Search Results (93)

This paper discusses the evolution of convolutional (CNN) and recurrent (RNN) artificial neural networks in applications for Building Information Modeling (BIM). The paper outlines the milestones reached in the last two decades. The article organizes the current state of knowledge and technology in terms of three aspects: (1) computer visualization coupled with BIM models (detection, segmentation, and quality verification in images, videos, and point clouds), (2) sequence and time series modeling (prediction of costs, energy, work progress, risk), and (3) integration of deep learning results with the semantics and topology of Industry Foundation Class (IFC) models. The paper identifies the most used architectures, typical data pipelines (synthetic data from BIM models, transfer learning, mapping results to IFC elements) and practical limitations: lack of standardized benchmarks, high annotation costs, a domain gap between synthetic and real data, and discontinuous interoperability. We indicate directions for development: combining CNN/RNN with graph models and transformers for wider use of synthetic data and semi-/supervised learning, as well as explainability methods that increase trust in AECOO (Architecture, Engineering, Construction, Owners & Operators) processes. A practical case study presents a new application, Bimetria, which uses a hybrid CNN/OCR (Optical Character Recognition) solution to generate 3D models with estimates based on two-dimensional drawings. A deep review shows that although the importance of attention-based and graph-based architectures is growing, CNNs and RNNs remain an important part of the BIM process, especially in engineering tasks, where, in our experience and in the Bimetria case study, mature convolutional architectures offer a good balance between accuracy, stability and low latency. The paper also raises some fundamental questions to which we are still seeking answers. Thus, the article not only presents the innovative new Bimetria tool but also aims to stimulate discussion about the dynamic development of AI (Artificial Intelligence) in BIM. Full article

Objectives: The objective of this study was to explore the views expressed online by COPD patients regarding adherence to inhaled therapy. Methods: This study applied a qualitative, exploratory-interpretive design and an inductive methodology. Sources analyzed included COPD websites, patient forums, and social networks. Units of analysis were videos, stories, questions and answers, and conversation threads. Saturation criteria were applied. Applying a constant comparative methodology, analyses were conducted at textual (quotes, initial and focused coding, families) and conceptual (categories, networks, meta-network, provisional and final model) levels using ATLAS.ti 7.5. Reports were returned to patients. Results: There were 248 patients (51 men, 148 women, 49 unidentified) corresponding to 29 testimonies (6 narratives, 11 videos, 10 conversation threads, 2 questions collections). Adherence to inhalers is based on their perception of effectiveness to enable a normal life, and benefits should outweigh adverse effects. Adherence facilitators included mutual support between patients encouraging adherence and effective doctor-patient communication. Adherence barriers included (1) side effects; (2) mistaken beliefs about inhalers (habituation, attribution of non-existent side effects, fear of corticosteroids); (3) poor doctor-patient relationship (lack of listening, failure to consider patient’s preferences, communication iatrogenesis); (4) considering natural remedies as substitutes for treatment. Conclusions: Adherence to inhalers as reported in online testimony from COPD patients depends on the balance between efficacy and side effects. Adherence is influenced by peer support and doctor-patient communication. Doubts, erroneous beliefs, and iatrogenic effects of poor communication can hinder adherence. Full article

Creating engaging narratives from visual data is crucial for automated digital media consumption, assistive technologies, and interactive entertainment. This survey covers methodologies used in the generation of these narratives, focusing on their principles, strengths, and limitations. The survey also covers tasks related to automatic story generation, such as image and video captioning, and Visual Question Answering. These tasks share common challenges with Visual Story Generation (VSG) and have served as inspiration for the techniques used in the field. We analyze the main datasets and evaluation metrics, providing a critical perspective on their limitations. Full article

Mastering client-side Web programming is essential for the development of responsive and interactive Web applications. To support novice students’ self-study, in this paper, we propose a novel exercise format called the phrase fill-in-blank problem (PFP) in the Web Programming Learning Assistant System (WPLAS). A PFP instance presents a source code with blanked phrases (a set of elements) and corresponding Web page screenshots. Then, it requests the user to fill in the blanks, and the answers are automatically evaluated through string matching with predefined correct answers. By increasing blanks, PFP can come close to writing a code from scratch. To facilitate scalable and context-aware question creation, we implemented the PFP instance generation algorithm in Python using regular expressions. This approach targets meaningful code segments in HTML, CSS, and JavaScript that reflect the interactive behavior of front-end development. For evaluations, we generated 10 PFP instances for basic Web programming topics and 5 instances for video games and assigned them to students at Okayama University, Japan, and the State Polytechnic of Malang, Indonesia. Their solution results show that most students could solve them correctly, indicating the effectiveness and accessibility of the generated instances. In addition, we investigated the ability of generative AI, specifically ChatGPT, to solve the PFP instances. The results show 86.7% accuracy for basic-topic PFP instances. Although it still cannot fully find answers, we must monitor progress carefully. In future work, we will enhance PFP in WPLAS to handle non-unique answers by improving answer validation for flexible recognition of equivalent responses. Full article

With the accelerated digital transformation in education, the efficient integration of massive multimodal instructional resources and the support for interactive question answering (QA) remains a prominent challenge. This study introduces Multimodal Disciplinary Knowledge-Augmented Generation (MDKAG), a framework integrating retrieval-augmented generation (RAG) with a multimodal disciplinary knowledge graph (MDKG). MDKAG first extracts high-precision entities from digital textbooks, lecture slides, and classroom videos by using the Enhanced Representation through Knowledge Integration 3.0 (ERNIE 3.0) model and then links them into a graph that supports fine-grained retrieval. At inference time, the framework retrieves graph-adjacent passages, integrates multimodal data, and feeds them into a large language model (LLM) to generate context-aligned answers. An answer-verification module checks semantic overlap and entity coverage to filter hallucinations and triggers incremental graph updates when new concepts appear. Experiments on three university courses show that MDKAG reduces hallucination rates by up to 23% and increases answer accuracy by 11% over text-only RAG and knowledge-augmented generation (KAG) baselines, demonstrating strong adaptability across subject domains. The results indicate that MDKAG offers an effective route for scalable knowledge organization and reliable interactive QA in education. Full article

Every minute, vast amounts of video and image data are uploaded worldwide to the internet and social media platforms, creating a rich visual archive of human experiences—from weddings and family gatherings to significant historical events such as war crimes and humanitarian crises. When properly analyzed, this multimodal data holds immense potential for reconstructing important events and verifying information. However, challenges arise when images and videos lack complete annotations, making manual examination inefficient and time-consuming. To address this, we propose a novel event-based focal visual content text attention (EFVCTA) framework for automated past event retrieval using visual question answering (VQA) techniques. Our approach integrates a Long Short-Term Memory (LSTM) model with convolutional non-linearity and an adaptive attention mechanism to efficiently identify and retrieve relevant visual evidence alongside precise answers. The model is designed with robust weight initialization, regularization, and optimization strategies and is evaluated on the Common Objects in Context (COCO) dataset. The results demonstrate that EFVCTA achieves the highest performance across all metrics (88.7% accuracy, 86.5% F1-score, 84.9% mAP), outperforming state-of-the-art baselines. The EFVCTA framework demonstrates promising results for retrieving information about past events captured in images and videos and can be effectively applied to scenarios such as documenting training programs, workshops, conferences, and social gatherings in academic institutions Full article

Reviews of literacy coaching show positive outcomes for teaching and learning, yet also that coaching’s impact varies widely, especially at increased scale. Thus, some scholars argue the quality of coaching interactions may matter more than broad coaching actions (e.g., co-planning, observing). Situated within Habermas’s notion of “public sphere”, we used discourse analysis to examine video-recorded pre- and post-interviews, coaching meetings, and coach retrospective think-aloud protocols of a literacy coach and elementary school teacher who described their partnership as “successful”. We examined participants’ values expressed about coaching; how each participant positioned themselves, each other, and the coaching context; and the nature of the coach–teacher discourse therein to answer the following question: what occurs in the interactional space between a coach and teacher when engaged in coaching meetings? We found four categories of values focused on participatory choice, their sense of connectedness, knowledge development, and their approach to working with/as a coach. Further, participants’ positionings signified agency for both the coach and teachers in the interactional space. While bracketing and leveraging their own authority, the coach’s language choices promoted teachers’ agency within the interactional space, providing insight into how language functions to shape the “public sphere” of coaching interactions. Full article

Architectural ambiance refers to the mood perceived in a built environment, assessed through human reactions to virtual drawings of prospective spaces. This paper investigates the use of a ready-made artificial intelligence model to automate this task. Based on professional BIM models, videos of virtual tours of typical urban areas were built: a business district, a strip mall, and a residential area. GPT-4V was used to assess the aesthetic quality of the built environment based on keyframes of the videos and characterize these spaces shaped by subjective attributes. The spatial qualities analyzed through subjective human experience include space and scale, enclosure, style, and overall feelings. These factors were assessed with a diverse set of mood attributes, ranging from balance and protection to elegance, simplicity, or nostalgia. Human participants were surveyed with the same questions based on the videos. The answers were compared and analyzed according to these subjective attributes. Our findings indicate that, while GPT-4V demonstrates adequate proficiency in interpreting urban spaces, there are significant differences between the AI and human evaluators. In nine out of twelve cases, the AI’s assessments aligned with the majority of human voters. The business district environment proved more challenging to assess, while the green environment was effectively modeled. Full article

Background/Objectives: Although medical radiation practice is essential for current medical care, many nursing students and nurses lack sufficient basic knowledge about radiation, and they are unfamiliar with learning about it. This study aimed to evaluate the usefulness of self-made video teaching materials for radiation education for nursing students and nurses after clarifying their basic knowledge of radiation. Methods: Educational video materials were developed to provide basic radiation knowledge. The video materials included scenes of radiation measurement, such as the attenuation of scattered X-rays with distance, and illustrations drawn by nursing students to make them familiar to nursing staff. This study included 29 nursing students and 16 nurses. The participants were instructed to answer 20 questions regarding the characteristics of radiation and its influence and protection measures. The same questions were asked again after watching the video materials. Results: Nursing students and nurses correctly recognized the classification of medical or occupational exposure and the three principles for reducing external exposure; however, it became clear that dose limits do not apply to medical exposure and that radiation units and their effects on the human body were not correctly recognized. Furthermore, the educational materials were effective because the scores and the percentage of correct answers increased after viewing the video materials. Furthermore, positive comments were expressed regarding the scenes of the experiments and the illustrations drawn by the students about the teaching materials. Conclusions: The contents that should be addressed more intensively were clarified, and the effectiveness of using video teaching materials in radiation nursing education was demonstrated. Full article

This paper explores the transformative potential of Foundation Models (FMs) in agriculture, driven by the need for efficient and intelligent decision support systems in the face of growing global population and climate change. It begins by outlining the development history of FMs, including general FM training processes, application trends and challenges, before focusing on Agricultural Foundation Models (AFMs). The paper examines the diversity and applications of AFMs in areas like crop classification, pest detection, and crop image segmentation, and delves into specific use cases such as agricultural knowledge question-answering, image and video analysis, decision support, and robotics. Furthermore, it discusses the challenges faced by AFMs, including data acquisition, training efficiency, data shift, and practical application challenges. Finally, the paper discusses future development directions for AFMs, emphasizing multimodal applications, integrating AFMs across the agricultural and food sectors, and intelligent decision-making systems, ultimately aiming to promote the digitalization and intelligent transformation of agriculture. Full article

Timely prediction of collisions enables advanced driver assistance systems to issue warnings and initiate emergency maneuvers as needed to avoid collisions. With recent developments in computer vision and deep learning, collision warning systems that use vision as the only sensory input have emerged. They are less expensive than those that use multiple sensors, but their effectiveness must be thoroughly assessed. We systematically searched academic literature for studies proposing ego-centric, vision-based collision warning systems that use deep learning techniques. Thirty-one studies among the search results satisfied our inclusion criteria. Risk of bias was assessed with PROBAST. We reviewed the selected studies and answer three primary questions: What are the (1) deep learning techniques used and how are they used? (2) datasets and experiments used to evaluate? (3) results achieved? We identified two main categories of methods: Those that use deep learning models to directly predict the probability of a future collision from input video, and those that use deep learning models at one or more stages of a pipeline to compute a threat metric before predicting collisions. More importantly, we show that the experimental evaluation of most systems is inadequate due to either not performing quantitative experiments or various biases present in the datasets used. Lack of suitable datasets is a major challenge to the evaluation of these systems and we suggest future work to address this issue. Full article

The teaching of environmental education must change to promote critical, sustainable, and reflective engagement with environmental problems. This study introduces a social-science question for primary education focused on pharmaceuticals in surface water. The aims of the paper are to evaluate the level of students’ performance in arguing their answers in relation to the reference answer; their use and interpretation of provided materials from which they draw the evidence to justify their arguments; and the type of solutions they propose in the framework of sustainability. This is carried out by analyzing the content of their written reports and the discourse during their group discussions. Statistical tests are also used to compare their individual and group performance. The results show that students perform at an intermediate level. They use text and video effectively but struggle with graphs and maps. Their proposed solutions are contextually appropriate and consider multiple perspectives. Notably, their performance is similar whether working individually or in groups. All in all, this pedagogical intervention in the framework of scientific practices and transformative environmental education supports the development of scientific thinking and sheds light on how students process information when addressing socio-environmental issues. Full article

Understanding sports presents a fascinating challenge for Natural Language Processing (NLP) due to its intricate and ever-changing nature. Current NLP technologies struggle with the advanced cognitive demands required to reason over complex sports scenarios. To explore the current boundaries of this field, we extensively evaluated mainstream and emerging large models on various sports tasks and addressed the limitations of previous benchmarks. Our study ranges from answering simple queries about basic rules and historical facts to engaging in complex, context-specific reasoning using strategies like few-shot learning and chain-of-thought techniques. Beyond text-based analysis, we also explored the sports reasoning capabilities of mainstream video language models to bridge the gap in benchmarking multimodal sports understanding. Based on a comprehensive overview of main-stream large models on diverse sports understanding tasks, we presented a new benchmark, which highlighted the critical challenges of sports understanding for NLP and the varying capabilities of state-of-the-art large models on sports understanding. We also provided an extensive set of error analyses that pointed to detailed reasoning defects of large model reasoning which model-based error analysis failed to reveal. We hope the benchmark and the error analysis set will help identify future research priorities in this field. Full article

Background/Objectives: Fabry disease is an X-linked lysosomal storage disease. Earlier studies have mentioned dizziness/balance issues and vestibular involvement as a symptom of Fabry disease. Research on the matter remains scarce. This pilot study aims to show the prevalence of dizziness/balance issues and whether it is due to peripheral, central, or other factors. Methods: A Dizziness Handicap Inventory, with added questions, was sent out to 91 Fabry patients to estimate the prevalence of dizziness/balance issues. Additionally, this study reports analyses from eight Fabry patients with self-reported dizziness/balance issues who were offered referrals for in-depth investigations of their condition. All eight underwent a comprehensive oto-neurological examination, Videonystagmography, a Video Head impulse test, vestibular myogenic evoked potential, and audiometry. Results: A total of 55 of the 91 patients with Fabry disease answered the survey. Of these, 78.2% felt symptoms of dizziness/balance issues. The most common form of dizziness/balance issues was short-lasting attacks. All eight ENT-examined patients had normal outer and middle ear conditions. Five of eight Fabry patients had abnormal results in the optokinetic test and audiometry. Conclusions: The survey showed a high prevalence of dizziness/balance issues in Fabry patients. The abnormal optokinetic test suggested a central cause and was the only objective measurement we found that could lead to an explanation for dizziness/balance issues. Polypharmacy was present in all eight examined patients and could also explain the dizziness/balance issues in Fabry patients. There is no other clear pattern regarding the characteristics of dizziness/balance issues in Fabry patients in this exploratory study. Full article

In recent years, advancements in the interaction and collaboration between humans and have garnered significant attention. Social intelligence plays a crucial role in facilitating natural interactions and seamless communication between humans and Artificial Intelligence (AI). To assess AI’s ability to understand human interactions and the components necessary for such comprehension, datasets like Social-IQ have been developed. However, these datasets often rely on a simplistic question-and-answer format and lack justifications for the provided answers. Furthermore, existing methods typically produce direct answers by selecting from predefined choices without generating intermediate outputs, which hampers interpretability and reliability. To address these limitations, we conducted a comprehensive evaluation of AI methods on a video-based Question Answering (QA) benchmark focused on human interactions, leveraging additional annotations related to human responses. Our analysis highlights significant differences between human and AI response patterns and underscores critical shortcomings in current benchmarks. We anticipate that these findings will guide the creation of more advanced datasets and represent an important step toward achieving natural communication between humans and AI. Full article