Maximize User Satisfaction Research Articles

An Expectation-Maximization framework for Personalized Itinerary Recommendation with POI Categories and Must-see POIs

In this paper, we introduce a novel deterministic method based on Expectation Maximization (EM) to solve the rather complex problem of designing a tourist trip or Personalized Itinerary Recommendation (PIR). PIR objective is to recommend a personalized tour consisting of successive Points of Interest (POIs), which maximizes user satisfaction and respects user time-frame constraints. On top of that, the POIs are divided into categories, in order for travelers to be able to set limits on the maximum (and minimum) number of POIs that belong to one category and are included in the itinerary. In the proposed framework, emphasis is given on the POIs sequence selection, which exploits the customized POI recommendations offered by a recommender system. Additionally, the proposed methodology with POIs categories is able to solve the TourMustSee problem, so that the tour includes a set of POIs that must be visited. The proposed system has been successfully incorporated into a mobile app, offering a complete tourist trip design. The high performance, resilience, and computational efficiency of the proposed framework are demonstrated by experimental findings and comparisons to existing approaches on numerous synthetic and real datasets.

Can Optimized Genetic Algorithms Improve the Effectiveness of Homestay Recommendation Systems in Smart Villages? A Case of Thailand

ABSTRACTThis paper introduces a novel approach to optimize genetic algorithms (GAs) for homestay recommendation systems, specifically designed for smart village tourism destinations. Researchers developed an advanced GA focused on maximizing user satisfaction, the main quality metric. The algorithm was tailored to address the dynamic nature of homestay offerings and the varied preferences of travelers, using users' reviews, listing attributes, and historical booking data. The GA framework included a custom encoding scheme, fitness function, and parameters. Validation occurred through a case study in a smart village, with the algorithm's effectiveness tested via user surveys and ratings. Results showed that GA‐driven recommendations surpassed traditional methods, enhancing user satisfaction, trust, and booking rates while benefiting hosts with positive reviews. The optimized GA improved recommendation accuracy and efficiency, boosting economic benefits for local communities and contributing significantly to recommendation system research.

Applying Multi-Armed Bandit algorithms for music recommendations at Spotify

This study explores the application of multi-armed bandit algorithms in enhancing music recommendation systems, with a focus on Spotify. It delves into the Explore-Then-Commit (ETC), Upper Confidence Bound (UCB), and Thompson Sampling (TS) algorithms, evaluating their efficacy within the Spotify context. The primary objective is to determine which algorithm optimally balances exploration and exploitation to maximize user satisfaction and engagement. The research reveals that the ETC algorithm, with its rigid exploration and exploitation phases, incurs a notably higher regret value. This rigidity can lead to missed opportunities in identifying optimal choices and hinder adaptability to evolving user preferences. Conversely, the UCB and TS algorithms exhibit remarkable adaptability and a flexible balance between exploration and exploitation. This flexibility translates into more personalized and satisfactory user experiences in music recommendations. However, the selection of the most appropriate algorithm should be contingent on the size and characteristics of the specific user dataset, as well as the fine-tuning of algorithm parameters to align with user preferences and behaviors.

A Task Offloading Method Based on User Satisfaction in C-RAN With Mobile Edge Computing

With the continuous development of the communication service industry, users pay more attention to the quality of network service. Previous studies on offloading problems, especially in the Cloud Radio Access Network (C-RAN) architecture with Mobile Edge Computing (MEC), are primarily focused on the economic perspective, with little consideration given to user-oriented satisfaction problems. To fill this gap, this paper proposes a mathematical model for maximizing user satisfaction in the C-RAN architecture with multi-layer MEC. The problem is divided into two stages for solution. The first stage addresses the optimal connection problem between users and Remote Radio Heads (RRHs). The second stage then schedules user tasks reasonably based on the solution obtained in the first stage. The two-stage problems are all proved to be NP-Hard. Two efficient approximation algorithms, namely User-to-RRH Association Algorithm (URAA) and Maximum Satisfaction Algorithm (MSA), are proposed to solve the problems in different stages. This paper proves and analyzes the theoretical performance of the two algorithms. Finally, the performance of the proposed algorithms is verified by simulation experiments. The experimental results demonstrate that the two proposed algorithms can achieve reasonable solutions to the problems, and the user satisfaction level can be maintained at a high level.

Sample-Constrained Black Box Optimization for Audio Personalization

We consider the problem of personalizing audio to maximize user experience. Briefly, we aim to find a filter h*, which applied to any music or speech, will maximize the user’s satisfaction. This is a black-box optimization problem since the user’s satisfaction function is unknown. Substantive work has been done on this topic where the key idea is to play audio samples to the user, each shaped by a different filter hi, and query the user for their satisfaction scores f(hi). A family of “surrogate” functions is then designed to fit these scores and the optimization method gradually refines these functions to arrive at the filter ˆh* that maximizes satisfaction. In certain applications, we observe that a second type of querying is possible where users can tell us the individual elements h*[j] of the optimal filter h*. Consider an analogy from cooking where the goal is to cook a recipe that maximizes user satisfaction. A user can be asked to score various cooked recipes (e.g., tofu fried rice) or to score individual ingredients (say, salt, sugar, rice, chicken, etc.). Given a budget of B queries, where a query can be of either type, our goal is to find the recipe that will maximize this user’s satisfaction. Our proposal builds on Sparse Gaussian Process Regression (GPR) and shows how a hybrid approach can outperform any one type of querying. Our results are validated through simulations and real world experiments, where volunteers gave feedback on music/speech audio and were able to achieve high satisfaction levels. We believe this idea of hybrid querying opens new problems in black-box optimization and solutions can benefit other applications beyond audio personalization.

Efficient User Association Strategy for Maximizing User Satisfaction and Resource Utilization in Heterogeneous Cloud Radio Access Networks (H-CRANs)

The primary aim of this study is to present a User Association Strategy that can effectively optimize the Heterogeneous Cloud Radio Access Network (H CRAN). The primary objective of this strategy is to enhance customer satisfaction by optimizing the utilization of available network resources, such as transmission power and bandwidth. To achieve this objective, the proposed approach employs a logarithmic barrier function to address inequality constraints and transform the optimization problem into a formulation that facilitates effective convergence towards the optimal solution.

Visit planner: A personalized mobile trip design application based on a hybrid recommendation model

The paper presents Visit Planner (ViP), a mobile application prototype that provides a solution to the challenging tourist trip design problem. ViP follows a holistic approach offering personalized recommendations for Points of Interest (POIs) based on preferences either explicitly collected by the application, or inferred by the users? ongoing interaction with the system. ViP proposes to the final user, a trajectory of POIs calculated using an Expectation Maximization method that maximizes user satisfaction taking into consideration a variety of time and spatial constraints for both users and POIs. Additionally, POIs are divided into categories, so that a certain number of POIs from each category to be included in the final itinerary. The application is implemented as a user-interactive system that allows the flexibility for easy content adaptation and facilitates management of content and services by the user. The prototype has been implemented for Android-based smartphones, on an open application environment, using standard communication protocols and open database technology. Currently, it is applied to the city of Agios Nikolaos in Crete, and is available for download from Google play.

Interference-Aware Deployment for Maximizing User Satisfaction in Multi-UAV Wireless Networks

In this letter, we study the deployment of Unmanned Aerial Vehicle mounted Base Stations (UAV-BSs) in multi-UAV cellular networks. We model the multi-UAV deployment problem as a user satisfaction maximization problem, that is, maximizing the proportion of served ground users (GUs) that meet a given minimum data rate requirement. We propose an interference-aware deployment (IAD) algorithm for serving arbitrarily distributed outdoor GUs. The proposed algorithm can alleviate the problem of overlapping coverage between adjacent UAV-BSs to minimize inter-cell interference. Therefore, reducing co-channel interference between UAV-BSs will improve user satisfaction and ensure that most GUs can achieve the minimum data rate requirement. Simulation results show that our proposed IAD outperforms comparative methods by more than 10% in user satisfaction in high-density environments.

Location Optimization for Community Smart Parcel Lockers Based on Bilevel Programming

With the rapid development of e-commerce and the dramatic upsurge in direct-to-consumer deliveries, the last-mile problem has become increasingly apparent. With the distinct advantages of bringing economies of scale and providing 24/7 contactless self-service, smart parcel lockers play a critical role in solving the last-mile problem. However, due to a lack of planning, myopia expansion, and an ambiguous profit model, smart parcel locker suppliers in China have been suffering huge economic losses, restricting their further development. In the study, on the basis of an in-depth analysis of the cost elements and major revenue sources of smart parcel lockers, we propose a bilevel programming model to optimize the location of community smart parcel lockers with the upper-level model maximizing the profit of a third-party smart parcel locker supplier and the lower-level model maximizing user satisfaction. Then, a solution algorithm based on the genetic algorithm is proposed. Finally, some numerical experiments are carried out based on a medium-scale residential community in Jiading District, Shanghai. The sensitivity analyses conducted in this study reveal how the user satisfaction evaluation and the investment budget influence the expected profit. The modelling framework and numerical results can provide third-party smart parcel locker suppliers with significant theoretical support and practical guidance on planning the investment budget and optimizing the smart parcel locker locations to maximize their profit.

An Energy Saving Control Strategy Based on Multi-Agent Q-Learning Algorithm for Data Center

In recent years, the application of green renewable energy to data centers has become an important trend. Traditional solutions lack the consideration of matching tasks to renewable energy supplies. Therefore, in the face of diverse real-time computing tasks, how to reduce the total energy cost while ensuring the quality of service is an important challenge for the data center in the future. In this paper, our focus is on using the information on renewable energy supply and task characteristics as input states to assign tasks that maximize user satisfaction while meeting the minimum total cost of energy consumption. We consider the diversity of real-time tasks and design three different task types: the most crucial task, the crucial task and the non-crucial task. According to the different characteristics of these tasks, we propose a scheduling algorithm based on multi-agent, which uses multiple sets of agents with different initial positions to parallel search in different dimensions of the parameter space to find the optimal solution. To further optimize the algorithm, we eliminate the centralized noise solution based on the Pareto sorting method and sort the multiple optimal solutions to highlight the most suitable solution. The experimental results show that the proposed algorithm compared with other algorithms can reduce the total energy consumption by 11% and increase the customer satisfaction by 13% on average, and has better performance and applicability.

Adversarial Machine Learning in Recommender Systems

Recommender systems are ubiquitous. Our digital lives are influenced by their use when, for instance, we select the news to read, the product to buy, the friend to connect with, and the movie to watch. While enormous academic research efforts have been mainly focused on getting high-quality recommendations to reach maximum user satisfaction, little effort has been devoted to studying the integrity and security of these systems. Is there an underlying relationship between the characteristics of the historical user-item interactions and the efficacy of injection of false users/feedback strategies against collaborative models? Can public semantic data be used to perform attacks more potent in raising the recommendability of victim items? Can a malicious user poison or evade the image data of visual recommenders with adversarial perturbed product images? Is the family of model-based recommenders more vulnerable to multi-step gradient-based adversarial perturbations? Furthermore, is the adversarial training robustification still effective in the last scenario? Is this training defense influencing the beyond-accuracy and bias performance? This dissertation intends to pave the way towards more robust recommender systems, beginning with understanding how to robustify a model, what is the cost of robustness in terms of reduction of recommendation accuracy, and which are the novel adversarial risks of modern recommenders. This thesis, getting inspiration from the literature on the security of collaborative models against the insertion of hand-engineered fake profiles and the recent advances of adversarial machine learning methods in other research areas like computer vision, contributes to several directions: (i) the proposal of a practical framework to interpret the impact of data characteristics on the robustness of collaborative recommenders [Deldjoo et al., 2020], (ii) the design of powerful attack strategies using publicly available semantic data [Anelli et al., 2020], (iii) the identification of severe adversarial vulnerabilities of visual-based recommender models where adversaries can break the recommendation integrity by pushing products to the highest recommendation positions with a simple and human-imperceptible perturbation of products' images [Anelli et al., 2021b], (iv) the proposal of robust adversarial perturbation methods capable of completely breaking the accuracy of matrix factorization recommenders [Anelli et al., 2021a], and (v) a formal study that examines the effects of adversarial training in reducing the recommendation quality of state-of-the-art model-based recommenders Anelli et al. [2021c]. Awarded by: Politecnico di Bari, Bari, Italy on 24 January 2022. Supervised by: Tommaso DI Noia. Available at: https://iris.poliba.it/retrieve/dd89f8a6-faa4-ccdd-e053-6605fe0a1b87/Adversarial_Machine_Learning_in_Recommender_Systems.pdf.

Study on Sustainable Development Oriented Community Public Hospital in China Based on Optimal Decision Making Model for Environment Renovation

Community public hospital provides public health and basic medical services, and their construction environment has an important impact on the health and well-being of the residents. Due to the long construction period of most community hospitals, the population expansion and the change in age structure have led to a mismatch between the needs of patients and the current situation, which is in urgent need of renovation. This paper aims to support the government and hospitals in making decisions by eliminating the blind spots in capital investment and benefit evaluation. In this study, environmental modification design variables are first established, and on this basis, the fuzzy Delphi method is used to understand the willingness for renovation on the part of patients, accompanying personnel, staff, healthcare workers as well as hospital administrators. Besides, the I-S model is used to identify the renovation projects that would maximize user satisfaction. Furthermore, the differences between patients and medical staff are compared. The ODM (Optimal Decision-making) model is used to evaluate the cost investment and benefits, which provides support for the decision-making of government and hospitals. The results clarify the key renovation design variables that can significantly improve user satisfaction and extend them into renovation strategies that can be landed, and identify renovation strategies with larger improvement scores and the range of renovation funds that maximize benefits to promote the sustainable development of community public hospitals. It can be seen that the ODM model can also be well applied to the renovation of community healthcare services. In addition, the reference classification and design variables should be adjusted according to the characteristics of China, taking into consideration the specificity of individual hospitals.

A research on family flexible load scheduling based on improved non-dominated sorting genetic algorithm

In demand response scheduling, residential electricity load has huge scheduling potential. However, the diversification of characteristics of residential electricity load, the diversity of user demands, and the poor convergence and susceptibility to local optimal solutions of scheduling optimization algorithms significantly increase the difficulty of demand response scheduling. To address the heterogeneity of the load, this paper proposes a new classification method for household electricity load, which is divided into rigid load and flexible load based on different electricity characteristics, and further divides flexible load into interruptible load, non-interruptible load, and reducible load, and establishes mathematical models for each type of load. To address the diversity of user demands, this paper proposes three optimization objectives: minimum electricity cost, minimum carbon emissions, and maximum user satisfaction, which can be comprehensively optimized based on user electricity demands. To address the slow convergence and susceptibility to local optimal solutions of the traditional NSGA-III algorithm, this paper improves the traditional NSGA-III algorithm by using adaptive crossover and mutation to improve algorithm convergence speed and selecting individuals based on crowding distance to avoid local optimal solutions. The results show that compared with the user's original electricity consumption behavior, this method can save up to 21.1% of electricity costs, reduce carbon emissions by up to 10.2%, improve user electricity satisfaction by up to 41.2%, and reduce peak-to-valley difference by up to 42.3%. This provides a powerful basis for residential buildings to participate in demand response scheduling and provides a reference path for achieving low-carbon development goals in the building field.

Hierarchical Vehicle Scheduling Research on Tide Bicycle-Sharing Traffic of Autonomous Transportation Systems

To facilitate the intelligent and automated provision of mobility services by autonomous transportation systems, bike-sharing can be a supplement to public transport for addressing their point-to-point issue, namely, “last mile” service. However, according to the different nature of land use, the uneven spatio-temporal distribution of travel demand can directly lead to difficult access to bikes with high travel costs for users and operating costs for operators. Based on this, this paper analyzes the user behavior patterns within different areas by using GeoHash encoding and proposes a hierarchical autonomous vehicle scheduling model based on tide bicycle-sharing traffic, namely, HATB. It minimizes operating costs and maximizes user satisfaction to dynamically optimize scheduling routes and required vehicles within each layered zone. As for extracting historical orders of Mobike in Beijing, an example analysis through the genetic algorithm of HATB is conducted to support effective and efficient scheduling. Compared to existing scheduling methods, HATB has faster convergence and lower time complexity, which improves bike turnaround efficiency and practical application ability, thus making it more convenient for the public to travel during peak hours.

Usability analysis of environmental disaster mitigation efforts in Lampung Province: case study ofJaring Bencanaapplication

Disaster management requires a variety of innovations to intervene or prevent the adverse effects of the disaster, including through various applications made for various purposes and uses. One of the applications is theJaring Bencana, to strengthen the mitigation aspects of natural and non-natural disasters, including environmental disasters. This study aims to examine the levelof usabilityin disaster applications by measuring the variables of effectiveness, efficiency, and user satisfaction. The method used in this study isusability testingwith techniqueperformance measurementsandretrospective think-aloud. Respondents in this study 30 individuals as test participants, were selected purposively based on criteria of interest and responsibility in disaster management. Results from testingusabilityshow that mark component effectiveness is significant at 89%, mark efficiency component of 0.24goals/second, and satisfaction score of 68. It can be concluded that theJaring Bencanaapplication has been functionally effective and efficient, although it must be optimized to achieve maximum user satisfaction. The results of this research have implications for the development of disaster applications that are in accordance with disaster needs.

Dynamic clustering based contextual combinatorial multi-armed bandit for online recommendation

Recommender systems still face a trade-off between exploring new items to maximize user satisfaction and exploiting those already interacted with to match user interests. This problem is widely recognized as the exploration/exploitation (EE) dilemma, and the multi-armed bandit (MAB) algorithm has proven to be an effective solution. As the scale of users and items in real-world application scenarios increases, their purchase interactions become sparser. Then three issues need to be investigated when building MAB-based recommender systems. First, large-scale users and sparse interactions increase the difficulty of user preference mining. Second, traditional bandits model items as arms and cannot deal with ever-growing items effectively. Third, widely used Bernoulli-based reward mechanisms only feedback 0 or 1, ignoring rich implicit feedback such as behaviors like click and add-to-cart. To address these problems, we propose an algorithm named Dynamic Clustering based Contextual Combinatorial Multi-Armed Bandits (DC3MAB), which consists of three configurable key components. Specifically, a dynamic user clustering strategy enables different users in the same cluster to cooperate in estimating the expected rewards of arms. A dynamic item partitioning approach based on collaborative filtering significantly reduces the scale of arms and produces a recommendation list instead of one item to provide diversity. In addition, a multi-class reward mechanism based on fine-grained implicit feedback helps better capture user preferences. Extensive empirical experiments on three real-world datasets demonstrate the superiority of our proposed DC3MAB over state-of-the-art bandits (On average, +75.8% in F1 and +54.3% in cumulative reward). The source code is available at https://github.com/HaixHan/DC3MAB.

Dynamic Coverage Optimization for 5G Ultra-dense Cellular Networks Based on Their User Densities

This paper has proposed a user-density-based coverage optimization technique for ultra-dense cellular networks. Antenna tilting is a promising coverage optimization technique to be used in 5G networks, that significantly improve the signal to interference plus noise ratio (SINR) by choosing the appropriate angle of tilt. In this paper, the cellular coverage has been optimized for scattered user densities/user hotspots using an adaptive antenna tilting mechanism that steers the beams towards the temporal hot spot in the coverage area. The proposed method has the competence to improve the desired SINR level and coverage area for a group of users rather than a single user. In this work, a reinforcement learning (RL) algorithm has been implemented to optimize the tilt angle. The performance of the proposed technique has been evaluated in the simulation platform considering a three-sectored multicellular mobile network where the groups of user clusters are distributed randomly. The result confirms the improvement in RSS and SINR values in the group of users having high density with maximum user satisfaction.

Consensus Building using Deep Reinforcement Learning for Energy Management

A variety of information is collected from IoT devices. As those devices become more familiar to users, network services must consider the influence of the user. We propose a method to maximize the value from power consumption and minimize the cost incurred to ensure user satisfaction. However, one problem is that user satisfaction cannot increase because it is considered a constraint on power consumption. In this paper, we propose a consensus building method to minimize power consumption and maximize user satisfaction. An exhaustive search incurs a large calculation overhead to determine device parameters. Thus, the proposed method uses reinforcement learning to solve this problem. From its evaluation, we clarify that the proposed method attains about 1.5 times the total reward compared with the conventional method. Moreover, we also clarify that 99.9% of the total reward can be achieved, compared to the exhaustive search.

Effect Measurement for Human Motion Rehabilitation Training Using Improved Deep Reinforcement Learning and IoT Networks

Measuring the effect of human motion rehabilitation training is important to help persons develop motion rehabilitation training plans. The current human motion rehabilitation training effect measurement algorithm has the problems of too large gap between the smoothness of the motion speed curve and the reality, high key frame extraction error rate, low measurement accuracy, long measurement time, and low satisfaction. Therefore, this paper proposes a human motion rehabilitation training effect measurement algorithm using improved deep reinforcement learning and Internet of Things (IoT) networks using IoT network technology to collect human motion rehabilitation training videos. The key frames of the human motion rehabilitation video data are extracted according to the interframe distance, and the metalearning method is used to improve the deep reinforcement learning network, and the obtained key frames are input into the improved deep reinforcement learning network to obtain the motion speed curve of human motion rehabilitation training. The smoothness of the motion velocity curve is calculated, and high smoothness indicates a good human motion rehabilitation training effect, while low smoothness indicates a poor human motion rehabilitation training effect, so as to complete the measure of human motion rehabilitation training effect. The results show that the smoothness of the motion speed curve of the proposed algorithm is closer to reality, the average error rate of key frame extraction is 1.45%, the measurement accuracy of rehabilitation training is more than 90%, the measurement time is controlled below 2.1 s, and the maximum user satisfaction is 93.1, which shows that the practical application of the algorithm is good.

Decentralized cooperative approach for electric vehicle charging

The proliferation in the deployment of electric vehicles has brought up several challenges in the planning and operation of power systems. The health of power system components and the satisfaction of electric vehicle users are becoming equally important with the increasing presence of electric vehicles on the power grid. The charging strategy is crucial as it plays a significant role in shaping users’ behavior to deal with the adverse effects of electric vehicles on grid components. There is a lack of a proper unified framework for the charging management, which considers both the system perspectives such as transformer overloading, shortage of power, and users perspectives such as satisfaction, charging urgency, and privacy. This paper presents a fully decentralized cooperative approach/strategy for charging electric vehicles. The solution is achieved by developing a decentralized iterative algorithm based on a consensus concept to protect the privacy of EV owners. The charging priority factor is incorporated to address the charging urgency of electric vehicles. Multiple electric vehicles can be charged simultaneously without a central decision-maker or coordinator using the proposed strategy. As a result, electric vehicles fulfill their charging needs by the deadline to maximize user satisfaction while respecting their constraints and limitations imposed by the available charging power and charging station capacity. The convergence of the proposed approach is demonstrated by observing the charging of multiple electric vehicles. The results are benchmarked against the centralized approach to verify the effectiveness of the proposed approach.