Artificial Intelligence Research Articles

Sustainability Awareness in Manufacturing: A Review of IoT Audio Sensor Applications in the Industry 5.0 Era

The integration of Internet of Things audio sensors with Artificial Intelligence techniques is revolutionizing predictive maintenance systems in machining operations, playing a pivotal role in advancing the sustainability goals of Industry 5.0. The synergy between these technologies enhances operational efficiency, reduces downtime, and minimizes waste, aligning with energy conservation and resource optimization goals. The use of audio sensors provides a cost-effective, non-intrusive solution for machining operations. In this work, a bibliometric analysis of the progress achieved in this field is performed, identifying which challenges have been extensively addressed and which remain unexplored. By assessing the existing research, this study aims to highlight gaps that necessitate further investigation, guiding future research efforts toward the most critical and promising directions for enhancing predictive maintenance in machining processes. Through a comprehensive analysis of publication trends, collaboration networks, and research gaps, this study intends to provide valuable insights for academia and industry stakeholders, to motivate their efforts in this field. Understanding these trends is essential for fostering innovation and ensuring that the development of predictive models continues to evolve to maximize both production efficiency and sustainability.

Evaluating the Impact of AI in Orthopedics: A Quantitative Analysis of Advancements and Challenges

Abstract This study systematically evaluates the development of artificial intelligence applications in orthopedics using bibliometric analysis methods. Data obtained from the Web of Science database, analyzing 1833 documents published between 1988 and 2024, reveal an annual growth rate of 19.45%, increased interdisciplinary collaboration, and a high level of international interaction. Co-occurrence analysis identifies key themes, including diagnostic classification methods utilizing image processing for spine and low back pain, AI-based modeling in diagnosis, risk assessment and management of orthopedic diseases, outcome evaluation, risk and quality assessments in orthopedic surgery and joint prostheses, as well as orthopedic trauma and reconstruction methods. Co-citation analysis highlights themes such as the integration of machine learning models into clinical applications, the use of artificial intelligence in spine surgery, current knowledge and practical application guidelines, spine metastases and clinical decision support systems, deep learning techniques in imaging and diagnostics, patient-based payment modeling and health economics, and AI-supported patient communication and clinical information systems. Referenced Publication Years Spectroscopy (RPYS) analysis indicates that foundational studies and key breakthroughs were concentrated in the years 2001, 2010, 2015, and 2019. Recent publications support the application of artificial intelligence in areas such as tibiofemoral cartilage strain analysis, mechanical alignment, automatic segmentation, clinical prediction models, and pediatric orthopedics through deep learning and machine learning techniques.

Use of Artificial Intelligence in Recognition of Fetal Open Neural Tube Defect on Prenatal Ultrasound.

To compare the axial cranial ultrasound images of normal and open neural tube defect (NTD) fetuses using a deep learning (DL) model and to assess its predictive accuracy in identifying open NTD.It was a prospective case-control study. Axial trans-thalamic fetal ultrasound images of participants with open fetal NTD and normal controls between 14 and 28 weeks of gestation were taken after consent. The images were divided into training, testing, and validation datasets randomly in the ratio of 70:15:15. The images were further processed and classified using DL convolutional neural network (CNN) transfer learning (TL) models. The TL models were trained for 50 epochs. The data was analyzed in terms of Cohen kappa score, accuracy score, area under receiver operating curve (AUROC) score, F1 score validity, sensitivity, and specificity of the test.A total of 59 cases and 116 controls were fully followed. Efficient net B0, Visual Geometry Group (VGG), and Inception V3 TL models were used. Both Efficient net B0 and VGG16 models gave similar high training and validation accuracy (100 and 95.83%, respectively). Using inception V3, the training and validation accuracy was 98.28 and 95.83%, respectively. The sensitivity and specificity of Efficient NetB0 was 100 and 89%, respectively, and was the best.The analysis of the changes in axial images of the fetal cranium using the DL model, Efficient Net B0 proved to be an effective model to be used in clinical application for the identification of open NTD. · Open spina bifida is often missed due to the nonrecognition of the lemon sign on ultrasound.. · Image classification using DL identified open spina bifida with excellent accuracy.. · The research is clinically relevant in low- and middle-income countries..

Medioznawstwo lingwistyczne

In the article, the term media studies linguistics (medioznawstwo lingwistyczne) is proposed to denote research on the functioning of language in the media. This term is constructed similarly to designations of branches of applied linguistics such as psycholinguistics, sociolinguistics, legal linguistics (jurislinguistics), political linguistics (politological linguistics), or mathematical linguistics, in which both components of the name are names of subdisciplines: linguistics and law, linguistics and sociology, linguistics and psychology, linguistics and political science (politics), linguistics and mathematics, and not just the name of the environment in which the language functions—that is, media (medio-)—and the designation of the discipline that studies it—linguistics; mediolinguistics. Media studies linguistics deals with the study of the use of language in the media, that is, its functioning in printed, audiovisual, logovisual, digital, and network mass communication media. Today, we are dealing with new (digital) forms of language existence and a completely different semiotic code, conditioned by the development of new media technologies, which, in the era of artificial intelligence and virals, also require a new approach to studying media communication.

An information theoretic limit to data amplification

Abstract In recent years generative artificial intelligence has been used to create data to support scientific analysis. For example, Generative Adversarial Networks (GANs) have been trained using Monte Carlo simulated input and then used to generate data for the same problem. This has the advantage that a GAN creates data in a significantly reduced computing time. N training events for a GAN can result in NG generated events with the gain factor G being greater than one. This appears to violate the principle that one cannot get information for free. This is not the only way to amplify data so this process will be referred to as data amplification which is studied using information theoretic concepts. It is shown that a gain greater than one is possible whilst keeping the information content of the data unchanged. This leads to a mathematical bound, 2 log(Generated Events) ≥ 3log(Training Events), which only depends on the number of generated and training events. This study determined the conditions for both the underlying and reconstructed probability distributions to ensure this bound. In particular, the resolution of variables in amplified data is not improved by the process but the increase in sample size can still improve statistical significance. The bound was confirmed using computer simulation and analysis of GAN generated data from the literature. 

Managing expectations towards AI tools for software development: a multiple-case study

Abstract Software development organizations (SDOs) are increasingly working to adopt artificial intelligence (AI) tools, like GitHub Copilot, to meet varied expectations. Nevertheless, we know little about how SDOs manage these expectations. This paper investigates how different SDOs expect AI tools to impact software development, and how these expectations change after a period of considering and evaluating AI tools. We conducted a multiple-case study involving three SDOs. To elicit initial expectations towards AI tools, we collected data using semi-structured interviews and field visits. To assess the persistence of expectations towards AI tools, we collected data from meetings, a debriefing, and retrospectives on AI tools. We found three expectations particular to one SDO; four shared between two SDOs; and six pervasive across all SDOs. Five expectations did not persist after experiential learning with AI tools, due to platform- and SDO-related factors. SDOs must carefully manage their expectations towards AI tools due to the variety and complexity of expectations. Some expectations are niche-specific based on their compatibility with the unique SDOs' people- and structure-related aspects, while others are becoming mainstream for a broader array of SDOs. Recognizing factors that affect the persistence of expectations and how they manifest in the individual SDO will enable SDOs to form their initial expectations and understand how these might change during adoption of AI tools, supporting expectation management.

Smart quality control: integrating six sigma, machine learning and real-time defect prediction in manufacturing

Purpose This study aims to develop a smart quality control framework integrating Six Sigma methodology, real-time sensing technologies and machine learning algorithms to enhance manufacturing defect prediction and process optimization. By leveraging predictive capabilities and real-time data analysis, the framework seeks to reduce costs associated with poor quality and improve overall process capability. Design/methodology/approach The proposed framework uses the Define-Measure-Analyze-Improve-Control methodology to identify and address critical process parameters. A robust Internet of Things (IoT) sensing network is incorporated for continuous process monitoring. At the same time, multiple machines learning models, including decision trees, random forests, boosted decision trees, linear regression and k-star algorithms, are evaluated for predictive defect detection. Implementation was conducted at an electrical conductor manufacturing facility, enabling real-time analysis and intervention to prevent defects. Findings The implementation of the framework demonstrated significant improvements in quality and efficiency. The cost of poor quality was reduced from 5% to 1.7%, a 66% improvement. Process capability was enhanced, with sigma levels increasing from 3.14 to 4.3. These results validate the effectiveness of combining traditional quality control techniques with advanced Artificial Intelligence and IoT technologies, delivering predictive capabilities and enabling real-time process optimization. Originality/value This study highlights the innovative integration of Six Sigma, machine learning and IoT sensing technologies to transform manufacturing quality control. The smart quality control framework represents a significant advancement in manufacturing intelligence, offering a scalable, data-driven solution that improves efficiency, competitiveness and sustainability across diverse industrial applications.

A Novel Hybrid Deep Learning Model Enhanced with Explainable AI for Brain Tumor Multi-Classification from MRI Images

The life span and quality of a patient are greatly diminished by a brain tumor, a type of cancer. For patients, early diagnosis and effective treatment are very significant in this respect. To assist medical professionals in this difficult and error-prone process and improve both the accuracy and interpretability of the model, this study proposes a new hybrid deep learning model enhanced with explainable artificial intelligence for brain tumor multi-classification from MRI images. It integrates a customized CNN model for feature extraction from images and the optimized XGBoost method with high classification success. It also incorporates Grad-CAM, which makes the black-box structure of the model transparent and the decision-making process more understandable. The proposed model classified four different brain tumors, namely glioma, meningioma, notumor and pituitary, with 99.77% accuracy and demonstrated superior performance when compared with existing methods. The results show that a robust, interpretable and high-performance hybrid classification model has been developed for brain tumor detection.

Beyond boundaries: unveiling the art of blockchain-enshrined molecules through xSublimatio

In 2023, the xSublimatio project showcased a fusion of art and science, presenting an interactive platform where molecules were transformed into digital artworks within the blockchain. This innovative concept leveraged advanced artificial intelligence predictions to bridge empirical precision with creative expression, offering a unique exploration of scientific data through artistic interpretation.The creation of xSublimatio involved meticulous selection and representation of molecules, blending scientific accuracy with aesthetic appeal. Through AlphaFold-inspired insights, the project reimagined molecular design, transcending traditional boundaries.During its presentation at the GDR ChemBio conference in Strasbourg, xSublimatio sparked insightful discussions within the French chemistry community. This article explores its technical implementation, its potential for introducing blockchain and non-fungible token concepts to diverse communities, and its broader implications for interdisciplinary collaboration and decentralized science.

Semantic Clinical Artificial Intelligence (SCAI) Usability Testing.

We evaluated the performance of Semantic Clinical Artificial Intelligence (SCAI, pronounced Sky), a large language model (LLM) knowledge resource through usability testing. This pretest-intervention-posttest mixed-methods user interface (UI) design study investigates usability to determine whether the LLM provides a more comprehensive, efficient, and enhanced user-friendly means of delivering end user information as compared to using primary sources of information from the Internet (Web). Our analysis focused on assessing the LLM's efficiency and usability in helping users arrive at accurate and reliable outcomes, to ultimately determine its value as an innovative tool for packaging and presenting information. Usability test sessions were conducted using the cognitive walkthrough approach, via Zoom. Participants were asked to respond to scenarios using only the LLM, and then only the web, and vice versa. These sessions were followed by user feedback sessions where participants rated their experiences and responded to open-ended questions related to the overall usability and satisfaction with SCAI.

Human creativity versus artificial intelligence: source attribution, observer attitudes, and eye movements while viewing visual art

IntroductionArtificial Intelligence (AI) has the capability to create visual images with minimal human input, a technology that is being applied to many areas of daily life. However, the products of AI are consistently judged to be worse than human-created art, even when comparable in quality. The purpose of this study is to determine whether explicit cognitive bias against AI is related to implicit perceptual mechanisms active while viewing art.MethodsParticipants’ eye movements were recorded while viewing religious art, a notably human domain meant to maximize potential bias against AI. Participants (n = 92) viewed 24 pieces of Biblically-inspired religious art, created by the AI tool DALL-E 2. Participants in the control group were told prior to viewing that the pieces were created by art students, while participants in the experimental group were told the pieces were created by AI. Participants were surveyed after viewing to ascertain their opinions on the quality and artistic merit of the pieces.ResultsParticipants’ gaze patterns (fixation counts, fixation durations, fixation dispersion, saccade amplitude, blink rate, saccade peak velocity, and pupil size) did not differ based on who they believed created the pieces, but their subjective opinions of the pieces were significantly more positive when they believed pieces were created by humans as opposed to AI.DiscussionThis study did not obtain any evidence that a person’s explicit “valuation” of artworks modulates the pace or spatial extent of visual exploration nor the cognitive effort expended to develop an understanding of them.

Can Generative Artificial Intelligence Reduce Pain?

Can Generative Artificial Intelligence Reduce Pain?

Integrating Virtual Reality into Welding Training: An Industry 5.0 Approach

In the context of Industry 5.0, Virtual Reality (VR) is transforming workforce training by enhancing skill acquisition and smart assistance to improve safety, among other things. This study presents a VR-based welding training simulator, developed in Unreal Engine 5 and deployed on Meta Quest 3, designed to teach and standardize soldering techniques through progressive training stations, interactive guidance, and real-time feedback. A mixed-methods evaluation, combining quantitative metrics (execution time, positioning errors, grip errors) and qualitative user feedback, demonstrated a significant reduction in execution time and elimination of errors in positioning and grip. Additionally, no errors were made in real-world soldering post-training, confirming a high transfer of learning and reduced variability in performance among users. These findings highlight VR as a viable and scalable alternative to traditional training, ensuring process consistency, reduced learning time, and increased training efficiency. Future work will explore enhanced haptic feedback and the integration of generative artificial intelligence to improve real-time analysis.

Deep Learning-Based Analysis of Emotional Expression and Performance Characteristics in Vocal Music Teaching

Nowadays, the rapid progress in art education and artificial intelligence technology has indirectly promoted the joint exploration of multimedia and computer technology. Vocal music is art with emotional expression, and performers should have a common emotional interaction with the emotional expression of music itself. Therefore, this paper proposes a data analysis of emotional expression and performance characteristics of vocal music teaching based on deep learning. First, Mel-Frequency Cepstral Coefficients (MFCC) and Gamma Tone Filter (GTF) features of audio are extracted. Then, two different features are sent into the same filter structure to extract emotional features. Finally, the audio fusion features output by the filter are input into the BiLTM network, and the high-dimensional emotion features are extracted based on the forward and reverse networks. Through the model training results, the analysis performance of the method proposed is relatively excellent, and the vocal music emotional features can be effectively extracted through a variety of fusion features. The performance of RMSE, RME and [Formula: see text] is the best when fusing MFCC and GIF features. When the audio features are relatively rich, this paper can get better weights to facilitate the iteration of the model, and use multi-modal feature fusion to effectively improve the prediction accuracy of Arousal and Valence values. It has important reference significance for the emotional analysis of multimodal vocal music and the emotional expression analysis of vocal music teaching.

Opportunity and threat: how employees’ perceptions of artificial intelligence influence job crafting

PurposeArtificial Intelligence (AI) application imposes a complicated and uncertain situation for employees to comprehend and react. Existing research has examined employees’ positive and negative perceptions of AI and their reactions separately. Little is known about how the two opposing perceptions of AI could coexist and interact to shape employees’ behavioral reactions. Drawing on the categorization theory, our research aims to examine how employees’ opportunity and threat perceptions of AI interact to influence job crafting and boundary conditions for this interaction.Design/methodology/approachWe conducted a two-wave study of 250 employees in China who had experienced AI transformation in their organizations. SPSS and Hayes PROCESS were used to test the hypotheses.FindingsThe positive effect of employees’ opportunity perceptions of AI on job crafting was attenuated by their threat perceptions. This attenuating effect was stronger for younger employees.Originality/valueOur research extends categorization theory and the literature on AI perceptions by demonstrating the interaction effect of employees’ opposing perceptions of AI on job crafting and identifying age as a boundary condition for this interaction.

Investigation of Bleeding Disorders: When and How Should We Test Platelet Functions?

Inherited platelet disorders (IPDs) are rare conditions with diverse underlying pathophysiology which should be suspected in patients presenting with mucocutaneous bleeding or hemorrhages upon hemostatic challenges, in the presence or not of thrombocytopenia. Identifying IPDs is critical for providing appropriate care, preventing misdiagnosis, and avoiding unnecessary interventions, such as splenectomy. Syndromic IPDs, which may be associated with severe complications like kidney failure, infection, and malignancies, underscore the importance of accurate diagnosis and tailored management.Diagnosing IPDs remains challenging, requiring a comprehensive approach that integrates clinical assessment, evaluation of the bleeding history using standardized tools, like the ISTH-BAT, and first-line laboratory tests, such as light transmission aggregometry and flow cytometry. Second-line and specialized tests, including transmission electron microscopy, genetic analysis, and biochemical studies, may provide further insight in complex cases. Technological advancements, including multicolor flow cytometry and microfluidic tools, may in perspective improve IPD diagnostics by providing high-throughput and precise laboratory assays. In particular, mass cytometry and multi-omics may contribute to unraveling IPD pathophysiology, identifying novel markers, and refining disease classification. The application of artificial intelligence shows potential for improving diagnostic accuracy through the automated analysis of platelet morphology and function, from flow cytometry and digital microscopy assays, and for improving the understanding of pathogenic mechanisms of IPD through the examination of big data.This review summarizes current IPD platelet function testing strategies, emphasizing the need for a structured, tiered approach and examining emerging technologies and AI applications that could revolutionize diagnostic workflows, leading to personalized care and to an expanded understanding of IPDs.

Global Health care Professionals' Perceptions of Large Language Model Use In Practice: Cross-Sectional Survey Study.

ChatGPT is a large language model-based chatbot developed by OpenAI. ChatGPT has many potential applications to health care, including enhanced diagnostic accuracy and efficiency, improved treatment planning, and better patient outcomes. However, health care professionals' perceptions of ChatGPT and similar artificial intelligence tools are not well known. Understanding these attitudes is important to inform the best approaches to exploring their use in medicine. Our aim was to evaluate the health care professionals' awareness and perceptions regarding potential applications of ChatGPT in the medical field, including potential benefits and challenges of adoption. We designed a 33-question online survey that was distributed among health care professionals via targeted emails and professional Twitter and LinkedIn accounts. The survey included a range of questions to define respondents' demographic characteristics, familiarity with ChatGPT, perceptions of this tool's usefulness and reliability, and opinions on its potential to improve patient care, research, and education efforts. One hundred and fifteen health care professionals from 21 countries responded to the survey, including physicians, nurses, researchers, and educators. Of these, 101 (87.8%) had heard of ChatGPT, mainly from peers, social media, and news, and 77 (76.2%) had used ChatGPT at least once. Participants found ChatGPT to be helpful for writing manuscripts (n=31, 45.6%), emails (n=25, 36.8%), and grants (n=12, 17.6%); accessing the latest research and evidence-based guidelines (n=21, 30.9%); providing suggestions on diagnosis or treatment (n=15, 22.1%); and improving patient communication (n=12, 17.6%). Respondents also felt that the ability of ChatGPT to access and summarize research articles (n=22, 46.8%), provide quick answers to clinical questions (n=15, 31.9%), and generate patient education materials (n=10, 21.3%) was helpful. However, there are concerns regarding the use of ChatGPT, for example, the accuracy of responses (n=14, 29.8%), limited applicability in specific practices (n=18, 38.3%), and legal and ethical considerations (n=6, 12.8%), mainly related to plagiarism or copyright violations. Participants stated that safety protocols such as data encryption (n=63, 62.4%) and access control (n=52, 51.5%) could assist in ensuring patient privacy and data security. Our findings show that ChatGPT use is widespread among health care professionals in daily clinical, research, and educational activities. The majority of our participants found ChatGPT to be useful; however, there are concerns about patient privacy, data security, and its legal and ethical issues as well as the accuracy of its information. Further studies are required to understand the impact of ChatGPT and other large language models on clinical, educational, and research outcomes, and the concerns regarding its use must be addressed systematically and through appropriate methods.

Fuzzy Rules for Explaining Deep Neural Network Decisions (FuzRED)

This paper introduces a novel approach to explainable artificial intelligence (XAI) that enhances interpretability by combining local insights from Shapley additive explanations (SHAP)—a widely adopted XAI tool—with global explanations expressed as fuzzy association rules. By employing fuzzy association rules, our method enables AI systems to generate explanations that closely resemble human reasoning, delivering intuitive and comprehensible insights into system behavior. We present the FuzRED methodology and evaluate its performance on models trained across three diverse datasets: two classification tasks (spam identification and phishing link detection), and one reinforcement learning task involving robot navigation. Compared to the Anchors method FuzRED offers at least one order of magnitude faster execution time (minutes vs. hours) while producing easily interpretable rules that enhance human understanding of AI decision making.

Physical Adaptation of Articulated Robotic Arm into 3D Scanning System

Robots and 3D scanning systems are essential in modern industrial production, enhancing quality control, reducing costs, and improving production efficiency. Such systems align with Industry 4.0 trends, incorporating the Internet of Things (IoT), Big Data, Cyber–Physical Systems, and Artificial Intelligence to drive innovation. This paper focuses on the physical adaptation of old or out-of-use articulated robot arms for new tasks such as manipulation with a handheld 3D scanner, with the goal of automated quality control. The adaptation was carried out using a methodology that features the application of several techniques such as 3D digitization (photogrammetry), reverse engineering and 3D modeling (SolidWorks), the CAD search engine (3Dfindit), and 3D printing (fused deposition modeling—FDM). Reconstructed 3D models were used to design connecting elements, such as gripper jaws. The final results show that it is possible to create a connecting element utilizing this approach with very little expenditure of resources and time.

I won’t become obsolete! exploring the acceptance and use of GenAI by marketing professionals

PurposeGenerative Artificial Intelligence (GenAI) is reshaping the marketing landscape by enhancing creativity, enabling personalised customer engagement, and streamlining operations. Its transformative impact on content creation opens new opportunities for marketing communication. This study examines how marketing professionals perceive its strategic value and investigates the psychological factors shaping their expectations and attitudes towards its adoption.Design/methodology/approachThis study adopts a qualitative research approach, using semi-structured interviews with marketing professionals in the pharmaceutical sector to explore their expectations for GenAI adoption. The pharmaceutical industry’s complex communication needs, strict regulatory requirements, and focus on innovation make it an ideal context for this investigation. Additionally, its underrepresentation in academic marketing research adds further relevance to the study.FindingsMarketing experts do not view GenAI as an immediate threat. However, they are concerned about its long-term impact, particularly its potential to automate complex creative and strategic tasks, reducing the need for human involvement. The results emphasise the lasting importance of human creativity and sensibility, especially in pharmaceutical marketing, where effective communication relies on nuance and empathy. This study contributes to theory by incorporating psychological factors, such as the fear of obsolescence, into traditional technology adoption models, offering new insights into how GenAI can enhance rather than replace human creativity.Originality/valueThis study offers fresh insights into the adoption and implications of GenAI in marketing by focusing on the perspectives of industry professionals. Unlike prior research centred on technical advancements or consumer outcomes, this paper highlights the managerial viewpoint, exploring how GenAI enhances creativity, transforms content creation, and supports strategic goals in marketing communication. It also addresses key challenges, such as regulatory hurdles and the psychological impact of automation, providing a comprehensive understanding of how GenAI is poised to redefine marketing practices.