In an increasingly competitive market, where affective values are key for differentiation, understanding user opinions is crucial to ensuring success in product design. Traditionally, designers have collected data on product evaluation using self-report questionnaires, such as Osgood’s Semantic Differential technique, a widely used method for assessing product aesthetics and affect. However, some authors question the temporal stability of responses, suggesting users may not be consistent in their opinions over time. This study presents two case studies where a group of volunteers evaluated two types of products (chair and watering can) using the Semantic Differential technique in separate sessions. Data on response confidence was also collected. The main objective was to determine if statistically significant differences exist between measurements to assess the stability of responses and the reliability of self-report methods over time. Results showed that some attributes were affected by the temporal factor for both products, with a consistency rate of 91.67

When engineering drawings are regenerated across design iterations or reused across part families, subtle discrepancies often arise, making manual comparison error-prone and labor-intensive. This paper presents Drawing-Checker, a vision Retrieval-Augmented Generation (RAG) framework that automates drawing comparison using reference standards. The system integrates YOLO-based view detection, CLIP-based embedding retrieval, and a state-of-the-art multimodal Large Language Model (LLM) reasoning to identify annotation and geometric discrepancies between reference and target drawings. By decomposing full drawings into semantically matched view pairs and flagging unmatched views, Drawing-Checker achieves higher precision, substantially higher recall, and better overall F1 than a full-image prompting baseline, without increasing false positives, across 500 customized test cases. These gains confirm the effectiveness of view-level prompting in surfacing localized differences (particularly missing, added, or altered features) while maintaining precision. At the same time, the study highlights persistent challenges in geometric reasoning, localization accuracy, and hallucination control, underscoring the need for enhanced prompt design, view detector generalization, and domain-specific model adaptation to achieve robust and scalable deployment.

This research addresses the challenge of applying Building Information Modeling (BIM)-based design methodology for cross-drainage works (CDW) in road projects. It investigates the application of BIM in hydraulic and structural design of road projects, as an alternative to traditional methods. A mixed-methods approach was employed. Quantitative analysis was conducted on a sample of 19 road projects developed by a small Spanish civil engineering firm. The objective of the study was to demonstrate that BIM methodology has significant qualitative and quantitative benefits that justify the associated initial cost increase. The BIM methodology has been implemented in recent years and represents an advance over traditional methods based on working with the floor and section plans of CDW. The results of the study show that the proposed methodology led to an average time saving of 9.1 h over the 14.2 h required by the traditional method for each drainage work. This represented an average time reduction of 63 % in the proposed workflow for the CDW. The study's main contribution lies in providing a framework for BIM-based CDW management that can be adapted to different geographical contexts. Furthermore, it offers a qualitative evaluation of the benefits of BIM implementation. The findings suggest that BIM can significantly improve the efficiency and effectiveness of CDW projects. However, successful implementation requires addressing the identified challenges. The proposed framework provides a valuable tool for infrastructure professionals seeking to leverage BIM for CDW management.

Most of the information we gather from our environment is obtained from sight, hence, visual evaluation is vital for assessing products. However, designers have traditionally relied on self-report questionnaires for this purpose, which have proven to be insufficient in some cases. Consequently, physiological measures are being employed to gain a deeper understanding of the cognitive and perceptual processes involved in product evaluation, and, thanks to their integration in Virtual Reality (VR) headsets, they have become a powerful tool for virtual prototype assessment. Still, using virtual prototypes raises some concerns, as previous studies have found that the medium can influence product perception. These results rely solely on self-report techniques, highlighting the need to explore the use of ET for product assessment, which is the main objective of this research. We present two case studies where a group of people assessed through two display mediums (CS-1) a set of furniture comprising a general scene using a ranking-type evaluation (i.e., joint assessment) and (CS-2) two armchairs individually using the Semantic Differential technique. Moreover, the dwell time of the Areas of Interest (AOIs) defined was recorded. Primarily, our results showed that, despite VR being sensitive to aesthetic differences between designs of the same product typology, the medium may still influence the perception of specific product attributes -e.g., fragility (pMODERN < 0.001, pTRADITIONAL = 0.002)-, and observation of specific AOIs -e.g., AOI1 (pMODERN = 0.003, pTRADITIONAL < 0.001), AOI9 and AOI10 (p < 0.001). At the same time, no differences were found in the perception of the general scene, whereas dwell time was influenced for AOI1 (p = 0.003), AOI4 (p = 0.006), and AOI5 (<.001). Additionally, the university of origin may also be a factor influencing product evaluation, while confidence in the response was not affected by the medium. Hence, this study contributes to a deeper understanding of how the medium influences product perception by employing ET with self-report methods, offering valuable insights into user behavior.

Generative Artificial Intelligence (GenAI) is transforming how design students conceptualize and interpret core disciplinary principles. This exploratory study investigates how AI-generated visual representations influence the association of five key design concepts functionality, feasibility, aesthetics, sustainability, and ideation while examining students’ visual attention patterns during a forced-association task. Thirty-six design students participated in an eye-tracking (ET) experiment in which they analyzed digital images derived from two iconic chairs represented as hand drawings, sketches, and cardboard mock-ups using GenAI. Visual behavior data were evaluated using Visit Counts (VC) and Total Fixation Duration (TFD), supported by exit-survey responses. Results indicate that students could correctly associate concepts with the stimuli, demonstrating meaningful cognitive–semantic processing. Representations selected as correct presented higher fixation durations during decision-making, reflecting deeper visual validation. Overall, the study highlights an experimental protocol and pedagogical potential of GenAI examination in supporting conceptual and visual interpretation in design education.

The immersive, multisensory experiences offered by virtual reality have been transformative across multiple disciplines, enhancing practical and theoretical skills while increasing user motivation and learning. On the other hand, multi-agent systems have proven to be effective in facilitating the expansion and modularity of computer systems. This paper presents an application developed in a virtual reality environment based on multi-agent systems for the conceptual design of mechanical assemblies from primitives. As a main novelty, the primitives can be defined by the user of the application from a set of models and images, and an Excel document, without the need for programming knowledge, taking advantage of the possibilities offered by multi-agent systems. In addition, for each primitive, it is possible to define a set of geometric and dimensional modifications, as well as a set of position relations with respect to other primitives to generate mechanical assemblies.

Oftentimes, designers need to reverse engineer detailed design drawings to create 3D models. These drawings are commonly accepted as complete information sources in design datasets but may contain errors or ambiguities and lead to misinterpretation, resulting in digital CAD models that inherit such ambiguities, or modelling situations with no solution. We propose a classification of errors based on the type of ambiguity they produce (redundancy, omission, contradiction, and polysemy) and discuss the results of an experiment designed to evaluate the effectiveness of a strategy based on this classification. The classification represents an essential step for developing a checklist to ensure drawing ambiguities are fully resolved before the corresponding 3D models are built. In the long term, the proposed classification can guide a divide-and-conquer strategy for training artificial intelligence systems in the detection and repair of these ambiguities.

The quality of mechanical 3D models generated with Computer-Aided Design (CAD) systems is a key aspect of the product development process. Evidence shows that formal modeling methodologies contribute to creating higher-quality 3D models that improve design performance, but little attention has been drawn to actual practices in industrial companies. Some of the challenges involved in studying these strategies include lack of access to what is often considered an intellectual asset for organizations and thus kept secret, as well as the variety of industrial products and different levels of automation for a particular design within the organization. In this paper, we describe the process of creating a comprehensive assessment instrument for diagnosing the level of awareness of CAD quality among the different stakeholders involved in the product development process and the extent to which organizations have implemented strategies to leverage and promote the creation and use of high-quality parametric CAD models. The survey instrument contains questions about key aspects of 3D CAD model quality, from methodologies to training. A formal survey validation process was conducted using the expert judgement technique. The modified Kappa coefficient was used to identify questions that needed improvement. The final version of this instrument is provided in the appendix.

This study investigates an Adaptive Feedback System (AFS) that integrates deep learning (a recurrent neural network trained with historical student data) and GPT-4 to provide personalized feedback in a Digital Art course. In a quasi-experimental design, the intervention group (n = 42) received weekly feedback generated from model predictions, while the control group (n = 39) followed the same program without this intervention across four learning blocks or levels. The results revealed (1) a cumulative effect with a significant performance difference in the fourth learning block (+12.63 percentage points); (2) a reduction in performance disparities between students with varying levels of prior knowledge in the experimental group (−56.5%) versus an increase in the control group (+103.3%); (3) an “overcoming effect” where up to 42.9% of students surpassed negative performance predictions; and (4) a positive impact on active participation, especially in live class attendance (+30.21 points) and forum activity (+9.79 points). These findings demonstrate that integrating deep learning with LLMs can significantly improve learning outcomes in online educational environments, particularly for students with limited prior knowledge.

Packaging design is pivotal in motivating consumer decisions, as a key communication tool from creation to purchase. Currently, the interpretation and evaluation of packaging’s impact are shifting toward non-traditional methods. This pilot study evaluated the packaging perception of York Ham and Turkey Breast products. The event-related potential (ERP) technique, the methodology priming words (positive and negative), and target images (original and modified packaging) were applied. A total of 23 participants were sampled using a 32-channels scalp elastic electrode cap and viewed 200 trials of word–image matching. Participants responded whether the images and adjectives matched or not, using the two groups of images. The results demonstrate an N400 effect in the parietal area. This region was observed to show evidence of cognitive processing related to congruency or incongruency, by contrasting the priming and target of this study. The evaluation positioned the York Ham packaging as the best rated. The findings show a relevant contribution to ERPs and research related to the food packaging perception.

Advanced product presentation methods can enhance the product evaluation experience both during the design process and online shopping, as static images often fail to convey essential product details. Virtual Reality (VR) technologies hold great potential in this regard, becoming increasingly accessible to all users. However, the influence of display mediums on emotional responses and product assessment needs further investigation, especially using physiological measures to obtain more objective insights. In this study, we investigate the influence of VR and photorealistic images on assessing and observing virtual prototypes of game controllers. The Semantic Differential technique was employed for product assessment, while built-in eye-tracking was used to measure participants’ viewing time on various areas of interest (AOIs). Our findings show that the medium significantly affects not only product evaluation and confidence in the response but also how the user observes it, with sensory-related features being particularly influenced. These findings hold practical implications for product design and vendors, as understanding the relationship between visualization mediums and product evaluation enhances the design process and improves consumer experiences.

This study investigates the application of a deep learning-based predictive model to predict student performance. The objective was to enhance student performance by predicting and monitoring their academic activities, including attendance at synchronous sessions, interaction with digital content, participation in forums, and performance in portfolio creation tasks over an academic year. The predictive model was applied to an experimental group of students. Unlike the control group, which did not receive continuous feedback, the experimental group received personalized, continuous feedback based on predictions from a pre-trained model and interpreted by OpenAI’s GPT-4 language model. Significant improvements were observed in the performance of the experimental group compared to the control group. The average score on quizzes for the experimental group was 0.81, notably higher than the control group's 0.67. Recorded session engagement for the experimental group was 0.84, compared to 0.65 for the control group. Live session participation and forum activity were also significantly higher in the experimental group, with rates of 0.61 and 0.62 respectively, compared to the control group's 0.42 and 0.37. However, the average practice score was slightly higher in the control group, with a mean of 0.76 compared to 0.74 in the experimental group. Portfolio assessment scores were higher in the experimental group, with an average of 0.73 compared to 0.69 in the control group. These results support the hypothesis that using predictive models complemented by language models to provide continuous feedback improves learning effectiveness.

Previous research in human-computer interaction (HCI) has focused relatively little attention on making parametric Computer-Aided Design (CAD) tools user-friendly.This study aims to address key research questions about the difficulties beginners encounter when using parametric CAD tools, the reasons behind these challenges, and the principles of interface design that can improve their understanding.To answer these questions, a comprehensive three-stage design framework for CAD Graphical User Interfaces (GUIs) is proposed.The first stage involves analyzing user experience (UX) within the context of the CAD interface, followed by developing customized solutions to meet specific requirements in the second stage.Finally, the framework includes rigorous testing and evaluation of the CAD GUI solutions against the identified requirements.Statistical analysis was used to validate the improved usability perception of the new interfaces.This framework leads to the creation of rules supporting the design of understandable GUIs for parametric CAD tools.Ultimately, this research contributes to advancing comprehensible GUIs by shedding light on the challenges beginners face, offering practical recommendations to enhance their experience, and facilitating a better understanding of tools to increase their efficiency.

Sketched drawings sometimes include non-solid lines drawn as sets of consecutive strokes. They represent dashed lines, which are useful for various purposes. Recognizing such dashed lines while parsing drawings is reasonably straightforward if they are outlined with a ruler and compass but becomes challenging when they are hand-drawn. The problem is manageable if the strokes are drawn consecutively so we can leverage the entire sequence. However, it becomes more challenging if they are drawn unordered, and/or we do not have access to the sequence (like in batch vectorization). In this paper, we describe a new approach to identify groups of strokes as depicting single hand-drawn dashed lines. The approach does not use sequence information and is tolerant with irregularities and imprecisions of the strokes. Our goal is to identify hidden lines of sketched engineering line-drawings, which would enable the interpretation of line-drawings with hidden edges, which currently cannot be efficiently vectorized. We speculate that other fields like hand-drawn graph interpretation may also benefit from our approach.

During the last two decades, industrial applications of augmented reality (AR) have been incorporated in sectors such as automotive or aeronautics in tasks including manufacturing, maintenance, and assembly. However, AR’s potential has yet to be demonstrated in the railway sector due to its complexity and difficulties in automating tasks. This work aims to present an AR system based on HoloLens 2 to assist the assembly process of insulation panels in the railway sector significantly decreasing the time required to perform the assembly. Along with the technical description of the system, an exhaustive validation process is provided where the assembly using the developed system is compared to the traditional assembly method as used by a company that has facilitated a case study. The results obtained show that the system presented outperforms the traditional solution by 78% in the time spent in the localization subtask, which means a 47% decrease in the global assembly time. Additionally, it decreases the number of errors in 88% of the cases, obtaining a more precise and almost error-free assembly process. Finally, it is also proven that using AR removes the dependence on users’ prior knowledge of the system to facilitate assembly.

This study presents the development and evaluation of an immersive virtual reality (VR) application designed for lathe operation training. The VR application, built using Unity for Oculus Rift headsets, aims to simulate a realistic lathe machining experience, allowing users to interact with the machine’s various controls and levers. The experimental analysis involved 20 s-year Mechanical Engineering students who performed machining tasks in the virtual environment. The usability and user experience of the application were assessed using the System Usability Scale (SUS) and a 12-item questionnaire. The SUS results yielded a high mean score of 96.25 (SD = 6.41), indicating excellent usability. The user experience evaluation also showed positive feedback, with high ratings for the sense of presence, realism, and usefulness for training purposes. However, some users reported minor physical discomforts such as dizziness. The study concludes that immersive VR is a valuable tool for enhancing training in lathe operations, offering an engaging and realistic experience that encourages active learning. Future work should focus on reducing physical discomfort and further improving the application’s realism and interactivity.

The use of Virtual Reality (VR) technologies in product design allows for the creation of virtual prototypes, which can be evaluated in immersive environments in a realistic and controlled manner. Unlike traditional assessment methods which rely on self-reporting, novel techniques based on eye-tracking and face-tracking technologies enable a more accurate and unbiased understanding of users’ emotions in response to a product. In this paper, we report the development of a system for the collection of real-time behavioral data during product evaluation in virtual environments through face tracking techniques. Our findings suggest that the ability to interpret users’ emotions during their interactions with virtual prototypes provides valuable information for designing products that can more effectively meet the needs and preferences of users.