Search

Rip Currents are contributing around 25 fatal drownings each year in Australia. Previous research has indicated that most of beachgoers cannot correctly identify a rip current, leaving them at risk of experiencing a drowning incident. Automated detection of rip currents could help to reduce drownings and assist lifeguards in supervision planning; however, varying beach conditions have made this challenging. This work presents the effectiveness of an improved lightweight framework for detecting rip currents: RipDet+ 1 1 This work is an extended work of our earlier work accepted in IJCNN (Rashid et al., 2020) and ICONIP (Rashid et al., 2021). This work presents a deep learning framework aided with residual mapping to predict based on a limited number of samples. Unlike our previous work, we present lightweight framework aided with residual mapping to predict based on a limited number of samples. , aided with residual mapping to boost the generalization performance. We have used Yolo-V3 architecture to build RipDet + framework and utilize pretrained weight by fully exploiting the detection training set from some base classes which in result quickly adapt the detection prediction to the available rip data. Extensive experiments are reported which show the effectiveness of RipDet+ architecture in achieving a detection accuracy of 98.55%, which is significantly greater compared to other state-of-the-art methods for Rip currents detection. [ABSTRACT FROM AUTHOR]

In an educational setting, a teacher plays a crucial role in various classroom teaching patterns. Similarly, mirroring this aspect of human learning, the learning using privileged information (LUPI) paradigm introduces additional information to instruct learning models during the training stage. A different approach to train the twin variant of the regression model is provided by the new least square twin support vector regression using privileged information (LSTSVR+). It integrates the LUPI paradigm to utilize additional sources of information into the least square twin support vector regression. The proposed LSTSVR+ solves system of linear equations which adds up to the efficiency of the model. Further, we also establish a generalization error bound based on the Rademacher complexity of the proposed LSTSVR+ and incorporate the structural risk minimization principle. The proposed LSTSVR+ fills the gap between the contemporary paradigm of LUPI and classical LSTSVR. Further, to assess the performance of the proposed model, we conduct numerical experiments along with the baseline models across artificially generated datasets and 21 real-world datasets. The various experiments and statistical analysis infer the superiority of the proposed model. Moreover, the proposed LSTSVR+ outperforms baseline models in real-world applications on time-series datasets. The link for the code of the proposed LSTSVR+ is as follows: https://github.com/mtanveer1/LSTSVR-plus. • Privileged information is fused with least twin SVR. • The regularization terms adhere to the SRM principle and prevent over-fitting. • LSTSVR-PI solves system of linear equations, leading to an efficient model. • The experimental results demonstrate the superiority of the proposed model. • The proposed model has a real-world application on time-series datasets. [ABSTRACT FROM AUTHOR]

Random Forest is an ensemble of decision trees based on the bagging and random subspace concepts. As suggested by Breiman, the strength of unstable learners and the diversity among them are the ensemble models' core strength. In this paper, we propose two approaches known as oblique and rotation double random forests. In the first approach, we propose rotation based double random forest. In rotation based double random forests, transformation or rotation of the feature space is generated at each node. At each node different random feature subspace is chosen for evaluation, hence the transformation at each node is different. Different transformations result in better diversity among the base learners and hence, better generalization performance. With the double random forest as base learner, the data at each node is transformed via two different transformations namely, principal component analysis and linear discriminant analysis. In the second approach, we propose oblique double random forest. Decision trees in random forest and double random forest are univariate, and this results in the generation of axis parallel split which fails to capture the geometric structure of the data. Also, the standard random forest may not grow sufficiently large decision trees resulting in suboptimal performance. To capture the geometric properties and to grow the decision trees of sufficient depth, we propose oblique double random forest. The oblique double random forest models are multivariate decision trees. At each non-leaf node, multisurface proximal support vector machine generates the optimal plane for better generalization performance. Also, different regularization techniques (Tikhonov regularization, axis-parallel split regularization, Null space regularization) are employed for tackling the small sample size problems in the decision trees of oblique double random forest. The proposed ensembles of decision trees produce trees with bigger size compared to the standard ensembles of decision trees as bagging is used at each non-leaf node which results in improved performance. The evaluation of the baseline models and the proposed oblique and rotation double random forest models is performed on benchmark 121 UCI datasets and real-world fisheries datasets. Both statistical analysis and the experimental results demonstrate the efficacy of the proposed oblique and rotation double random forest models compared to the baseline models on the benchmark datasets. [ABSTRACT FROM AUTHOR]