An accurate and efficient Large-for-Gestational-Age (LGA) classification system is developed to classify a fetus as LGA or non-LGA, which has the potential to assist paediatricians and experts in establishing a state-of-the-art LGA prognosis process. The performance of the proposed scheme is validated by using LGA dataset collected from the National Pre-Pregnancy and Examination Program of China (2010–2013). A master feature vector is created to establish primarily data pre-processing, which includes a features’ discretization process and the entertainment of missing values and data imbalance issues. A principal feature vector is formed using GridSearch-based Recursive Feature Elimination with Cross-Validation (RFECV) + Information Gain (IG) feature selection scheme followed by stacking to select, rank, and extract significant features from the LGA dataset. Based on the proposed scheme, different features subset are identified and provided to four different machine learning (ML) classifiers. The proposed GridSearch-based RFECV+IG feature selection scheme with stacking using SVM (linear kernel) best suits the said classification process followed by SVM (RBF kernel) and LR classifiers. The Decision Tree (DT) classifier is not suggested because of its low performance. The highest prediction precision, recall, accuracy, Area Under the Curve (AUC), specificity, and F1 scores of 0.92, 0.87, 0.92, 0.95, 0.95, and 0.89 are achieved with SVM (linear kernel) classifier using top ten principal features subset, which is, in fact higher than the baselines methods. Moreover, almost every classification scheme best performed with ten principal feature subsets. Therefore, the proposed scheme has the potential to establish an efficient LGA prognosis process using gestational parameters, which can assist paediatricians and experts to improve the health of a newborn using computer aided-diagnostic system.

For autonomous robots, 3D perception of environment is an essential tool, which can be used to achieve better navigation in an obstacle rich environment. This understanding requires a huge amount of computational resources; therefore, the real-time 3D reconstruction of surrounding environment has become a topic of interest for countless researchers in the recent past. Generally, for the outdoor 3D models, stereo cameras and laser depth measuring sensors are employed. The data collected through the laser ranging sensors is relatively accurate but sparse in nature. In this paper, we propose a novel mechanism for the incremental fusion of this sparse data to the dense but limited ranged data provided by the stereo cameras, to produce accurate dense depth maps in real-time over a resource limited mobile computing device. Evaluation of the proposed method shows that it outperforms the state-of-the-art reconstruction frameworks which only utilizes depth information from a single source.