Binary optimization
Dotaz
Zobrazit nápovědu
Infertility has emerged as a significant public health concern, with assisted reproductive technology (ART) is a last-resort treatment option. However, ART's efficacy is limited by significant financial cost and physical discomfort. The aim of this study is to build Machine learning (ML) decision-support models to predict the optimal range of embryo numbers to transfer, using data from infertile couples identified through literature reviews. Binary classification models were developed to classify cases into two groups: those transferring two or fewer embryos and those transferring three or four. Four popular ML algorithms were used, including random forest (RF), logistic regression (LR), support vector machine (SVM), and artificial neural network (ANN), considering seven criteria: the woman's age, sperm origin, the developmental qualities of four potential embryos, infertility duration, assessment of the woman, morphological qualities of the four best embryos on the day of transfer, and number of oocytes extracted. The stratified 3-fold cross-validation results show that the SVM model obtained the highest average accuracy (95.83%) and demonstrated the best overall performance, closely followed by the ANN and LR models with an average accuracy equal to 91.67%. The RF model achieved a slightly lower average accuracy (88.89%), which demonstrated the lowest variability. Testing on a new dataset revealed all models performed well, with ANN and SVM models classified all test set instances correctly, while the RF and LR models achieved 91.68% accuracy. These results highlight the superior generalization and effectiveness of the ANN and SVM models in guiding ART decisions.
- Klíčová slova
- Artificial neural network, assisted reproductive technology, embryo transfer, infertility, multi-criteria decision aiding, number of embryos,
- MeSH
- asistovaná reprodukce * MeSH
- dospělí MeSH
- infertilita * terapie MeSH
- lidé MeSH
- neuronové sítě MeSH
- přenos embrya * MeSH
- strojové učení * MeSH
- support vector machine MeSH
- těhotenství MeSH
- Check Tag
- dospělí MeSH
- lidé MeSH
- mužské pohlaví MeSH
- těhotenství MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
The generation of a large amount of ground truth data is an essential bottleneck for the application of deep learning-based approaches to plant image analysis. In particular, the generation of accurately labeled images of various plant types at different developmental stages from multiple renderings is a laborious task that substantially extends the time required for AI model development and adaptation to new data. Here, generative adversarial networks (GANs) can potentially offer a solution by enabling widely automated synthesis of realistic images of plant and background structures. In this study, we present a two-stage GAN-based approach to generation of pairs of RGB and binary-segmented images of greenhouse-grown plant shoots. In the first stage, FastGAN is applied to augment original RGB images of greenhouse-grown plants using intensity and texture transformations. The augmented data were then employed as additional test sets for a Pix2Pix model trained on a limited set of 2D RGB images and their corresponding binary ground truth segmentation. This two-step approach was evaluated on unseen images of different greenhouse-grown plants. Our experimental results show that the accuracy of GAN predicted binary segmentation ranges between 0.88 and 0.95 in terms of the Dice coefficient. Among several loss functions tested, Sigmoid Loss enables the most efficient model convergence during the training achieving the highest average Dice Coefficient scores of 0.94 and 0.95 for Arabidopsis and maize images. This underscores the advantages of employing tailored loss functions for the optimization of model performance.
- Klíčová slova
- Deep learning, Generative adversarial network (GAN), Ground truth data generation, High-throughput greenhouse imaging, Image segmentation, Plant phenotyping,
- Publikační typ
- časopisecké články MeSH
Accurate modeling of drug-polymer solubility is essential for the rational design of amorphous solid dispersions and other advanced pharmaceutical formulations. The perturbed-chain statistical associating fluid theory (PC-SAFT) equation of state has emerged as a robust framework for capturing complex thermodynamic interactions in such systems. However, its predictive accuracy is often constrained by the limited availability of validated pure-component parameters and the frequent need to optimize the binary interaction parameter (kij) to match experimental data. In this study, we present a novel application of PC-SAFT as a data-driven extrapolation tool in which model parameters are directly regressed to experimental solubility data for specific drug-polymer pairs. This approach repositions PC-SAFT from a purely predictive model to a pragmatic extrapolative framework, enabling solubility estimation without reliance on pretabulated parameters or speculative kij adjustments. In a separate analysis, we further demonstrate that using arbitrary pure-component parameter values─when coupled with kij optimization─can achieve predictive performance comparable to that of literature-derived parameters. This finding underscores the dominant role of the binary interaction parameter and suggests that detailed pure-component calibration may not be essential for capturing the solubility behavior. Case studies confirm that both strategies reliably reproduce experimental trends and offer practical paths for bridging data gaps in the thermodynamic modeling of drug-polymer systems.
- Klíčová slova
- PC-SAFT, amorphous solid dispersion, drug solubility, phase diagram, poly(2-oxazoline),
- Publikační typ
- časopisecké články MeSH
The study investigated and analyzed the contamination of the fabric surface due to cotton waste yarn woven into the weft. The impact of cotton waste proportion and cleaning methods on open-end rotor yarn quality, using blends from 100 to 0% cotton waste mixed with virgin cotton fibers were investigated. The study proves that cotton waste can be effectively incorporated into yarn production without significantly compromising fabric properties, supporting the sustainable use of recycled fibers. The innovative cleaning channel W increases fiber yield but also raises contamination levels, leading to a higher number of detected impurities on the fabric surface. The classification method for dust and trash particles significantly affects the contamination evaluation, though contamination trends remain consistent. The classification of dust and trash particles by the maximal Ferret's diameter is preferred based on the obtained outputs from the realized experiment. Additionally, while the size of dust particles decreases as the cotton waste proportion decreases, trash particle size is unaffected by the cleaning channel or waste ratio in the weft yarn. In the case of the binary portion, contaminant levels decrease as cotton waste content in weft yarns is reduced, with the lowest found in cleaning channel A, followed by C and W. Surprisingly, dust and trash particles contribute to the binary portion equally. It leads to the recommendation connected with optimizing fabric quality, the final treatment should focus mainly on eliminating the visual impact of larger contaminants. The reason is that smaller particles can be mostly removed during pretreatment because they are not firmly fixed in a woven structure. The results also highlight the link between fabric contamination and potential health risks from respirable dust particles in the workplace, underscoring the need for effective control during processing to protect workers and ensure stable production not only in weaving but also in the following processes.
- Klíčová slova
- Contamination of fabrics by seed coat fragments, Cotton waste, Image analysis, Open-end rotor cotton spun yarn, Trash and dust, Trash count and dust count,
- Publikační typ
- časopisecké články MeSH
The development of highly efficient photoanodes is crucial for enhancing the energy conversion efficiency in photoelectrochemical water splitting. Herein, we report an innovative approach to fabricating an Au/BiVO4/WO3 ternary junction that leverages the unique benefits of WO3 for efficient electron transport, BiVO4 for broadband light absorption, and Au nanoparticles (NPs) for surface plasmon effects. The BiVO4/WO3 binary junction was constructed by depositing a BiVO4 layer onto the surface of the WO3 nanobricks via consecutive drop casting. Au NPs were subsequently integrated into the BiVO4/WO3 structure through electrochromic activation of WO3. The optimal BiVO4 loading for the highest-performing BiVO4/WO3 heterostructure and the light intensity dependence of the photocurrent efficiency were also determined. Flat-band potential measurements confirmed an appropriate band alignment that facilitates electron transfer from BiVO4 to WO3, while work function measurements corroborated the formation of a Schottky barrier between the incorporated Au NPs and BiVO4/WO3, improving charge separation. The best-performing Au NP-sensitized BiVO4/WO3 photoanode thin films exhibited a photocurrent density of 0.578 mA cm-2 at 1.23 V vs RHE under AM 1.5G (1 sun) illumination and a maximum applied-bias photoconversion efficiency of 0.036% at 1.09 V vs RHE, representing an enhancement factor of 12 and 2.3 compared to those of pristine BiVO4 and WO3 photoanodes, respectively. This study presents a promising and scalable route for fabricating noble metal-sensitized, metal oxide-based nanocomposite photoanodes for solar water splitting.
- Publikační typ
- časopisecké články MeSH
The exponential deployment of electric vehicles (EVs) in the residential sectors in recent years allows better energy utilization in the decentralized and centralized levels of distribution systems due to their bidirectional operation and energy storage capabilities. However, to execute these, it is necessary to adopt residential demand side management (RDSM) to schedule energy utilization effectively to fetch economical and efficient energy consumption and grid stability and reliability, particularly during peak load conditions. The paper aims to formulate a robust and efficient RDSM technique to provide an energy utilization scheduling considering various influential factors and critical roles of EVs in RDSM. A Binary Whale Optimization Algorithm (BWOA) approach is proposed as an efficient algorithm for EV's impact on the RDSM for better energy scheduling. A single-objective formulation is presented with detailed modelling considering economic energy utilization as the primary objective with all possible equality and inequality system operational constraints. Secondly, the impact of EVs on the RDSM is studied from various perspectives in result analysis, considering EVs as load, storage devices, and different bidirectional modes of operation with other vehicles, residential components, and grids. In addition, the EVs role and the mutual influence with the integration of renewable energy sources (RES) and energy storage devices (ESDs) are extensively analyzed to provide better residential energy management (REM) in terms of economic, environmental, robust, and reliable points of view. The load priority based on consumer choice is also incorporated in the formulation. Extensive simulation is done for the proposed approach to show the effect of EVs on REM, and the results are impressive to show the EV's role as a load, as a storage device, and as a mutually supportive device to RES, ESD, and grid.
Nowadays, most of the newly developed active pharmaceutical ingredients (APIs) consist of cohesive particles with a mean particle size of <100μm, a wide particle size distribution (PSD) and a tendency to agglomerate, therefore they are difficult to handle in continuous manufacturing (CM) lines. The current paper focuses on the impact of various glidants on the bulk properties of difficult-to-handle APIs. Three challenging powders were included: two extremely cohesive APIs (acetaminophen micronized (APAPμ) and metoprolol tartrate (MPT)) which previously have shown processing issues during different stages of the continuous direct compression (CDC)-line and a spray dried placebo (SD) powder containing hydroxypropylmethyl cellulose (HPMC), known for its sub-optimal flow with a high specific surface area (SSA) and low density. Four flow-enhancing excipients were used: a hydrophilic (Aerosil® 200) and hydrophobic (Aerosil® R972) fumed silica grade, a mesoporous silica grade (Syloid® 244FP), and a calcium phosphate excipient (TRI-CAFOS® 200-7). The APIs and binary API/glidant blends (varied between 0.5-2.75 w/w%) were characterized for their bulk properties relevant for CDC. The results indicated that optimizing different bulk parameters (e.g., density, flow, compressibility..) of an API required varying weight percentages of the glidant (e.g., different surface area coverage (SAC)) depending on the APIs. Moreover, even at similar SAC, the impact of the glidant on the bulk characteristic of the APIs depended on the glidant type properties. While nano-sized silicon dioxide were effective for improving the flowability of a powder, other glidants (mesoporous silica and tricalcium phosphate (TCP)) showed also promise as alternatives. Additionally, an excess of glidant, referred to as oversilication, negatively impacted some bulk parameters, but other characteristics were unaffected. Finally, to determine the appropriate concentration of the different classes of glidants, SAC calculations, an understanding of the glidant's working mechanism, and knowledge about the API's characteristics (i.e., morphology, compressibility, flowability, aeration, density, and wall friction) are required. This study confirmed the necessity of including various material characterization techniques to assess the impact of glidants on the bulk characteristics of APIs.
- Klíčová slova
- Continuous manufacturing, Flow enhancers, Glidant, Material characterization, Rheological properties,
- MeSH
- deriváty hypromelózy chemie MeSH
- fosforečnany vápenaté chemie MeSH
- metoprolol * chemie MeSH
- nerozplněné léky MeSH
- oxid křemičitý chemie MeSH
- paracetamol * chemie MeSH
- pomocné látky * chemie MeSH
- prášky, zásypy, pudry chemie MeSH
- příprava léků metody MeSH
- reologie MeSH
- velikost částic MeSH
- Publikační typ
- časopisecké články MeSH
- Názvy látek
- deriváty hypromelózy MeSH
- fosforečnany vápenaté MeSH
- metoprolol * MeSH
- nerozplněné léky MeSH
- oxid křemičitý MeSH
- paracetamol * MeSH
- pomocné látky * MeSH
- prášky, zásypy, pudry MeSH
INTRODUCTION: Precise localization of the epileptogenic zone is critical for successful epilepsy surgery. However, imbalanced datasets in terms of epileptic vs. normal electrode contacts and a lack of standardized evaluation guidelines hinder the consistent evaluation of automatic machine learning localization models. METHODS: This study addresses these challenges by analyzing class imbalance in clinical datasets and evaluating common assessment metrics. Data from 139 drug-resistant epilepsy patients across two Institutions were analyzed. Metric behaviors were examined using clinical and simulated data. RESULTS: Complementary use of Area Under the Receiver Operating Characteristic (AUROC) and Area Under the Precision-Recall Curve (AUPRC) provides an optimal evaluation approach. This must be paired with an analysis of class imbalance and its impact due to significant variations found in clinical datasets. CONCLUSIONS: The proposed framework offers a comprehensive and reliable method for evaluating machine learning models in epileptogenic zone localization, improving their precision and clinical relevance. SIGNIFICANCE: Adopting this framework will improve the comparability and multicenter testing of machine learning models in epileptogenic zone localization, enhancing their reliability and ultimately leading to better surgical outcomes for epilepsy patients.
- Klíčová slova
- Binary classification, Class imbalance, Epilepsy, Epileptogenic tissue localization, Epileptogenic zone, Evaluation metrics, Intracranial electroencephalography, Machine learning, Seizure onset zone,
- MeSH
- dospělí MeSH
- elektrokortikografie metody normy MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- refrakterní epilepsie * chirurgie patofyziologie MeSH
- strojové učení * MeSH
- Check Tag
- dospělí MeSH
- lidé středního věku MeSH
- lidé MeSH
- mladiství MeSH
- mladý dospělý MeSH
- mužské pohlaví MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
BACKGROUND: Antineutrophil cytoplasmic antibody (ANCA)-associated vasculitis is a heterogenous autoimmune disease. While traditionally stratified into two conditions, granulomatosis with polyangiitis (GPA) and microscopic polyangiitis (MPA), the subclassification of ANCA-associated vasculitis is subject to continued debate. Here we aim to identify phenotypically distinct subgroups and develop a data-driven subclassification of ANCA-associated vasculitis, using a large real-world dataset. METHODS: In the collaborative data reuse project FAIRVASC (Findable, Accessible, Interoperable, Reusable, Vasculitis), registry records of patients with ANCA-associated vasculitis were retrieved from six European vasculitis registries: the Czech Registry of ANCA-associated vasculitis (Czech Republic), the French Vasculitis Study Group Registry (FVSG; France), the Joint Vasculitis Registry in German-speaking Countries (GeVas; Germany), the Polish Vasculitis Registry (POLVAS; Poland), the Irish Rare Kidney Disease Registry (RKD; Ireland), and the Skåne Vasculitis Cohort (Sweden). We performed model-based clustering of 17 mixed-type clinical variables using a parsimonious mixture of two latent Gaussian variable models. Clinical validation of the optimal cluster solution was made through summary statistics of the clusters' demography, phenotypic and serological characteristics, and outcome. The predictive value of models featuring the cluster affiliations were compared with classifications based on clinical diagnosis and ANCA specificity. People with lived experience were involved throughout the FAIRVASVC project. FINDINGS: A total of 3868 patients diagnosed with ANCA-associated vasculitis between Nov 1, 1966, and March 1, 2023, were included in the study across the six registries (Czech Registry n=371, FVSG n=1780, GeVas n=135, POLVAS n=792, RKD n=439, and Skåne Vasculitis Cohort n=351). There were 2434 (62·9%) patients with GPA and 1434 (37·1%) with MPA. Mean age at diagnosis was 57·2 years (SD 16·4); 2006 (51·9%) of 3867 patients were men and 1861 (48·1%) were women. We identified five clusters, with distinct phenotype, biochemical presentation, and disease outcome. Three clusters were characterised by kidney involvement: one severe kidney cluster (555 [14·3%] of 3868 patients) with high C-reactive protein (CRP) and serum creatinine concentrations, and variable ANCA specificity (SK cluster); one myeloperoxidase (MPO)-ANCA-positive kidney involvement cluster (782 [20·2%]) with limited extrarenal disease (MPO-K cluster); and one proteinase 3 (PR3)-ANCA-positive kidney involvement cluster (683 [17·7%]) with widespread extrarenal disease (PR3-K cluster). Two clusters were characterised by relative absence of kidney involvement: one was a predominantly PR3-ANCA-positive cluster (1202 [31·1%]) with inflammatory multisystem disease (IMS cluster), and one was a cluster (646 [16·7%]) with predominantly ear-nose-throat involvement and low CRP, with mainly younger patients (YR cluster). Compared with models fitted with clinical diagnosis or ANCA status, cluster-assigned models demonstrated improved predictive power with respect to both patient and kidney survival. INTERPRETATION: Our study reinforces the view that ANCA-associated vasculitis is not merely a binary construct. Data-driven subclassification of ANCA-associated vasculitis exhibits higher predictive value than current approaches for key outcomes. FUNDING: European Union's Horizon 2020 research and innovation programme under the European Joint Programme on Rare Diseases.
- MeSH
- ANCA-asociované vaskulitidy * klasifikace diagnóza epidemiologie krev imunologie MeSH
- dospělí MeSH
- kohortové studie MeSH
- lidé středního věku MeSH
- lidé MeSH
- mikroskopická polyangiitida klasifikace epidemiologie krev diagnóza imunologie MeSH
- registrace * statistika a číselné údaje MeSH
- senioři MeSH
- shluková analýza MeSH
- Check Tag
- dospělí MeSH
- lidé středního věku MeSH
- lidé MeSH
- mužské pohlaví MeSH
- senioři MeSH
- ženské pohlaví MeSH
- Publikační typ
- časopisecké články MeSH
- Geografické názvy
- Evropa epidemiologie MeSH
Early fault detection and diagnosis of grid-connected photovoltaic systems (GCPS) is imperative to improve their performance and reliability. Low-cost edge devices have emerged as innovative solutions for real-time monitoring, reducing latency, and improving response times. In this work, a lightweight Convolutional Neural Network (CNN) is designed and fine-tuned using Energy Valley Optimizer (EVO) for fault diagnosis. The CNN input consists of two-dimensional scalograms generated using Continuous Wavelet Transform (CWT). The proposed diagnosis technique demonstrated superior performance compared to benchmark architectures, namely MobileNet, NASNetMobile, and InceptionV3, achieving higher test accuracies and lower losses on binary and multi-fault classification tasks on balanced, unbalanced, and noisy datasets. Further, a quantitative comparison is conducted with similar recent studies. The obtained results indicate good performance and high reliability of the proposed fault diagnosis method.
- Klíčová slova
- Continuous wavelet transform, Convolutional neural networks, Faults diagnosis, Grid-connected PV systems,
- Publikační typ
- časopisecké články MeSH