VTT Research System
Not a member yet
161399 research outputs found
Sort by
CEMIS-UURA TP3 Mittaustekniikka: Vajaatäytteisen putken virtausmittaus:Tekninen loppuraportti
Get PDFRaportissa kuvataan CEMIS-UURA -hankkeen VTT MIKES Kajaanin osuus, joka liittyy työpakettiin 3: Mittaustekniikka. VTT MIKESin tavoitteena oli kehittää ultraäänivirtausmittaustekniikkaa veden virtausmittaukseen ensin täysissä, teollisuuden kokoluokan putkissa ja jatkokehittää menetelmää vajaatäytteisen putken virtausmittauksiin ja selvittää mitä muita mittaustekniikoita siihen täytyy yhdistää, jotta virtaus saadaan mitattua luotettavasti.Hankkeessa toteutettiin ultraääneen perustuva, putken ulkopintaan kiinnitettävä clamp-on ultraäänivirtausmittari nestevirtaukseen. Mittauksissa käytettiin referenssilaitteistona VTT MIKES Kajaanin nestevirtauslaboratorion D500-laitteiston DN150-kokoista mittauslinjaa, jossa on referenssimittareina kaksi magneettista virtausmittaria. Menetelmää on testattu vedellä täydessä, paineisessa putkessa. Ultraäänivirtauslaitteistolle on tehty alustava mittausepävarmuusanalyysi, jossa on määritetty mittauksen suurimmat epävarmuuskomponentit, niiden suuruus ja vaikutus kokonaisepävarmuuteen sekä yhdistetty laajennettu epävarmuus. Vajaatäytteisen putken testimittauksissa tutkittiin ultraäänisignaalin käyttäytymistä vajaatäytteisessä putkessa ilman veden virtausta. <br/
Innovative approaches to collecting, aggregating, and analyzing adverse drug events in smart hospitals
No full textBackgroundThe increasing integration of electronic health records (EHRs) and their secondary use provide new pathways to advance drug safety. Smart hospitals use advanced data collection to enhance pharmacovigilance and better detect adverse drug events (ADEs). Finland's secondary-use legislation embodies this data-sharing shift.ObjectiveThis work synthesizes current evidence and proposes strategies to strengthen ADE detection and analysis in smart hospitals by integrating multimodal data sources, including EHRs, sensor data, and the Internet of Medical Things (IoMT), to raise overall drug safety standards.MethodsWe review the Global Trigger Tool (GTT), sensor technologies, and IoMT for ADE detection and outline how these techniques can be combined, offering a more comprehensive approach to monitoring.ResultsIntegrating GTT, sensors, and IoMT into a unified system could improve ADE detection and prevention. Combining pharmacovigilance tools with advanced technology can increase the volume and quality of ADE data and supports a preventive focus on patient safety.ConclusionsThe study underscores the importance of the smart-hospital concept and emerging data-collection methods in pharmacovigilance. By adopting a holistic approach to ADE detection and integrating diverse data sources, more robust drug-safety surveillance and patient care can be achieved when coupled with human oversight and regulatory compliance.</p
Machine learning based fault classification for improved induction motor performance
No full textThis study explores the design of an effective fault classification algorithm for 3 phase induction motor, an integral unit in many industrial systems. It is found that traditional fault detection methods and deep learning approaches are both effective; however, current techniques can either be computationally exhaustive, or suffer from low accuracy, thus making them inapplicable in many real-world settings. To address these limitations, this study evaluates different machine learning algorithms for accurate and efficient fault detection using a dataset of triaxial vibrational data converted into current variables. A dataset of triaxial vibrational current data at 0.7 mm bearing and rotor faults at various loads (100W, 200W, and 300W) were considered. For the data preprocessing, we handled with the missing values by interpolation and handle data imbalance fault types with Synthetic Minority Over-sampling Technique (SMOTE). Through Fast Fourier Transform (FFT) techniques, the frequency domain information were extracted, which is key for current signals, adding to the feature set. In addition, dimensionality reduction with Principal Component Analysis (PCA) and feature selection was done with SelectKBest. Then, the different machine learning models such as Random Forest (RF), Decision Tree (DT), k-nearest neighbors (KNN), and eXtreme Gradient Boosting (XGBoost) was trained to optimize the hyperparameters and make them perform to its best possible. The results shows the accuracy and performance of all models, DT and RF show good performance, with 99.95% accuracy, while KNN performs well, but at a higher computational cost in testing. Generally known for its capability to handle all the complex dataset, XGBoost wasn’t able to perform in this scenario as it got an accuracy of 87.13%, indicating potentially more optimization is required for the model. This work serves as the groundwork for future work with a multiplicity of fault types, motor specifications, and the incorporation of additional feature-engineering techniques to develop a more robust and intelligent framework for fault detection
Smarter Crowdsourcing With NLP and Attention Mechanisms for Task Complexity Prediction
No full textCompetitive Crowdsourcing Software Development (CCSD) has emerged as a powerful tool for developing software solutions, attracting researchers and the development market. Using crowdsourced collective intelligence, CCSD ensures the delivery of innovative, cost-effective, and high-quality solutions within specified time frames, making it an attractive approach for addressing complex challenges in software development. However, as the CCSD environment gains popularity, it also introduces challenges, particularly in predicting job complexity, which must be tackled to optimize the crowdsourcing process. In software platforms, client organizations register and upload jobs related to development projects. These jobs are manually reviewed by the copilots responsible for assessing the complexity of the job, a process that can lead to delays and an overburden of experts. To streamline this process, we propose an approach that automatically predicts job complexity and classifies it accordingly. We collect data from the TopCoder CCSD platform, focusing on projects related to software development. The collected data are pre-processed and tokenized using NLP techniques. We convert the text data into a word embedding vector matrix using a pre-trained GloVe model, which captures the semantic and contextual meaning of the text. The Sequence Attention (SA) mechanism is introduced in LSTM to identify the key parts of the input sequence that are most relevant for predicting the output, thereby improving job complexity classification. The proposed approach is then trained on these word embeddings using SA-LSTM and benchmarked against LSTM and other state-of-the-art techniques. The proposed approach, GloVe- based (GB) SA-LSTM, outperforms other approaches by achieving an accuracy improvement of 31.4%, 152.04%, 20.07%, 10.99%, 9.16%, and 17.64% over ZeroR, RP, LR, BERT, SVM, and DT. To verify the impact of SA, the proposed approach is compared with GB-LSTM. The GB- SA- LSTM outperforms GB-LSTM by 4.88%. This enhanced accuracy in task complexity prediction within software crowdsourcing platforms can significantly contribute to the efficient and effective development of crowdsourced projects.</p
External and Internal Barriers to Urban Circular Economy Transition in an Early Phase:The Case of Critical Raw Materials
Get PDFThis article contributes to expanding the literature on and understanding about urban circular economy (CE) transitions towards circular cities, with a particular focus on the circularity of critical raw materials (CRMs), by identifying barriers in the transition’s exploration phase. We collected our empirical research data from 7 Finnish cities by interviewing 14 administrative officers responsible for procurement and for CE development and strategies. According to our findings, financial, institutional, policy and regulatory, technical, knowledge, and social factors are both internal and external barriers that city governments face in preventing urban CE transition of CRMs. Our findings suggest that an overarching problem with the identified barriers is regarding knowledge. Furthermore, we argue that intervening in local transformation paths towards circular cities requires the understanding and development of multilevel interactions between actors and their possibly conflicting interests. This contributes to the current understanding of early phases of urban CE transitions, that is, how knowledge deficits between multilevel systemic urban CE transitions should be addressed.</p
Ceramide and phosphatidylcholine lipids-based risk score predicts major cardiovascular outcomes in patients with heart failure
No full textBackground: Ceramide and phosphatidylcholine lipids-based risk score (CERT2) has shown a strong prognostic value in predicting cardiovascular (CV) events in patients with ischemic heart disease. This study aimed to investigate the prognostic value of CERT2 risk score in patients with heart failure (HF). Methods: The current study combines data for 4234 subjects from the COMMANDER-HF trial and 1227 subjects from the GISSI-HF trial, which enrolled patients with a history of HF. The CERT2 risk score was calculated for all the participants as previously described. The primary outcome was CV death, but all-cause death and major adverse CV events (three-point MACE) were analysed as well. Results: After adjustment for established CV risk factors and potential confounders, patients with the highest CERT2 risk category remained at almost three-fold higher risk of CV death (COMMANDER-HF: HR 2.80, 95% CI 2.18–3.60, GISSI-HF: 2.84, 95% CI 1.70–4.74), all-cause death (COMMANDER-HF: HR 2.97, 95% CI 2.36–3.75, GISSI-HF: 2.83, 95% CI 1.83–4.38) and MACE (COMMANDER-HF: HR 2.73, 95% CI 2.20–3.38, GISSI-HF: 2.67, 95% CI 1.67–4.26) compared to those with the lowest CERT2 risk category. Conclusions: The CERT2 risk score is strongly associated with an increased risk of CV death, all-cause death and MACE in patients with HF.</p
Enhancement of Thermal, Mechanical, and Oxidative Properties of Polypropylene Composites with Exfoliated Hexagonal Boron Nitride Nanosheets
No full textThis study investigates the enhancement of polypropylene (PP) composites through the incorporation of exfoliated hexagonal boron nitride (h-BN) nanosheets. The preparation process involved exfoliating h-BN in a liquid phase using a high-pressure homogenizer, followed by the coating of PP pellets with the exfoliated nanosheets using an acoustic mixer. Melt extrusion was then employed to fabricate h-BN-reinforced PP composite films. Characterization techniques, including scanning electron microscopy, confirmed the uniform dispersion of exfoliated h-BN within the PP matrix, which is crucial for improving thermal conductivity, mechanical strength, and oxidative stability. Tensile testing demonstrated that exfoliated h-BN significantly enhanced the strength and toughness of homopolymer PP, while the improvements in impact copolymer PP were more modest. Thermal analysis revealed no significant change in the decomposition temperatures of PP but indicated improved oxidative stability with the incorporation of h-BN nanosheets. Notably, the oxidation resistance of PP was enhanced, as evidenced by reduced carbonyl index values in thermally aged samples. Overall, exfoliated h-BN nanosheets significantly improve the performance of PP composites, demonstrating their potential for diverse industrial applications that require superior thermal and mechanical properties, as well as enhanced oxidation resistance
Predicting rice yield and impact of climate change on rice production using machine learning models
Get PDFClimate change poses a critical threat to agricultural sustainability, with direct implications for the global food supply. Rice, a staple crop throughout Asia, is particularly vulnerable to variations in temperature and rainfall, making it essential to understand how it responds to changing climatic conditions. This study integrates historical climate records, rice yield data, and projections from Global Climate Models (GCMs; CMIP3) to assess the potential effects of climate change on rice production in Punjab, Pakistan. We employed multiple machine learning approaches, including Multiple Linear Regression (MLR), Boosted Tree Regression (BTR), Probabilistic Neural Network (PNN), Generalized Feed-Forward (GFF) Neural Network, Linear Regression (LR), and a Multilayer Perceptron (MLP) Artificial Neural Network. The models were trained and validated using observed climate and yield data from 1990 to 2020. Future yields were projected under three IPCC emission scenarios (SR-A2, SR-A1B, SR-B1) through the year 2050. Model evaluation showed that the Multilayer Perceptron (MLP) achieved the highest predictive performance ( = 0.791, R = 0.868, MAE = 0.215, MSE = 0.0869, NMSE = 0.3681), followed by Boosted Tree Regression (BTR; = 0.779, R = 0.845, MAE = 0.334, MSE = 0.1308). The Probabilistic Neural Network (PNN) and Generalized Feed-Forward (GFF) model also performed respectably ( = 0.745, R = 0.811, MAE = 0.176, MSE = 0.380 and = 0.643, R = 0.825, MAE = 0.398, MSE = 0.178, respectively). In contrast, Multiple Linear Regression (MLR) and Linear Regression (LR) performed poorly, with low values (0.535), underscoring their inability to capture the non-linear relationships between climate variables and yield. Our analysis identifies maximum temperature as the primary climatic driver of yield loss. Based on the projections, we estimate an average yield decline of 0.12% by 2050. This study demonstrates that non-linear machine learning models, particularly the MLP, are essential for reliable agricultural forecasting under climate change. The results highlight the growing vulnerability of rice production to rising temperatures and provide a robust evidence base for designing adaptation strategies, such as developing heat-tolerant rice varieties, to enhance food security in vulnerable regions
100 European Cities' Path to Climate Neutrality by 2030
Get PDFNetZeroCities programme supports 100 European cities on their path to climate neutrality by 2030, thus showing the way for the whole continent to become climate neutral by 2050. As of now, 92 cities have outlined actions and investments to achieve this goal but time is running out. The timely implementation of the required actions depends on further efforts related to funding, capability improvement, evaluation, stakeholder engagement and upscaling
Metabolites associated with abnormal glucose metabolism responding to primary care lifestyle intervention
No full textType 2 diabetes can be prevented by lifestyle intervention. We aimed to identify metabolites that associate with glucose metabolism and respond to lifestyle intervention with evidence-based targets for nutrition and physical activity in individuals at high risk of type 2 diabetes. Standard oral glucose tolerance test (OGTT) was used to categorize 624 participants into those having normal glucose tolerance (NGT), isolated impaired glucose tolerance (IGT), IGT with increased fasting glucose (IGT + IFG), and type 2 diabetes. Plasma LC-MS metabolomics was performed to reveal metabolic signatures. The baseline group differences were analysed with the Kruskal–Wallis test and the effect of intervention with a linear mixed-effects model. Significant differences in the metabolite signature were observed between the baseline groups, particularly in amino acids, acylcarnitines, and phospholipids. Fatty acid amides, phospholipids, amino acids, dimethylguanidinovaleric acid, and 5-aminovaleric acid betaine responded most to the lifestyle intervention. Lysophosphatidylcholines containing odd-chain fatty acids showed associations with improved glucose metabolism. Twenty-five metabolites differed between the baseline groups, responded to the intervention, and were associated with changes in glucose metabolism. The findings suggest a metabolite panel could be used in distinguishing individuals with varying degrees of glucose metabolism and in predicting response to lifestyle interventions.</p