No abstract

Background: Medical image segmentation plays a vital role in computer-aided diagnosis (CAD) systems. Both convolutional neural networks (CNNs) with strong local information extraction capacities and transformers with excellent global representation capacities have achieved remarkable performance in medical image segmentation. However, because of the semantic differences between local and global features, how to combine convolution and transformers effectively is an important challenge in medical image segmentation. Methods: In this paper, we proposed TransConver, a U-shaped segmentation network based on convolution and transformer for automatic and accurate brain tumor segmentation in MRI images. Unlike the recently proposed transformer and convolution based models, we proposed a parallel module named transformerconvolution inception (TC-inception), which extracts local and global information via convolution blocks and transformer blocks, respectively, and integrates them by a cross-attention fusion with global and local feature (CAFGL) mechanism. Meanwhile, the improved skip connection structure named skip connection with cross-attention fusion (SCCAF) mechanism can alleviate the semantic differences between encoder features and decoder features for better feature fusion. In addition, we designed 2D-TransConver and 3D-TransConver for 2D and 3D brain tumor segmentation tasks, respectively, and verified the performance and advantage of our model through brain tumor datasets. Results: We trained our model on 335 cases from the training dataset of MICCAI BraTS2019 and evaluated the model's performance based on 66 cases from MICCAI BraTS2018 and 125 cases from MICCAI BraTS2019. Our TransConver achieved the best average Dice score of 83.72% and 86.32% on BraTS2019 and BraTS2018, respectively. Conclusions: We proposed a transformer and convolution parallel network named TransConver for brain tumor segmentation. The TC-Inception module effectively extracts global information while retaining local details. The experimental results demonstrated that good segmentation requires the model to extract local fine-grained details and global semantic information simultaneously, and our TransConver effectively improves the accuracy of brain tumor segmentation.

We consider the problem of learning predictive models from longitudinal data, consisting of irregularly repeated, sparse observations from a set of individuals over time. Such data often exhibit longitudinal correlation (LC) (correlations among observations for each individual over time), cluster correlation (CC) (correlations among individuals that have similar characteristics), or both. These correlations are often accounted for using mixed effects models that include fixed effects and random effects, where the fixed effects capture the regression parameters that are shared by all individuals, whereas random effects capture those parameters that vary across individuals. However, the current state-of-the-art methods are unable to select the most predictive fixed effects and random effects from a large number of variables, while accounting for complex correlation structure in the data and non-linear interactions among the variables. We propose Longitudinal Multi-Level Factorization Machine (LMLFM), to the best of our knowledge, the first model to address these challenges in learning predictive models from longitudinal data. We establish the convergence properties, and analyze the computational complexity, of LMLFM. We present results of experiments with both simulated and real-world longitudinal data which show that LMLFM outperforms the state-of-the-art methods in terms of predictive accuracy, variable selection ability, and scalability to data with large number of variables. The code and supplemental material is available at https://github.com/junjieliang672/LMLFM.

Online mobile advertising plays a vital financial role in supporting free mobile apps, but detecting malicious apps publishers who generate fraudulent actions on the advertisements hosted on their apps is difficult, since fraudulent traffic often mimics behaviors of legitimate users and evolves rapidly. In this paper, we propose a novel bipartite graph-based propagation approach, iBGP, for mobile apps advertising fraud detection in large advertising system. We exploit the characteristics of mobile advertising user’s behavior and identify two persistent patterns: power law distribution and pertinence and propose an automatic initial score learning algorithm to formulate both concepts to learn the initial scores of non-seed nodes. We propose a weighted graph propagation algorithm to propagate the scores of all nodes in the user-app bipartite graphs until convergence. To extend our approach for large-scale settings, we decompose the objective function of the initial score learning model into separate one-dimensional problems and parallelize the whole approach on an Apache Spark cluster. iBGP was applied on a large synthetic dataset and a large real-world mobile advertising dataset; experiment results demonstrate that iBGP significantly outperforms other popular graph-based propagation methods.

No abstract

Supervised machine learning classifiers have been widely used for attack detection, but their training requires abundant high-quality labels. Unfortunately, high-quality labels are difficult to obtain in practice due to the high cost of data labeling and the constant evolution of attackers. Without such labels, it is challenging to train and deploy targeted countermeasures. In this paper, we propose FARE, a clustering method to enable fine-grained attack categorization under low-quality labels. We focus on two common issues in data labels: 1) missing labels for certain attack classes or families; and 2) only having coarsegrained labels available for different attack types. The core idea of FARE is to take full advantage of the limited labels while using the underlying data distribution to consolidate the lowquality labels. We design an ensemble model to fuse the results of multiple unsupervised learning algorithms with the given labels to mitigate the negative impact of missing classes and coarsegrained labels. We then train an input transformation network to map the input data into a low-dimensional latent space for fine-grained clustering. Using two security datasets (Android malware and network intrusion traces), we show that FARE significantly outperforms the state-of-the-art (semi-)supervised learning methods in clustering quality/correctness. Further, we perform an initial deployment of FARE by working with a large e-commerce service to detect fraudulent accounts. With realworld A/B tests and manual investigation, we demonstrate the effectiveness of FARE to catch previously-unseen frauds. Proposed Solution. In this paper, we aim to enable finegrained attack categorization using low-quality labels. The goal is to discover the clustering structures in the data to assist human analysts to derive high-quality labels. We propose FARE, a semi-supervised method to address the issues of both missing classes and coarse-grained labels in poorlylabeled datasets. At the high-level, FARE's input is a dataset where only a small portion of the data is labeled, and the labels are of a low-quality. After running FARE, it outputs the clustering assignment for all the data samples. The data samples are expected to be either correctly clustered under the known labels or form new groups to represent the new labels. By correctly recovering the clustering structures in the input dataset, FARE provides the much-needed support for human analysts to generate high-quality labels. The core idea of FARE is to take full advantage of the limited labels while using the underlying data distribution to

We propose Top-N-Rank, a novel family of listwise Learning-to-Rank models for reliably recommending the N top-ranked items. The proposed models optimize a variant of the widely used discounted cumulative gain (DCG) objective function which differs from DCG in two important aspects: (i) It limits the evaluation of DCG only on the top N items in the ranked lists, thereby eliminating the impact of low-ranked items on the learned ranking function; and (ii) it incorporates weights that allow the model to leverage multiple types of implicit feedback with differing levels of reliability or trustworthiness. Because the resulting objective function is non-smooth and hence challenging to optimize, we consider two smooth approximations of the objective function, using the traditional sigmoid function and the rectified linear unit (ReLU). We propose a family of learning-to-rank algorithms (Top-N-Rank) that work with any smooth objective function. Then, a more efficient variant, Top-N-Rank.ReLU, is introduced, which effectively exploits the properties of ReLU function to reduce the computational complexity of Top-N-Rank from quadratic to linear in the average number of items rated by users. The results of our experiments using two widely used benchmarks, namely, the MovieLens data set and the Amazon Video Games data set demonstrate that: (i) The "top-N truncation" of the objective function substantially improves the ranking quality of the top N recommendations; (ii) using the ReLU for smoothing the objective function yields significant improvement in both ranking quality as well as runtime as compared to using the sigmoid; and (iii) Top-N-Rank.ReLU substantially outperforms the well-performing list-wise ranking methods in terms of ranking quality.

Laminar burning velocities and Markstein lengths of premixed methane−n-heptane−air mixtures were experimentally investigated at an initial pressure of 0.1 MPa, initial temperatures of 358, 393, and 428 K, and equivalence ratios of 0.7−1.5. The methane content in the methane−n-heptane mixtures ranges from 0 to 1. The experiments were conducted in a combustion chamber with central ignition. In the present study, the difference between the linear and nonlinear extrapolation methods was analyzed quantitatively for methane−n-heptane−air flames. Comparisons of the laminar burning velocities of methane−air and n-heptane−air flames were conducted, respectively, between the present and other studies. Subsequently, effects of the initial temperature and methane content on the laminar burning velocity and flame instability of methane−n-heptane−air mixtures were analyzed. Then, the critical methane content at which the laminar burning velocity and flame instability of methane−n-heptane−air flames start to change relatively significantly was explored. The results show that the laminar burning velocities of methane−air and n-heptane−air flames measured in the present study are in good agreement with the data available in the literature. Laminar burning velocities and flame instabilities of methane−n-heptane−air flames seem to be less sensitive to the methane content when the methane content is below 0.75. The change in the initial temperature tends to diminish the difference in the laminar burning velocity between methane−air and n-heptane−air flames and only has weak effects on the flame instability of methane−n-heptane−air mixtures. According to variations of the laminar burning velocities and Markstein lengths of methane−n-heptane−air flames with the methane content, the value of 0.75 can be treated preliminarily as the critical methane content.