Combination Model Research Articles

Synergism of colistin and globular endolysins against multidrug-resistant gram-negative bacteria

Endolysins (lysins), a novel class of antibacterial agents derived from bacteriophages, efficiently lyse bacteria by degrading the peptidoglycan layer within the bacterial wall. Colistin, a classic peptide antibiotic with the ability to permeabilize the outer membrane, has recently shown great promise in synergizing with lysins against gram-negative bacteria. However, the exact mechanisms responsible for their synergy remain unclear. Here, we first demonstrated the synergistic bacterial killing of various lysin and colistin combinations. With a model lysin, LysAB2, we then confirmed that there is a threshold concentration of colistin causing sufficient permeabilization of the outer membrane for lysin to access the peptidoglycan layer and subsequently exert its lytic ability. The threshold colistin concentrations were found to range 0.2−0.8 μM for the tested bacteria, with the exact value largely depending on the density of lipopolysaccharides on the outer membrane. Beyond the threshold colistin level, LysAB2 could synergize with colistin at a concentration as low as 0.31 μM. Next, we proved for the first time that lysin-induced degradation of the peptidoglycan layer facilitated the disruption of cytoplasmic membrane by colistin, elevated the level of reactive oxygen species in bacterial cells, and boosted the killing effect of colistin. Additionally, the colistin-lysin combination could effectively eliminate established biofilms due to the biofilm dispersal ability of lysin. The in-vivo efficacy was preliminary confirmed in a Galleria mellonella infection model for combination with colistin doses (≥ 1.8 μg/larvae), which could reach beyond the threshold concentration, and a fixed LysAB2 dose (10 μg/larvae). In summary, our study provided the first experimental evidence unravelling the mechanisms behind the synergy of colistin and lysins. All these findings provided important insights in guiding the dosing strategy for applying this combination in future development.

Hybrid model for sentiment analysis combination of PSO, genetic algorithm and voting classification

As social network services like Weibo and Twitter have grown in popularity, natural language processing (NLP) has seen a great deal of interest in sentiment analysis of social media messages and Information mining. Social media users, whose numbers are always increasing, have the ability to exchange information on their platforms. The study of sentiment, domains and themes are closely related. Manually collecting enough labelled data from the vast array of subjects covered by large-scale social media to train sentiment classifiers across several domains would be extremely difficult. The literature review conducted concludes that models already proposed in the previous researches are not able to achieve good accuracy. This work suggests a unique model that combines of genetic algorithm and particle swarm optimization to effectively extract the features and then the voting technique is applied for the classification. Model proposed is compared with 4 ensemble datasets achieving a consistent accuracy of more than 90% for three different diversified database owing to natural selection of sequences by GA and at the same time achieves a fast convergence with PSO, the model may be employed for highly accurate recommenders demanding precision and accuracy.

تصميم نظام أمثل باستخدام الفاصل التقريبي لبرمجة دي نوڨو متعددة الأهداف

تُعد برمجة دي نوڤو متعددة الأهداف، أداة فعالة تتعامل مع تصميم نظام أمثل، وذلك من خلال تحديد المستوى الأمثل لتخصيص الموارد، وتحسين قيمة دوال الهدف وفقاً لسعر الموارد (هذا فيما لو كانت الظروف طبيعية ولا يوجد تقلب في الاسعار). في هذه البحث اُقتِرحَ نهجاً جديداً لحل مشكلة عدم اليقين لمشكلة برمجة دي نوفو، وذلك باستخدام أنموذج مركب يتضمن نوعين من البرمجة: الأول هو برمجة متعددة الأهداف ذات الفاصل التقريبي (RIMOP)، والثاني: برمجة دي نوڤو(DNP)، علماً بأن معاملات متغيرات القرار لدالة الهدف والقيود عبارة عن فاصل تقريبي RIC. وقد استخدامنا ثلاث طرائق لحل الانموذج المقترح وإيجاد تصميم نظام أمثل، الطريقة الاولى هي طريقة المجموع الموزون WSM والتي تُستخدم قبل اعادة صياغة النموذج المقترح RIMOP (وكانت الموارد معروفة)، وقد وجد ان نتائج طريقة WSM تعطي حلاً واحداً (حل وسط قريب من المثالية) من بين الحلول المقبولة تحت كل حد من حدود المشكلة، وبالتالي يمكن تقديم أربع حلول (بدائل) لصانع القرار (DM). اما منهجية زيلني وطريقة نسب المسار الأمثل فقد استخدمت بعد صياغة الانموذج المقترح (RIMODNP) (وكانت الموارد للطرف الأيمن للقيود ليست معروفة). وجد ان منهجية زيلني تعطي تصميم نظام أمثل واحداً لكل حد من حدود المشكلة، في حين ان طريقة المسار الأمثل طبقت بعد ان تم التأكد من حدود النموذج المقترح وفقاً النظرية شاي فقد استخدمنا ثلاثة أنواع من النسب تحت كل مشكلة فرعية، فقد وجد ان هذهِ الطريقة تعطي ثلاث تصاميم انظمة مثلى تحت كل حد للمشكلة، وقد اتضح من خلال النتائج ان طريقة نسب المسار الامثل هي أكثر كفاءة من غيرها بعد تطبيقها على النموذج المقترح، لأنها اعطت اثنا عشر بديلاً لـ(DM)، لوحظ ان الانموذج المقترح يتوافق مع شروط ونظريات RIC. يُعد الانموذج المقترح مناسباً جداً لظروف عدم اليقين، اخيراً، طبق مثال رقمي على الانموذج المقترح.

Rational Design of PARP1/c-Met Dual Inhibitors for Overcoming PARP1 Inhibitor Resistance Induced by c-Met Overexpression.

The emergence of resistance to PARP1 inhibitors poses a current therapeutic challenge, necessitating the development of novel strategies to overcome this obstacle. The present study describes the design and synthesis of a series of small molecules that target both PARP1 and c-Met. Among them, compound 16 is identified as a highly potent dual inhibitor, exhibiting excellent inhibitory activities against PARP1 (IC50 = 3.3 nM) and c-Met (IC50 = 32.2 nM), as well as demonstrating good antiproliferative effects on HR-proficient cancer cell lines and those resistant to PARP1 inhibitors. Importantly, compound 16 demonstrates superior antitumor potency compared to the PARP1 inhibitor Olaparib and the c-Met inhibitor Crizotinib, either alone or in combination, in MDA-MB-231 and HCT116OR xenograft models. These findings highlight the potential of PARP1/c-Met dual inhibitors for expanding the indications of PARP1 inhibitors and overcoming tumor cells' resistance to them.

Short term power load forecasting system based on improved neural network deep learning model

AbstractThe electricity load prediction is closely related to production and daily life. The electricity load prediction is also a very important task. With the widespread application of smart grids, load data shows an exponential growth trend. The huge amount of data in the load makes power prediction even more difficult. On the basis of traditional prediction algorithms, a power load prediction model based on machine learning and neural networks is designed. Because the single model prediction has the unstable results, a combined model is obtained based on the ensemble learning idea and two single model prediction method. The prediction results are detected by the load data. From the experimental results, the mean absolute percentage error (MAPE) of the AdaBoost‐GRU data fusion model is 0.066%. Compared to the AdaBoost‐GRU data fusion model, the MAPE decreases by 1.59% and 1.12%, respectively. The relative mass scores of the two groups decrease by 132.57% and 89.14%, respectively. The prediction accuracy is improved, which has advantages compared to traditional combination models. It can effectively enhance the accuracy of short‐term power grid load forecasting. It is an important scientific and practical reference for power grid decision‐making.

Allocation of reservoirs sites for runoff management towards sustainable water resources: Case study of Harirud River Basin, Afghanistan

The intensification of drought conditions in arid and semi-arid regions coupled with the growing population increased water demands (domestic, and irrigation). It signifies the importance of addressing the pressing need for sustainable water resource management. Seventeen criteria spanning topographical, hydrological, geological, environmental, and socio-economic categories, were used for dam site suitability analysis for Harirud River Basin, Afghanistan. Weighted Linear Combination (WLC) model and Geographic Information System (GIS) were employed to perform multi-criteria analysis (MCA) method. The results revealed that the final suitability map exposed 12.31 % highly suitable, 21.0 % moderately suitable, and 66.68 % non-suitable sites, totaling 125.8 km, 214.6 km, and 681.4 km, respectively. Segmentation accuracy assessment was utilized to evaluate the existing dam’s accuracies. The study revealed that accuracies of 84.65 % for the Salma Dam and 88.08 % for the Pashdan Dam were achieved, respectively. Six new dams, along with the existing two, formed the series of eight dams. The dam series were optimized for the total annual runoff of (1,600,000,000 m3), and the final dam heights were determined as follows: 107.5 m, 42 m, 100 m, 23.9 m, 30 m, 18 m, 23.44 m, and 22.65 m for dams (1 to 8), respectively. The study underscores the methodology's superiority in site suitability analysis and runoff optimization, while recommending future focus on observational data and higher-resolution digital elevation model (DEM) files for enhanced precision, environmental impact assessment, climate change considerations, social and economic implications, improved data resolution, and transboundary cooperation.

Using combination of albumin to fibrinogen ratio and prognostic nutritional index model for predicting disease activity in patients with systemic lupus erythematosus.

Background: Systemic lupus erythematosus (SLE) is chronic autoimmune disease with multiple organ damage and is associated with poor prognosis and high mortality. Identification of universal biomarkers to predict SLE activity is challenging due to the heterogeneity of the disease. This study aimed to identify the indicators that are sensitive and specific to predict activity of SLE.Methods: We retrospectively analyzed 108 patients with SLE. Patients were categorized into SLE with activity and without activity groups on the basis of SLE disease activity index. We analyzed the potential of routine and novel indicators in predicting the SLE activity using receiver operating characteristic curves and multivariate logistic regression. The Spearman method was used to understand the correlation between albumin to fibrinogen ratio (AFR), prognostic nutritional index (PNI), AFR-PNI model and disease activity.Results: SLE with activity group had higher ESR, CRP, D-dimer, fibrinogen, CRP to albumin ratio, positive rate of anti-dsDNA and ANUA, and lower C3, total bilirubin, total protein, albumin, albumin/globulin, creatinine, high density liptein cholesterol, hemoglobin, hematocrit, lymphocyte count, positive rate of anti-SSA, AFR, PNI than SLE without activity. A further established model based on combination of AFR and PNI (AFR-PNI model) showed prominent value in distinguishing SLE with activity patients from SLE without activity patients. In addition, the sensitivity and specificity of AFR-PNI model + anti-dsDNA combination model were superior to AFR-PNI model. AFR and PNI were risk factors for SLE activity. Moreover, AFR+PNI model correlated with disease activity and AFR-PNI model was associated with fever, pleurisy, pericarditis, renal involvement.Conclusion: These findings suggest that predictive model based on combination of AFR and PNI may be useful markers to identify active SLE in clinical practice.

A novel two-stage combination model for tourism demand forecasting

The tourism literature has shown that a combination of tourism forecasting models can provide better performance than individual models. In the literature, the models to be combined are usually subjectively selected and authors focus on the combination method. In this study, a new direction is represented by the integration of forecasts from several models using a two-stage forecasting system. In stage I, a subset of the best available models is objectively selected according to their performance. Then, in stage II, linear and nonlinear combination methods are utilized to integrate the forecast values of the optimal subset. The empirical study using tourist arrivals in Hong Kong from five major source markets indicates that the proposed two-stage tourism forecasting system with linear combination substantially improves forecasting performance compared with benchmarks. This study also finds that when combining forecasts from different models, the linear combination method is more suitable than nonlinear AI models.

Combining biomarkers of BNIP3 L, S100B, NSE, and accessible measures to predict sepsis-associated encephalopathy: a prospective observational study

Background Accurate identification of delirium in sepsis patients is crucial for guiding clinical diagnosis and treatment. However, there are no accurate biomarkers and indicators at present. We aimed to identify which combinations of cognitive impairment-related biomarkers and other easily accessible assessments best predict delirium in sepsis patients. Methods One hundred and one sepsis patients were enrolled in a prospective study cohort. S100B, NSE, and BNIP3 L biomarkers were detected in plasma and cerebrospinal fluid and patients’ optic nerve sheath diameter (ONSD). The optimal biomarkers identified by Logistic regression are combined with other factors such as ONSD to filter out the perfect model to predict delirium in sepsis patients through Logistic regression, Naïve Bayes, decision tree, and neural network models. Main results Among all biomarkers, compared with BNIP3 L (AUC = .706, 95% CI = .597–.815) and NSE (AUC = .711, 95% CI = .609–.813) in cerebrospinal fluid, plasma S100B (AUC = .729, 95% CI = .626–.832) had the best discrimination performance for delirium in sepsis patients. Logistic regression analysis showed that the combination of cerebrospinal fluid BNIP3 L with plasma S100B, ONSD, neutrophils, and age provided the best discrimination to cognitive impairment in sepsis patients (accuracy = .901, specificity = .923, sensitivity = .911), which was better than Naïve Bayes, decision tree, and neural network models. Neutrophils, ONSD, and cerebrospinal fluid BNIP3 L were consistently the major contributors in a few models. Conclusions The logistic regression showed that the combination model was strongly correlated with cognitive dysfunction in sepsis patients.

Indigenous Peoples’ Phronetic Leadership: A Trailblazing Case Study of Bacut Man-Made Lake for Agri-Eco-Tourism, Apayao, Philippines

Indigenous Phronetic Leaders inspired and promoted immense developments in communities through collective organizational knowledge creation. The study aimed to identify the problem of farmers, determine how phronetic leadership was practiced by the key informant, and describe the present situation of Bacut, Santa Marcela, Apayao, Cordillera Administrative Region (CAR), Philippines. Mr. Elorde P. Anniban, an indigenous phronetic leaders was the main participant and the protagonist. He is an indigenous respected elder or “pangat” who, despite being physically disabled, initiated reforms in Bacut. In-depth interviews and document reviews were applied in this management case study. Results revealed that the main problem of the farmers was low rice production because there was no water system to irrigate their farmlands. Without the knowledge of the key participant, he applied the socialization, externalization, combination, and internalization (SECI) model and encouraged the mining of bright ideas of the people, engaged stakeholders and relentlessly sought government intervention to address the problem of farmers. Through the phronetic leadership of the key informant, the farmers, and the government leaders, an environment-friendly dam, fondly called the Bacut Lake was constructed irrigating farmlands and doubling and even tripling rice production addressing poverty in Santa Marcela, Apayao. In addition, indigenous peoples' phronetic leadership, the province of Apayao has now an astounding agri-eco-tourism site, a national park, rich in biodiversity, and several existing organizations are working together to boost the economy of the farmers and the province. On the other hand, Ifugao State University, a government higher education institution in the country, crystallized a phronetic leadership framework as an offshoot of the study.
 
 Received: 28 September 2023 / Accepted: 23 February 2024 / Published: 5 March 2024

A Grain Size Profile Prediction Method Based on Combined Model of Extreme Gradient Boosting and Artificial Neural Network and Its Application in Sand Control Design

Summary The grain size distribution along the well depth is of great significance for the prediction of the physical properties and the staged sand control design of the unconsolidated or weakly consolidated sandstone reservoir. In this paper, a new method for predicting the formation median grain size profile based on the combination model of extreme gradient boosting (XGBoost) and artificial neural network (ANN) is proposed. The machine learning algorithm and weighted combination model are applied to the prediction and analysis of reservoir grain size. The prediction model is improved from two aspects: First, the feature engineering of the XGBoost-ANN model is constructed by using the data of multiple sampling points on the logging curve. Second, the prediction accuracy is improved by increasing the dimension of the prediction model, that is, the XGBoost and ANN single-prediction models are weighted by the error reciprocal method and a combined prediction model containing multidimensional information is established. The research results show that compared with the single-point mapping model, the prediction accuracy of the multipoint mapping model considering the vertical geological continuity of the reservoir is higher than that of the single-point prediction and the coefficient of determination in the testing set can be improved up to 14.5%. The influence of different weighting methods on prediction performance is studied, and the prediction performance of original XGBoost, ANN, and XGBoost-ANN combined models is compared. The combined prediction model has a higher prediction accuracy than the single XGBoost and ANN models with the same number of sampling points and the coefficient of determination can be improved by up to 16.5%. The prediction accuracy and generalization ability of the XGBoost-ANN combined model are evaluated comprehensively. The combined model is used to design layered sand control of a well in an adjacent block, and good results have been achieved in production practice. This study provides a new method with high accuracy and efficiency for the prediction of unconsolidated sand median grain size profile.

Factors of tacit knowledge acquisition and its mechanism of action on academic research performance: an empirical research from Chinese universities

PurposeThis study examines the relationship between higher education improvement and tacit knowledge importance. In this context, the scarcity of empirical and theoretical studies on acquiring tacit knowledge to enhance academic performance in higher education suggests that this research area holds significant importance for experts and policymakers. Consequently, this study aims to explore the factors that influence academic research performance at Chinese universities by acquiring tacit knowledge.Design/methodology/approachTo achieve the study aims, the current approach utilizes the research technique based on the socialization, externalization, internalization and combination (SECI) model and knowledge management (KM) theory. To analyze the study objective, the authors collected data from post-graduate students at Chinese universities and analyzed it using structural equation modeling (SEM) to test the model and hypotheses.FindingsThe results indicated that social interaction, internalization and self-motivation have a positive impact on academic research performance through the acquisition of tacit knowledge. Furthermore, the findings suggest that academic researchers can acquire more knowledge through social interaction than self-motivation, thereby advancing research progress.Originality/valueThis study addresses the critical issues surrounding the acquisition of tacit knowledge and presents a comprehensive framework and achievements that can contribute to achieving exceptional academic performance.

Intra- and peritumoral radiomics features based on multicenter automatic breast volume scanner for noninvasive and preoperative prediction of HER2 status in breast cancer: a model ensemble research

The aim to investigate the predictive efficacy of automatic breast volume scanner (ABVS), clinical and serological features alone or in combination at model level for predicting HER2 status. The model weighted combination method was developed to identify HER2 status compared with single data source model method and feature combination method. 271 patients with invasive breast cancer were included in the retrospective study, of which 174 patients in our center were randomized into the training and validation sets, and 97 patients in the external center were as the test set. Radiomics features extracted from the ABVS-based tumor, peritumoral 3 mm region, and peritumoral 5 mm region and clinical features were used to construct the four types of the optimal single data source models, Tumor, R3mm, R5mm, and Clinical model, respectively. Then, the model weighted combination and feature combination methods were performed to optimize the combination models. The proposed weighted combination models in predicting HER2 status achieved better performance both in validation set and test set. For the validation set, the single data source model, the feature combination model, and the weighted combination model achieved the highest area under the curve (AUC) of 0.803 (95% confidence interval [CI] 0.660–947), 0.739 (CI 0.556,0.921), and 0.826 (95% CI 0.689,0.962), respectively; with the sensitivity and specificity were 100%, 62.5%; 81.8%, 66.7%; 90.9%,75.0%; respectively. For the test set, the single data source model, the feature combination model, and the weighted combination model attained the best AUC of 0.695 (95% CI 0.583, 0.807), 0.668 (95% CI 0.555,0.782), and 0.700 (95% CI 0.590,0.811), respectively; with the sensitivity and specificity were 86.1%, 41.9%; 61.1%, 71.0%; 86.1%, 41.9%; respectively. The model weighted combination was a better method to construct a combination model. The optimized weighted combination models composed of ABVS-based intratumoral and peritumoral radiomics features and clinical features may be potential biomarkers for the noninvasive and preoperative prediction of HER2 status in breast cancer.

New Multi-Parameters Combination of Technetium-99m-Diethylene-Triamine-Pentaacetate Orbital Single-Photon Emission Computed Tomography/Computed Tomography for the Evaluation of Graves’ Orbitopathy Activity

ABSTRACT Purpose This study investigates the new combined parameters of 99mTc-DTPA orbital single-photon emission computed tomography/computed tomography (SPECT/CT) for the evaluation of Graves’ orbitopathy (GO) activity. Methods A retrospective analysis was performed on 41 patients. All the patients undergone the 99mTc-DTPA orbital SPECT/CT and were categorized into active and inactive group based on the standard combined by the clinical active score (CAS), magnet resonance imaging (MRI) and/or follow-up results. Quantitative parameters of lacrimal gland (LG) including the protruding degree of lacrimal gland herniation (LGH) and uptake ratios (URs) of region of interest (ROI) drawn on lacrimal gland and occipital bone. SPECT/CT reading results were based on visual analysis. Parameters were compared between the two groups and the diagnostic value on discrimination of GO activity was also evaluated. Results All parameters of SPECT/CT for active GO groups were significantly higher than those of the inactive groups (p<.05). There were notable linear positive correlations between the assumption standard and readings as well as combination models 2 and 3 (r = .794, r = .772, r = .760, respectively). ROC analysis indicated that model 2 provided the highest diagnostic performance, exhibiting an area under the curve (AUC) of .947, a sensitivity of 92.7%, and a specificity of 88.6%. Conclusions The combined use of SPECT/CT reading results and DTPA uptake parameters of LG offers a more objective and precise evaluation of active GO. This study further recommends 99mTc-DTPA SPECT/CT might be serving as a supplementary beneficial approach for CAS in evaluating GO activity.

AI monitoring and warning system for low visibility of freeways using variable weight combination model

AbstractIn intelligent vehicles, road environment perception technology is a key component of autonomous driving assistance systems. This component is the foundation for vehicle decision‐making and control, and is a guarantee of safety during the driving of the vehicle. The existing environment perception technology mainly targets well‐lit environments and requires visible light imaging equipment. Therefore, in low visibility environments, this technology cannot make good judgments about the external environment. Many existing perception systems mainly rely on sensors. Under low visibility conditions, these sensors weaken their effectiveness due to signal transmission, reflection, or absorption, resulting in incomplete or distorted data collection. Reduced visibility often affects the sensing range of various sensors, hindering the system's ability to detect and recognize distant objects, thereby limiting the necessary advance warning and response time for safe navigation. In response to this issue, this study proposed a combined method of infrared imaging and polarized imaging to collect feature data on road conditions in low visibility environments. Then, the obtained images were denoised and enhanced. The processed images were input into the system for recognition, and the images were analyzed and recognized using a low visibility road situation semantic segmentation algorithm based on deep learning. The research outcomes denoted that the pixel accuracy, average pixel accuracy, and average intersection ratio of the variable weight combination model in polarized degree images were 91.2%, 89.1%, and 71.6%, respectively. Those in infrared images were 83.6%, 90.6%, and 62.1%, respectively. The various indicators of the variable weight combination model were higher than those of the U‐shaped neural network model, indicating its performance is relatively excellent. The research results indicated that infrared imaging helps to acquire information at night or in low light conditions, while polarized imaging can provide better adaptation to cluttered light and reflections, enabling the system to provide more robust environmental sensing in complex weather conditions. It fills a critical gap in perception for autonomous driving systems in adverse weather conditions.

Immune signatures predict response to house dust mite subcutaneous immunotherapy in patients with allergic rhinitis.

Identifying predictive biomarkers for allergen immunotherapy response is crucial for enhancing clinical efficacy. This study aims to identify such biomarkers in patients with allergic rhinitis (AR) undergoing subcutaneous immunotherapy (SCIT) for house dust mite allergy. The Tongji (discovery) cohort comprised 72 AR patients who completed 1-year SCIT follow-up. Circulating T and B cell subsets were characterized using multiplexed flow cytometry before SCIT. Serum immunoglobulin levels and combined symptom and medication score (CSMS) were assessed before and after 12-month SCIT. Responders, exhibiting ≥30% CSMS improvement, were identified. The random forest algorithm and logistic regression analysis were used to select biomarkers and establish predictive models for SCIT efficacy in the Tongji cohort, which was validated in another Wisco cohort with 43 AR patients. Positive SCIT response correlated with higher baseline CSMS, allergen-specific IgE (sIgE)/total IgE (tIgE) ratio, and frequencies of Type 2 helper T cells, Type 2 follicular helper T (TFH2) cells, and CD23+ nonswitched memory B (BNSM) and switched memory B (BSM) cells, as well as lower follicular regulatory T (TFR) cell frequency and TFR/TFH2 cell ratio. The random forest algorithm identified sIgE/tIgE ratio, TFR/TFH2 cell ratio, and BNSM frequency as the key biomarkers discriminating responders from nonresponders in the Tongji cohort. Logistic regression analysis confirmed the predictive value of a combination model, including sIgE/tIgE ratio, TFR/TFH2 cell ratio, and CD23+ BSM frequency (AUC = 0.899 in Tongji; validated AUC = 0.893 in Wisco). A T- and B-cell signature combination efficiently identified SCIT responders before treatment, enabling personalized approaches for AR patients.

Integrated forecasting method of medium-and long-term runoff by ridge regression based on optimal sub-model selection

Abstract Numerous studies have demonstrated that the combination models can improve the runoff forecast performance compared to individual forecasts. However, some models do not take into account the effects of inappropriate sub-models on the combination models. Based on this, a medium-and long-term runoff integrated forecasting method based on optimal sub-models selection was proposed. First, the sub-models, including linear regression (MLR), BP neural network (BPNN), wavelet neural network (WNN), and support vector regression (SVR), are optimally selected based on the nearness degree. Second, ridge regression (RR) is used to combine the optimal sub-models to predict runoff. Finally, the Guandi hydropower station is taken as an example to verify the effect of the integrated forecasting model. The results show that SVR, BPNN, and WNN are the optimal sub-models, and RR-3 is the optimal integrated forecasting model composed of the optimal sub-models. In addition, compared with the other two combination models, the RR-3 performs better.

A novel predict method for muscular invasion of bladder cancer based on 3D mp-MRI feature fusion

Objective. To assist urologist and radiologist in the preoperative diagnosis of non-muscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC), we proposed a combination models strategy (CMS) utilizing multiparametric magnetic resonance imaging. Approach. The CMS includes three components: image registration, image segmentation, and multisequence feature fusion. To ensure spatial structure consistency of T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced imaging (DCE), a registration network based on patch sampling normalized mutual information was proposed to register DWI and DCE to T2WI. Moreover, to remove redundant information around the bladder, we employed a segmentation network to obtain the bladder and tumor regions from T2WI. Using the coordinate mapping from T2WI, we extracted these regions from DWI and DCE and integrated them into a three-branch dual-channel input. Finally, to fully fuse low-level and high-level features of T2WI, DWI, and DCE, we proposed a distributed multilayer fusion model for preoperative MIBC prediction with five-fold cross-validation. Main results. The study included 436 patients, of which 404 were for the internal cohort and 32 for external cohort. The MIBC was confirmed by pathological examination. In the internal cohort, the area under the curve, accuracy, sensitivity, and specificity achieved by our method were 0.928, 0.869, 0.753, and 0.929, respectively. For the urologist and radiologist, Vesical Imaging-Reporting and Data System score >3 was employed to determine MIBC. The urologist demonstrated an accuracy, sensitivity, and specificity of 0.842, 0.737, and 0.895, respectively, while the radiologist achieved 0.871, 0.803, and 0.906, respectively. In the external cohort, the accuracy of our method was 0.831, which was higher than that of the urologist (0.781) and the radiologist (0.813). Significance. Our proposed method achieved better diagnostic performance than urologist and was comparable to senior radiologist. These results indicate that CMS can effectively assist junior urologists and radiologists in diagnosing preoperative MIBC.

Application of a Variable Weight Time Function Combined Model in Surface Subsidence Prediction in Goaf Area: A Case Study in China

To attain precise forecasts of surface displacements and deformations in goaf areas (a void or cavity that remains underground after the extraction of mineral resources) following coal extraction, this study based on the limitations of individual time function models, conducted a thorough analysis of how the parameters of the model impact subsidence curves. Parameter estimation was conducted using the trust-region reflective algorithm (TRF), and the time function models were identified. Then we utilized a combined model approach and introduced the sliding window mechanism to assign variable weights to the model. Based on this, the combined model was used for prediction, followed by the application of this composite prediction to engineering scenarios for the dynamic forecasting of surface movements and deformations. The results indicated that, in comparison with DE, GA, PSO algorithms, the TRF exhibited superior stability and convergence. The parameter models obtained using this method demonstrated a higher level of predictive accuracy. Moreover, the predictive precision of the variable-weight time function combined model surpassed that of corresponding individual time function models. When employing six different variable-weight combination prediction models for point C22, the Weibull-MMF model demonstrated the most favorable fitting performance, featuring a root mean square error (RMSE) of 32.98 mm, a mean absolute error (MAE) of 25.66 mm, a mean absolute percentage error (MAPE) of 7.67%; the correlation coefficient R2 reached 0.99937. These metrics consistently outperformed their respective individual time function models. Additionally, in the validation process of the combined model at point C16, the residuals were notably smaller than those of individual models. This reaffirmed the accuracy and reliability of the proposed variable-weight combined model. Given that the variable-weight combination model was an evolution from individual time function models, its applicability extends to a broader range, offering valuable guidance for the dynamic prediction of surface movement and deformation in mining areas.

An integration scheme of simultaneous cycle slips determination combining improved geometry-free combination and TDCP model for undifferenced GNSS data

Fast and reliable cycle slip determination can ensure successive ambiguity resolution and precise positioning. Generally, it is not difficult to determine big cycle slips using the linear combination of observations, for instance, the geometry-free (GF) combination and the Hatch–Melbourne–Wübbena (HMW) combination. However, the participation of pseudorange observations may fail to identify small cycle slips. This contribution proposes an integration scheme combining the improved geometry-free (IGF) combination and time-difference carrier phase (TDCP) model to determine simultaneous cycle slips for undifferenced kinematic data. The IGF combination, which is improved from the modified geometry-free (MGF) combination and utilizes the Gauss floor function to take the decimal part of GF, can directly determine small cycle slips on a specific frequency. The TDCP model is used to estimate the differences of position and clock error between adjacent epochs by least-square adjustment using clean phase observations, and repair the remaining cycle slips by the predicted TDCP measurements obtained from the predetermined parameters. The proposed method is tested against 1 Hz kinematic dataset with simulation and highway dataset with real cycle slips. In the simulation test, all cycle slips can be correctly repaired by IGF for L1/L5, E1/E5 and E1/E5a. These combinations are unavailable for MGF. Compared to the HMW-GF method, the repair success rate of IGF improves from 96.80% to 99.16%, and the number of incorrect cases reduces from 9650 to 2535. The IGF-TDCP integration scheme can further improve the performance of IGF, whose repair success rate is more than 99.97% and incorrect cases are 38. The highway test shows that the proposed method effectively processes simultaneous cycle slips on more than half of the tracking satellites caused by the overpasses, even in the case of simultaneous 3 second data gaps on 5 satellites of 6 tracking satellites.