Mobile Recommender System Research Articles

From efficiency to equity: A multi-user paradigm in mobile route optimization

This study addresses the challenge of optimizing vehicle mobility in urban environments, which is significant for the advancement of smart city initiatives and spatial data analysis. We introduce a novel mobile recommendation system designed for multi-user scenarios, aiming to achieve a balance between effectiveness and fairness. The system prioritizes maximizing the profitability of vehicle service providers while ensuring an equitable distribution of recommended routes among users. Our approach features a redefined objective function that integrates a fairness criterion alongside path quality optimization. We further propose PSA-DLMA (Parallel Simulated Annealing with Deep Learning-Guided Move Adaptation), a stochastic path search method that leverages deep learning to guide move and strategy selection, alongside a dynamic termination mechanism and a parallel processing strategy. We validate our methodology using recent yellow taxi data from New York City and its surroundings, conducting comprehensive experiments to assess the performance of the system. The results demonstrate the superiority of PSA-DLMA over existing state-of-the-art solutions, offering significant contributions to improving urban vehicle mobility within the smart city framework.

Designing, Developing and Examining the Effectiveness of a Machine Learning–Based Mobile Recommendation System for Parents' Digital Parenting Skills

ABSTRACTIt is of paramount importance that children are equipped with the requisite digital parenting skills to protect them from the risks and threats that they may encounter in the digital environment while also enabling them to seize the opportunities that the digital realm presents. Mobile recommendation systems (MRS) represent a significant intervention for the development of digital parenting competencies among adults. Nevertheless, there is no evidence in the literature of any attempt to develop the system. The objective of this study is to examine the process of developing an MRS for parents' digital parenting skills and to evaluate the effectiveness of the developed system through a pilot study. The study employed the developmental research Type 1 model. The study was structured in three stages: the design of the MRS, the development of the recommendation system (RS) and the pilot study. In order to facilitate the development of the MRS, three distinct working groups were established. The research yielded several key findings. Primarily, it established the theoretical foundation of the MRS, delineated the design principles to be considered in system design and elucidated their application in the system. Additionally, it identified the essential components and functions that should be incorporated into the system. In light of the expert opinions on compliance with andragogical principles, it was observed that the consideration of environmental factors emerged as a prominent theme. It was observed that the experts assigned the highest suitability scores to fault tolerance, low physical effort and an instructional environment in the system design. The system was found to be effective in terms of redundancy, sound and picture quality for all content titles and multimedia principles. The findings of this study indicate that the MRS may be an effective tool for fostering digital parenting skills. However, further research is necessary to develop age‐appropriate measures and to assess the long‐term impact of the system.

Mobile Recommendation System to Provide Emotional Support and Promote Active Aging for Older Adults in the Republic of Panama

Aging brings with it physical and cognitive changes that can lead to health problems such as chronic disease and cognitive impairment. Technology is a fundamental ally in improving the quality of life of older adults by enabling accurate and early diagnosis. In this context, we present a mobile application designed to provide emotional support and guidance, thus contributing to the well-being of this demographic group. Our study was based on quantitative research methods, using an experimental approach on a sample of users aged between 60 and 80 years. The results showed that 93.3% of users found the app to be a useful resource for adopting a healthier lifestyle. The app provides specific recommendations, such as breathing exercises to reduce anxiety, recreational activities, exercises tailored to physical ability, and meditation practices. These specific features have been shown to improve the well-being of older adults by providing a personalized approach to the challenges of aging.

An approach for proactive mobile recommendations based on user-defined rules

In the Big Data era, context-aware mobile recommender systems are crucial in assisting citizens and tourists in making informed decisions, providing a suitable way for users to find the relevant data. These systems should be proactive, able to detect the ideal time and location to provide recommendations for a specific item or activity. To accomplish this, push-based recommender systems can be employed, utilizing context rules to determine when a recommendation should be initiated. However, there is very limited reported experience in defining and implementing such systems and a complete generic solution that adapts flexibly to the preferences of users and protects their privacy is still missing.In this paper, we present a novel approach where appropriate types of recommendations are provided automatically, without the need for user input. Our proposal allows users to easily activate, deactivate, customize, and create rules for improved personalization. Additionally, the module that, based on the context, decides the types of recommendations required is executed on the user’s mobile device, reducing wireless communication and safeguarding the user’s privacy, as context data are evaluated locally. To illustrate the approach, we have developed R-Rules, a prototype for Android devices focused on the triggering of recommendation rules, which provides a friendly user interface that facilitates user personalization. We have evaluated various technological options and demonstrated the feasibility, performance, and scalability of the proposal, as well as its suitability to users’ needs.

CoRec: An Efficient Internet Behavior-based Recommendation Framework with Edge-cloud Collaboration on Deep Convolution Neural Networks

Both accurate and fast mobile recommendation systems based on click behaviors analysis are crucial in e-business. Deep learning has achieved state-of-the-art accuracy and the traditional wisdom often hosts these computation-intensive models in powerful cloud centers. However, the cloud-only approaches put significant computational pressure on cloud servers and increase the latency in heavy-load scenarios. Moreover, existing work often adopts RNN structures to model behaviors that suffer from low processing speed for under-utilization of parallel devices such as GPUs. In this work, we propose an efficient internet behavior-based recommendation framework with edge-cloud collaboration on deep CNNs (CoRec) to improve both the accuracy and speed for mobile recommendation. A novel convolutional interest network (CIN) improves the accuracy by modeling the long- and short-term interests and accelerates the prediction through parallel-friendly convolutions. To further improve the serving throughput and latency, a novel device-cloud collaboration strategy reduces workloads by pre-computing and caching long-term interests in the cloud offline and real-time computation of short-term interests in devices. Extensive experiments on real-world datasets show that CoRec significantly outperforms the state-of-the-art methods in accuracy and has achieved at least an order of magnitude improvement in latency and throughput compared to cloud-only RNN-based approaches for long behaviors.

ACUX Recommender: A Mobile Recommendation System for Multi-Profile Cultural Visitors Based on Visiting Preferences Classification

In recent years, Recommendation Systems (RSs) have gained popularity in different scientific fields through the creation of (mostly mobile) applications that deliver personalized services. A mobile recommendation system (MRS) that classifies in situ visitors according to different visiting profiles could act as a mediator between their visiting preferences and cultural content. Drawing on the above, in this paper, we propose ACUX Recommender (ACUX-R), an MRS, for recommending personalized cultural POIs to visitors based on their visiting preferences. ACUX-R experimentally employs the ACUX typology for assigning profiles to cultural visitors. ACUX-R was evaluated through a user study and a questionnaire. The evaluation conducted showed that the proposed ACUX-R satisfies cultural visitors and is capable of capturing their nonverbal visiting preferences and needs.

Using big data and federated learning for generating energy efficiency recommendations

Internet of Things (IoT) devices are becoming popular solutions for smart home and office environments and contribute the most to energy efficiency. The most common implementation of such solutions relies on smart home systems that are hosted on the cloud. They collect data from a multitude of sensors, process it in real-time on the cloud and deliver immediate actions to sets of actuators that are installed locally. In this work, we present the (EM) $$^3$$ project (Consumer Engagement towards Energy Saving Behaviour by Means of Exploiting Micro Moments and Mobile Recommendation Systems), which combines data collection, information abstraction, timed recommendations for energy saving actions and automations that promote energy saving in a household or office setup. The advantage of the (EM) $$^3$$ project is that each room or office setup is controlled locally on an edge device, thus removing the need to share data to the cloud. The current article details on the data and information processing aspects of the (EM) $$^3$$ solution, which efficiently handles thousands of sensor events on a daily basis and provides useful analytics and recommendations to the end user to support habit change. It also demonstrates the scalability of the solution by simulating a simple scenario of distributed data collection and processing on the edge nodes, which takes advantage of federated learning in order to adapt to the needs of multiple users without exposing their privacy.

Mobile recommender system based on smart city graph

<span>Mobile recommender systems have changed the way people find items, purposes of intrigue, administrations, or even new companions. The innovation behind mobile recommender systems has developed to give client inclinations and social impacts. This paper introduces a first way to build a mobile recommendation system based on smart city graphs that appear topic features, user profiles, and impacts acquired from social connections. It exploits graph centrality measures to expand customized recommendations from the semantic information represented in the graph. The graph shows and chooses graph algorithms for computing chart centrality that is the center of the mobile recommender system are exhibited. Semantic ideas, for example, semantic transcendence and likeness measures, are adjusted to the graph model. Usage challenges confronted to settle execution issues are additionally examined.</span>

Smart, hybrid and context-aware POI mobile recommender system in tourism in Oman

PurposeThe purpose of this study is to identify the knowledge gap and future opportunities for developing mobile recommender system in tourism sector that lead to comfortable, targeted and attractive tourism. A recommender system improves the traditional classification algorithms and has incorporated many advanced machine learning algorithms.Design/methodology/approachDesign of this application followed a smart, hybrid and context-aware recommender system, which includes various recommender systems. With the recommender system's help, useful management for time and budget is obtained for tourists, since they usually have financial and time constraints for selecting the point of interests (POIs) and so more purposeful trip planned with decreased traffic and air pollution.FindingsThe finding of this research showed that the inclusion of additional information about the item, user, circumstances, objects or conditions and the environment could significantly impact recommendation quality and information and communications technology has become one part of the tourism value chain.Practical implicationsThe application consists of (1) registration: with/without social media accounts, (2) user information: country, gender, age and his/her specific interests, (3) context data: available time, alert, price, spend time, weather, location, transportation.Social implicationsThe study’s social implications include connecting the app and registration through social media to a more social relationship, with its textual reviews, or user review as user-generated content for increasing accuracy.Originality/valueThe originality of this research work lies on introducing a new content- and knowledge-based algorithm for POI recommendations. An “Alert” context emphasizing on safety, supplies and essential infrastructure is considered as a novel context for this application.

Route recommendation based on temporal–spatial metric

The acquisition and analysis of large amounts of mobile trajectory data promote the rapid development of mobile recommender systems, which can essentially recommend a series of positions to the mobile users. In this paper, we concentrate on the mobile sequential recommendation problem by considering both the distance and time factors, the objective of which is to recommend an optimal driving route consisting of a sequence of pick-up locations for the drivers. Firstly, we formulate this problem and develop a potential travel cost function to comprehensively evaluate each candidate route. Then we propose an efficient and effective Route recommendation based on Temporal-Spatial metric scheme called RTS, which adopts the simulated annealing algorithm and can achieve real-time route recommendation without severely sacrificing the recommendation performance. The extensive experiments based on both the real-world and synthetic data are conducted, the results of which demonstrate the efficiency and effectiveness of the proposed RTS scheme.

Multi-modality Search and Recommendation on Palestinian Cultural Heritage Based on the Holy-Land Ontology and Extrinsic Semantic Resources

The Cultural Heritage (CH) sector and its associated tourism services have been affected notably by the advancement of the Internet as well as the explosive growth of smartphones and other handheld devices. These days, visitors can access reliable CH content using Web and mobile-based interfaces. However, conventional CH systems still lack the ability to provide meaningful semantically overt results that precisely meet user information needs in this domain. In addition, they often ignore the user search context and experience, which hinders their ability to adapt their behavior to the preferences, tasks, interests, and other user functionalities. In this article, we aim to address the issue of designing a precision-oriented multilingual and multi-criteria semantic-based mobile recommender system specifically targeting Palestine's CH, a country with great historical and cultural importance. We aim to better facilitate users’ access to CH content by providing them with multiple search functionalities. In this context, a user can search for relevant information using keywords (a.k.a. tags) or sentence-like queries and the system retrieves all relevant documents based on their semantic similarity. A second option is to search using current location information to retrieve correlated historical places and events. Finally, starting from a picture of interest, a third option makes it possible to extract captions describing its content that can be used to search for additional contextually relevant information. Additionally, the proposed system aims at personalizing users’ experience through progressively delivering output that meets their information needs based on a number of parameters such as users' logging data, interests, previous searches, and location-based information. A prototype of the proposed system has been developed and tested using Android smartphones and a manually constructed ontology enriched with CH links to the Art & Architecture Thesaurus (AAT) and DBpedia. By comparing our system with similar systems in this domain, findings demonstrate that it provides additional search features and functionalities to users. The proposed Holy-Land ontology is the first of its kind attempting to encode knowledge about Palestine's CH. It plays a crucial role in our proposal, serving as a pivotal entity in the combination of language-based, location-based, and visual-based retrieval strategies.

Design and Research of Mobile Learning Recommendation System Based on Deep Learning Perspective

With the advent of the era of big data, the amount of information shows an exponential explosive growth trend. At the same time, the personalized needs of users are increasing. Facing the massive data, how to help users quickly and accurately obtain the information they need is the main challenge facing them at present. With the rapid development of computer technology and communication technology, mobile teaching and deep learning have become new research hotspots in the field of education. Mobile education has become a very fashionable education mode, which not only brings modern people a more convenient education system, but also makes modern learners need not worry about learning time and content. Traditional recommendation methods generally have problems such as sparse data, cold start and difficulty in feature extraction. On the basis of expounding the concept, connotation and main characteristics of deep learning, this paper applies deep learning theory to mobile recommendation system, hoping to gradually improve and promote the existing mobile education and provide an effective learning way and method for learners.

The quality of user experiences for mobile recommendation systems: an end-user perspective

PurposeThis paper attempts to identify key factors (i.e., personalization, privacy awareness and social norms) that affect user experiences (UXs) of mobile recommendation systems according to the user involvement theory (push-based and pull-based) and their relationships.Design/methodology/approachThe study is based on an online survey with students from an international business school located in southwestern China. The sample population for the study included randomly selected 600 university students who are active mobile phone users. A total of 470 questionnaires were returned; 456 were valid (14 were invalid due to the incompleteness of their responses), providing a response rate of 65%.FindingsSocial norms have the largest impact on user experience quality, followed by personalization and privacy awareness. User involvement in mobile recommendation systems has mediating effects on the above relationships, with larger effects on pull-based systems than on push-based systems.Originality/valueThis study provides an integrated framework for researchers to measure the effects of social, personal and risk factors on the quality of user experience. The results enrich the literature on user involvement, mobile recommendation systems and UX. The findings provide significant implications for both retailers and developers of mobile recommendation systems.

A Mobile-Based Tailored Recommendation System for Parents of Children with Overweight or Obesity: A New Tool for Health Care Centers

Childhood obesity is associated with unbalanced lifestyle patterns, and new strategies are needed to support parents in the compliance with the guidelines for children’s age. Tailored automatic recommendations mimic interpersonal counseling and are promising strategies to be considered for health promotion programs. This study aimed to develop and test a mobile recommendation system for parents of preschool children identified with overweight/obesity at health care centers. Evidence-based recommendations related to children’s eating, drinking, moving, and sleeping habits were developed and tested using a questionnaire. A pilot study was conducted in a health care center to test how using an app with those tailored recommendations, in video format, influenced parents’ perceptions of the child’s weight status and their knowledge about the guidelines, compared to a control group. The chi-squared test was used for categorical variables and the Mann–Whitney U test for continuous variables (p < 0.05). A high proportion of parents were already informed about the guidelines, but their children were not meeting them. After watching the tailored recommendations, there was an increased knowledge of the guideline on water intake, but there was no improvement in the perception of the child’s excessive weight. Parents may benefit from a mobile-based tailored recommendation system to improve their knowledge about the guidelines. However, there is a need to work with parents on motivation to manage the child’s weight with additional strategies.

Makan@Local Chatok: Mobile Eatery Recommendation System Based on Local Knowledge

&lt;p&gt;This paper discusses a unique business model of eatery recommender system based on local knowledge using mobile platform. The business model is developed to define the business concept of the innovation which is a rural innovation involving multiple entities (locals, eatery owners and users who are searching for eatery). The innovation highlights on local knowledge crowdsourced from the participation of locals through gamification activities included in the mobile app. In achieving the aim, the design science methodology was adapted in this study which consists of 4 phases: (i) Awareness of Problem, (ii) Suggestion, (iii) Evaluation, and (iv) Conclusion. The proposed business model was developed through a few activities including literature review, comparative study dan preliminary study. Then, the study continued with developing a prototype known as Makan@Local Chatok (M@LC) app and evaluated the app in terms of its usability aspects. Results from the usability testing concludes that the app is perceived as easy to use. It was also found that the proposed business model has been well-accepted by users. In conclusion, it is hoped that this study will not only demonstrate the potential and impact of mobile eatery recommendation system using local knowledge, but also provide a capstone on business research in the field of tourism industry.&lt;/p&gt;

High-Performance Homomorphic Matrix Completion on Multiple GPUs

In various applications such as trajectory tracking in mobile social networks and online recommendation systems, the massive raw data are often incomplete due to various unpredictable or unavoidable reasons. Matrix completion algorithms are effective for reconstructing two-dimensional data, but sending raw data containing personal, sensitive information to cloud computing nodes for matrix completion may lead to privacy exposure issue. The homomorphic matrix completion is a promising approach to perform matrix completion while preserving privacy. However, CPU-based homomorphic matrix completion has low performance, making it impractical to process multiple or large-scale data completion tasks in real-time. In this paper, we propose a high-performance homomorphic matrix completion scheme by exploiting commodity GPUs (Graphics Processing Units) that are widely available in HPC servers and cloud computing nodes. First, we design and implement a baseline GPU-based homomorphic matrix completion, and propose techniques to optimize memory accesses, GPU utilization, and communications. Second, we propose a shard mode for large-scale matrices exceeding GPU memory capacity. Third, we propose a multi-GPU mode to fully utilize multiple GPUs in computing nodes. Experiment results show that the proposed scheme is both fast and accurate. On matrices of varying sizes, the proposed scheme running on a single Tesla V100 GPU achieves up to 116.23× speedups over the CPU MATLAB implementation running on dual Xeon CPUs. The multi-GPU mode achieves up to 1.84× speedups on two GPUs versus on a single GPU. For large-scale matrices, the shard mode achieves up to 174.92× speedups on a single GPU over the CPU MATLAB implementation on two CPUs, and further achieves up to 1.35× speedups when running on two GPUs using the multi-GPU mode.

Improving Itinerary Recommendations for Tourists Through Metaheuristic Algorithms: An Optimization Proposal

In recent years, recommender systems have been used as a solution to support tourists with recommendations oriented to maximize the entertainment value of visiting a tourist destination. However, this is not an easy task because many aspects need to be considered to make realistic recommendations: the context of a tourist destination visited, lack of updated information about points of interest, transport information, weather forecast, etc. The recommendations concerning a tourist destination must be linked to the interests and constraints of the tourist. In this research, we present a mobile recommender system based on Tourist Trip Design Problem (TTDP)/Time Depending (TD) - Orienteering Problem (OP) - Time Windows (TW), which analyzes in real time the user's constraints and the points of interest's constraints. For solving TTDP, we clustered preferences depending on the number of days that a tourist will visit a tourist destination using a k-means algorithm. Then, with a genetic algorithm (GA), we optimize the proposed itineraries to tourists for facilitating the organization of their visits. We also used a parametrized fitness function to include any element of the context to generate an optimized recommendation. Our recommender is different from others because it is scalable and adaptable to environmental changes and users' interests, and it offers real-time recommendations. To test our recommender, we developed an application that uses our algorithm. Finally, 131 tourists used this recommender system and an analysis of users' perceptions was developed. Metrics were also used to detect the percentage of precision, in order to determine the degree of accuracy of the recommender system. This study has implications for researchers interested in developing software to recommend the best itinerary for tourists with constraint controls with regard to the optimized itineraries.

A switching hybrid mobile recommender system for tourists

This paper proposes a switching feature-based model that leverages the needs of both new and existing users for recommendation of tourist locations. In an attempt to solve the cold-start problem, recommendations to new users are implemented with Bayesian algorithm on supplied demographic data. For existing users, the system switches to the collaborative filtering subsystem, where recommendation results are produced using Pearson correlation computation and offered based on the items in the database. The model was validated with discounted cumulative gain, precision, and recall. A comparative analysis with some existing systems showed lower mean absolute error. Experimental results obtained from the survey of different categories of users showed the effectiveness of the proposed techniques.

A switching hybrid mobile recommender system for tourists

A switching hybrid mobile recommender system for tourists

A scientometric analysis of mobile recommender systems

A scientometric analysis of mobile recommender systems