Optimal Combination Method Research Articles

Multimodal AI Combining Clinical and Imaging Inputs Improves Prostate Cancer Detection.

Deep learning (DL) studies for the detection of clinically significant prostate cancer (csPCa) on magnetic resonance imaging (MRI) often overlook potentially relevant clinical parameters such as prostate-specific antigen, prostate volume, and age. This study explored the integration of clinical parameters and MRI-based DL to enhance diagnostic accuracy for csPCa on MRI. We retrospectively analyzed 932 biparametric prostate MRI examinations performed for suspected csPCa (ISUP ≥2) at 2 institutions. Each MRI scan was automatically analyzed by a previously developed DL model to detect and segment csPCa lesions. Three sets of features were extracted: DL lesion suspicion levels, clinical parameters (prostate-specific antigen, prostate volume, age), and MRI-based lesion volumes for all DL-detected lesions. Six multimodal artificial intelligence (AI) classifiers were trained for each combination of feature sets, employing both early (feature-level) and late (decision-level) information fusion methods. The diagnostic performance of each model was tested internally on 20% of center 1 data and externally on center 2 data (n = 529). Receiver operating characteristic comparisons determined the optimal feature combination and information fusion method and assessed the benefit of multimodal versus unimodal analysis. The optimal model performance was compared with a radiologist using PI-RADS. Internally, the multimodal AI integrating DL suspicion levels with clinical features via early fusion achieved the highest performance. Externally, it surpassed baselines using clinical parameters (0.77 vs 0.67 area under the curve [AUC], P < 0.001) and DL suspicion levels alone (AUC: 0.77 vs 0.70, P = 0.006). Early fusion outperformed late fusion in external data (0.77 vs 0.73 AUC, P = 0.005). No significant performance gaps were observed between multimodal AI and radiologist assessments (internal: 0.87 vs 0.88 AUC; external: 0.77 vs 0.75 AUC, both P > 0.05). Multimodal AI (combining DL suspicion levels and clinical parameters) outperforms clinical and MRI-only AI for csPCa detection. Early information fusion enhanced AI robustness in our multicenter setting. Incorporating lesion volumes did not enhance diagnostic efficacy.

Effect of Al(OH)3 prepared from fly ash on the structural and catalytic properties of g-C3N4-based materials

In order to find the optimal combination method of secondary utilization of fly ash and g-C3N4 modification, an efficient composite photocatalyst of γ-Al2O3/g-C3N4 was obtained by calcining the composite precursors of Al(OH)3/DCDA. The introduction of Al(OH)3 prepared by fly ash into the precursors causes hydrogen bonding interactions between Al(OH)3 and DCDA, which facilitate the removal of N atoms from the edges of the CN framework of g-C3N4 during condensation, and the composites prepared possess more cyano defects. In addition, γ-Al2O3 and g-C3N4 form a chemical bond at the interface, and this chemical bonding causes the density of the electron cloud in the vicinity of the N atoms to increase. Among them, the strongest chemical bonding between Al2O3 and g-C3N4 was observed in ACN-1, while the most cyanine defects were formed in ACN-1, which made ACN-1 exhibit the best photocatalytic degradation of methylene blue, which is 2.48 times higher than that of the pristine g-C3N4.

Internal Flow Characteristics of Centrifugal Pumps under Different Startup Combination Schemes

Pump station engineering is a water conservancy project used for long-distance water transfer, irrigation and drainage, and urban living and industrial water supply. Centrifugal pumps are one of the main pump types commonly used in pumping stations, and their operation is of considerable importance for the safety, stability, and efficient operation of pumping stations. This paper takes a large pumping station with seven centrifugal pump units as the research object and combines experimental research and numerical simulation. The axial flow velocity uniformity, average cross-sectional deviation angle, and hydraulic loss of the pump inlet section are evaluated, and the internal flow characteristics of the pump under different startup combination conditions are analyzed based on entropy generation and vorticity. This study also explores the operational performance of the pump station under different startup combination conditions, revealing the mutual influence mechanism between different startup combinations of pump stations and the internal and external characteristics of centrifugal pumps and introducing the optimal startup combination scheme for the pump station system. Research results indicate that the difference in energy loss of centrifugal pumps under different startup combinations is mainly manifested in the impeller and guide vane flow channels. For the two existing inlet flow channel structures in the pump station, the unit effectively operates when the inlet flow channel is tilted to the left. The optimal startup combination method of the pump station under different startup combinations is determined.

Harnessing the joint effect of approach bridges in arch bridge construction: an analytical study on thrust stiffness and elevation error mitigation

Achieving full equilibrium for the horizontal component force of the backstay in cable-stayed arch bridges is challenging, and the stiffness of the buckle tower has a notable influence on the overall shape of the main arch structure. Increased stiffness in the buckle tower leads to reduced construction complexity. Therefore, this study proposed a method of enhancing the longitudinal thrust stiffness of the buckle tower using the joint effect of approach bridges. A sensitivity analysis was conducted on the approach bridge–composite buckle tower structure to determine the optimal combination method, resulting in the formulation of an analytical expression for the thrust stiffness of this structure. In this study, numerical analysis was performed to explore the composition mechanism of the thrust stiffness influenced by the pier–girder connection, and we discussed the applicability of the joint effect of approach bridges during the cantilever assembly process of arch ribs. The following conclusions were obtained: 1) prior to installing the main girder of the approach bridge, when the steel buckle tower and the junction pier have already been secured, the most effective approach is to form a “T” rigid structure by firmly connecting the main girder of the approach bridge with the composite buckle tower. This configuration provides self-weight deflection and pier–girder rotation restriction effects. 2) The study presents analytical formulas for the completely rigid pier–girder connection of the approach bridge–composite buckle tower structure, partially rigid pier–girder connection, and pre-deviation. Combined with the calculation program, this can guide structural design. 3) When a large downward elevation error of the arch ribs occurs in the middle and later stages, the cable force needed to install new arch segments becomes overly large. Therefore, the joint effect of approach bridges can be utilized to substitute for a portion of the cable force, effectively reducing potential elevation errors that might arise in subsequent arch ribs in the absence of this joint effect.

Preclinical Study of Dual-Wavelength Light-Emitting Diode Therapy in an Osteoarthritis Rat Model.

To evaluate the efficacy of light-emitting diode (LED) and their dual-wavelengths as a treatment strategy for osteoarthritis. We induced osteoarthritis in male Sprague-Dawley rats by intra-articular injection of sodium iodoacetate into the right rear knee joint. The animals with lesions were divided into an untreated group and an LED-treated group (n=7 each). In the LED-treated group, the lesioned knee was irradiated with lasers (850 and 940 nm) and dose (3.15 J/cm2) for 20 minutes per session, twice a week for 4 weeks. Knee joint tissues were stained and scanned using an in vivo micro-computed tomography (CT) scanner. Serum interleukin (IL)-6 and IL-18 levels were determined using enzyme-linked immuno-sorbent assay. Several functional tests (lines crossed, rotational movement, rearing, and latency to remain rotating rod) were performed 24 hours before LED treatment and at 7, 14, 21, and 28 days after treatment. LED-treated rats showed improved locomotor function and suppressed matrix-degrading cytokines. Micro-CT images indicated that LED therapy had a preserving effect on cartilage and cortical bone. LED treatment using wavelengths of 850 and 940 nm resulted in significant functional, anatomical, and histologic improvements without adverse events in a rat model. Further research is required to determine the optimal wavelength, duration, and combination method, which will maximize treatment effectiveness.

Optimal Combination Method for Weights Loading of the Deadweight Force Standard Machine

Optimal Combination Method for Weights Loading of the Deadweight Force Standard Machine

Offshore wind power ramp prediction based on optimal combination model

ABSTRACT Wind power ramp event is a small probability and large hazard event, for effectively avoiding its impact on the grid, an offshore wind power ramp prediction method based on optimal combination model is proposed. First, on the basis of the output power data of existing offshore wind turbines, the data preprocessing of the wind power series is carried out by using the Variational Modal Decomposition method optimized by the novel Seagull Optimization Algorithm, which is decomposed into several Intrinsic Mode Function components and one residual component to extract the salient features of the power signal and reduce the data fluctuation. Second, the prediction models of Extreme Learning Machine and Bayesian optimized Long Short Term Memory network are built, respectively, while the optimal combined prediction method is adopted to combine the two single models for obtaining the optimal combined model. Individual components are treated as the inputs of the model, then the final offshore wind power is obtained by superimposing and integrating the prediction results of each component. Eventually, adopting the definition method to predict and characterize the offshore wind power ramp. The research shows that, compared with BP, RNN, LSTM and single model, the wind power prediction error of the combined model proposed in this paper is smaller, with RMSE of 71.10 kW, MAE of 50.26 kW and SMAPE of 0.01%, and it can completely predict 7 ramp events with a higher accuracy. Meanwhile, the applicability of the proposed method is verified by varying the time resolution. The final results show that the proposed method in this paper has a high accuracy in offshore wind power ramp prediction.

Multi-level arch characteristics and flow enhancement regulation of nano powders discharged from silo

Nanoparticles have broad application prospects, but their poor flowability poses a challenge to the handling and transportation. Here, we experimentally demonstrate that modulated pulsed aeration can destroy the consolidation of nano powder and achieve a breakthrough in silo discharge from clogging to flow. We confirm the multi-level arch structure in the silo discharge of nano powders: free-fall arch and cohesive arch. And the location of multi-level arch can be determined by the yield stress of material. Furthermore, the method of combined pulsed aeration was proposed to enhance the discharge flow. Specifically, the influence of modulation of pulsed airflow including frequency and duty cycle and aeration location configuration on nanoparticles silo discharge flow was explored. And the optimal combination method of double pulsed aeration was determined to eliminate the cohesive arch and greatly increase the discharge rate, which is close to the hypothesis liquid-like flow rate.

Enhancing Current Cardiorespiratory-based Approaches of Sleep Stage Classification by Temporal Feature Stacking.

This paper presents a generic method to enhance performance and incorporate temporal information for cardiorespiratory-based sleep stage classification with a limited feature set and limited data. The classification algorithm relies on random forests and a feature set extracted from long-time home monitoring for sleep analysis. Employing temporal feature stacking, the system could be significantly improved in terms of Cohen's κ and accuracy. The detection performance could be improved for three classes of sleep stages (Wake, REM, Non-REM sleep), four classes (Wake, Non-REM-Light sleep, Non-REM Deep sleep, REM sleep), and five classes (Wake, N1, N2, N3/4, REM sleep) from a κ of 0.44 to 0.58, 0.33 to 0.51, and 0.28 to 0.44 respectively by stacking features before and after the epoch to be classified. Further analysis was done for the optimal length and combination method for this stacking approach. Overall, three methods and a variable duration between 30 s and 30 min have been analyzed. Overnight recordings of 36 healthy subjects from the Interdisciplinary Center for Sleep Medicine at Charité-Universitätsmedizin Berlin and Leave-One-Out-Cross-Validation on a patient-level have been used to validate the method.Clinical relevance- The method can be employed generically to feature sets for (small scale) datasets to improve classification performance for classification problems with temporal relations with random forest classifiers.

A novel method for selecting the set optimal wavelength combination in multi-spectral transmission image

In the process of detecting heterogeneity in breast tissue based on multi-spectral transmission imaging, the detection accuracy will be affected due to the high redundancy degree of information between bands. In order to select the reasonable wavelength combination, this paper uses various nonlinear transformations to convert the multi-spectral images into spectral data for the first time, so as to select the set optimal wavelength combination based on the successive projections algorithm (SPA). Firstly, we design the collection experiment of 4-wavelength multi-spectral image. And then, K-SVD dictionary learning method, texture extraction method and gray correlation analysis method are used to obtain the feature spectral information. Finally, the set optimal wavelength combination is selected based on SPA. The experimental results show that random forest (RF) classification model and Faster-RCNN recognition models effectively verify that the combination of wavelengths 1,2,4 selected has the highest accuracy in the heterogeneous detection. In conclusion, this paper uses modulation-frame accumulation technique to improve the quality of multi-spectral transmission images. And based on the RF and Faster-RCNN models, the effectiveness of SPA-based optimal wavelength combination method proposed is verified, which will provide a new idea of feature wavelength selection for screening early breast masses through multi-spectral transmission imaging.

A Landslide Displacement Prediction Method with Iteration-Based Combined Strategy

Predicting landslide displacement is of great significance in geotechnical engineering. An iteration-based combined prediction method was proposed for predicting the landslide displacement in this paper. Firstly, the landslide displacement was predicted by 10 latest multivariable grey models, and then the final landslide displacement prediction value was obtained through an iteration-based combined strategy. Concurrently, the reliability of the quadratic programming-based combined prediction method (QPCPM) and the iteration-based combined prediction method (ICPM) was rigorously proved in this paper. In addition, the inapplicability conditions of the optimal weight-based combined prediction method (OWCPM) were pointed out. ICPM could be regarded as a simplified version of QPCPM. The Bazimen and Baishuihe landslides in the Three Gorges Reservoir area of China were used as numerical examples to elaborate the performance of ICPM. This paper also demonstrated the reliability of ICPM by considering the effects of rainfall and reservoir water level on landslide displacement. Overall, ICPM features in simple and easy calculation and has rosy engineering application prospects.

Design and analysis of dual mixed refrigerant processes for high-ethane content natural gas liquefaction

Recovery and purification of ethane has a significant impact on economic benefit improvement of the high-ethane content natural gas. However, current LNG-NGL integrated processes mainly focus on conventional natural gas, which are not applicable to natural gas with high ethane content. To fill this gap, three dual mixed refrigerant processes are proposed for simulation study of high-ethane content natural gas liquefaction. The proposed processes are optimized by a combination method of sequence optimization and genetic algorithm. Comparatively analysis is conducted to evaluate the three processes from the energetic and exergetic points of view. The results show that the power consumption of Process 3 which compressing natural gas after distillation is the lowest. For safety or other considerations, some common compositions of the mixed refrigerant may need to be removed under certain circumstances. Considering this, case studies of mixed refrigerant involving six composition combinations are carried out to investigate the effects of refrigerant selection on the process performance.

Restoration and Calibration of Tilting Hyperspectral Super-Resolution Image

Tilting sampling is a novel sampling mode for achieving a higher resolution of hyperspectral imagery. However, most studies on the tilting image have only focused on a single band, which loses the features of hyperspectral imagery. This study focuses on the restoration of tilting hyperspectral imagery and the practicality of its results. First, we reduced the huge data of tilting hyperspectral imagery by the p-value sparse matrix band selection method (pSMBS). Then, we restored the reduced imagery by optimal reciprocal cell combined modulation transfer function (MTF) method. Next, we built the relationship between the restored tilting image and the original normal image. We employed the least square method to solve the calibration equation for each band. Finally, the calibrated tilting image and original normal image were both classified by the unsupervised classification method (K-means) to confirm the practicality of calibrated tilting images in remote sensing applications. The results of classification demonstrate the optimal reciprocal cell combined MTF method can effectively restore the tilting image and the calibrated tiling image can be used in remote sensing applications. The restored and calibrated tilting image has a higher resolution and better spectral fidelity.

Optimal partner wavelength combination method applied to NIR spectroscopic analysis of human serum globulin

Human serum globulin (GLB), which contains various antibodies in healthy human serum, is of great significance for clinical trials and disease diagnosis. In this study, the GLB in human serum was rapidly analyzed by near infrared (NIR) spectroscopy without chemical reagents. Optimal partner wavelength combination (OPWC) method was employed for selecting discrete information wavelength. For the OPWC, the redundant wavelengths were removed by repeated projection iteration based on binary linear regression, and the result converged to stable number of wavelengths. By the way, the convergence of algorithm was proved theoretically. Moving window partial least squares (MW-PLS) and Monte Carlo uninformative variable elimination PLS (MC-UVE-PLS) methods, which are two well-performed wavelength selection methods, were also performed for comparison. The optimal models were obtained by the three methods, and the corresponding root-mean-square error of cross validation and correlation coefficient of prediction (SECV, RP,CV) were 0.813 g L−1 and 0.978 with OPWC combined with PLS (OPWC-PLS), and 0.804 g L−1 and 0.979 with MW-PLS, and 1.153 g L−1 and 0.948 with MC-UVE-PLS, respectively. The OPWC-PLS and MW-PLS methods achieved almost the same good results. However, the OPWC only contained 28 wavelengths, so it had obvious lower model complexity. Thus it can be seen that the OPWC-PLS has great prediction performance for GLB and its algorithm is convergent and rapid. The results provide important technical support for the rapid detection of serum.

Combined Optimization of Neural Network Fault Diagnosis Methods for Analog Circuits on Ships

Guo, S.; Li, H.; Wu, B.; Zhou, J.; Su, C., and Guan, C., 2020. Combined optimization of neural network fault diagnosis methods for analog circuits on ships. In: Zheng, C.W.; Wang, Q.; Zhan, C., and Yang, S.B. (eds.), Air-Sea Interaction and Coastal Environments of the Maritime and Polar Silk Roads. Journal of Coastal Research, Special Issue No. 99, pp. 158–164. Coconut Creek (Florida), ISSN 0749-0208.With increasing automation, electronic systems are becoming more widely used on ships. When electronic systems fail, it will greatly affect the safety of ship operation or even cause catastrophic accidents. Therefore, it is necessary to diagnose a circuit fault in order to repair the equipment in time. In electronic systems, more than 80% of the faults come from analog circuits. To obtain better fault diagnosis accuracy for analog circuits, neural network classification algorithms are often combined with optimization steps, such as circuit feature collection, feature engineering, regularization and so on, significantly affecting the accuracy of the classification algorithm, such as circuit feature collection, feature engineering, and regularization. However, the accuracy of analog circuit fault diagnosis is often not high in practical applications because of the tolerance of analog circuit components and other factors. To solve the above problems, this paper proposes a neural network combination optimization method based on hypothesis testing and applies it this method to the fault diagnosis of analog circuits on ships. This method uses hypothesis testing to combine and sort the optimization methods of each step in a neural network classification algorithm to obtain a model ranking based on the accuracy rate with mathematical statistics rules, thereby obtaining the optimal combination method. Finally, the validity of the method is verified by experiments.

Prediction of Agricultural plastic agricultural plastic film use based on combined prediction model

Although increasing the yield of crops, the large-scale use of agricultural plastic film in agricultural production, has caused damage to the ecological environment. This paper analyzes the current situation of the use of plastic agricultural plastic agricultural plastic film in China from 1999 to 2015. The GM(1, 1) model and the ARIMA(0, 2, 0) model are used to predict the mulch usage, and then the optimal weight combination method is used to obtain the grey-time series combination prediction model. The results show that the accuracy of synthetic prediction model is higher than that of the single model and has better applicability. The prediction results of the combined model can be used as a reference for the scientific use and management of agricultural plastic film in China.

Coil combination using linear deconvolution in k-space for phase imaging.

The combination of multi-channel data is a critical step for the imaging of phase and susceptibility contrast in magnetic resonance imaging (MRI). Magnitude-weighted phase combination methods often produce noise and aliasing artifacts in the magnitude images at accelerated imaging sceneries. To address this issue, an optimal coil combination method through deconvolution in k-space is proposed in this paper. The proposed method firstly employs the sum-of-squares and phase aligning method to yield a complex reference coil image which is then used to calculate the coil sensitivity and its Fourier transform. Then, the coil k-space combining weights is computed, taking into account the truncated frequency data of coil sensitivity and the acquired k-space data. Finally, combining the coil k-space data with the acquired weights generates the k-space data of proton distribution, with which both phase and magnitude information can be obtained straightforwardly. Both phantom and in vivo imaging experiments were conducted to evaluate the performance of the proposed method. Compared with magnitude-weighted method and MCPC-C, the proposed method can alleviate the phase cancellation in coil combination, resulting in a less wrapped phase. The proposed method provides an effective and efficient approach to combine multiple coil image in parallel MRI reconstruction, and has potential to benefit routine clinical practice in the future.

Research on the optimal combination and scheduling method of crowdsourcing members in a cloud design platform

Cloud design has become a potential emerging design service mode. More and more design service providers are clustered in a cloud design platform to become crowdsourcing members. Collaborative tasks published by the platform are usually performed by several crowdsourcing members, and the collaborative mode of crowdsourcing members is an asynchronous collaborative working mode. However, due to the variety of crowdsourcing members in terms of ability, time, and so on, how to combine crowdsourcing members into a rational crowdsourcing team has become a challenge. At the same time, due to the looseness and uncertainty of their collaborative mode, there is no effective guidance mechanism in the cooperation process. Therefore, we propose a method of crowdsourcing the optimal combination and scheduling of members. By evaluating the comprehensive abilities of crowdsourcing members, the method optimizes the selection of suitable crowdsourcing members for each subtask and combines them into a crowdsourcing team. At the same time, besides establishing a collaborative workflow simulation model to plan the timing of subtasks and the workflow of crowdsourcing members, the method also optimizes and schedules crowdsourcing members to process different subtasks in turn. Finally, in the case of the collaborative design task of a medical analgesia pump, this method is used to establish a rational crowdsourcing team for collaborative tasks and effectively plan the collaborative work process of crowdsourcing members. The results demonstrate that the proposed method is feasible and effective.

Improved Probability Prediction Method Research for Photovoltaic Power Output

Due to solar radiation and other meteorological factors, photovoltaic (PV) output is intermittent and random. Accurate and reliable photovoltaic power prediction can improve the stability and safety of grid operation. Compared to solar power point prediction, probabilistic prediction methods can provide more information about potential uncertainty. Therefore, this paper first proposes two kinds of photovoltaic output probability prediction models, which are improved sparse Gaussian process regression model (IMSPGP), and improved least squares support vector machine error prediction model (IMLSSVM). In order to make full use of the advantages of the different models, this paper proposes a combined forecasting method with divided-interval and variable weights, which divides one day into four intervals. The models are combined by the optimal combination method in each interval. The simulation results show that IMSPGP and IMLSSVM have better prediction accuracy than the original models, and the combination model obtained by the combination method proposed in this paper further improves the prediction performance.

A composite model of field reliability based on a generalized Arrhenius model and a support vector machine model for spindle systems

A spindle system is one of the key subsystems of machine tools, whose reliability affects machining precision and production cycle directly. In the field, spindle systems expose to operating environmental conditions and complex working conditions that are referred to as stresses in this article collectively, which can accelerate or decelerate the process of failure. In order to analyze field reliability of spindle systems, the main structure, failure modes of spindle systems are analyzed, and main stresses involved with reliability are determined preliminarily. Then, based on the failure mode and the characteristics of stresses, a linear relationship of stresses and field reliability is built based on generalized Arrhenius models assuming that stresses are independent of each other. The non-linear, coupling relationship of stresses is described by a support vector machine model, whose parameters are selected by cross-validation. Then, two models are integrated to a composite model for minimum assessment error using optimal combined forecasting method. Finally, the proposed model is validated by a real case study, and the assessment errors conform to the production requirement.