Combined Model Research Articles

Droop parameter-based economic dispatch for islanded microgrid considering demand response

The droop parameter setting of the distributed generator (DG) has an essential role in islanded microgrid (MG) systems. This paper presents droop-based economic load dispatch (ELD) in an islanded MG. In this approach, the Power–frequency (P–f) droop characteristic of DG is integrated into its incremental cost, which is the derivative of the cost function of DG. The optimisation problem is formulated by considering the standard deviations of the incremental costs of DGs. Under steady-state conditions, DGs operate at a single frequency and the P–f droop-based ELD ensures that the incremental costs of DGs are equal, minimising the overall cost of active power generation, following the equal incremental cost principle. Furthermore, an incentive-based demand response (DR) programme is integrated into the system to maximise the utility benefit function by incentivising customers for power curtailment. The results exhibit significant power curtailment during peak load hours, indicating the effectiveness of the DR programme. The proposed combined mathematical model is applied to the modified 33-bus islanded MG and solved using basic particle swarm optimisation. It calculates optimal droop parameters for a day-ahead scenario and emphasises the efficiency benefits of optimised droop settings and the integration of DR in islanded MGs.

Combination of clinical information and radiomics models for the differentiation of acute simple appendicitis and non simple appendicitis on CT images.

To investigate the radiomics models for the differentiation of simple and non-simple acute appendicitis. This study retrospectively included 334 appendectomy cases (76 simple and 258 non-simple cases) for acute appendicitis. These cases were divided into training (n = 106) and test cohorts (n = 228). A radiomics model was developed using the radiomic features of the appendix area on CT images as the input variables. A CT model was developed using the clinical and CT features as the input variables. A combined model was developed by combining the radiomics model and clinical information. These models were tested, and their performance was evaluated by receiver operating characteristic curves and decision curve analysis (DCA). The variables independently associated with non-simple appendicitis in the combined model were body temperature, age, percentage of neutrophils and Rad-score. The AUC of the combined model was significantly higher than that of the CT model (P = 0.041). The AUC of the radiomics model was also higher than that of the CT model but did not reach a level of statistical significance (P = 0.053). DCA showed that all three models had a higher net benefit (NB) than the default strategies, and the combined model presented the highest NB. A nomogram of the combined model was developed as the graphical representation of the final model. It is feasible to use the combined information of clinical and CT radiomics models for the differentiation of simple and non-simple acute appendicitis.

Prediction of Baltic Dry Index Based on GRA-BiLSTM Combined Model

The Baltic dry index (BDI) is not only one of the most important indicators of shipping costs but is also an important barometer of global trade and manufacturing sentiment. The BDI is highly volatile and subject to complex factors, which make it difficult to predict. In this paper, a neural network model-based BDI forecasting system was proposed to effectively forecast the BDI. We used the gray relational degree analysis method to select seven factors with higher correlation from 15 factors affecting the variation of BDI index to be used as input indicators for the bi-directional long short-term memory (BiLSTM) model to forecast BDI. From the experimental results, the prediction model proposed in this paper had an excellent prediction effect on the BDI. The mape value of the prediction result was 9.19%. The accuracy was better than the common machine learning models SVR and REG and the neural network model LSTM. In addition, in order to further optimize the prediction performance of the combined model GRA-BiLSTM, this paper introduced the MIV method to conduct an in-depth analysis of the contribution of each variable to the prediction results. Rice price, Shanghai securities composite index and crude oil price were found to be the three most relevant indicators to the prediction accuracy of the model.

How can the Pearl River Delta urban agglomeration achieve the carbon peak target: Based on the perspective of an optimal stable economic growth path

The Pearl River Delta (PRD) has high concentrations of energy consumption and carbon emissions, and the conflict between its economic development and environmental protection is relatively prominent. Beginning from the ideal path of economic growth, this study proposes a framework for carbon emission prediction under the optimal economic growth path of the PRD via the cross-analysis of low-carbon economic analysis and artificial intelligence prediction. First, the generalized Divisia index method (GDIM) is used to decompose carbon emissions to quantify the contribution rate of each influencing factor. Then, the genetic algorithm (GA) is introduced to optimize the backpropagation (BP) neural network to construct a GA-BP combined prediction model. Finally, the optimal economic growth rate models under different scenarios are constructed, and the carbon peak in the PRD under stable economic growth is accurately predicted. The results show that under the optimal economic growth path, the carbon peak in the PRD under the scenario with carbon constraints will be reached in 2029, while that under the scenario without carbon constraints will only begin to appear around 2035. Thus, the achievement of the carbon peak target in the PRD still requires insisting on stringent carbon emission reduction measures.

A PET/CT radiomics model for predicting distant metastasis in early-stage non–small cell lung cancer patients treated with stereotactic body radiotherapy: a multicentric study

ObjectivesStereotactic body radiotherapy (SBRT) is a treatment option for patients with early-stage non-small cell lung cancer (NSCLC) who are unfit for surgery. Some patients may experience distant metastasis. This study aimed to develop and validate a radiomics model for predicting distant metastasis in patients with early-stage NSCLC treated with SBRT.MethodsPatients at five institutions were enrolled in this study. Radiomics features were extracted based on the PET/CT images. After feature selection in the training set (from Tianjin), CT-based and PET-based radiomics signatures were built. Models based on CT and PET signatures were built and validated using external datasets (from Zhejiang, Zhengzhou, Shandong, and Shanghai). An integrated model that included CT and PET radiomic signatures was developed. The performance of the proposed model was evaluated in terms of its discrimination, calibration, and clinical utility. Multivariate logistic regression was used to calculate the probability of distant metastases. The cutoff value was obtained using the receiver operator characteristic curve (ROC), and the patients were divided into high- and low-risk groups. Kaplan-Meier analysis was used to evaluate the distant metastasis-free survival (DMFS) of different risk groups.ResultsIn total, 228 patients were enrolled. The median follow-up time was 31.4 (2.0-111.4) months. The model based on CT radiomics signatures had an area under the curve (AUC) of 0.819 in the training set (n = 139) and 0.786 in the external dataset (n = 89). The PET radiomics model had an AUC of 0.763 for the training set and 0.804 for the external dataset. The model combining CT and PET radiomics had an AUC of 0.835 for the training set and 0.819 for the external dataset. The combined model showed a moderate calibration and a positive net benefit. When the probability of distant metastasis was greater than 0.19, the patient was considered to be at high risk. The DMFS of patients with high- and low-risk was significantly stratified (P < 0.001).ConclusionsThe proposed PET/CT radiomics model can be used to predict distant metastasis in patients with early-stage NSCLC treated with SBRT and provide a reference for clinical decision-making.Plain language summaryIn this study, the model was established by combining CT and PET radiomics signatures in a moderate-quantity training cohort of early-stage NSCLC patients treated with SBRT and was successfully validated in independent cohorts. Physicians could use this easy-to-use model to assess the risk of distant metastasis after SBRT. Identifying subgroups of patients with different risk factors for distant metastasis is useful for guiding personalized treatment approaches.

Ensemble learning based compressive strength prediction of concrete structures through real-time non-destructive testing

This study conducts an extensive comparative analysis of computational intelligence approaches aimed at predicting the compressive strength (CS) of concrete, utilizing two non-destructive testing (NDT) methods: the rebound hammer (RH) and the ultrasonic pulse velocity (UPV) test. In the ensemble learning approach, the six most popular algorithms (Adaboost, CatBoost, gradient boosting tree (GBT), random forest (RF), stacking, and extreme gradient boosting (XGB)) have been used to develop the prediction models of CS of concrete based on NDT. The ML models have been developed using a total of 721 samples, of which 111 were cast in the laboratory, 134 were obtained from in-situ testing, and the other samples were gathered from the literature. Among the three categories of analytical models—RH models, UPV models, and combined RH and UPV models; seven, ten, and thirteen models have been used respectively. AdaBoost, CatBoost, GBT, RF, Stacking, and XGB models have been used to improve the accuracy and dependability of the analytical models. The RH-M5, UPV-M6, and C-M6 (combined UPV and RH model) models were found with highest performance level amongst all the analytical models. The MAPE value of XGB was observed to be 84.37%, 83.24%, 77.33%, 59.46%, and 81.08% lower than AdaBoost, CatBoost, GBT, RF, and stacking, respectively. The performance of XGB model has been found best than other soft computing techniques and existing traditional predictive models.

БІЗНЕС-МОДЕЛІ ОСНОВНИХ ГРАВЦІВ НА ПОЛІ ЦИФРОВОЇ ДИСТРИБУЦІЇ ЕЛЕКТРОННИХ КНИЖОК В УКРАЇНІ. 2011–2023

&lt;p&gt;&lt;em&gt;A new field of e-book distribution has emerged and developed in Ukraine due to the impact of digital technology on the publishing industry.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt;This research aims to&lt;/em&gt;&lt;/strong&gt;&lt;em&gt;: Identify the key players in the field of digital distribution of e-books by Ukrainian publishers from 2011 to 2023. Analyse and describe the value propositions and business models of digital book distribution start-ups in Ukraine.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt;Research methodology. &lt;/em&gt;&lt;/strong&gt;&lt;em&gt;The study analyses the value propositions and business models of various companies operating in e-book distribution in Ukraine, using the case study method and mystery shopping. The generalisation of the data obtained as a result of the case study was achieved by using historical, analytical, synthetic and comparative methods, classification methods and a systematic approach.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt;Results. &lt;/em&gt;&lt;/strong&gt;&lt;em&gt;Thirteen players were found to be active in e-book distribution between 2011 and 2023 (seven entered the market in 2011&lt;/em&gt;&lt;em&gt;–&lt;/em&gt;&lt;em&gt;2018 and another six in 2019&lt;/em&gt;&lt;em&gt;–&lt;/em&gt;&lt;em&gt;2023), with three platforms closing in the last five years. Of the ten active players, six specialise in e-book sales with a «digital only» business model (Booxters, Booknet, Chytanka, Librarius, Pocketbook) and four are online bookstores with an omnichannel business model, selling both print books and e-books (Yakaboo, KnigoLand, Knygarnya «E», Nash format). The main business model for all players in e-book distribution is direct sales, although distributors are increasingly adopting combined business models (direct sales plus subscription). A positive trend is the implementation in the field of digital distribution of e-books in Ukraine of business models that are popular in foreign digital publishing, in particular, self-publishing (Booknet) and e-book lending (Librarius). Important for the development of Ukrainian digital book production and sales is the focus of distributors on ensuring closed access and strict protection of book content against piracy sharing.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt;The novelty &lt;/em&gt;&lt;/strong&gt;&lt;em&gt;lies in the development of a chronological list of the main players who have worked (or are working) in the field of digital distribution of Ukrainian e-books; identifying their business models and analysing their value propositions: e-book formats, types of access to content and ways of protecting content.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt;Practical significant&lt;/em&gt;&lt;/strong&gt;&lt;em&gt;. The results of this research will be used in lectures for students of the educational program «Publishing and editing» in Ukrainian universities, and will also draw the attention of the publishing community to the problems of the development of digital book publishing.&lt;/em&gt;&lt;/p&gt;&lt;p&gt;&lt;strong&gt;&lt;em&gt;Key words&lt;/em&gt;&lt;/strong&gt;&lt;em&gt;: bookselling, business models, digital distribution, digital book publishing, e-book, field of digital distribution, omnichannel.&lt;/em&gt;&lt;/p&gt;

External Validation of Ultrasound Radiomics for Small (≤ 4 cm) Renal Mass Differentiation: A Comparison with Radiologists.

Renal cell carcinoma, especially in small renal masses (≤ 4 cm) (SRM), has increased. Pathological analysis revealed a high proportion of benign masses, highlighting the urgent need for precise SRM differentiation. This research aimed to independently validate the performance of machine learning-based ultrasound (US) radiomics analysis in differentiating benign from malignant SRM, and to compare its performance with that of radiologists. A total of 499 patients from two hospitals were retrospectively included in this study and divided into two cohorts. US images were used to extract radiomics features. To obtain the most robust features, inter-observer correlation coefficient, Spearman correlation coefficient, and least absolute shrinkage and selection operator methods were applied for feature selection. Three models were developed in the training data using the stochastic gradient boosting algorithm, including a clinical model, a radiomics model, and a combined model that integrated clinical factors and radiomics features. The performance of these models was evaluated in the independent external validation data, including discrimination, calibration, and clinical usefulness, and compared with pooled radiologists' assessments. The AUCs of the clinical, radiomics, and combined models were 0.844, 0.942, and 0.954, respectively. The radiomics and combined models significantly outperformed the clinical model (all p < 0.05), while no significant difference was observed between them (p = 0.32). The radiomics and combined models showed good discrimination and calibration. Decision curve analysis exhibited that the combined model had clinical usefulness. Compared with the pooled radiologists' assessment (AUC, 0.799), the combined model showed superior classification results (p < 0.01) and higher specificity (p < 0.01) with similar sensitivity (p = 0.62). The combined model incorporating clinical factors and radiomics features accurately distinguished benign from malignant SRM.

Enabling countries to manage outbreaks: statistical, operational, and contextual analysis of the early warning and response system (EWARS-csd) for dengue outbreaks.

Dengue is currently the fastest-spreading mosquito-borne viral illness in the world, with over half of the world's population living in areas at risk of dengue. As dengue continues to spread and become more of a health burden, it is essential to have tools that can predict when and where outbreaks might occur to better prepare vector control operations and communities' responses. One such predictive tool, the Early Warning and Response System for climate-sensitive diseases (EWARS-csd), primarily uses climatic data to alert health systems of outbreaks weeks before they occur. EWARS-csd uses the robust Distribution Lag Non-linear Model in combination with the INLA Bayesian regression framework to predict outbreaks, utilizing historical data. This study seeks to validate the tool's performance in two states of Colombia, evaluating how well the tool performed in 11 municipalities of varying dengue endemicity levels. The validation study used retrospective data with alarm indicators (mean temperature and rain sum) and an outbreak indicator (weekly hospitalizations) from 11 municipalities spanning two states in Colombia from 2015 to 2020. Calibrations of different variables were performed to find the optimal sensitivity and positive predictive value for each municipality. The study demonstrated that the tool produced overall reliable early outbreak alarms. The median of the most optimal calibration for each municipality was very high: sensitivity (97%), specificity (94%), positive predictive value (75%), and negative predictive value (99%; 95% CI). The tool worked well across all population sizes and all endemicity levels but had slightly poorer results in the highly endemic municipality at predicting non-outbreak weeks. Migration and/or socioeconomic status are factors that might impact predictive performance and should be further evaluated. Overall EWARS-csd performed very well, providing evidence that it should continue to be implemented in Colombia and other countries for outbreak prediction.

Major drivers of soil acidification over 30 years differ in paddy and upland soils in China

Elevated nitrogen (N) fertilization has largely increased crop production in China, but also increased acidification risks, thereby threatening crop yields. However, natural soil acidification due to bicarbonate (HCO3) leaching and base cation (BC) removal by crop harvest also affect soil acidity whereas the input of HCO3 and BC via fertilizers and manure counteract soil acidification. Insights in rates and drivers of soil acidification in different land use types is too limited to support crop- and site-specific mitigation strategies. In this study, we assessed the historical changes in cropland acidification rates and their drivers for the period 1985–2019 at 151 sites in a typical Chinese county with the combined nutrient and soil acidification model VSD+. VSD+ could well reproduce long-term changes in pH and in the BC concentrations of calcium, magnesium and potassium between 1985 and 2019 in non-calcareous soils. In paddy soils, the acidity production rate decreased from 1985 onwards, mainly driven by a pH-induced reduction in HCO3 leaching and N transformations. In upland soils, however, acidity production was mainly driven by N transformations and hardly changed over time. Crop BC removal by harvesting played a minor role in both paddy and upland soils, but its relative importance increased in paddy soils. The acidity input was partly neutralized by HCO3 input from fertilizers and manure, which decreased over time due to a change from ammonia bicarbonate to urea. Soil buffering by both BC and aluminium release decreased in paddy soils due to a reduction in net acidity production, while it stayed relatively constant in upland soils. We conclude that acidification management in paddy soils requires a focus on avoiding high HCO3 leaching whereas the management in upland soils should focus on balancing N with recycling organic manure and crop residues.

Electrical resistivity, seismic velocity, and porosity of crustal rocks from the Oman ophiolite under brine-saturated ocean floor conditions

In order to examine the effects of crack properties on electrical resistivity and seismic velocity, we conducted simultaneous measurements of electrical resistivity, seismic velocity and porosity at brine-saturated hydrostatic pressures using mafic crustal rocks from the Oman ophiolite. The resistivity and velocity of the samples increase systematically with increasing confining pressure owing to the closure of cracks, as monitored by changes in porosity. Apparent formation factors of each sample are related to the porosity, but nonlinear relationships on logarithmic plots indicate that Archie's law cannot explain these experimental data. We evaluated the effect of crack porosity and aspect ratio for the measured velocity based on the effective medium theory, and the electrical resistivity was inferred from the crack porosity and connectivity according to the percolation model. The experimental velocity and resistivity results are consistent with the model calculations in terms of crack density, aspect ratio and connectivity. We applied a combined velocity-resistivity model to the geophysical logging and borehole data for the oceanic crust in Hole 504B. Our inversion results indicate that the seismic layer 2/3 transition is primarily caused by an alteration front controlled by interconnected cracks and fluid flow in the oceanic crust.

A nomogram based on CT intratumoral and peritumoral radiomics features preoperatively predicts poorly differentiated invasive pulmonary adenocarcinoma manifesting as subsolid or solid lesions: a double-center study.

The novel International Association for the Study of Lung Cancer (IASLC) grading system suggests that poorly differentiated invasive pulmonary adenocarcinoma (IPA) has a worse prognosis. Therefore, prediction of poorly differentiated IPA before treatment can provide an essential reference for therapeutic modality and personalized follow-up strategy. This study intended to train a nomogram based on CT intratumoral and peritumoral radiomics features combined with clinical semantic features, which predicted poorly differentiated IPA and was tested in independent data cohorts regarding models' generalization ability. We retrospectively recruited 480 patients with IPA appearing as subsolid or solid lesions, confirmed by surgical pathology from two medical centers and collected their CT images and clinical information. Patients from the first center (n =363) were randomly assigned to the development cohort (n = 254) and internal testing cohort (n = 109) in a 7:3 ratio; patients (n = 117) from the second center served as the external testing cohort. Feature selection was performed by univariate analysis, multivariate analysis, Spearman correlation analysis, minimum redundancy maximum relevance, and least absolute shrinkage and selection operator. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the model performance. The AUCs of the combined model based on intratumoral and peritumoral radiomics signatures in internal testing cohort and external testing cohort were 0.906 and 0.886, respectively. The AUCs of the nomogram that integrated clinical semantic features and combined radiomics signatures in internal testing cohort and external testing cohort were 0.921 and 0.887, respectively. The Delong test showed that the AUCs of the nomogram were significantly higher than that of the clinical semantic model in both the internal testing cohort(0.921 vs 0.789, p< 0.05) and external testing cohort(0.887 vs 0.829, p< 0.05). The nomogram based on CT intratumoral and peritumoral radiomics signatures with clinical semantic features has the potential to predict poorly differentiated IPA manifesting as subsolid or solid lesions preoperatively.

Prediction of antibiotic sorption in soil with machine learning and analysis of global antibiotic resistance risk

Although the sorption of antibiotics in soil has been extensively studied, their spatial distribution patterns and sorption mechanisms still need to be clarified, which hinders the assessment of antibiotic resistance risk. In this study, machine learning was employed to develop the models for predicting the soil sorption behavior of three classes of antibiotics (sulfonamides, tetracyclines, and fluoroquinolones) in 255 soils with 2203 data points. The optimal independent models obtained an accurate predictive performance with R2 of 0.942 to 0.977 and RMSE of 0.051 to 0.210 on test sets compared to combined models. Besides, a global map of the antibiotic sorption capacity of soil predicted with the optimal models revealed that the sorption potential of fluoroquinolones was the highest, followed by tetracyclines and sulfonamides. Additionally, 14.3% of regions had higher antibiotic sorption potential, mainly in East and South Asia, Central Siberia, Western Europe, South America, and Central North America. Moreover, a risk index calculated with the antibiotic sorption capacity of soil and population density indicated that about 3.6% of soils worldwide have a high risk of resistance, especially in South and East Asia with high population densities. This work has significant implications for assessing the antibiotic contamination potential and resistance risk.

CT-based radiomics signature for differentiating pyelocaliceal upper urinary tract urothelial carcinoma from infiltrative renal cell carcinoma.

To develop a CT-based radiomics model and a combined model for preoperatively discriminating infiltrative renal cell carcinoma (RCC) and pyelocaliceal upper urinary tract urothelial carcinoma (UTUC), which invades the renal parenchyma. Eighty patients (37 pathologically proven infiltrative RCCs and 43 pathologically proven pyelocaliceal UTUCs) were retrospectively enrolled and randomly divided into a training set (n = 56) and a testing set (n = 24) at a ratio of 7:3. Traditional CT imaging characteristics in the portal venous phase were collected by two radiologists (SPH and ZXL, who have 4 and 30 years of experience in abdominal radiology, respectively). Patient demographics and traditional CT imaging characteristics were used to construct the clinical model. The radiomics score was calculated based on the radiomics features extracted from the portal venous CT images and the random forest (RF) algorithm to construct the radiomics model. The combined model was constructed using the radiomics score and significant clinical factors according to the multivariate logistic regression. The diagnostic efficacy of the models was evaluated using receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC). The RF score based on the eight validated features extracted from the portal venous CT images was used to build the radiomics model. Painless hematuria as an independent risk factor was used to build the clinical model. The combined model was constructed using the RF score and the selected clinical factor. Both the radiomics model and combined model showed higher efficacy in differentiating infiltrative RCC and pyelocaliceal UTUC in the training and testing cohorts with AUC values of 0.95 and 0.90, respectively, for the radiomics model and 0.99 and 0.90, respectively, for the combined model. The decision curves of the combined model as well as the radiomics model indicated an overall net benefit over the clinical model. Both the radiomics model and the combined model achieved a notable reduction in false-positive and false-negativerates, resulting in significantly higher accuracy compared to the visual assessments in both the training and testing cohorts. The radiomics model and combined model had the potential to accurately differentiate infiltrative RCC and pyelocaliceal UTUC, which invades the renal parenchyma, and provide a new potentially non-invasive method to guide surgery strategies.

Future fire-PM2.5 mortality varies depending on climate and socioeconomic changes

Fire emits hazardous air pollutants, the most dominant of which is fine particulate matter of diameter ⩽2.5 μm (PM2.5). PM2.5 is a great concern due to its adverse effects on public health. Previous studies have examined the health burden from fire-related PM2.5 for the historical period; however, future global mortality associated with fire-PM2.5, particularly under the coexisting impacts of climate and socioeconomic changes, is yet to be projected. Here, we estimated the mortality associated to fire-PM2.5 (fire-PM2.5 mortality) for the present period (2010s) and then projected the mortality for the 2050s and 2090s under 10 scenarios created by combining two Representative Concentration Pathways (RCP2.6 or 6.0) with five Shared Socioeconomic Pathways (SSP1–5). We used the Li-Park fire model in combination with a chemical transport model and health risk assessment to calculate fire-PM2.5 mortality. For the present period, the estimated fire-PM2.5 mortality was 135 180 (105 403–163 738), which is 1.7 deaths per 100 000 population globally. When countries were grouped by income, the fire-PM2.5 mortality rate was the highest in the high-income country group and lowest in the lowest-income country group. For the 2050s and 2090s, the fire-PM2.5 mortality rate was projected to decrease under most scenarios because of decreases in fire emissions and baseline mortality rate. However, a scenario of high population growth and low technical development (SSP3) together with severe global warming (RCP6.0) would lead to an increase in the fire-PM2.5 mortality rate in the 2090s, particularly in the highest-income countries, due to increased fire under drier and warmer weather conditions. Stratification of countries by gross domestic product indicated the need for adaptation efforts in the highest-income countries to avoid future increases of mortality associated with fire-PM2.5.

Optimal planning and scheduling of information processes during interaction among mobile objects

The purpose of the research was to improve the quality of information process control in the interaction of mobile object grouping. This proposal is based on developing and implementing new combined models with algorithms for optimal planning and scheduling of information processes during interaction among mobile objects. The proposed approach would guarantee the required level of aircraft maintenance at the airport. The novel aspect of the proposed solution is that it divides the spatially distributed task of selecting a plan and a schedule for information processes in mobile objects into two subtasks, describing the spatial and temporal features of the original task. The spatial component of the original problem is described as a static model. Using this model, the optimal distribution of information operations over the resources of mobile objects is carried out without binding these operations to time. The time component is described as a dynamic model, within which the information operations are tied to time and the corresponding resources. Examples of construction and research of synthesized plans and schedules are given. Abbreviations: DM, Dynamic model; FIFO, First-In First-Out; Gr, Grouping; HSC, Hardware and software complex; ITS, Intelligent Transport System; IP, Information Processes; MO, Mobile object; PC, Programmed control; SM, Static model; SMS, Special mathematic support; LDM, Logical-dynamic models

Development and Internal Validation of a Clinical and Genetic Risk Score for Rheumatoid Arthritis-Associated Interstitial Lung Disease.

Although clinical and genetic risk factors have been identified for rheumatoid arthritis-associated interstitial lung disease (RA-ILD), there are no current tools allowing for risk stratification. We sought to develop and validate an ILD risk model in a large, multicentre, prospective RA cohort. Participants in the Veterans Affairs RA (VARA) registry were genotyped for 12 single nucleotide polymorphisms (SNPs) associated with idiopathic pulmonary fibrosis. ILD was validated through systematic record review. A genetic risk score (GRS) was computed from minor alleles weighted by effect size with ILD, using backward selection. The GRS was combined with clinical risk factors within a logistic regression model. Internal validation was completed using bootstrapping, and model performance was assessed by the area under the receiver operating curve (AUC). Of 2,386 participants (89% male, mean age 69.5 years), 9.4% had ILD. Following backward selection, five SNPs contributed to the GRS. The GRS and clinical factors outperformed clinical factors alone in discriminating ILD (AUC 0.675 vs 0.635, p< 0.001). The shrinkage-corrected performance for combined and clinical-only models was 0.667 (95% CI 0.628, 0.712) and 0.623 (95% CI 0.584, 0.651), respectively. Twenty percent of the cohort had a combined risk score below a cut-point with >90% sensitivity. A clinical and genetic risk model discriminated ILD in a large, multicentre RA cohort better than a clinical-only model, excluding 20% of the cohort from low-yield testing. These results demonstrate the potential utility of a GRS in RA-ILD and support further investigation into individualized risk stratification and screening.

Deep ensemble model-based moving object detection and classification using SAR images

In recent decades, image processing and computer vision models have played a vital role in moving object detection on the synthetic aperture radar (SAR) images. Capturing of moving objects in the SAR images is a difficult task. In this study, a new automated model for detecting moving objects is proposed using SAR images. The proposed model has four main steps, namely, preprocessing, segmentation, feature extraction, and classification. Initially, the input SAR image is pre-processed using a histogram equalization technique. Then, the weighted Otsu-based segmentation algorithm is applied for segmenting the object regions from the pre-processed images. When using the weighted Otsu, the segmented grayscale images are not only clear but also retain the detailed features of grayscale images. Next, feature extraction is carried out by gray-level co-occurrence matrix (GLCM), median binary patterns (MBPs), and additive harmonic mean estimated local Gabor binary pattern (AHME-LGBP). The final step is classification using deep ensemble models, where the objects are classified by employing the ensemble deep learning technique, combining the models like the bidirectional long short-term memory (Bi-LSTM), recurrent neural network (RNN), and improved deep belief network (IDBN), which is trained with the features extracted previously. The combined models increase the accuracy of the results significantly. Furthermore, ensemble modeling reduces the variance and modeling method bias, which decreases the chances of overfitting. Compared to a single contributing model, ensemble models perform better and make better predictions. Additionally, an ensemble lessens the spread or dispersion of the model performance and prediction accuracy. Finally, the performance of the proposed model is related to the conventional models with respect to different measures. In the mean-case scenario, the proposed ensemble model has a minimum error value of 0.032, which is better related to other models. In both median- and best-case scenario studies, the ensemble model has a lower error value of 0.029 and 0.015.

Development of a combined radiomics and CT feature-based model for differentiating malignant from benign subcentimeter solid pulmonary nodules

BackgroundWe aimed to develop a combined model based on radiomics and computed tomography (CT) imaging features for use in differential diagnosis of benign and malignant subcentimeter (≤ 10 mm) solid pulmonary nodules (SSPNs).MethodsA total of 324 patients with SSPNs were analyzed retrospectively between May 2016 and June 2022. Malignant nodules (n = 158) were confirmed by pathology, and benign nodules (n = 166) were confirmed by follow-up or pathology. SSPNs were divided into training (n = 226) and testing (n = 98) cohorts. A total of 2107 radiomics features were extracted from contrast-enhanced CT. The clinical and CT characteristics retained after univariate and multivariable logistic regression analyses were used to develop the clinical model. The combined model was established by associating radiomics features with CT imaging features using logistic regression. The performance of each model was evaluated using the area under the receiver-operating characteristic curve (AUC).ResultsSix CT imaging features were independent predictors of SSPNs, and four radiomics features were selected after a dimensionality reduction. The combined model constructed by the logistic regression method had the best performance in differentiating malignant from benign SSPNs, with an AUC of 0.942 (95% confidence interval 0.918–0.966) in the training group and an AUC of 0.930 (0.902–0.957) in the testing group. The decision curve analysis showed that the combined model had clinical application value.ConclusionsThe combined model incorporating radiomics and CT imaging features had excellent discriminative ability and can potentially aid radiologists in diagnosing malignant from benign SSPNs.Relevance statementThe model combined radiomics features and clinical features achieved good efficiency in predicting malignant from benign SSPNs, having the potential to assist in early diagnosis of lung cancer and improving follow-up strategies in clinical work.Key points• We developed a pulmonary nodule diagnostic model including radiomics and CT features.• The model yielded the best performance in differentiating malignant from benign nodules.• The combined model had clinical application value and excellent discriminative ability.• The model can assist radiologists in diagnosing malignant from benign pulmonary nodules.Graphical

Prediction of Disease-Free Survival in Breast Cancer using Deep Learning with Ultrasound and Mammography: A Multicenter Study

BackgroundBreast cancer is a leading cause of cancer morbility and mortality in women. The possibility of overtreatment or inappropriate treatment exists, and methods for evaluating prognosis need to be improved. Materials and MethodsPatients (from January 2013 to December 2018) were recruited and divided into a training group and a testing group. All patients were followed for more than 3 years. Patients were divided into a disease-free group and a recurrence group based on follow up results at 3 years. Ultrasound (US) and mammography (MG) images were collected to establish deep learning models (DLMs) using ResNet50. Clinical data, MG, and US characteristics were collected to select independent prognostic factors using a cox proportional hazards model to establish a clinical model. DLM and independent prognostic factors were combined to establish a combined model. ResultsIn total, 1242 patients were included. Independent prognostic factors included age, neoadjuvant chemotherapy, HER2, orientation, blood flow, dubious calcification, and size. We established 5 models: the US DLM, MG DLM, US + MG DLM, clinical and combined model. The combined model using US images, MG images, and pathological, clinical, and radiographic characteristics had the highest predictive performance (AUC = 0.882 in the training group, AUC = 0.739 in the testing group). ConclusionDLMs based on the combination of US, MG, and clinical data have potential as predictive tools for breast cancer prognosis.