Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This article proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It increases the randomness (diversity) by drawing the cut-points randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest generally outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 35 classification and regression datasets. Remarkably, BoostForest tunes its parameters by simply sampling them randomly from a parameter pool, which can be easily specified, and its ensemble learning framework can also be used to combine many other base learners.

Dimensionality reduction is an important operation in information visualization, feature extraction, clustering, regression, and classification, especially for processing noisy high dimensional data. However, most existing approaches preserve either the global or the local structure of the data, but not both. Approaches that preserve only the global data structure, such as principal component analysis (PCA), are usually sensitive to outliers. Approaches that preserve only the local data structure, such as locality preserving projections, are usually unsupervised (and hence cannot use label information) and uses a fixed similarity graph. We propose a novel linear dimensionality reduction approach, supervised discriminative sparse PCA with adaptive neighbors (SDSPCAAN), to integrate neighborhood-free supervised discriminative sparse PCA and projected clustering with adaptive neighbors. As a result, both global and local data structures, as well as the label information, are used for better dimensionality reduction. Classification experiments on nine high-dimensional datasets validated the effectiveness and robustness of our proposed SDSPCAAN.

In this letter, measurements of the cross-loop antenna patterns in the Ocean State Measuring and Analyzing Radar type S (OSMAR-S) for monitoring ocean environments are discussed. First, the patterns of the cross-loop antenna are measured by using a moving transponder. The results are not so good, as expected, due to the unstable transmitting signals and impacts of the environments. Then, an improved measurement method of the cross-loop antenna patterns is presented. The transmitting antenna is fixed, and the cross-loop antenna is fixed on a turntable and rotated with it to receive signals coming from different directions. In addition, the cross-loop antenna is connected to capacitors to resonate at the operating frequency. Then, the receiving signals of the operating frequency are strengthened, and the effects of environment are reduced. The near-field and far-field experiments are performed, and the measured patterns are of “8” shapes. Impacts of metal obstacles are also discussed, which provide a basis for evaluating antenna erection of the OSMAR-S. The ocean currents calculated from the patterns measured by the method in this letter are compared with that measured by an acoustic Doppler current profiler. They are in a good agreement, which proves the validation of the measurement method.