Prediction Of Parameters Research Articles

Abstract PO3-27-01: Prediction of pathological complete response to neoadjuvant treatment in loco-regional advancedbreast cancer by using advanced PET/CT metabolic parameters

Abstract Prediction of pathological complete response to neoadjuvant treatment in loco-regional advanced breast cancer by using advanced PET/CT metabolic parameters. Abstract: Background: The standard treatment for locally advanced breast cancer (LABC) is neoadjuvant systemic therapy followed by surgery. The usefulness of FDG PET/CT for evaluating the treatment efficacy in breast cancer is well established; however, the role of quantitative functional PET/CT parameters, such as the metabolic tumor volume (MTV) and total lesion glycolysis (TLG), remains inconclusive. The aim of this study was to determine the correlation between quantitative functional parameters derived from PET/CT in LABC patients at staging and the response to neoadjuvant therapy. Methods: Seventy-eight consecutive patients (aged 25-82 y) with confirmed LABC (stages II-III) who underwent PET/CT as a part of their staging assessment and received neoadjuvant therapy followed by surgery were retrospectively included in this study. All patients underwent an FDG PET/CT at staging; and values of SUV max, SUV mean, MTV, and TLG were determined from the PET/CT studies. The patients were divided into two groups, based on the completeness of histopathologic response to neoadjuvant therapy, both in the primary tumor and axillary lymph nodes. Clinical, imaging and demographic data were collected from patient’s medical record. Results: A complete pathologic response (pCR) was achieved in 33/78 (42%) patients. Among patients with ER/PR positive, Her2-neu negative tumors, in 23/27 (85%) patients only partial pathologic response was reached; 91% of patients with ER/PR negative, Her2-neu positive and 43% of Triple-negative patients had complete pathological? response. For the primary breast tumor response, a higher SUV max, 10.7±5.34 for pCR vs. 7.24±4.62 for non-pCR group was measured, p-value=0.003; threshold value of 6.625. A higher SUV mean in the primary tumor resulted in a significantly higher rate of pCR, 5.95±2.36 vs 4,4±2.16, p=0.004, with a threshold value of 5.795. Neither MTV, not TLG were predictive parameters of the primary tumor response. For lymph nodes response, SUV max and SUV mean had no role in the prediction of pCR. Statistically significant difference however, was found between pCR and non-pCR in MTV values in the involved lymph nodes, with a median =2.13 cm³ [0-7.85] in pCR group vs 5.43 cm³ [3.11-15.3] in non-pCR, p=0.01 (threshold value 2.375) as well as in TLG measurements, with a median of 4.64 [0-19.8] vs. 12.7 [3.21-23.1], p=0.047, (25-75 IQR). Conclusion: Primary breast tumor SUV max/mean values have a significant correlation with the treatment response and threshold values were found. Low MTV and TLG measurements in lymph nodes may predict pCR. Neither MTV nor TLG had were found to have a significant role in the prediction of the primary tumor response. Citation Format: Maisun Shamya, Olga Kagna, Zohar Keidar, Tala Palchan-Hazan, Salem Billan, Roxolyana Abdah-Bortnyak. Prediction of pathological complete response to neoadjuvant treatment in loco-regional advancedbreast cancer by using advanced PET/CT metabolic parameters [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO3-27-01.

A novel local grey model considering fluctuation based on kernel function for energy production prediction

The structure of energy production is constantly evolving, particularly in a low-carbon context, to align with the development of various industries. To pursue the global goal of carbon neutrality, it is essential to strike a balance between traditional energy and clean energy. Thus, it is of great practical significance to forecast different energy production effectively. Firstly, this paper proposes a novel local grey forecasting model to predict different energy production. Energy production has fluctuated in the past few years due to government policies. Secondly, the novel local grey forecasting model focuses on each year’s production in the modeling process and uses a kernel function to measure the validity of the information. Meanwhile, different from other grey models, the dynamic model proposed makes it possible that there are no static parameters for the overall prediction. Then, the window width in the local model is determined using the particle swarm optimization algorithm. Furthermore, energy production prediction including traditional energy and clean energy production in total North America, Europe and Asia Pacific is conducted. Results show that the novel local grey model has satisfactory prediction accuracy compared with other models, whose MAPEs have controlled under 5% for different energy production. Finally, reasonable suggestions for energy production are proposed to meet various energy needs.

Evaluation of the Co–Go–Me angle as a predictor in Class II patients treated with Herbst appliance and skeletal anchorage: a retrospective cohort study

IntroductionA condylion–gonion–menton (Co–Go–Me) angle threshold of 125.5° has been introduced as a predictive parameter of cephalometric mandibular response in the orthopedic treatment of growing Class II patients with functional appliances, despite some contradictions in the literature. Considering the lack of studies evaluating the role of skeletal anchorage, this study aims to reassess the threshold of 125.5° in the Co–Go–Me angle as a useful predictor in growing skeletal Class II patients treated with acrylic splint Herbst appliance and two mini-screws in the lower arch (STM2).MethodsThirty-five consecutively treated patients (20 males, 15 females; mean age, 11.37 years) with mandibular retrusion were classified into two groups according to their Co–Go–Me baseline values (Group 1, <125.5°; Group 2, >125.5°). The STM2 protocol involved the use of the MTH Herbst appliance with an acrylic splint in the lower arch and two interradicular mini-screws as anchorage reinforcement. Cephalometric analysis was performed by the same operator for each patient at baseline (T0) and at the end of the Herbst phase (T1). The effects of time and group on the variables were assessed by a repeated-measures analysis of variance. The primary research outcome was the difference between the groups in terms of mandibular responsiveness to treatment referred to as the relative difference (T1−T0) in Co_Gn.ResultsThe mean duration of the treatment was 9.5 months. No statistically significant differences between groups were detected at baseline, except from the expected SN/GoMe° (p < 0.001) and Co–Go mm (p = 0.028). No statistically significant changes between groups, which were caused by the treatment, were found considering the mandibular sagittal and vertical skeletal parameters. Similarly, no statistically significant differences were found in the dental changes between the high-angle and low-angle patients, apart from the upper molar sagittal position (p = 0.013).Discussion and conclusionsThe 125.5° threshold in the Co–Go–Me value was not a reliable predictive parameter for the mandibular response in growing patients treated with the MTH Herbst appliance and lower skeletal anchorage. Due to its effective control in the sagittal and vertical planes, the STM2 technique might be an appropriate protocol to use in treating skeletal Class II patients, regardless of the growth pattern.

Research on Optimization of Intelligent Driving Vehicle Path Tracking Control Strategy Based on Backpropagation Neural Network

To enhance path tracking precision in intelligent vehicles, this study proposes a lateral–longitudinal control strategy optimized with a Backpropagation (BP) neural network. The strategy employs the BP neural network to dynamically adjust prediction and control time-domain parameters within an established Model Predictive Control (MPC) framework, effectively computing real-time front-wheel steering angles for lateral control. Simultaneously, it integrates an incremental Proportional–Integral–Derivative (PID) approach with a meticulously designed acceleration–deceleration strategy for accurate and stable longitudinal speed tracking. The strategy’s efficiency and superior performance are validated through a comprehensive CarSim(2020)/Simulink(2020b) simulation, demonstrating that the proposed controller adeptly modulates control parameters to adapt to various road adhesion coefficients and vehicle speeds. This adaptability significantly improves tracking and driving dynamics, thereby enhancing accuracy, safety, stability, and real-time responsiveness in the intelligent vehicle tracking control system.

A Path-Planning Method for UAV Swarm under Multiple Environmental Threats

To weaken or avoid the impact of dynamic threats such as wind and extreme weather on the real-time path of a UAV swarm, a path-planning method based on improved long short-term memory (LSTM) network prediction parameters was constructed. First, models were constructed for wind, static threats, and dynamic threats during the flight of the drone. Then, it was found that atmospheric parameters are typical time series data with spatial correlation. The LSTM network was optimized and used to process time series parameters to construct a network for predicting atmospheric parameters. The state of the drone was adjusted in real time based on the prediction results to mitigate the impact of wind or avoid the threat of extreme weather. Finally, a path optimization method based on an improved LSTM network was constructed. Through simulation, it can be seen that compared to the path that does not consider atmospheric effects, the optimized path has significantly improved flightability and safety.

An adaptive distribution-matched recurrent network for wind power prediction using time-series distribution period division

Precise wind power prediction (WPP) can address the issue caused by large-scale wind power grid integration to the power system operation. Most WPP research focus on the randomness and high volatility problem of wind power but ignore the time-series distribution shift (TSDS) problem. To solve the TSDS issue, this study proposes a novel hybrid model that incorporates complementary ensemble empirical mode decomposition (CEEMD), time-series distribution period division (TSDPD) and adaptive distribution-matched GRU (ADMGRU). First, CEEMD is utilized to decompose the nonstationary data into in sub-sequence, reducing complexity and randomness. Second, TSDPD is employed to automatically identify the underlying temporal segments within wind power sequence by maximizing discrepancies in distribution information between two periods, determining the quantity and respective boundaries of periods. Finally, ADMGRU, comprising Pre-train and Boosting-based importance assessment components, learns prediction model accurately by dynamically matching distribution periods. The former component initializes predictive model parameters and the latter learns the importance of each hidden state to assigns corresponding weights to different distributions. Numerous comparative experiments demonstrate the CEEMD-TSDPD-ADMGRU hybrid model surpasses existing popular models. Especially in spring scenario, compared with other four advanced models, the maximum reduction in MAE and RMSE are 54.64 % and 73.33 %, respectively.

Simplified models of wind-wave relationships in China's shallow-water coasts based on SWAN+ADCIRC simulations

The study of the shallow-water wind-wave relationship holds considerable importance in the realm of coastal engineering construction. However, existing empirical formulas for China's coastal areas face predictive accuracy challenges due to the discontinuity and insufficient temporal and spatial resolution of conventional observations, such as buoy and satellite data. Therefore, this study emphasizes two representative shallow-water areas along China's coast, the Pearl River Estuary and Bohai Bay. Based on the advanced SWAN + ADCIRC wave-current coupling model, numerical models for calculating wave evolution are established, calibrated and validated by real observation data. From these numerical foundations, a new model capturing shallow-water wind-wave relationship is proposed, demonstrating substantive applicability specifically tailored to the estuary and bay regions. The accuracy and applicability of the model are validated by comparing with real observation data. In addition, probabilistic models are introduced in this study accounting for the randomness of the significant wave height. These enhancements allow for refined quantification of significant wave height occurrence probabilities relative to specified wind speeds, offering informed predictive parameters, including upper and lower limits.

PD-L1 expression in tumor and inflammatory cells is associated with favorable tumor features and favorable prognosis in muscle-invasive urothelial carcinoma of the bladder not treated by immune checkpoint inhibitors

BackgroundA high level of PD-L1 expression is the most relevant predictive parameter for response to immune checkpoint inhibitor (CPI) therapy in urinary bladder cancer. Existing data on the relationship between PD-L1 expression and the natural course of disease are controversial and sparse.MethodsTo expand our understanding of the relationship between PD-L1 expression and parameters of cancer aggressiveness, PD-L1 was analyzed on tissue microarrays containing 2710 urothelial bladder carcinomas including 512 patients with follow-up data who underwent radical cystectomy and follow-up therapies in the pre-immune checkpoint inhibitor therapy era.ResultsTumor cell positivity in ≥10% of cells were seen in 513 (20%) and an immune cell positivity occurred in 872 (34%) of 2566 interpretable cancers. PD-L1 positivity in tumor cells increased from pTaG2 low grade (0.9% positive) to pTaG3 high grade (4.1%; p = 0.0255) and was even higher in muscle-invasive (pT2–4) carcinomas (29.3%; p < 0.0001). However, within pT2–4 carcinomas, PD-L1 positivity was linked to low pT stage (p = 0.0028), pN0 (p < 0.0001), L0 status (p = 0.0005), and a better prognosis within 512 patients with cystectomy who never received CPIs (p = 0.0073 for tumor cells and p = 0.0086 for inflammatory cells). PD-L1 staining in inflammatory cells was significantly linked to PD-L1 staining in tumor cells (p < 0.0001) and both were linked to a positive p53 immunostaining (p < 0.0001).ConclusionIt cannot be fully excluded that the strong statistical link between PD-L1 status and favorable histological tumor features as well as better prognosis could influence the outcome of studies evaluating CPIs in muscle-invasive urothelial carcinoma.

Assessing the influence of aneurysm dimensions on hemodynamic patterns and wall deformation dynamics for predicting rupture risk

Cerebral aneurysms are among the most dangerous cardiovascular diseases which display no symptoms prior to reaching critical conditions. As cerebral aneurysms are deadly diseases with a very small treatment window after reaching the critical stage, numerical investigations of this phenomenon are commonly used to assess the risk of rupture. In this study, the fluid-structure interaction (FSI) method is used to analyze the effects of aneurysm size on hemodynamic factors predicting rupture in three aneurysms of different geometries, at the same location, and using the same boundary conditions. In the present study, the aneurysms experience TAWSS at values under 2 Pa in incremented areas as the aneurysmal sizes increase, this is while the relatively larger distribution of high TAWSS (as high as 20 Pa) regions are perceived in smaller aneurysms. Furthermore, the maximum OSI stands at below 0.05 in the smaller cases while the larger case experiences a maximum OSI as high as 0.2, which is considered a predictive parameter for rupture. The vortex core lines experience discontinuities with increased aneurysmal size, which is in agreement with the development of flow complexities with size. The hemodynamics factors such as the time-averaged wall shear stress (TAWSS), oscillatory shear index (OSI), and vortex core line investigated in this study, suggest that greater size can be considered a major risk factor for rupture. In addition to that, we have found that the displacement trend of the aneurysm changes as size increases; developing more in the dome rather than the aneurysmal sac. This change in trend might also present a potential to be used as a predictive parameter.

0559 Predictive Parameters of Veterans with False Negative Home Sleep Apnea Test in Diagnosis of Obstructive Sleep Apnea

0559 Predictive Parameters of Veterans with False Negative Home Sleep Apnea Test in Diagnosis of Obstructive Sleep Apnea

Image-Based Approach Applied to Load Torque Estimation in Three-Phase Induction Motors.

This paper presents a novel method for load torque estimation in three-phase induction motors using air gap flux measurement and the conversion of this type of time-domain signal into grayscale images for further processing as inputs for an inception-type convolutional neural network. The magnetic flux was measured employing a Hall effect sensor installed inside the machine, near the stator slots, and above the stator windings. In this case, the sensor was able to measure a resultant magnetic flux density, having both rotor and stator magnetic flux contributions. The present methodology does not require motor parameters for torque prediction. The proposed approach successfully estimated load torque using three optimizers across almost the entire motor load operational range, spanning from 1.5% to 93.9% of the rated load. Four model configurations achieved a mean absolute percentage error (MAPE) less than or equal to 3.7%. Specifically, two models for a 40 × 50 pixel image achieved MAPE of 3.7% and 3%, one model for a 40 × 25 pixel image achieved a MAPE of 3.5%, and one model for a 50 × 80 pixel image achieved a MAPE of 3.3%. This research has been experimentally validated with a 7.5 kW squirrel cage induction machine.

Quantifying the impact of homophily and influencer networks on song popularity prediction.

Forecasting the popularity of new songs has become a standard practice in the music industry and provides a comparative advantage for those that do it well. Considerable efforts were put into machine learning prediction models for that purpose. It is known that in these models, relevant predictive parameters include intrinsic lyrical and acoustic characteristics, extrinsic factors (e.g., publisher influence and support), and the previous popularity of the artists. Much less attention was given to the social components of the spreading of song popularity. Recently, evidence for musical homophily-the tendency that people who are socially linked also share musical tastes-was reported. Here we determine how musical homophily can be used to predict song popularity. The study is based on an extensive dataset from the last.fm online music platform from which we can extract social links between listeners and their listening patterns. To quantify the importance of networks in the spreading of songs that eventually determines their popularity, we use musical homophily to design a predictive influence parameter and show that its inclusion in state-of-the-art machine learning models enhances predictions of song popularity. The influence parameter improves the prediction precision (TP/(TP FP)) by about 50% from 0.14 to 0.21, indicating that the social component in the spreading of music plays at least as significant a role as the artist's popularity or the impact of the genre.

Age and Stroke Severity Matter Most for Clinical Outcome in Acute Arteriosclerotic Tandem Lesions.

Background: Tandem lesions (TLs) cause up to 15-30% of all acute ischemic strokes (AISs). Endovascular treatment (EVT) is regarded as the first-line treatment; however, uncertainties remain with respect to the treatment and predictive outcome parameters. Here, we aimed to identify the clinical and demographic factors associated with functional short- and long-term outcomes in AIS patients with arteriosclerotic TLs undergoing EVT. Methods: This was a retrospective, mono-centric cohort study of 116 consecutive AIS patients with arteriosclerotic TLs who were endovascularly treated at a stroke center, with analysis of the relevant demographic, procedural, and imaging data. Results: A total of 116 patients were included in this study, with a median age of 72 years (IQR 63-80), 31% of whom were female (n = 36). The median NIHSS on admission was 14 (IQR 7-19), with a median ASPECT score of 9 (IQR 8-10) and median NASCET score of 99% (IQR 88-100%). A total of 52% of the patients received intravenous thrombolysis. In 77% (n = 89) of the patients, an antegrade EVT approach was used, with a good recanalization (mTICI2b3) achieved in 83% of patients (n = 96). Symptomatic intracerebral hemorrhage occurred in 12.7% (n = 15) of patients. A favorable outcome (mRS0-2) and mortality at 3 months were obtained for 40% (n = 47) and 28% of patients (n = 32), respectively. Age and NIHSS on admission were strongly associated with outcome parameters. Diabetes mellitus and previous neurological disorders were independently associated with long-term mortality (median 11 months, IQR 0-42). Conclusions: Younger age, lower stroke severity, and good recanalization were found to be independently associated with a favorable outcome. In contrast, older age, higher stroke severity, previous neurological disorders, and diabetes were correlated with mortality. The endovascular treatment of acute arteriosclerotic tandem lesions is feasible and relatively safe.

Bond strength between recycled aggregate concrete and rebar: Interpretable machine learning modeling approach for performance estimation and engineering design

Recycled aggregate concrete has a large potential for application as a sustainable building material. To assist in guiding the engineering design of this low-carbon material, the complex relationship between its bond strength to the rebar and various design parameters was modeled. Comparative studies of multiple machine learning methods have shown that the extreme random tree model demonstrates outstanding performance with root mean square error of 1.982, mean absolute error of 1.202 and coefficient of determination of 0.954. To determine the role of design parameters in performance prediction, importance analysis and sensitivity analyses for parameters were used to explore the complex relationship in the model. The results indicated that rebar type, water-cement ratio, anchorage length, and compressive strength are crucial factors affecting the bond strength between recycled aggregate concrete and rebar. In addition, to further demonstrate the reliability and accuracy of machine learning models, explicit models in some specifications were used for comparative analysis. Due to variability in influencing factors, limited test data, and variability in material properties, the explicit models have limited accuracy for bond strength between recycled aggregate concrete and rebar. Therefore, the interpretable modeling approach can provide an accurate estimate of the bond strength between recycled concrete aggregates and rebar and guide the engineering design of this structure.

Utility of clinical and MR imaging parameters for prediction and monitoring of response to capecitabine and temozolomide (CAPTEM) therapy in patients with liver metastases of neuroendocrine tumors.

This study explores the predictive and monitoring capabilities of clinical and multiparametric MR parameters in assessing capecitabine and temozolomide (CAPTEM) therapy response in patients with neuroendocrine tumors (NET). This retrospective study (n = 44) assessed CAPTEM therapy response in neuroendocrine liver metastases (NELM) patients. Among 33 monitored patients, as a subgroup of the overall study cohort, pretherapeutic and follow-up MRI data (size, apparent diffusion coefficient [ADC] values, and signal intensities), along with clinical parameters (chromogranin A [CgA] and Ki-67%), were analyzed. Progression-free survival (PFS) served as the reference. Responders were defined as those with PFS ≥ 6 months. Most patients were male (75%) and had G2 tumors (76%) with a pancreatic origin (84%). Median PFS was 5.7 months; Overall Survival (OS) was 25 months. Non-responders (NR) had higher Ki-67 in primary tumors (16.5 vs. 10%, p = 0.01) and increased hepatic burden (20% vs. 5%, p = 0.007). NR showed elevated CgA post-treatment, while responders (R) exhibited a mild decrease. ADC changes differed significantly between groups, with NR having decreased ADCmin (-23%) and liver-adjusted ADCmean/ADCmean liver (-16%), compared to R's increases of ADCmin (50%) and ADCmean/ADCmean liver (30%). Receiver operating characteristic (ROC) analysis identified the highest area under the curve (AUC) (0.76) for a single parameter for ∆ ADC mean/liver ADCmean, with a cut-off of < 6.9 (76% sensitivity, 75% specificity). Combining ∆ Size NELM and ∆ ADCmin achieved the best balance (88% sensitivity, 60% specificity) outperforming ∆ Size NELM alone (69% sensitivity, 65% specificity). Kaplan-Meier analysis indicated significantly longer PFS for ∆ ADCmean/ADCmean liver < 6.9 (p = 0.024) and ∆ Size NELM > 0% + ∆ ADCmin < -2.9% (p = 0.021). Survival analysis emphasizes the need for adapted response criteria, involving combined evaluation of CgA, ADC values, and tumor size for monitoring CAPTEM response in hepatic metastasized NETs.

Interobserver variability in preclinical assessment of collision variables following traffic accidents.

Traffic accidents persist as a leading cause of death. European law mandates the integration of automatic emergency call systems (eCall). Our project focuses on an automated injury prediction device for car accidents, correlating technical and epidemiological input data, such as age, gender, seating position, impact on the passenger compartment, seatbelt usage, impact direction, EES, vehicle class, and airbag deployment. This study aims to explore interobserver variability in data collection quality in real accident scenarios. The assessment will evaluate the impact of user training and measure the time needed for data collection to inform user recommendations for the prehospital assessment. Insights from this study can aid in evaluating the ability of different professional groups to identify potential accident-independent parameters at accident scenes. This includes, among other things, relaying information to dispatchers at rescue control centers, also within the context of telemedicine approaches. During group sessions, real accident scenarios were presented both before and after a training presentation. Participants, including laypersons, accident research staff, emergency services, hospital physicians, and emergency physicians, visually assessed injury prediction parameters within a time limit. Training involved defining and explaining parameters using accident images. The study analyzed participant demographics, prediction accuracy, and time required, comparing assessment quality between professional groups and before and after training. In summary, the study demonstrates that training had a significantly positive impact on the quality of assessment for technical accident parameters. The processing time decreased significantly after training. A notable training effect was observed, particularly for the parameters of rigid collision object, affected passenger compartment, energy equivalent speed (EES), and front and side airbags. It was recommended that individuals without prior knowledge should receive training on assessing EES. Overall, it was evident that technical parameters following a traffic accident can be well assessed through training, irrespective of the professional group. Significant differences in the assessment quality of technical accident parameters were observed based on technical and medical expertise. After user training, interdisciplinary differences were reconciled, and all professional groups yielded comparable results, indicating that training can enhance the assessment abilities of all participants in the rescue chain, while the time required for assessing accident parameters was significantly reduced with training.

An Analytical Method for Timely Predicting of Coal Seam Pressure during Gas Production for Undersaturated Coalbed Methane Reservoirs

Coal seam pressure is an important parameter for production performance evaluation and prediction of coalbed methane (CBM). CBM production from undersaturated CBM reservoirs can be divided into two stages according to critical desorption pressure. At present, few prediction models of coal seam pressure performance consider the comprehensive influence of critical desorption pressure, dissolved gas, matrix shrinkage, and stress sensitivity. For the purpose of accurately predicting coal seam pressure during gas production for an undersaturated coalbed methane reservoir, the material balance principle is used to establish the analytical method for predicting coal seam pressure, considering the comprehensive influence of the critical desorption pressure, dissolved gas, matrix shrinkage, and stress sensitivity. Then, the proposed method is verified against a numerical simulation case using a computer modelling group (CMG) and two actual coalbed methane wells. Finally, the sensitivities of influencing factors on the coal seam pressure are analyzed. The results show that good agreements were obtained between the calculated coal seam pressures using the proposed method and those from the CMG-GEM simulation case and actual CBM wells, with the relative errors all being less than 1%. When ignoring the influence of critical desorption pressure and mistaking pd for pi as well as ignoring Cs, the relative error can reach as high as 31.3%. The main factors affecting the coal seam pressure are the critical desorption pressure and free gas saturation. The proposed method is simple to use, and without shutting-in the well, it can provide an important basis for production performance evaluation and development strategies.

Data-driven health state estimation and remaining useful life prediction of fuel cells

Proton exchange membrane fuel cells (PEMFCs) can revolutionise transportation energy and promote environmentally friendly development. The purpose of this study is to predict the state of health (SOH) of PEMFCs and provide guidance for fuel cell maintenance. Under changing power demand situations, a practical method based on the Fréchet distance is proposed to predict the SOH, along with an empirical model to differentiate between the running-in and degradation periods. The proposed method does not require complex and expensive testing instruments and has a relative error of approximately 4.3 %. A voltage drop prediction model is established for steady power demand situations using the particle swarm optimisation-extreme learning machine (PSO-ELM) algorithm. Different activation functions and hidden layer neurons are investigated to enhance prediction accuracy. This study shows that the model effectively tracks the decreasing trend in the transmission voltage of the PEMFC stack. Additionally, a comprehensive analysis framework is developed to address the issue of the possibility of missing system parameters in practical applications. The influence of the system parameters on voltage drop prediction is thoroughly analysed, and the necessary parameters for accurate prediction are defined, providing theoretical guidance for practical monitoring and data collection.

Evolutive Models, Algorithms and Predictive Parameters for the Progression of Hepatic Steatosis.

The utilization of evolutive models and algorithms for predicting the evolution of hepatic steatosis holds immense potential benefits. These computational approaches enable the analysis of complex datasets, capturing temporal dynamics and providing personalized prognostic insights. By optimizing intervention planning and identifying critical transition points, they promise to revolutionize our approach to understanding and managing hepatic steatosis progression, ultimately leading to enhanced patient care and outcomes in clinical settings. This paradigm shift towards a more dynamic, personalized, and comprehensive approach to hepatic steatosis progression signifies a significant advancement in healthcare. The application of evolutive models and algorithms allows for a nuanced characterization of disease trajectories, facilitating tailored interventions and optimizing clinical decision-making. Furthermore, these computational tools offer a framework for integrating diverse data sources, creating a more holistic understanding of hepatic steatosis progression. In summary, the potential benefits encompass the ability to analyze complex datasets, capture temporal dynamics, provide personalized prognostic insights, optimize intervention planning, identify critical transition points, and integrate diverse data sources. The application of evolutive models and algorithms has the potential to revolutionize our understanding and management of hepatic steatosis, ultimately leading to improved patient outcomes in clinical settings.

Variation coefficient of stone density and renal cortical thickness: the parameters evaluating non-contrast computed tomography imaging for predict extracorporeal shock wave lithotripsy success.

The stone density (SD) is not the same in all parts of the stone due to the heterogeneous nature of the stone and the shock wave (SW) passes through tissues of many different densities until it reaches the stone. These factors affect the success of Extracorporeal Shock Wave Lithotripsy (ESWL). We aimed to evaluate the effect of the Variation Coefficient of Stone Density (VCSD) and Renal Cortical Tickness (RCT) on the success of ESWL. Between 2020 and 2023, 510 patients who underwent ESWL were divided into 2 groups treatment success (n:304) and treatment failure (n:206). Non-Contrast Computed Tomography (NCCT) imaging values of hydronephrosis degree of the kidney, stone location, stone volume (SV), stone-skin distance (SSD), SD, Standard deviation of Stone Density (SDSD), VCSD, RCT, Soft-Tissue Thickness (STT), Muscle Thickness (MT) were analyzed. VCSD value was obtained by dividing SDSD by SD. Along the SW, tissues were divided into three components: kidney (renal cortex), muscle and other soft tissues. RCT, MT and SSD were measured at three different angles (0°, 45°, and 90°) and these 3 lengths were averaged. In univariate analysis, Body Mass Index (BMI), SV, SD, VCSD, SSD, RCT and STT were demonstrated to affect ESWL success. In multivariate analysis, low BMI, SV, SD, RCT and large VCSD were significant independent predictors of ESWL success. Among these parameters, VCSD had the highest prediction accuracy, followed by SD, SV, RCT and BMI, respectively. This study demonstrated that VCSD value and RCT are predictive parameters in determining the treatment of patients with urinary calculi and selecting suitable ESWL candidates.