Search Results (219)

Recipes available on the web often lack nutritional transparency and clear indicators of dietary suitability. While searching by title is straightforward, exploring recipes that meet combined dietary needs, nutritional goals, and ingredient-level preferences remains challenging. Most existing recipe search systems do not effectively support flexible multi-dietary reasoning in combination with user preferences and restrictions. For example, users may seek gluten-free and dairy-free dinners with suitable substitutions, or compound goals such as vegan and low-fat desserts. Recent systematic reviews report that most food recommender systems are content-based and often non-personalized, with limited support for dietary restrictions, ingredient-level exclusions, and multi-criteria nutrition goals. This paper introduces DietQA, an end-to-end, language-adaptable chatbot system that integrates a Knowledge Graph (KG), Retrieval-Augmented Generation (RAG), and a Large Language Model (LLM) to support personalized, dietary-aware recipe search and question answering. DietQA crawls Greek-language recipe websites to extract structured information such as titles, ingredients, and quantities. Nutritional values are calculated using validated food composition databases, and dietary tags are inferred automatically based on ingredient composition. All information is stored in a Neo4j-based knowledge graph, enabling flexible querying via Cypher. Users interact with the system through a natural language chatbot friendly interface, where they can express preferences for ingredients, nutrients, dishes, and diets, and filter recipes based on multiple factors such as ingredient availability, exclusions, and nutritional goals. DietQA supports multi-diet recipe search by retrieving both compliant recipes and those adaptable via ingredient substitutions, explaining how each result aligns with user preferences and constraints. An LLM extracts intents and entities from user queries to support rule-based Cypher retrieval, while the RAG pipeline generates contextualized responses using the user query and preferences, retrieved recipes, statistical summaries, and substitution logic. The system integrates real-time updates of recipe and nutritional data, supporting up-to-date, relevant, and personalized recommendations. It is designed for language-adaptable deployment and has been developed and evaluated using Greek-language content. DietQA provides a scalable framework for transparent and adaptive dietary recommendation systems powered by conversational AI. Full article

Antimicrobial resistance (AMR) poses a significant global threat to human and animal health, necessitating robust surveillance and stewardship tools. While existing systems address aspects of veterinary AMR, a comprehensive, user-centric dashboard for U.S. veterinarians remains a critical unmet need. This study aimed to identify U.S. veterinarians’ preferences and perceived needs for such a dashboard, to help guide its design and development. A cross-sectional survey was conducted between January and March 2024, targeting U.S. veterinarians through professional channels. The survey instrument captured demographics, experiences with existing tools, preferences for data types and visualizations, desired technical specifications, and open-ended feedback. Of the 677 respondents, a near-unanimous consensus (over 75%) emerged on the importance of functionalities like antimicrobial stewardship education, off-label use guidance, surveillance data, and empirical treatment support. Over 70% expressed comfort sharing aggregated geographic and de-identified animal data. A strong preference was observed for making the dashboard accessible by veterinary colleges (78.87%), diagnostic laboratories (72.61%), and federal agencies (USDA: 71.47%, CDC: 66.67%, FDA: 62.11%), indicating a desire for a collaborative, authoritative system. The findings provide a robust foundation for developing a U.S. veterinary AMR dashboard. Future phases should adopt an iterative, user-centered design, incorporating qualitative research with diverse stakeholders and piloting a prototype with preferred institutional partners. This approach will ensure a trusted, sustainable tool that effectively translates surveillance data into actionable insights for improved animal and public health. Full article

With the rapid expansion of the electric vehicle (EV) market, optimizing the distribution of charging stations has attracted increasing attention. Unlike internal combustion engine vehicles, EVs are typically charged at the end of a trip rather than during transit. Therefore, analyzing EV users’ charging preferences based on their activity–travel patterns is essential. This study seeks to improve the operational efficiency and accessibility of EV charging stations in Lanzhou City by optimizing their spatial distribution. To achieve this, a novel multi-objective optimization model integrating NSGA-III and TOPSIS is proposed. The methodology consists of two key steps. First, the NSGA-III algorithm is applied to optimize three objective functions: minimizing construction costs, maximizing user satisfaction, and maximizing user convenience, thereby identifying charging station locations that address diverse needs. Second, the TOPSIS method is employed to rank and evaluate various location solutions, ultimately determining the final sitting strategy. The results show that the 232 locations obtained by the optimization model are reasonably distributed, with good operational efficiency and convenience. Most of them are distributed in urban centers and commercial areas, which is consistent with the usage scenarios of EV users. In addition, this study demonstrates the superiority in determining the distribution of charging station locations of the proposed method. In summary, this study determined the optimal distribution of 232 EV charging stations in Lanzhou City using multi-objective optimization and ranking methods. The results are of great significance for improving the operational efficiency and convenience of charging station location optimization and offer valuable insights for other cities in northwestern China in planning their charging infrastructure. Full article

Plant-based meat analogues (PBMAs) are positioned as promising alternatives to animal-based foods due to their potential environmental and health benefits. This study aimed to investigate the acceptability of PBMAs among trend-sensitive Swedish consumers, including both those who already eat PBMAs and those who do not. A questionnaire with both closed and open-ended questions was distributed digitally via social media using convenience/snowball sampling (n = 291). Data were analyzed using descriptive statistics, chi-square tests, and qualitative content analysis. The results show that PBMA consumption was significantly more common among women, urban dwellers, and individuals identifying as flexitarians or vegetarians. Environmental concerns and animal welfare were the most important motivators for PBMA consumption, whereas non-consumers cited issues such as imported ingredients, high processing levels, and poor sensory qualities as barriers. Consumers valued flavor and visual appeal more than production or nutritional attributes. Interestingly, while current PBMA consumers did not seek meat-like sensory properties, non-consumers and potential users preferred products resembling meat in taste and texture. The name “plant-based protein” was rated most appealing, compared to alternatives like “meat analogue” or “meat substitute.” The study highlights the heterogeneity in consumer expectations and emphasizes the need for tailored product development and communication strategies. Improving sensory quality, enhancing nutritional value, and positive product naming may support a broader acceptance of PBMAs. Full article

The transport sector significantly contributes to global greenhouse gas emissions, making electromobility crucial in the race toward the United Nations Sustainable Development Goals. In recent years, the increasing competition among manufacturers, the development of cheaper batteries, the ongoing policy support, and people’s greater environmental awareness have consistently increased electric vehicles (EVs) adoption. Nevertheless, EVs charging needs—highly influenced by EV drivers’ behavior uncertainty—challenge their integration into the power grid on a massive scale, leading to potential issues, such as overloading and grid instability. Smart charging strategies can mitigate these adverse effects by using information and communication technologies to optimize EV charging schedules in terms of power systems’ constraints, electricity prices, and users’ preferences, benefiting stakeholders by minimizing network losses, maximizing aggregators’ profit, and reducing users’ driving range anxiety. To this end, accurately forecasting EV charging demand is paramount. Traditionally used forecasting methods, such as model-driven and statistical ones, often rely on complex mathematical models, simulated data, or simplifying assumptions, failing to accurately represent current real-world EV charging profiles. Machine learning (ML) methods, which leverage real-life historical data to model complex, nonlinear, high-dimensional problems, have demonstrated superiority in this domain, becoming a hot research topic. In a scenario where EV technologies, charging infrastructure, data acquisition, and ML techniques constantly evolve, this paper conducts a systematized literature review (SLR) to understand the current landscape of ML-based EV charging demand forecasting, its emerging trends, and its future perspectives. The proposed SLR provides a well-structured synthesis of a large body of literature, categorizing approaches not only based on their ML-based approach, but also on the EV charging application. In addition, we focus on the most recent technological advances, exploring deep-learning architectures, spatial-temporal challenges, and cross-domain learning strategies. This offers an integrative perspective. On the one hand, it maps the state of the art, identifying a notable shift toward deep-learning approaches and an increasing interest in public EV charging stations. On the other hand, it uncovers underexplored methodological intersections that can be further exploited and research gaps that remain underaddressed, such as real-time data integration, long-term forecasting, and the development of adaptable models to different charging behaviors and locations. In this line, emerging trends combining recurrent and convolutional neural networks, and using relatively new ML techniques, especially transformers, and ML paradigms, such as transfer-, federated-, and meta-learning, have shown promising results for addressing spatial-temporality, time-scalability, and geographical-generalizability issues, paving the path for future research directions. Full article

Content caching and recommendation for content delivery over the Internet are two key techniques for improving the content delivery effectiveness determined by delivery efficiency and user satisfaction, which is increasingly important in the booming Internet of Things (IoT). While content caching seeks the “greatest common denominator” among users to reduce end-to-end delay in content delivery, personalized recommendation, on the contrary, emphasizes users’ differentiation to enhance user satisfaction. Existing studies typically address them separately rather than jointly due to their contradictory objectives. They focus mainly on heuristics and deep reinforcement learning methods without the provision of performance guarantees, which are required in many real-world applications. In this paper, we study the problem of joint optimization of caching and recommendation in which recommendation is performed in the cached contents instead of purely according to users’ preferences, as in the existing work. We show the NP-hardness of this problem and present a greedy solution with a performance guarantee by first performing content caching according to user request probability without considering recommendations to maximize the aggregated request probability on cached contents and then recommendations from cached contents to incorporate user preferences for cache hit rate maximization. We prove that this problem has a monotonically increasing and submodular objective function and develop an efficient algorithm that achieves a $1-{\displaystyle \frac{1}{e}}\approx 0.63$ approximation ratio to the optimal solution. Experimental results demonstrate that our algorithm dramatically improves the popular least-recently used (LRU) algorithm. We also show experimental evaluations of hit rate variations by Jensen–Shannon Divergence on different parameter settings of cache capacity and user preference distortion limit, which can be used as a reference for appropriate parameter settings to balance user preferences and cache hit rate for Internet content delivery. Full article

The ability to effectively engineer robots with appropriate social behaviors that conform to acceptable social norms and with the potential to influence human behavior remains a challenging area in robotics. Given this, we sought to provide insights into “what can be considered a socially appropriate and effective behavior for robots charged with enforcing social compliance of various magnitudes”. To this end, we investigate how social robots can be equipped with context-inspired persuasive behaviors for human–robot interaction. For this, we conducted three separate studies. In the first, we explored how the android robot “ERICA” can be furnished with negative persuasive behaviors using a video-based within-subjects design with N = 50 participants. Through a video-based experiment employing a mixed-subjects design with N = 98 participants, we investigated how the context of norm violation and individual user traits affected perceptions of the robot’s persuasive behaviors in the second study. Lastly, we investigated the effect of the robot’s appearance on the perception of its persuasive behaviors, considering two humanoids (ERICA and CommU) through a within-subjects design with N = 100 participants. Findings from these studies generally revealed that the robot could be equipped with appropriate and effective context-sensitive persuasive behaviors for human–robot interaction. Specifically, the more assertive behaviors (displeasure and anger) of the agent were found to be effective (p < 0.01) as a response to a situation of repeated violation after an initial positive persuasion. Additionally, the appropriateness of these behaviors was found to be influenced by the severity of the violation. Specifically, negative behaviors were preferred for persuasion in situations where the violation affects other people (p < 0.01), as in the COVID-19 adherence and smoking prohibition scenarios. Our results also revealed that the preference for the negative behaviors of the robots varied with users’ traits, specifically compliance awareness (CA), agreeableness (AG), and the robot’s embodiment. The current findings provide insights into how social agents can be equipped with appropriate and effective context-aware persuasive behaviors. It also suggests the relevance of a cognitive-based approach in designing social agents, particularly those deployed in sensitive social contexts. Full article

The rapid progress of Large Language Models (LLMs) has intensified the demand for flexible evaluation frameworks capable of accommodating diverse user needs across a growing variety of applications. While numerous standardized benchmarks exist for evaluating general-purpose LLMs, they remain limited in both scope and adaptability, often failing to capture domain-specific quality criteria. In many specialized domains, suitable benchmarks are lacking, leaving practitioners without systematic tools to assess the suitability of LLMs for their specific tasks. This paper presents LLM PromptScope (LPS), a customizable, real-time evaluation framework that enables users to define qualitative evaluation criteria aligned with their domain-specific needs. LPS integrates a novel LLM-as-a-Judge mechanism that leverages multiple language models as evaluators, minimizing human involvement while incorporating subjective preferences into the evaluation process. We validate the proposed framework through experiments on widely used datasets (MMLU, Math, and HumanEval), comparing conventional benchmark rankings with preference-driven assessments across multiple state-of-the-art LLMs. Statistical analyses demonstrate that user-defined evaluation criteria can significantly impact model rankings, particularly in open-ended tasks where standard benchmarks offer limited guidance. The results highlight LPS’s potential as a practical decision-support tool, particularly valuable in domains lacking mature benchmarks, offering both flexibility and rigor in model selection for real-world deployment. Full article

The optimization of land development requires a deep understanding of end-user expectations to ensure that new residential environments are both market-responsive and socially sustainable. This paper presents a novel prioritization-based technique for identifying and ranking property features according to buyer preferences. Using the MoSCoW method in combination with conjoint analysis, the study evaluates the relative importance of various housing attributes, such as layout, number of rooms, access to transportation, and availability of parking or green areas. The results provide structured insights into demand-side priorities and offer actionable guidelines for developers, urban planners, and decision-makers engaged in land use planning. By linking individual housing preferences with broader planning strategies, the proposed framework contributes to the creation of better-aligned, user-centric urban developments. The approach is tested on a local property market, and its potential applications in strategic zoning, infrastructure placement, and residential density modeling are discussed. Full article

AutoML is enabling many practitioners to use sophisticated Machine Learning pipelines even without being experienced in building application-specific solutions. Adapting AutoML to the field of unsupervised learning, particularly to the task of clustering, is challenging, as clustering is highly subjective and application-specific; the goal is not to find the best way to group data objects based on previously seen examples, but to find interesting new structures within potentially unknown data objects that provide actionable insights. The level of interestingness of a clustering is highly subjective and is subject to a variety of different characteristics making different clusterings of the same dataset (e.g., grouping people by age, gender, or special interests). In this paper, we propose an Automated Exploratory Clustering framework which determines multiple clusterings satisfying different notions of interestingness automatically. To this end, we generate multiple clusterings via AutoML processes and return a selection of clusterings, from which the user can explore the most preferred ones. We use different methods like the skyline operator to prune non-Pareto-optimal clusterings wrt. different dimensions of interestingsness and deliver a small set of valuable clusterings. In this way, our approach enables practitioners as well as domain experts to identify valuable clusterings without becoming experts in clustering as well, thus reducing human efforts and resources in finding application-specific solutions. Our empirical investigation with current state-of-the-art methods is carried out on a number of benchmark datasets, where a well-established ground truth can proxy for the wishes of a domain expert and multiple interestingness properties of the clusterings. Full article

Online review texts serve as a valuable source of auxiliary information for addressing the data sparsity problem in recommender systems. These reviews often reflect user preferences across multiple item attributes and can be effectively incorporated into recommendation models to enhance both the accuracy and interpretability of recommendations. Review-based recommendation approaches can be broadly classified into implicit and explicit methods. Implicit methods leverage deep learning techniques to extract latent semantic representations from review texts but generally lack interpretability due to limited transparency in the training process. In contrast, explicit methods rely on hand-crafted features derived from domain knowledge, which offer high explanatory capability but typically capture only shallow information. Integrating the complementary strengths of these two approaches presents a promising direction for improving recommendation performance. However, previous research exploring this integration remains limited. In this study, we propose a novel recommendation model that jointly considers implicit and explicit representations derived from review texts. To this end, we incorporate a self-attention mechanism to emphasize important features from each representation type and utilize Bidirectional Encoder Representations from Transformers (BERT) to capture rich contextual information embedded in the reviews. We evaluate the performance of the proposed model through extensive experiments using three real-world datasets. The experimental results demonstrate that our model outperforms several baseline models, confirming its effectiveness in generating accurate and explainable recommendations. Full article

Background/Objectives: Existing patient information leaflets (ePILs), mandated by the FDA to accompany new prescriptions, are difficult to read and understand due to their complexity and poor visual design, especially for populations with low health literacy and low English proficiency. In this study, we developed infographic-based PILs (iPILs) with a concise question-and-answer format, emphasizing essential information, as specified by the FDA. This study compared iPILs and ePILs using the 5C factors: comprehension, cosmetics, convenience, content, and credibility, as perceived by English-speaking and Spanish-speaking populations. Methods: This multicenter, experimental survey study assessed the 5C factors. English and Spanish-speaking adults on ≥1 chronic medication were recruited from community pharmacies in California (CA) and Illinois (IL). They were stratified to review either an ePIL or an iPIL for one of four common medications. They completed a Medication Knowledge Quiz (MKQ) to show their comprehension using six open-ended questions. Subsequently, they received both PIL versions and answered preference questions about the 4C and media format and, lastly, about demographic and health literacy questions. Results: A total of 235 participants completed the surveys at three sites (CA-English, CA-Spanish, and IL-English), with differing participant characteristics. The CA-Spanish participants scored the lowest on health literacy and the number of health conditions. The MKQ scores for those using the iPILs were significantly higher than for those using the ePILs across all groups. They significantly correlated with health literacy results for the ePILs (r = 0.394, p < 0.001). The participants preferred the iPILs over the ePILs for four of the C factors, barring one content question. Regardless of age, printed formats were preferred (64.7%)—alone or with digital formats (21.3%)—over digital formats alone (3.4%). Overall, 79.1% of the participants preferred iPILs, 11.9% preferred ePILs, and 8.9% preferred either version. Conclusions: The infographic-based patient information leaflets (iPILs) were easier to read, navigate, and understand, making them more accessible to individuals with varying levels of health literacy. Infographic-based leaflets outperformed existing ones in user comprehension and were preferred due to their simple layout, ease of navigation, and helpfulness. Full article

End-users can design personalized furnishing products using remote web-based CAD systems. However, if these designs fail to incorporate design for disassembly (DfD) principles, the furniture’s subsequent repair, reconfiguration, recycling, and disposal can be significantly hindered. To address this drawback, this study supports DfD, a strategy that enables the creation of easily repairable, reusable, and recyclable furniture to reduce waste and environmental impact. Consequently, this review aims to classify and evaluate available furniture joinery systems for their suitability within DfD frameworks, ultimately promoting their implementation within CAD environments. To this end, various solutions were evaluated, including traditional joints, dowel/biscuit, hammered, directly screwed, snap-on, expandable, and cam/bolt fasteners. Based on a literature review and practical observations, the analyzed joinery systems were categorized into non-disassemblable, conditionally disassemblable, and fully disassemblable categories. Only the fully disassemblable solutions effectively align with DfD principles. The study postulates a preference for expandable and cam/bolt fasteners in furniture designs, noting that although snap-on fasteners can potentially support DfD, this outcome is not always ensured. To guarantee that the designed furniture adheres to the DfD principles, the following eight furniture design guidelines were formulated: develop web-accessible disassembly instructions, prioritize access to fast-wearing components, prioritize modularity, standardize parts in modules, label components, enable independent component removal, use materials that withstand repeated disassembly, and employ fully disassemblable joints. Full article

Mobile payment systems have rapidly expanded globally, especially in developing countries like Thailand, Malaysia, and Indonesia. Technological advances, public acceptance, and increased adoption during the COVID-19 pandemic drive this growth. Mobile payments involve key stakeholders: technology providers, end-users, government regulators, and merchants, each contributing to the adoption ecosystem. Users prefer mobile payments for their speed and convenience over traditional cash transactions. This study explores the driver and barrier factors influencing mobile payment QR adoption among merchants, particularly from the MSME perspective, using existing frameworks based on previous research adapted to MSME conditions. Conducted in Indonesia with 418 MSME business respondents, this study employs a quantitative, cross-sectional methodology with a 95% confidence level and an SEM analysis. The findings reveal that perceived ease of use does not significantly impact perceived experience, while perceived usefulness does. Perceived risk, convenience, experience, and word-of-mouth learning statistically significantly influence merchants’ intention to use mobile payments. However, customer engagement, cost, trust, and complexity appear less influential. Overall, this research advances understanding of the key factors affecting merchants’ adoption of mobile payment and provides insights relevant to MSME economic growth. Full article

Fog Computing extends Cloud computing capabilities by providing computational resources closer to end users. Fog Computing has gained considerable popularity in various domains such as drones, autonomous vehicles, and smart cities. In this context, the careful selection of suitable Fog resources and the optimal assignment of services to these resources (the service placement problem (SPP)) is essential. Numerous studies have attempted to tackle this issue. However, to the best of our knowledge, none of the previously proposed works took into consideration the dynamic context awareness and the user preferences for IoT service placement. To deal with this issue, we propose a hybrid recommendation system for service placement that combines two techniques: collaborative filtering and content-based recommendation. By considering user and service context, user preferences, service needs, and resource availability, the proposed recommendation system provides optimal placement suggestions for each IoT service. To assess the efficiency of the proposed system, a validation scenario based on Internet of Drones (IoD) was simulated and tested. The results show that the proposed approach leads to a considerable reduction in waiting time and a substantial improvement in resource utilization and the number of executed services. Full article