An accurate and efficient Large-for-Gestational-Age (LGA) classification system isdeveloped to classify a fetus as LGA or non-LGA, which has the potential to assist paediatricians andexperts in establishing a state-of-the-art LGA prognosis process. The performance of the proposedscheme is validated by using LGA dataset collected from the National Pre-Pregnancy and ExaminationProgram of China (2010–2013). A master feature vector is created to establish primarily datapre-processing, which includes a features’ discretization process and the entertainment of missingvalues and data imbalance issues. A principal feature vector is formed using GridSearch-basedRecursive Feature Elimination with Cross-Validation (RFECV) + Information Gain (IG) featureselection scheme followed by stacking to select, rank, and extract significant features from the LGAdataset. Based on the proposed scheme, different features subset are identified and provided tofour different machine learning (ML) classifiers. The proposed GridSearch-based RFECV+IG featureselection scheme with stacking using SVM (linear kernel) best suits the said classification processfollowed by SVM (RBF kernel) and LR classifiers. The Decision Tree (DT) classifier is not suggestedbecause of its low performance. The highest prediction precision, recall, accuracy, Area Underthe Curve (AUC), specificity, and F1 scores of 0.92, 0.87, 0.92, 0.95, 0.95, and 0.89 are achievedwith SVM (linear kernel) classifier using top ten principal features subset, which is, in fact higherthan the baselines methods. Moreover, almost every classification scheme best performed with tenprincipal feature subsets. Therefore, the proposed scheme has the potential to establish an efficientLGA prognosis process using gestational parameters, which can assist paediatricians and experts toimprove the health of a newborn using computer aided-diagnostic system.
3D reconstruction from mobile image sensors is crucial for many offline-inspection and online robotic application. While several techniques are known today to deliver high accuracy 3D models from images via offline-processing, 3D reconstruction in real-time remains a major goal still to achieve. This work focuses on incremental 3D modeling from error prone depth image data, since standard 3D fusion techniques are tailored on accurate depth data from active sensors such as the Kinect. Imprecise depth data is usually provided by stereo camera sensors or simultaneous localization and mapping (SLAM) techniques. This work proposes an incremental extension of the total variation (TV) filtering technique, which is shown to reduce the errors of the reconstructed 3D model by up to 77% compared to state of the art techniques.
Multipath (MP) and/or Non Line-Of-Sight (NLOS) reception remains a potential vulnerability to satellite-based positioning and navigation systems in high multipath environments, such as an urban canyon. In such an environment, satellite signals are reflected, scattered or faded, and sometimes completely blocked by roofs and walls of high-rise buildings, fly-over bridges, complex road structures, etc. making positioning and navigation information inaccurate, unreliable, and largely unavailable. The magnitude of the positioning error depends on the satellite visibility, geometric distribution of satellites in the sky, and received signal quality and characteristics. The quality of the received signal (i.e. its statistical characteristics) can significantly vary in different environments and these variations can reflect in signal strength or power, range measurements (i.e. path delay and phase difference), and frequency, all of which distort the correlation curve between the received signal and receiver-generated replicas, resulting in range errors of tens of meters. Therefore, in order to meet stringent requirements defined for the Standard Positioning Service (SPS), the characterization of distortions that could significantly affect a Global Navigation Satellite System (GNSS) signal is essentially important. The scope of this paper is to detect possible imperfections/deviations in the GNSS signal characteristics that can occur due to MP or NLOS reception and analyze its effects. For this purpose, analysis of fading patterns in received signal strength (i.e. Carrier-to-Noise Ratio and strength fluctuations) is carried out in both clear LOS and high MP environment and then its impact on satellite lock state (i.e. tracking) is assessed. Furthermore, phase fluctuations and range residuals are computed to analyze the effects of path delays. The results show that significant variations can occur in GNSS signal characteristics in the MP environment that may result in loss of lock event and inaccurate/faulty range measurements.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.