Medical Image Interpolation Using Recurrent Type-2 Fuzzy Neural Network

An imbalance-aware deep neural network for early prediction of preeclampsia

Preeclampsia (PE) is a hypertensive complication affecting 8-10% of US pregnancies annually. While there is no cure for PE, aspirin may reduce complications for those at high risk for PE. Furthermore, PE disproportionately affects racial minorities, with a higher burden of morbidity and mortality. Previous studies have shown early prediction of PE would allow for prevention. We approached the prediction of PE using a new method based on a cost-sensitive deep neural network (CSDNN) by considering the severe imbalance and sparse nature of the data, as well as racial disparities. We validated our model using large extant rich data sources that represent a diverse cohort of minority populations in the US. These include Texas Public Use Data Files (PUDF), Oklahoma PUDF, and the Magee Obstetric Medical and Infant (MOMI) databases. We identified the most influential clinical and demographic features (predictor variables) relevant to PE for both general populations and smaller racial groups. We also investigated the effectiveness of multiple network architectures using three hyperparameter optimization algorithms: Bayesian optimization, Hyperband, and random search. Our proposed models equipped with focal loss function yield superior and reliable prediction performance compared with the state-of-the-art techniques with an average area under the curve (AUC) of 66.3% and 63.5% for the Texas and Oklahoma PUDF respectively, while the CSDNN model with weighted cross-entropy loss function outperforms with an AUC of 76.5% for the MOMI data. Furthermore, our CSDNN model equipped with focal loss function leads to an AUC of 66.7% for Texas African American and 57.1% for Native American. The best results are obtained with 62.3% AUC with CSDNN with weighted cross-entropy loss function for Oklahoma African American, 58% AUC with DNN and balanced batch for Oklahoma Native American, and 72.4% AUC using either CSDNN with weighted cross-entropy loss function or CSDNN with focal loss with balanced batch method for MOMI African American dataset. Our results provide the first evidence of the predictive power of clinical databases for PE prediction among minority populations.

Predicting the Lateral Load Carrying Capacity of Reinforced Concrete Rectangular Columns: Gene Expression Programming

This research presents a novel approach of artificial intelligence (AI) based gene expression programming (GEP) for predicting the lateral load carrying capacity of RC rectangular columns when subjected to earthquake loading. To achieve the desired research objective, an experimental database assembled by the Pacific Earthquake Engineering Research (PEER) center consisting of 250 cyclic tested samples of RC rectangular columns was employed. Seven input variables of these column samples were utilized to develop the coveted analytical models against the established capacity outputs. The selection of these input variables was based on the linear regression and cosine amplitude method. Based on the GEP modelling results, two analytical models were proposed for computing the flexural and shear capacity of RC rectangular columns. The performance of both these models was evaluated based on the four key fitness indicators, i.e., coefficient of determination (R²), root mean squared error (RMSE), mean absolute error (MAE), and root relative squared error (RRSE). From the performance evaluation results of these models, R², RMSE, MAE, and RRSE were found to be 0.96, 53.41, 38.12, and 0.20, respectively, for the flexural capacity model, and 0.95, 39.47, 28.77, and 0.22, respectively, for the shear capacity model. In addition to these fitness criteria, the performance of the proposed models was also assessed by making a comparison with the American design code of concrete structures ACI 318-19. The ACI model reported R², RMSE, MAE, and RRSE to be 0.88, 101.86, 51.74, and 0.39, respectively, for flexural capacity, and 0.87, 238.74, 183.66, and 1.35, respectively, for shear capacity outputs. The comparison depicted a better performance and higher accuracy of the proposed models as compared to that of ACI 318-19.

How Sustainable Is People’s Travel to Reach Public Transit Stations to Go to Work? A Machine Learning Approach to Reveal Complex Relationships

Several previous studies examined the variables of public-transit-related walking and privately owned vehicles (POVs) to go to work. However, most studies neglect the possible non-linear relationships between these variables and other potential variables. Using the 2017 U.S. National Household Travel Survey, we employ the Bayesian Network algorithm to evaluate the non-linear and interaction impacts of health condition attributes, work trip attributes, work attributes, and individual and household attributes on walking and privately owned vehicles to reach public transit stations to go to work in California. The authors found that the trip time to public transit stations is the most important factor in individuals’ walking decision to reach public transit stations. Additionally, it was found that this factor was mediated by population density. For the POV model, the population density was identified as the most important factor and was mediated by travel time to work. These findings suggest that encouraging individuals to walk to public transit stations to go to work in California may be accomplished by adopting planning practices that support dense urban growth and, as a result, reduce trip times to transit stations.

An effective model for predicting serum albumin level in hemodialysis patients

Patients on hemodialysis (HD) are known to be at an increased risk of mortality. Hypoalbuminemia is one of the most important risk factors of death in HD patients, and is an independent risk factor for all-cause mortality that is associated with cardiac death, infection, and Protein-Energy Wasting (PEW). It is a clinical challenge to elevate serum albumin level. In addition, predicting trends in serum albumin level is effective for personalized treatment of hypoalbuminemia. In this study, we analyzed a total of 3069 records collected from 314 HD patients using a machine learning method that is based on an improved binary mutant quantum grey wolf optimizer (MQGWO) combined with Fuzzy K-Nearest Neighbor (FKNN). The performance of the proposed MQGWO method was evaluated using a series of experiments including global optimization experiments, feature selection experiments on open data sets, and prediction experiments on an HD dataset. The experimental results showed that the most critical relevant indicators such as age, presence or absence of diabetes, dialysis vintage, and baseline albumin can be identified by feature selection. Remarkably, the accuracy and the specificity of the method were 98.39% and 96.77%, respectively, demonstrating that this model has great potential to be used for detecting serum albumin level trends in HD patients.

Multi-Threshold Image Segmentation of Maize Diseases Based on Elite Comprehensive Particle Swarm Optimization and Otsu

Maize is a major global food crop and as one of the most productive grain crops, it can be eaten; it is also a good feed for the development of animal husbandry and essential raw material for light industry, chemical industry, medicine, and health. Diseases are the main factor limiting the high and stable yield of maize. Scientific and practical identification is a vital link to reduce the damage of diseases and accurate segmentation of disease spots is one of the fundamental techniques for disease identification. However, one single method cannot achieve a good segmentation effect to meet the diversity and complexity of disease spots. In order to solve the shortcomings of noise interference and oversegmentation in the Otsu segmentation method, a non-local mean filtered two-dimensional histogram was used to remove the noise in disease images and a new elite strategy improved comprehensive particle swarm optimization (PSO) method was used to find the optimal segmentation threshold of the objective function in this study. The experimental results of segmenting three kinds of maize foliar disease images show that the segmentation effect of this method is better than other similar algorithms and it has better convergence and stability.

Maximum-Likelihood-Based Adaptive and Intelligent Computing for Nonlinear System Identification

Most real-time systems are nonlinear in nature, and their optimization is very difficult due to inherit stiffness and complex system representation. The computational intelligent algorithms of evolutionary computing paradigm (ECP) effectively solve various complex, nonlinear optimization problems. The differential evolution algorithm (DEA) is one of the most important approaches in ECP, which outperforms other standard approaches in terms of accuracy and convergence performance. In this study, a novel application of a recently proposed variant of DEA, the so-called, maximum-likelihood-based, adaptive, differential evolution algorithm (ADEA), is investigated for the identification of nonlinear Hammerstein output error (HOE) systems that are widely used to model different nonlinear processes of engineering and applied sciences. The performance of the ADEA is evaluated by taking polynomial- and sigmoidal-type nonlinearities in two case studies of HOE systems. Moreover, the robustness of the proposed scheme is examined for different noise levels. Reliability and consistent accuracy are assessed through multiple independent trials of the scheme. The convergence, accuracy, robustness and reliability of the ADEA are carefully examined for HOE identification in comparison with the standard counterpart of the DEA. The ADEA achieves the fitness values of 1.43 × 10−8 and 3.46 × 10−9 for a population size of 80 and 100, respectively, in the HOE system identification problem of case study 1 for a 0.01 nose level, while the respective fitness values in the case of DEA are 1.43 × 10−6 and 3.46 × 10−7. The ADEA is more statistically consistent but less complex when compared to the DEA due to the extra operations involved in introducing the adaptiveness during the mutation and crossover. The current study may consider the approach of effective nonlinear system identification as a step further in developing ECP-based computational intelligence.