Savonia University of Applied Sciences

In industrial Predictive Maintenance (PdM), effective data-driven models are often limited by a scarcity of data, dataset imbalance, and the high costs of collecting failure data. By simulating realistic failure scenarios and enhancing model training, the synthetic data generation has emerged as a promising strategy to overcome these challenges. This article is a systematic literature review of 86 peer-reviewed articles published since 2020 that focus on synthetic data applications in medium-to-heavy machinery and industrial processes. Data generation techniques fall into four key categories: data augmentation, generative models, physics-based simulations and hybrid approaches, and feature-based transformations. This review analyzes the strengths, limitations, and adoption trends of each method. Findings reveal that hybrid and physics-informed models are particularly valuable in safety-critical domains where model transparency and adherence to physical laws are essential and industrial contexts demand higher reliability and contextual accuracy. To address these needs, the Synthetic Data-Enhanced PdM (SD-PdM) framework, a five-phase methodology for integrating synthetic data into maintenance strategies, is proposed. This framework supports scalable, explainable, and economically viable smart maintenance solutions.

Introduction Asthma, chronic obstructive pulmonary disease (COPD) and obstructive sleep apnoea (OSA) are prevalent chronic respiratory diseases associated with increased comorbidity, mortality and healthcare costs. Physical activity and exercise are widely recommended as part of treatment for these conditions, yet the specific effects of Nordic walking (NW) remain underexplored. The aims of this randomised controlled trial (RCT) are to improve physical fitness, functional capacity and respiratory health and increase regular physical activity and quality of life of older adults with asthma and/or COPD and/or OSA through a supervised 3-month group-based NW intervention combined with resistance, balance and mobility training.Methods and analysis This single-blinded, parallel-group RCT will recruit 100 adults aged 55–80 years diagnosed with asthma and/or COPD and/or OSA in the Northern Savo region of Finland. Participants will be randomly allocated to either an intervention group or a control group.The intervention group will participate in a 12-week supervised exercise programme consisting of progressive NW sessions twice per week and resistance, balance and mobility training once per week. The primary outcome is a change in cardiorespiratory endurance. Secondary outcomes include functional capacity, physical activity level, spirometry parameters and quality of life. The control group will continue their usual physical activity and receive physical activity guidance after 12 weeks. Measurements were conducted at baseline, three and 9 months. Data will be analysed according to the intention-to-treat principle. Group differences over time will be examined using appropriate parametric or non-parametric methods depending on data distribution.Ethics and dissemination Ethical approval was obtained from the Regional Medical Research Ethics Committee of Eastern Finland Collaborative Area (892/13.00/2023). Findings will be disseminated through publications in peer-reviewed journals and presentations at scientific conferences.Trial registration number The trial is registered at ISRCTN12097135, registration date: 7 June 2024.

ABSTRACT Objectives The aim of this study was to translate and validate the GOHAI Finnish version from the original English version. As the population ages rapidly, there is a growing prevalence of oral health issues among older adults, leading to a higher demand for oral health care services. Using tools like the Geriatric Oral Health Assessment Index (GOHAI) can effectively gather information on these oral health challenges among older individuals. Materials and Methods Translation of the original GOHAI version was performed by a forward‐backward process and tested by a questionnaire in three cities in southern and Eastern Finland in 2020–2021. Reliability was assessed by measuring internal consistency and validity through convergent validity, discriminant validity, and known‐group validity. Results A total of 209 participants aged 65 years or over (84 males and 125 females) completed the GOHAI questionnaire. The mean GOHAI‐ADD score (±SD) was 49.9 ± 6.2 (range 31–60). The Cronbach's alpha coefficient for the Finnish version of GOHAI was 0.79, indicating a high level of internal consistency. Item‐total score correlations were between 0.26 and 0.63. The use of removable dentures, perceived need for oral health care, and toothache or other problems with teeth or dentures were associated with poorer oral health‐related quality of life, whereas good self‐perceived oral health was associated with better oral health‐related quality of life. Conclusion The Finnish version of the GOHAI showed good reliability and moderate validity among older people who had sought oral health care. However, the study design, including its cross‐sectional nature, reliance on a convenience sample, and the absence of clinical examinations, limits the generalizability of the findings to all older adults in Finland.

BACKGROUND:The transformation of nursing education has emphasized the role of distance education as a permanent component. Nursing students' learning experiences and outcomes in this format show considerable variation and raise questions about the most effective distance learning methods. AIMS:The aim of this integrative review was to explore nursing students' experiences with distance learning, identify the learning outcomes it produces, and examine the distance learning methods used in nursing education. DESIGN:Integrative literature review. METHODS:A systematic literature search was conducted in the CINAHL (EBSCO, PubMed/Medline, Education database (ProQuest), Scopus and ERIC (EBSCO) databases, including peer-reviewed studies published in English between 2018 and 2024. The review followed the PRISMA 2020 guidelines. Quality appraisal was performed using Hawker et al.'s evaluation tool. Data was analyzed using inductive content analysis. RESULTS:A total of 43 studies were included in the review. Five main themes were identified describing students' experiences: the accessibility of digital learning platforms, the quality and structure of learning materials, the acquisition of practical and clinical skills, social interaction and peer support, motivation, self-regulation, and emotional well-being. Learning outcomes were categorized into cognitive, psychomotor, and affective domains. The most common learning methods included synchronous, asynchronous, and blended approaches, with blended learning showing particularly positive results. CONCLUSION:Distance education can support nursing students' learning when it is well-structured and combines pedagogical planning with interactive and practical elements. Not all competencies, particularly clinical skills, can be taught remotely. The learning experience is shaped by individual abilities, guidance, and technical conditions, and distance education may not suit all students equally well. Effective methods, especially blended learning, support engagement and learning when aligned with student needs and pedagogical goals.

Abstract Mineral Prospectivity Mapping (MPM) is an pivotal methodology for identifying prospective deposits across large regions using complex geophysical datasets. The application of machine learning could significantly improve these processes. However, a critical challenge in data-driven mineral prospectivity mapping is the class imbalance between the mineralized locations and large background, which can severely limit model performance. To address this, this study systematically evaluates two machine learning workflows: a supervised Multilayer Perceptron (MLP) and a contrastive representation learning with radius classifier. The algorithm applied to a geophysical dataset from Finland included integrated data balancing ( $$M \approx N$$ ), nested cross-validation, and methods for uncertainty quantification (radius distance and Shannon entropy) and interpretability (Shapley Additive exPlanations(SHAP)). The supervised MLP performed well with an Area Under the Curve (AUC) of 0.99, perfect of recall 100%, and Geometric Mean (G-mean) of 0.9937. The Shapley Additive explanations analysis showed that magnetic and pseudo-gravity anomalies are among those more significant features. Findings indicate that a well developed MLP can address significant data imbalance, successfully reducing the investigation footprint to around 1% of the total area while detecting all known deposits. The use of uncertainty maps showed that such deposits are found in high-confidence zones (low-uncertainty) along transitional corridors at geological boundaries, providing a reliable and economical framework for directing mineral exploration.