TB-NET: A Two-Branch Neural Network for Direction of Arrival Estimation under Model Imperfections

For direction of arrival (DoA) estimation, the data-driven deep-learning method has an advantage over the model-based methods since it is more robust against model imperfections. Conventionally, networks are based singly on regression or classification and may lead to unstable training and limited resolution. Alternatively, this paper proposes a two-branch neural network (TB-Net) that combines classification and regression in parallel. The grid-based classification branch is optimized by binary cross-entropy (BCE) loss and provides a mask that indicates the existence of the DoAs at predefined grids. The regression branch refines the DoA estimates by predicting the deviations from the grids. At the output layer, the outputs of the two branches are combined to obtain final DoA estimates. To achieve a lightweight model, only convolutional layers are used in the proposed TB-Net. The simulation results demonstrated that compared with the model-based and existing deep-learning methods, the proposed method can achieve higher DoA estimation accuracy in the presence of model imperfections and only has a size of 1.8 MB.

Joint Classification and Regression for Visual Tracking with Fully Convolutional Siamese Networks

Visual tracking of generic objects is one of the fundamental but challenging problems in computer vision. Here, we propose a novel fully convolutional Siamese network to solve visual tracking by directly predicting the target bounding box in an end-to-end manner. We first reformulate the visual tracking task as two subproblems: a classification problem for pixel category prediction and a regression task for object status estimation at this pixel. With this decomposition, we design a simple yet effective Siamese architecture based classification and regression framework, termed SiamCAR, which consists of two subnetworks: a Siamese subnetwork for feature extraction and a classification-regression subnetwork for direct bounding box prediction. Since the proposed framework is both proposal- and anchor-free, SiamCAR can avoid the tedious hyper-parameter tuning of anchors, considerably simplifying the training. To demonstrate that a much simpler tracking framework can achieve superior tracking results, we conduct extensive experiments and comparisons with state-of-the-art trackers on a few challenging benchmarks. Without bells and whistles, SiamCAR achieves leading performance with a real-time speed. Furthermore, the ablation study validates that the proposed framework is effective with various backbone networks, and can benefit from deeper networks. Code is available at https://github.com/ohhhyeahhh/SiamCAR.

Main Factors That Explain the Use of Fertilisers on Farms in the European Union

A deeper assessment of the main determinants associated with the use of fertilisers, for example, in the European Union farms may bring relevant insights about the respective frameworks and support to find more sustainable solutions. In this context, the main objective of this study is to identify factors that influence the use of fertilisers in the agricultural sector of the European Union regions. To achieve this objective, statistical information, at farm level, from the European Farm Accountancy Data Network was considered. These data were first analysed through exploratory approaches and after assessed with classification and regression tree methodologies. The results obtained provide interesting insights to promote a more sustainable development in the European farms, namely supporting the policymakers to design more adjusted measures and instruments. In addition, the fertilisers costs on the European Union farms are mainly explained by crop output, costs with inputs, current subsidies, utilised agricultural area, and gross investment.

Thresholding of prominent biomarkers of breast cancer on overall survival using classification and regression tree

BACKGROUND: HER2, ER, PR, and ERBB2 play a vital role in treating breast cancer. These are significant predictive and prognosis biomarkers of breast cancer. OBJECTIVE: We aim to obtain a unique biomarker-specific prediction on overall survival to know their survival and death risk. METHODS: Survival analysis is performed on classified data using Classification and Regression Tree (CART) analysis. Hazard ratio and Confidence Interval are computed using MLE and the Bayesian approach with the CPH model for univariate and multivariable illustrations. Validation of CART is executed with the Brier score, and accuracy and sensitivity are obtained using the k-nn classifier. RESULTS: Utilizing CART analysis, the cut-off value of continuous-valued biomarkers HER2, ER, PR, and ERBB2 are obtained as 14.707, 8.128, 13.153, and 6.884, respectively. Brier score of CART is 0.16 towards validation of methodology. Survival analysis gives a demonstration of the survival estimates with significant statistical strategies. CONCLUSIONS: Patients with breast cancer are at low risk of death, whose HER2 value is below its cut-off value, and ER, PR, and ERBB2 values are greater than their cut-off values. This comparison is with the patient having the opposite side of these cut-off values for the same biomarkers.

Intraoperative lactic acid concentration during liver transplantation and cutoff values to predict early mortality: a retrospective analysis of 3,338 cases

Background: We aimed to explore intraoperative lactic acid (LA) level distribution during liver transplantation (LT) and determine the optimal cutoff values to predict post-LT 30-day and 90-day mortality.Methods: Intraoperative LA data from 3,338 patients were collected between 2008 to 2019 and all-cause mortalities within 30 and 90 days were retrospectively reviewed. Of the three LA levels measured during preanhepatic, anhepatic, and neohepatic phase of LT, the peak LA level was selected to explore the distribution and predict early post-LT mortality. To determine the best cutoff values of LA, we used a classification and regression tree algorithm and maximally selected rank statistics with the smallest P value.Results: The median intraoperative LA level was 4.4 mmol/L (range: 0.5–34.7, interquartile range: 3.0–6.2 mmol/L). Of the 3,338 patients, 1,884 (56.4%) had LA levels > 4.0 mmol/L and 188 (5.6%) had LA levels > 10 mmol/L. Patients with LA levels > 16.7 mmol/L and 13.5–16.7 mmol/L showed significantly higher 30-day mortality rates of 58.3% and 21.2%, respectively. For the prediction of the 90-day mortality, 8.4 mmol/L of intraoperative LA was the best cutoff value.Conclusions: Approximately 6% of the LT recipients showed intraoperative hyperlactatemia of > 10 mmol/L during LT, and those with LA > 8.4 mmol/L were associated with significantly higher early post-LT mortality.

Identifikasi Website Phishing Menggunakan Algoritma Classification And Regression Trees (CART)

With the increase in internet users and the development of technology, the threats to its security are increasingly diverse. One of them is phishing which is the most important issue in cyberspace. Phishing is a threatening and trapping activity someone by luring the target to indirectly provide information to the trapper. The number of phishing crimes, this has the potential to cause several losses, one of which is namely about the loss of privacy of a person or company. This study aims to identify phishing websites. The Classification And Regression Trees (CART) algorithm is one of the classification algorithms, and the dataset in this research taken from the UCI Repository Learning obtained from the University of Huddersfield. The method used in this research is problem identification, data collection, pre-processing stage, use of the CART algorithm, validation and evaluation and withdrawal conclusion. Based on the test results obtained the value of accuracy of 95.28%. Thus the value of the accuracy obtained using the CART algorithm of 95.28% categorized very good classification.

Bias Correction Method of High-Resolution Satellite-Based Precipitation Product for Peninsular Malaysia

Satellite-based precipitation (SBP) is emerging as a reliable source for high-resolution rainfall estimates over the globe. However, uncertainty in SBP is still significant, limiting their use without evaluation and often without bias correction. The bias correction of SBP remained a challenge for atmospheric scientists. In this study, the performance of six SBPs, namely, SM2RAIN-ASCAT, IMERG, GsMap, CHIRPS, PERSIANN-CDS and PERSIANN-CSS in replicating observed daily rainfall at 364 stations over Peninsular Malaysia was evaluated. The bias of the most suitable SBP was corrected using a novel machine learning (ML)-based bias-correction method. The proposed bias-correction method consists of an ML classifier to correct the bias in estimating rainfall occurrence and an ML regression model to correct the amount of rainfall during rainfall events. The performance of different widely used ML algorithms for classification and regression were evaluated to select the suitable algorithms. IMERG showed better performance, showing a higher correlation coefficient (R2) of 0.57 and Kling-Gupta Efficiency (KGE) of 0.5 compared to the other products. The performance of random forest (RF) was better than the k-nearest neighbourhood (KNN) for both classification and regression. RF classified the rainfall events with a skill score of 0.38 and estimated the rainfall amount of a rainfall event with the modified Index of Agreement (md) of 0.56. Comparison of IMERG and bias-corrected IMERG (BIMERG) revealed an average reduction in RMSE by 55% in simulating observed rainfall. The proposed bias correction method performed much better when compared with the conventional bias correction methods such as linear scaling and quantile regression. The BIMERG could reliably replicate the spatial distribution of heavy rainfall events, indicating its potential for hydro-climatic studies like flood and drought monitoring in the study area.