Search Results (28)

Knowledge-graph-based recommendation aims to provide personalized recommendation services to users based on their historical interaction information, which is of great significance for shopping transaction rates and other aspects. With the rapid growth of online shopping, the knowledge graph constructed from users’ historical interaction data now incorporates multiattribute information, including timestamps, images, and textual content. The information of multiple modalities is difficult to effectively utilize due to their different representation structures and spaces. The existing methods attempt to utilize the above information through simple embedding representation and aggregation, but ignore targeted representation learning for information with different attributes and learning effective weights for aggregation. In addition, existing methods are not sufficient for effectively modeling temporal information. In this article, we propose MTR, a knowledge graph recommendation framework based on mixture of experts network. To achieve this goal, we use a mixture-of-experts network to learn targeted representations and weights of different product attributes for effective modeling and utilization. In addition, we effectively model the temporal information during the user shopping process. A thorough experimental study on popular benchmarks validates that MTR can achieve competitive results. Full article

The expansion of urban underground spaces has broadened the range of urban activities by accommodating functions such as transportation, retail, and entertainment. Underground shopping malls (USMs) have been widely developed as a sustainable strategy to expand urban space capacity, alleviate surface congestion, and optimize land-use efficiency. However, the development and utilization of USMs often neglect user-centered evaluations, risking mismatches between design outcomes and long-term sustainability goals such as energy efficiency, user retention, and spatial adaptability. Therefore, this study analyzes 12 typical USMs in Nanjing, China, based on environmental psychology principles, employing mixed-methods research that combines objective measurements of spatial elements with subjective user perception surveys to establish a regression model investigating correlations between USM spatial–physical environments and user comfort perception. The results show that users generally have a positive impression of the current underground environment, but there are significant differences in their subjective perceptions of the different attributes of the USMs. The USMs present a trend of humanization, human culture, and landscape in terms of spatial characteristics. These improvements are critical for fostering long-term sustainable use by minimizing vacancy rates and retrofitting needs. The findings reveal that the human-centric comfort level of the USMs is largely determined by multi-dimensional architecture-space features, as well as personal and social activity level features. Building on these insights, we propose actionable strategies to advance sustainable USM design, prioritizing adaptive reuse, energy-efficient layouts, and culturally resonant esthetics. This work clarifies the direction of USM design optimization and improvement from the perspective of users’ subjective perception and provides a theoretical foundation for aligning underground development with global sustainability frameworks like the UN SDGs. Full article

Background/Objectives: The integration of Augmented Reality (AR) and Artificial Intelligence (AI) in educational applications presents an opportunity to enhance learning outcomes in young users. This study focuses on ARFood, a serious game designed to teach Generation Alpha about nutritional health and environmental sustainability. The objective is to evaluate and improve the effectiveness of the app’s AI-driven feedback mechanisms in achieving specific educational goals in these domains. Methods: ARFood features two AI-powered Non-Player Characters (NPCs), each programmed to evaluate virtual shopping carts created by users. The nutritional NPC provides feedback on dietary choices, while the sustainability NPC assesses environmental impacts. Ninety-three participants were involved, generating 83 virtual carts that were evaluated by both NPCs. Each NPC’s feedback was assessed for alignment with five predefined educational objectives per theme using a zero-shot RoBERTa classifier. An iterative process was employed to refine the NPC prompts, increase the weight of underrepresented objectives, and re-evaluate virtual carts until all objectives were satisfactorily addressed. Results: Initial evaluations revealed uneven alignment across educational objectives, particularly in areas such as resource conservation and balanced diet planning. Prompt refinement led to a significant improvement in feedback quality, with the final iterations demonstrating comprehensive coverage of all educational objectives. Conclusions: This study highlights the potential of AR and AI in creating adaptive educational tools. Iterative prompt optimization, supported by zero-shot classification, was effective in enhancing the app’s ability to deliver balanced, goal-oriented feedback. Future applications can leverage this approach to improve educational outcomes across various domains. Full article

To improve recommendation systems, it is essential to enhance both their practicality and accuracy, thereby supporting users in making informed shopping decisions. Incorporating two types of product relationships can effectively achieve these goals: first, the product relationships, like complements, and second, the social relationships among users. However, existing studies have paid little attention to user-side information or item-side information. This paper proposes a product recommendation model that utilizes cross-elasticity of demand and hypergraphs, referred to as Hg-CR. First, users and items build a hypergraph. The user–item interactions form the hyperedges. Also, users build a hypergraph between themselves based on their social relationships. Second, hypergraph attention networks (HANs) learn the relationships between nodes. They capture the key features of nodes and hyperedges with a high degree of adaptability. A community detection algorithm organizes users into groups for product recommendations by assessing their similarities. Within different communities, individuals seek complementary products based on the cross-elasticity theory of demand. Additionally, we provide recommendations for complementary products. Tests on real datasets show that the Hg-CR model is about 10% more accurate than the other baseline models. Full article

This article examines the incorporation of the Shopping Assistance Automatic Suggestion (SAAS) model into Virtual Reality (VR) environments in order to improve the online shopping experience. The SAAS model employs sophisticated deep learning methods to offer customized product recommendations, which are conveyed by non-player characters (NPCs) via voice-based interactions. Our goal is to develop an interactive shopping experience that replicates real-life interactions by integrating AI-powered recommendations with immersive VR technology. We gather and standardize data from several open commerce databases, such as Amazon Product and Customer Reviews. The SAAS model, in conjunction with GPT-3, BERT, and T5, undergoes training and testing to evaluate its effectiveness across multiple criteria. The results demonstrate that the SAAS model surpasses other models in delivering contextually aware and pertinent recommendations. The integration process outlines the specific steps involved in capturing, processing, and transforming user interactions in virtual reality (VR) into vocal suggestions provided by non-player characters (NPCs). This strategy improves customization and utilizes the immersive features of virtual reality to effectively engage people. The results of our research establish a higher standard for e-commerce, with the goal of enhancing the user experience of online purchasing by making it more instinctive, engaging, and pleasurable. Full article

United Nations Sustainable Development Goal 11 indicates the need for and importance of inclusive public spaces as a prerequisite towards sustainable cities. Shopping malls in urban India attract a significantly large population daily, making them an important typology of urban structures which deserve universal design. Thus, in this paper, universal design features of shopping malls in Kolkata have been considered. Despite a significant increase in the number of elderly and specially-abled people, civic administration in Kolkata has not been able to successfully implement the national guidelines on inclusiveness in its shopping malls. Five shopping malls from the Kolkata Municipal Corporation were considered case areas for the fieldwork. The accessibility audit checklist included in the ‘Harmonized Guidelines and Standards for Universal Accessibility in India 2021’ published by the Ministry of Housing and Urban Affairs, Government of India, has been used in this paper. It was found that the accessibility percentage of shopping malls ranges between 14.4% and 44.8%, indicating the lack of universal design considerations. Pearson’s correlation between the year of establishment and the accessibility percentage of each case area was found to be −0.66, indicating an alarming deterioration in universal design considerations over the years. On comparing the accessibility performance with the diverse user groups, it was found that individual wheelchair users are likely to face the most difficulty in the case areas with a median accessibility value of 41.46%. This research indicated that accessible continuity in shopping malls in Kolkata can be imparted only by implementing case-specific universal design assessment through a primary survey. Full article

Efficient car parking management systems that minimize environmental impacts while maximizing user comfort are highly demanding for a future sustainable society. Using electric or gasoline vehicle-type information, emerging computation and communication technologies open the opportunity to provide practical solutions to achieve such goals. This paper proposes an eco-friendly smart parking management system that optimally allocates the incoming vehicles to reduce overall emissions in closed parking facilities while providing comfort incentives to the users of electric vehicles (EVs). Specifically, upon arrival of a car, the most suitable parking spot is determined by minimizing an adaptive objective function that indirectly reflects anticipatory operation for the overall performance maximization of the parking facility using electric or gasoline vehicle-type information. The adaptive objective function includes a trade-off factor that tunes driving and walking distances, relating emissions and comfort to treat incoming vehicles appropriately. The proposed system is simulated for managing a model car parking facility in a shopping complex in Japan, and the aspects related to fuel consumption, CO₂ emissions, and user comfort are evaluated and benchmarked with other standard parking management systems. The proposed system reduces CO₂ emissions and fuel consumption and improves parking efficiency compared to the current parking management systems, while also prioritizing user comfort. Full article

Cognitive ergonomics and the mental health of production workers have attracted increasing interest in industrial companies. However, there is still not much research available as it is regarding physical ergonomics and muscular load. This paper designs an experiment to analyze the cognitive ergonomics and mental stress of shop floor production workers interacting with different user interfaces of a Manufacturing Execution System (MES) that is adjustable for analyzing the influence of other assistive systems, too. This approach is going to be designed with the Design of Experiments (DoE) method. Therefore, the respective goals and factors are going to be determined. The environment will be the laboratories of the University of Applied Sciences Amberg-Weiden and its Campus for Digitalization in Amberg. In detail, there will be a sample assembly process from the automotive supplier industry for demonstration purposes. At this laboratory, the MES software from the European benchmark SAP is installed, and the respective standard Production Operator Desk is going to be used with slight adaptions. In order to make the cognitive ergonomics measurable, different approaches are going to be used. For instance, body temperature, heart rate and skin conductance as well as subjective methods of self-assessment are planned. The result of this paper is a ready-to-run experiment with sample data for each classification of participants. Further, possible limitations and adjustments are going to be discussed. Finally, an approach to validating the expected results is going to be shown and future intentions are going to be discussed. Full article

A recommendation system serves as a key factor for improving e-commerce users’ satisfaction by providing them with more accurate and diverse suggestions. A significant body of research has examined the accuracy and diversity of a variety of recommendation systems. However, little is known about the psychological mechanisms through which the recommendation system influences the user satisfaction. Thus, the purpose of this study is to contribute to this gap by examining the mediating and moderating processes underlying this relationship. Drawing from the traditional task-technology fit literature, the study developed a moderated mediation model, simultaneously considering the roles of a user’s feeling state and shopping goal. We adopted a scenario-based experimental approach to test three hypotheses contained in the model. The results showed that there is an interaction effect between shopping goals and types of recommendation (diversity and accuracy) on user satisfaction. Specifically, when a user’s shopping goal aligns with recommendation results in terms of accuracy and diversity, the user satisfaction is enhanced. Furthermore, this study evaluated the mediating role of feeling right and psychological reactance for a better understanding of this interactive relationship. We tested the moderated mediation effect of feeling right and the psychological reactance moderated by the user shopping goal. For goal-directed users, accurate recommendations trigger the activation of feeling right, consequently increasing the user satisfaction. Conversely, when exploratory users face accurate recommendations, they activate psychological reactance, which leads to a reduction in user satisfaction. Finally, we discuss the implications for the study of recommendation systems, and for how marketers/online retailers can implement them to improve online customers’ shopping experience. Full article

In recent years, the interest in recommendation systems (RSs) has dramatically increased, as they have become main components of all online stores. The aims of an RS can be multifaceted, related not only to the increase in sales or the convenience of the customer, but may include the promotion of alternative environmentally friendly products or to strengthen policies and campaigns. In addition to accurate suggestions, important aspects of contemporary RSs are therefore to align with the particular marketing goals of the e-shop and with the stances of the targeted audience, ensuring user acceptance, satisfaction, high impact, and achieving sustained usage by customers. The current review focuses on RS related to retail shopping, highlighting recent research efforts towards enhanced e-shops and more efficient sustainable digital marketing and personalized promotion. The reported research was categorized by main approach, key methods, and specialized e-commerce problems addressed, while technological aspects were linked with marketing aspects. The increasing number of papers in the field showed that it has become particularly popular, following the explosive growth in e-commerce and mobile shopping. The problems addressed have expanded beyond the performance of the core algorithms to the business aspects of recommendation, considering user acceptance and impact maximization techniques. Technologies have also shifted from the improvement of classic filtering techniques to complex deep learning architectures, in order to deal with issues such as contextualization, sequence-based methods, and automatic feature extraction from unstructured data. The upcoming goals seem to be even more intelligent recommendations that more precisely adapt not only to users’ explicit needs and hidden desires but also to their personality and sensitivity for more sustainable choices. Full article

The European Union is committed to both lowering greenhouse gas emissions and promoting the adoption of electric vehicles (EVs) on its roads. To achieve these goals, it is imperative to speed up the development of the charging infrastructure as well as to ensure the effective integration of the charging infrastructure into distribution networks. Given that EV charging costs significantly contribute to the total cost of owning an EV, it is important to hedge against rising electricity prices and ensure affordable charging for the end users. Connecting solar power plants and battery storage to the electric vehicle charging stations (EVCSs) serves as a measure of hedging against potential future electricity price increases but also as an option that can contribute to reducing impact on the distribution network loading. In addition to this, connecting EVCS through grid connections of existing consumers (office/residential buildings, shopping malls, etc.) can reduce grid connection costs for EVCS but also contribute to electricity cost reduction for both EVCS and existing end consumers. Additionally, by integrating advanced charging strategies like the vehicle-to-everything (V2X) approach, the overall charging costs can be reduced even further. This paper focuses on optimizing the power supply and operation of EVCS by considering strategic investments in grid connection, photovoltaic plants, and battery energy storage. The research explores the potential savings derived from reduced energy/charging costs, along with the reduction in peak power expenses for different power supply options. In addition to this, the research explores the effect of different EV charging strategies as well as EVCS grid connection on optimal investments and total system costs. The combined investment and energy management problem is focused on determining the optimal EVCS power supply and operation while minimizing total investment and operation expenditures over the project lifetime. The underlying optimization problems for different supply scenarios are cast as mixed-integer linear programming problems that can be solved efficiently. The results show the influence of different grid connection options and EV charging strategies on the joint operation and costs of EVCS and existing buildings. Full article

The Web has provided an increasing proportion of use as a medium for e-commerce in addition to various recommender systems. It can be used for analyzing recommendation system-based feedback (e.g., a form in which a user inputs their preferences for various items as numerical values into a specific evaluation system) to estimate customer interest; in addition, analyzing multi-modal types of feedback (e.g., product purchase traces, inquiry lists, inquiry times, and comments) with deep learning can also be used to estimate user interest. As many companies around the world promote their products through micro-influencers on the Web, related research has continued to predict the purchase conversion rate of the influencer through a variety of technologies. In this work, we present a multi-modal micro-influencer analysis scheme for a marketing maximization strategy. Our scheme uses the multi-modal data stored in Mecha Solution’s own shopping mall of Korea, as well as famous Korean Internet platforms, and Coupang, Naver, and Oliveyoung’s data such as article posting comments and statistics information. By extracting the main characteristics of the real article postings from real users as opposed to those from factitious influencers posting articles and comments and identifying articles other than advertisements, influencer scores are obtained, assuming that articles other than advertisements can further increase the purchase conversion rate. Based on influencer score, we propose a multi-modal micro-influencer analysis scheme that recommends influencers use content-based collaborative filtering and user-based collaborative filtering for items that the influencer has not yet reviewed. The experiment was implemented to prove that the proposed scheme successfully achieves this goal. Full article

Accessibility is an increasingly important topic for Ecommerce, especially for individuals with vision problems. To improve their online experience, the design of a voice assistant has been proposed to allow these individuals to browse and shop online more quickly and efficiently. This voice assistant forms an intelligent system that can understand and respond to users’ voice commands. The design considers the visual limitations of the users, such as difficulty reading information on the screen or identifying images. The voice assistant provides detailed product descriptions and ideas in a clear, easy-to-understand voice. In addition, the voice assistant has a series of additional features to improve the shopping experience. For example, the assistant can provide product recommendations based on the user’s previous purchases and information about special promotions and discounts. The main goal of this design is to create an accessible and inclusive online shopping experience for the visually impaired. The voice assistant is based on a conversational user interface, allowing users to easily navigate an eCommerce website, search for products, and make purchases. Full article

Mobility as a Service (MaaS) is an innovative mobility service that aims to redesign the future of urban mobility by integrating multi-modal transportation and app-based technologies to enable seamless urban mobility. While MaaS pilot demonstrations and schemes implementation have taken place in different cities at a global level, and relevant studies focus on the MaaS barriers and users’ characteristics, the planning process for implementing MaaS is rarely presented. This paper summarizes the services to be integrated into the MaaS Athens’ demo site in Greece and describes the planning process that was followed to showcase the demo. The demo site is located within the urban area of Athens, including a public transport operator, a bike-sharing service, a taxi operator, and a municipality public transport operator. The demonstration runs developments in a real corridor that has the potential to prepare the MaaS eco-system deployment and market uptake. Three travel cases are planned: (1) Multimodal work trip; (2) MaaS for tourists; and (3) Interurban/urban interfaces, for work and shopping/leisure trips. The user journeys are defined in detail and the main information for each user journey is presented. The study concludes with challenges that were faced during the demo planning and recommendations for achieving the MaaS goals. Full article

In today’s era, monitoring the health of the manufacturing environment has become essential in order to prevent unforeseen repairs, shutdowns, and to be able to detect defective products that could incur big losses. Data-driven techniques and advancements in sensor technology with Internet of the Things (IoT) have made real-time tracking of systems a reality. The health of a product can also be continuously assessed throughout the manufacturing lifecycle by using Quality Control (QC) measures. Quality inspection is one of the critical processes in which the product is evaluated and deemed acceptable or rejected. The visual inspection or final inspection process involves a human operator sensorily examining the product to ascertain its status. However, there are several factors that impact the visual inspection process resulting in an overall inspection accuracy of around 80% in the industry. With the goal of 100% inspection in advanced manufacturing systems, manual visual inspection is both time-consuming and costly. Computer Vision (CV) based algorithms have helped in automating parts of the visual inspection process, but there are still unaddressed challenges. This paper presents an Artificial Intelligence (AI) based approach to the visual inspection process by using Deep Learning (DL). The approach includes a custom Convolutional Neural Network (CNN) for inspection and a computer application that can be deployed on the shop floor to make the inspection process user-friendly. The inspection accuracy for the proposed model is 99.86% on image data of casting products. Full article