Search Results (458)

This paper introduces a novel framework enabling natural language question answering on Piping and Instrumentation Diagrams (P&IDs), addressing a critical gap between engineering design documentation and intuitive information retrieval. Our approach transforms static P&IDs into queryable knowledge bases through a three-stage pipeline. First, we recognize entities in a P&ID image and organize their relationships to form a base entity graph. Second, this entity graph is converted into a Labeled Property Graph (LPG), enriched with semantic attributes for nodes and edges. Third, a Large Language Model (LLM)-based information retrieval system translates a user query into a graph query language (Cypher) and retrieves the answer by executing it on LPG. For our experiments, we augmented a publicly available P&ID image dataset with our novel PIDQA dataset, which comprises 64,000 question–answer pairs spanning four categories: (I) simple counting, (II) spatial counting, (III) spatial connections, and (IV) value-based questions. Our experiments (using gpt-3.5-turbo) demonstrate that grounding the LLM with dynamic few-shot sampling robustly elevates accuracy by 10.6–43.5% over schema contextualization alone, even under high lexical diversity conditions (e.g., paraphrasing, ambiguity). By reducing barriers in retrieving P&ID data, this work advances human–AI collaboration for industrial workflows in design validation and safety audits. Full article

Background/Objectives: Bladder cancer, the most common and heterogeneous malignancy of the urinary tract, presents with diverse types and treatment options, making comprehensive patient education essential. As large language models (LLMs) emerge as a promising resource for disseminating medical information, their accuracy and validity compared to traditional methods remain under-explored. This study aims to evaluate the effectiveness of LLMs in educating the public about bladder cancer. Methods: Frequently asked questions regarding bladder cancer were sourced from reputable educational materials and assessed for accuracy, comprehensiveness, readability, and consistency by two independent board-certified urologists, with a third resolving any discrepancies. The study utilized a 3-point Likert scale for accuracy, a 5-point Likert scale for comprehensiveness, and the Flesch–Kincaid (FK) Grade Level and Flesch Reading Ease (FRE) scores to gauge readability. Results: ChatGPT-3.5, ChatGPT-4, and Gemini were evaluated on 12 general questions, 6 questions related to diagnosis, 28 concerning treatment, and 7 focused on prevention. Across all categories, the correct response rate was notably high, with ChatGPT-3.5 and ChatGPT-4 achieving 92.5%, compared to 86.3% for Gemini, with no significant difference in accuracy. However, there was a significant difference in comprehensiveness (p = 0.011) across the models. Overall, a significant difference in performance was observed among the LLMs (p < 0.001), with ChatGPT-4 providing the most college-level responses, though these were the most challenging to read. Conclusions: In conclusion, our study adds value to the applications of Artificial Intelligence (AI) in bladder cancer education, with notable insights into the accuracy, comprehensiveness, and stability of the three LLMs. Full article

Objectives: Prolonged disorders of consciousness (DoC) present complex diagnostic and therapeutic challenges. This study aimed to evaluate the accuracy of two ChatGPT models (ChatGPT 4o and ChatGPT o1) in answering questions about prolonged DoC, framed as if they were posed by a patient’s relative. Secondary objectives included comparing performance across languages (English vs. Italian) and assessing whether responses conveyed an empathetic tone. Methods: Fifty-seven open-ended questions reflecting common caregiver concerns were generated in both English and Italian, each categorized into one of three domains: clinical data, instrumental diagnostics, or therapy. Each question contained a background context followed by a specific query and was submitted once to both models. Two reviewers evaluated the responses on a four-point scale, ranging from “incorrect and potentially misleading” to “correct and complete”. Discrepancies were resolved by a third reviewer. Accuracy, language differences, empathy, and recommendation to consult a healthcare professional were analyzed using absolute frequencies, percentages, the Mann–Whitney U test, and Chi-squared tests. Results: A total of 228 responses were analyzed. Both models provided predominantly correct answers (80.7–96.8%), with English responses achieving higher accuracy only for ChatGPT 4o on clinical data. ChatGPT 4o exhibited greater empathy in its responses, whereas ChatGPT o1 more frequently recommended consulting a healthcare professional in Italian. Conclusions: Both ChatGPT models demonstrated high accuracy in addressing prolonged DoC queries, highlighting their potential usefulness for caregiver support. However, occasional inaccuracies emphasize the importance of verifying chatbot-generated information with professional medical advice. Full article

Autophagy critically regulates cellular development while maintaining pathophysiological homeostasis. Since the autophagic process is tightly regulated by the coordination of autophagy-related proteins (ATGs), precise identification of these proteins is essential. Although current computational approaches have addressed experimental recognition’s costly and time-consuming challenges, they still have room for improvement since handcrafted features inadequately capture the intricate patterns and relationships hidden in sequences. In this study, we propose PLM-ATG, a novel computational model that integrates support vector machines with the fusion of protein language model (PLM) embeddings and position-specific scoring matrix (PSSM)-based features for the ATG identification. First, we extracted sequence-based features and PSSM-based features as the inputs of six classifiers to establish baseline models. Among these, the combination of the SVM classifier and the AADP-PSSM feature set achieved the best prediction accuracy. Second, two popular PLM embeddings, i.e., ESM-2 and ProtT5, were fused with the AADP-PSSM features to further improve the prediction of ATGs. Third, we selected the optimal feature subset from the combination of the ESM-2 embeddings and AADP-PSSM features to train the final SVM model. The proposed PLM-ATG achieved an accuracy of 99.5% and an MCC of 0.990, which are nearly 5% and 0.1 higher than those of the state-of-the-art model EnsembleDL-ATG, respectively. Full article

The process of decision-making for machining box-type components plays a crucial role in the technological design of mechanical components. Currently, the selection of process parameters for box-type parts often relies on designers consulting manuals or on personal experience. Moreover, different designers utilize independent and heterogeneous Computer-Aided Process Planning (CAPP) systems, leading to uncertainties in process design and difficulties in sharing and transmitting process knowledge. This paper proposes an ontology-based process decision-making method for the planar machining of box-type parts to infer the appropriate machining process parameters. First, a hierarchical information representation model for process decision-making in planar machining is constructed to describe the decision-making process. Second, an ontology model for process decision-making in planar machining is developed based on relevant concepts and relationships involved in the decision-making process. Third, reasoning rules for planar machining process decisions are established using Semantic Web Rule Language (SWRL), incorporating part feature information and process knowledge to infer reasonable process methods and operation dimensions. Finally, a case study of gear transmission housing is presented to illustrate the working process of the proposed method and verify its effectiveness. Full article

Background/objectives: A child’s working memory needs to be efficient in order to perform well at school, because its manipulative function needs to work properly in order to compose and decompose words, a skill that is necessary for reading. Therefore, if a child with an alteration in this type of memory reads a more complex sentence, they will have difficulty storing it until other cognitive processes involved in language comprehension and production take place, leading to impaired reading comprehension. The aim of this study was to develop and verify the applicability of a remediation program for working memory and reading in students with learning difficulties from the third to fifth grades of primary school. Methods: The study was carried out in two phases: phase 1 developed the program on the basis of a literature review, and phase 2 verified the applicability of the program in a pilot study with 21 schoolchildren divided into two groups. The subjects were subjected to tests of metalinguistic and reading skills and the Brief Child Neuropsychological Assessment Instrument. Results: The working memory and reading remediation program consisted of 11 tasks developing phonological and visuospatial working memory. From the results of the application of the Remediation Program With Working Memory and Reading (RP-WMR) in a pilot study, it was possible to verify the applicability of the program; in other words, the strategies developed for students with learning difficulties can be generalised and applied to students who have deficits in working memory and reading. Conclusions: The result of this research indicates that the structured program for remediation of working memory difficulties has proven to be applicable and can help education professionals as a tool for intervening in working memory deficits and reading decoding skills presented by students with learning difficulties. Full article

The current paper offers a critical reflection on the role of the social dimension of the second language (L2) development of sociolinguistic competence. We center our discussion of L2 sociolinguistic competence on variationist approaches to second language acquisition (SLA) and the study of variable structures. We first introduce the framework of variationist SLA and offer a brief overview of some of the social, and more broadly extralinguistic, factors that have been investigated in this line of inquiry. We then discuss the three waves of variationist sociolinguistics and various social factors that have been examined in other socially oriented approaches to SLA. By reflecting on these bodies of research, our goal is to identify how the insights from this work (i.e., research couched in the second and third waves of variationist sociolinguistics and in other socially oriented approaches to SLA) could be extended to the study of L2 sociolinguistic competence. We argue that greater attention to the social nature of language in variationist SLA is needed in order to more fully understand the L2 development of variable structures. Full article

We study the relationship between tweets referencing Acute Respiratory Infections (ARI) or COVID-19 symptoms and confirmed cases of these diseases. Additionally, we propose a computational methodology for selecting and applying Machine Learning (ML) algorithms to predict public health indicators using social media data. To achieve this, a novel pipeline was developed, integrating three distinct models to predict confirmed cases of ARI and COVID-19. The dataset contains tweets related to respiratory diseases, published between 2020 and 2022 in the state of San Luis Potosí, Mexico, obtained via the Twitter API (now X). The methodology is composed of three stages, and it involves tools such as Dataiku and Python with ML libraries. The first two stages focuses on identifying the best-performing predictive models, while the third stage includes Natural Language Processing (NLP) algorithms for tweet selection. One of our key findings is that tweets contributed to improved predictions of ARI confirmed cases but did not enhance COVID-19 time series predictions. The best-performing NLP approach is the combination of Word2Vec algorithm with the KMeans model for tweet selection. Furthermore, predictions for both time series improved by 3% in the second half of 2020 when tweets were included as a feature, where the best prediction algorithm is DeepAR. Full article

Requirement Engineering (RE) is a critical phase in software development, integral to the successful execution of projects. The initial stage of RE involves requirement elicitation and analysis, where the prioritization of requirements is critical. Traditional methods of requirement prioritization (RP) are diverse, each presenting unique challenges. In response to the challenges of traditional methods, this paper proposes an entirely automated framework designed to eliminate the disadvantages associated with excessive stakeholder involvement. This innovative framework processes raw natural language inputs directly, applying a three-phase approach to systematically assign priority numbers to each requirement. The first phase preprocesses the input to standardize and prepare the data, the second phase employs advanced machine learning algorithms to analyze and rank the requirements, and the third phase consolidates the results to produce a final prioritized list. The effectiveness of this method was tested using the RALIC (Replacement Access, Library, and ID Card) dataset, a well-known benchmark in the field of requirement engineering. The results confirm that our automated approach not only enhances the efficiency and objectivity of the prioritization process but also scales effectively across diverse and extensive sets of requirements. This framework represents a significant advancement in the field of software development, offering a robust alternative to traditional, subjective methods of requirement prioritization. Full article

Eivissa/Ibiza, as per its names in its two official languages, Catalan and Spanish, is the third of the Balearic Islands in terms of extension and the second concerning population. It is also a well-known holiday destination in Europe. Numerous ethnobotanical prospections have been performed in the Balearic Islands, but to date, Ibiza lacks a monographic study on traditional knowledge related to plant biodiversity. In this paper, we present the results of the ethnobotanical investigation carried out in Ibiza from 2016 to 2023. A total amount of 95 interviews were conducted with 101 informants born between 1916 and 1983, with semi-structured interviews, participant observation and plant collection, identification and deposit in a public herbarium as basic methods. The total ethnoflora of the island is 254 taxa belonging to 71 botanical families. The most cited families are Solanaceae (1030 URs, 13.50%), followed by Fabaceae (770 URs, 10.09%), Lamiaceae (646 URs, 8.47%) and Rutaceae (578 URs, 7.57%). The most cited species are Vitis vinifera, Capsicum annuum, Solanum lycopersicum, Solanum tuberosum and Citrus sinensis. This study reveals that the local population still retains significant ethnobotanical knowledge. Further research in similar territories could help determine whether this pattern is consistent elsewhere. Full article

The public release of ChatGPT in late 2022 has resulted in considerable publicity and has led to widespread discussion of the usefulness and capabilities of generative Artificial intelligence (Ai) language models. Its ability to extract and summarise data from textual sources and present them as human-like contextual responses makes it an eminently suitable tool to answer questions users might ask. Expanding on a previous analysis of the capabilities of ChatGPT3.5, this paper tested what archaeological literature appears to have been included in the training phase of three recent generative Ai language models: ChatGPT4o, ScholarGPT, and DeepSeek R1. While ChatGPT3.5 offered seemingly pertinent references, a large percentage proved to be fictitious. While the more recent model ScholarGPT, which is purportedly tailored towards academic needs, performed much better, it still offered a high rate of fictitious references compared to the general models ChatGPT4o and DeepSeek. Using ‘cloze’ analysis to make inferences on the sources ‘memorized’ by a generative Ai model, this paper was unable to prove that any of the four genAi models had perused the full texts of the genuine references. It can be shown that all references provided by ChatGPT and other OpenAi models, as well as DeepSeek, that were found to be genuine, have also been cited on Wikipedia pages. This strongly indicates that the source base for at least some, if not most, of the data is found in those pages and thus represents, at best, third-hand source material. This has significant implications in relation to the quality of the data available to generative Ai models to shape their answers. The implications of this are discussed. Full article

Traditional text classification models predominantly rely on static text representations, failing to capture temporal variations in language usage and evolving semantic meanings. This limitation reduces their ability to accurately classify time-sensitive texts, where understanding context, detecting trends, and addressing semantic shifts over time are critical. This paper introduces a novel time-aware short text classification model incorporating temporal information, enabling tracking of and adaptation to evolving language semantics. The proposed model enhances contextual understanding by leveraging timestamps and significantly improves classification accuracy, particularly for time-sensitive applications such as News topic classification. The model employs a hybrid architecture combining Convolutional Neural Networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks, enriched with attention mechanisms to capture both local and global dependencies. To further refine semantic representation and mitigate the effects of semantic drift, the model fine-tunes GloVe embeddings and employs synonym-based data augmentation. The proposed approach is evaluated on three benchmark dynamic datasets, achieving superior performance with classification accuracy reaching 92% for the first two datasets and 85% for the third dataset. Furthermore, the model is applied to a different-fields categorization and trend analysis task, demonstrating its capability to capture temporal patterns and perform detailed trend analysis of domain-agnostic textual content. These results underscore the potential of the proposed framework to provide deeper insights into the evolving nature of language and its impact on short-text classification. This work advances natural language processing by offering a comprehensive time-aware classification framework, addressing the challenges of temporal dynamics in language semantics. Full article

This study aimed to increase the understanding of academic stress and coping strategies of third culture kids (TCKs) in South Korean colleges. For this aim, six Korean college students who are TCKs were interviewed. For analyzing the interview data, consensual qualitative research was used. As a result, participants’ academic stressors were related to language, interpersonal relationships, learning strategies, career issues, and financial difficulties. As their coping strategies, they reported preparation and review, help-seeking, group study, goal orientation, self-efficacy, and control belief. The results of this study can help South Korean TCK college students with academic stressors, reducing their related stress and allowing them to adjust well in college. We also discussed how educational institutions can help those students overcome academic stress and find their coping strategies. Full article

This study used an electrophysiological technique to investigate the perception mechanism of Mandarin native speakers and learners from non-tonal language backgrounds when processing the third tone (T3) and its variants in Mandarin. The experiments used a 2 × 2 two-factor mixed design to examine the perception of T3 and its variants and the processing mechanisms of learners and native speakers under different levels of attention. Differences in attention and language backgrounds in the perception of Mandarin tones were further investigated. These results provide evidence that there are no significant differences in the perception of the two T3 variants by native Mandarin speakers under different attentional conditions. In contrast, learners from non-tonal language backgrounds were more likely to perceive a low flat tone as T3 than a low concave tone in the attentive condition. This means that learners are more likely to rely on low-pitch cues rather than the concave contour of the tone when perceiving T3. Full article

This study explored how bilingual Latine teacher candidates (TCs)—undergraduate students in a teacher preparation program working toward obtaining a teaching license and identifying as individuals from Latin America or of Latin American descent, using the gender-neutral term in Spanish, “Latine”, to encompass all genders—identified and addressed cultural assumptions in mathematics questions on the STAAR (State of Texas Assessments of Academic Readiness) test. Twenty Latine TCs who were enrolled at a major southern research university (pseudonym: Southland University) program reviewed fifth-grade STAAR mathematics questions to assess cultural assumptions and suggest revisions for cultural relevancy. The findings reveal that the TCs identified cultural assumptions in questions about probable unfamiliar currency, non-standard measurement units, and culturally specific terms that could impede students’ understanding. In their revisions, the TCs proposed simplifying language and provided contextual examples to enhance clarity, aligning with the first tenet of culturally relevant pedagogy (CRP). However, few revisions addressed CRP’s second and third tenets, which involve fostering cultural competence and critical consciousness. This study underscores the importance of integrating comprehensive CRP training in teacher preparation programs to better equip TCs to create culturally responsive teaching practices. The findings contribute to ongoing discussions about improving the cultural relevancy in standardized tests and supporting diverse student populations in achieving academic success. Full article