innovation diffusion theory to explain the adoption of new technologies in societies with different cultures are also discussed. • We identify factors and cultural values that impact attitudes towards mobile recommender systems. • The cultural characteristics of users involve collectivism and uncertainty avoidance. • The research model is tested based on the data collected in China, South Korea, and the UK. • Functional and social factors have significant impacts on user attitudes towards MRSs. • The relationships between the factors and user attitudes differ according to the cultural values.

Implementation of the Pain, Agitation, and Delirium Clinical Practice Guidelines and Promoting Patient Mobility to Prevent Post-Intensive Care Syndrome

Surviving critical illness is associated with persistent and severe physical, cognitive, and psychological morbidities. The Society of Critical Care Medicine has developed pain, agitation, and delirium guidelines and promoted mobility to improve care of critically ill patients. A task force has developed tools to facilitate and rapidly implement the translation of guideline care recommendations into practice. The Society of Critical Care Medicine has also assembled a task force to assess the long-term consequences of critical illness. This article will explore relationships between the pain, agitation, and delirium guidelines, mobility recommendations, and post-intensive care syndrome initiative. Implementation of the pain, agitation, and delirium guidelines taking into account current data regarding post-intensive care syndrome outcomes and potential interventions are an important first step toward improving outcomes for patients and their families. Research is needed to reduce the impact of long-term negative consequences of critical illness and to fully understand the best within- and post-ICU interventions, along with the optimal timing and dose of such interventions to produce the best long-term outcomes.

An Overview on Augmented Reality Based Mobile Commerce Recommendation

Mobile commerce brings new requirements for the models of e-commerce recommendation systems. Due to the advantage of field experience of mobile internet devices, augmentation reality would be considered as a suitable technology platform for the implementation of e-commerce recommendation in mobile commerce. Specifically, the idea of using augmented reality to extract user instant interests and render recommended instant information would demonstrate its strong vitality. Currently, the research of augmented reality based mobile commerce recommendation systems consists of three parts: recommendation information processing, recommendation information presentation and augmented reality based interaction. Information processing refers to the use of techniques such as collaborative filtering analysis of user interests, goods or services to decide what information should be recommended to the user. Information representation refers to the way in which recommended information is transmitted to users. Augmentation reality based interaction model is responsible for the interaction of users with the goods and services information, is a concrete manifestation of the recommended way of e-commerce in the mobile business environments. In this paper, the feasibility and main techniques of augmented reality technology used in mobile commerce were analyzed, and the prospects for its applications were looked forward to.

Personalized Mobile Catering Recommender System Based on Context Ontology Model and Rule Inference

With the development of smart mobile terminals and pervasive computing, mobile recommender systems are proposed to realize context-aware personalized recommendation services. A context model plays a key role in a mobile recommender. We discussed the context ontology modeling approach specific for mobile recommendation, and developed a two-level context model including a upper ontology and a domain ontology. We also designed a personalized mobile catering recommender system based on the context ontology model and rule inference. The framework of the system is depicted. And the process of rule generation and rule inference based on the context ontologies is demonstrated.

Recommendations for mobility in children with spinal cord injury.

Mobility is an important aspect of the rehabilitation of children with spinal cord injury (SCI), is a necessary component of life, and is critical in a child's development. Depending upon the individual's age and degree of neurological impairment, the nature of mobility may vary. The objective of this article is to establish recommendations surrounding the selection of mobility for children with SCI. Extensive literature review and multidisciplinary peer review. Types of mobility including power, manual, upright, and community are discussed, and recommendations are made based on medical necessity, neurological level, ASIA Impairment Scale score, and developmental considerations and challenges. Mobility is critical for proper development to occur in the pediatric population, and it may be challenging to make recommendations for mobility in children with SCI. It is essential for clinicians providing care to children with SCI to address mobility in a comprehensive and longitudinal manner across the children's environments.

SMARTMUSEUM: A mobile recommender system for the Web of Data

Semantic and context knowledge has been envisioned as an appropriate solution for addressing the content heterogeneity and information overload in mobile Web information access, but few have explored their full potential in mobile scenarios, where information objects refer to their physical counterparts, and retrieval is context-aware and personalized for users. We present SMARTMUSEUM, a mobile ubiquitous recommender system for the Web of Data, and its application to information needs of tourists in context-aware on-site access to cultural heritage. The SMARTMUSEUM system utilizes Semantic Web languages as the form of data representation. Ontologies are used to bridge the semantic gap between heterogeneous content descriptions, sensor inputs, and user profiles. The system makes use of an information retrieval framework wherein context data and search result clustering are used in recommendation of suitable content for mobile users. Results from laboratory experiments demonstrate that ontology-based reasoning, query expansion, search result clustering, and context knowledge lead to significant improvement in recommendation performance. The results from field trials show that the usability of the system meets users’ expectations in real-world use. The results indicate that semantic content representation and retrieval can significantly improve the performance of mobile recommender systems in knowledge-rich domains.

Context Ontology Modeling for Mobile Petrol Station Recommendation

To support the personalized mobile recommendation service, a context modeling approach based on ontology was proposed. The role of context ontologies in mobile recommenders was discussed, and under the application background of petrol station recommendation, a two-level context ontology model was designed. The model contains an upper ontology to describe general concepts, and a domain ontology extended from the upper ontology. The context ontology provides formalizations representing the mainly entities including users, objects and contexts, and their interactive relationships in mobile recommendation environments. Finally, a use case of the instantiated context ontology was demonstrated.

Ontology-Based Context Modeling for Mobile Catering Recommendation

To support context-aware mobile recommendation, an ontology-based context modeling approach was proposed. We analyzed the framework of the mobile recommender system based on contextual model and suggested designing the model with two-layer structure including an upper ontology layer and a domain ontology layer. The ontologies provides formalizations representing the main entities, including users, objects, contexts, and their interactive relationships in mobile recommendation environments. A specific context ontology model for catering recommendation was developed and a use case of the instantiated context ontology was demonstrated.

Intelligent Petrol Station Recommender Based on Context Ontology and Rule Inference

An intelligent mobile petrol station recommender system based on context ontology and rule inference is deigned. The approach of context ontology modeling specific for mobile recommendation is discussed. And a two-level context ontology model including upper ontology and domain ontology used in petrol station recommender is developed. The generation of recommendation rules based on the context ontologies and the process of the rule inference for recommendation are also demonstrated.

A SURVEY OF CONTEXT-AWARE MOBILE RECOMMENDATIONS

Mobile recommender systems target on recommending the right product or information to the right mobile users at anytime and anywhere. It is well known that the contextual information is often the key for the performances of mobile recommendations. Therefore, in this paper, we provide a focused survey of the recent development of context-aware mobile recommendations. After briefly reviewing the state-of-the-art of recommender systems, we first discuss the general notion of mobile context and how the contextual information is collected. Then, we introduce the existing approaches to exploit contextual information for modeling mobile recommendations. Furthermore, we summarize several existing recommendation tasks in the mobile scenarios, such as the recommendations in the tourism domain. Finally, we discuss some key issues that are still critical in the field of context-aware mobile recommendations, including the privacy problem, the energy efficiency issues, and the design of user interfaces.

A weight-aware recommendation algorithm for mobile multimedia systems

In the last years, information flood is becoming a common reality, and the general user, hit by thousands of possible interesting information, has great difficulties identifying the best ones, that can guide him in his/her daily choices, like concerts, restaurants, sport gatherings, or culture events. The current growth of mobile smartphones and tablets with embedded GPS receiver, Internet access, camera, and accelerometer offer new opportunities to mobile ubiquitous multimedia applications that helps gathering the best information out of an always growing list of possibly good ones. This paper presents a mobile recommendation system for events, based on few weighted context-awareness data-fusion algorithms to combine several multimedia sources. A demonstrative deployment were utilized relevance like location data, user habits and user sharing statistics, and data-fusion algorithms like the classical CombSUM and CombMNZ, simple, and weighted. Still, the developed methodology is generic, and can be extended to other relevance, both direct background noise volume and indirect local temperature extrapolated by GPS coordinates in a Web service and other data-fusion techniques. To experiment, demonstrate, and evaluate the performance of different algorithms, the proposed system was created and deployed into a working mobile application providing real time awareness-based information of local events and news.

SMARTMUSEUM: A Mobile Recommender System for the Web of Data

Semantic and context knowledge have been envisioned as an appropriate solution for addressing the content heterogeneity and information overload in mobile Web information access, but few have explored their full potential in mobile scenarios, where information objects refer to their physical counterparts, and retrieval is context-aware and personalized for users. We present SMARTMUSEUM, a mobile ubiquitous recommender system for the Web of Data, and its application to information needs of tourists in context-aware, on-site access to cultural heritage. The SMARTMUSEUM system utilizes Semantic Web languages as the form of data representation. Ontologies are used to bridge the semantic gap between heterogeneous content descriptions, sensor inputs, and user profiles. The system makes use of an information retrieval framework where in context data and search result clustering are used in recommendation of suitable content for mobile users. Results from laboratory experiments demonstrate that ontology-based reasoning, query expansion, search result clustering, and context knowledge lead to significant improvement in recommendation performance. The results from field trials show that the usability of the system meets users’ expectations in real-world use. The results indicate that semantic content representation and retrieval can significantly improve the performance of mobile recommender systems in knowledge-rich domains.