Electrocardiogram (ECG) analysis is crucial for the diagnosis of cardiovascular disease. However, real-world deployment faces three key challenges: (1) the need for large amounts of manually labeled ECG data, which is time-consuming to collect. (2) the necessity of flexible addressing issues such as variations in clinical data distribution, noise, and low data quality. (3) the requirement for models to generalize across ECG data from different application scenarios. To address these issues, we propose ECGMind, a self-supervised foundational model for various ECG classification tasks. ECGMind is trained on unlabeled data and utilizes a masked autoencoder (MAE) backbone to selectively mask critical regions (e.g., R waves), thereby promoting the reconstruction of diagnostically important features. A dynamic energy score adjusts the importance of each ECG patch based on reconstruction difficulty, prioritizing hard-to-reconstruct areas to enhance feature learning. Our experiments are conducted on both static and dynamic ECG datasets, involving different classification tasks. The results demonstrate ECGMind 's superior performance and scalability, offering a solution for both clinical and ambulatory ECG analysis. ECGMind has deployed as an intelligent diagnostic service at http://heartmind.ecgdb.com. The core code can be evaluated at https://github.com/tianti1/ECGMind.

Unsupervised Outlier Detection (UOD) is an important data mining task. With the advance of deep learning, deep Outlier Detection (OD) has received broad interest. Most deep UOD models are trained exclusively on clean datasets to learn the distribution of the normal data, which requires huge manual efforts to clean the real-world data if possible. Instead of relying on clean datasets, some approaches directly train and detect on unlabeled contaminated datasets, leading to the need for methods that are robust to such challenging conditions. Ensemble methods emerged as a superior solution to enhance model robustness against contaminated training sets. However, the training time is greatly increased by the ensemble mechanism.

Graph Neural Networks (GNNs) with data augmentation obtain promising results among existing solutions for graph classification. Mixup-based augmentation methods for graph classification have already achieved state-of-the-art performance. However, existing mixup-based augmentation methods either operate in the input space and thus face the challenge of balancing efficiency and accuracy, or directly conduct mixup in the latent space without similarity guarantee, thus leading to lacking semantic validity and limited performance. To address these limitations, this paper proposes$\mathcal {G}$-MixCon, a novel framework leveraging the strengths ofMixup-based augmentation and supervisedContrastive learning (SCL). To the best of our knowledge, this is the first attempt to develop an SCL-based approach for learning graph representations. Specifically, the mixup-based strategy within the latent space named$GDA_{gl}$and$GDA_{nl}$are proposed, which efficiently conduct linear interpolation between views of the node or graph level. Furthermore, we design a dual-objective loss function namedSupMixConthat can consider both the consistency among graphs and the distances between the original and augmented graph.SupMixConcan guide the training process for SCL in$\mathcal {G}$-MixCon while achieving a similarity guarantee. Comprehensive experiments are conducted on various real-world datasets, the results show that$\mathcal {G}$-MixCon demonstrably enhances performance, achieving an average accuracy increment of 6.24%, and significantly increases the robustness of GNNs against noisy labels.

Abstract In the real world, road networks with weight and label on edges can be applied in several application domains. The shortest path query with label restrictions has been receiving increasing attention recently. To efficiently answer such kind of queries, a novel index, namely Contraction Hierarchies with Label Restrictions (CHLR), is proposed in the literature. However, existing studies mainly focus on the static road networks and do not support the CHLR maintenance when the road networks are dynamically changed. Motivated by this, in this paper, we investigate the CHLR maintenance problem in dynamic road networks. We first devise a baseline approach to update CHLR by recomputing the potential affected shortcuts. However, many shortcuts recomputed in baseline do not change in fact, which leads to unnecessary overhead of the baseline. To overcome the drawbacks of baseline, we further propose a novel CHLR maintenance algorithm which can only travel little shortcuts through an update propagate chain with accuracy guarantee. Moreover, an optimization strategy is presented to further improve the efficiency of index maintenance. Considering the frequency of edge changes, we also propose a batch index maintenance algorithm to handle batch edge changes which can process a large number of edge changes at once. Furthermore, a parallel method is proposed to further accelerate calculations. Extensive and comprehensive experiments are conducted on real road networks. The experimental results demonstrate the efficiency and effectiveness of our proposed algorithms.

Abstract In this paper, we study the problem of selectivity estimation on set containment search. Given a query record Q and a record dataset $${\mathcal {S}}$$ S , we aim to accurately and efficiently estimate the selectivity of set containment search of query Q over $${\mathcal {S}}$$ S . We first extend existing distinct value estimating techniques to solve this problem and develop an inverted list and G-KMV sketch-based approach IL-GKMV. We analyze that the performance of IL-GKMV degrades with the increase in vocabulary size. Motivated by limitations of existing techniques and the inherent challenges of the problem, we resort to developing effective and efficient sampling approaches and propose an ordered trie structure-based sampling approach named OT-Sampling. OT-Sampling partitions records based on element frequency and occurrence patterns and is significantly more accurate compared with simple random sampling method and IL-GKMV. To further enhance the performance, a divide-and-conquer-based sampling approach, DC-Sampling, is presented with an inclusion/exclusion prefix to explore the pruning opportunities. Meanwhile, we consider weighted set containment selectivity estimation and devise stratified random sampling approach named StrRS. We theoretically analyze the proposed techniques regarding various accuracy estimators. Our comprehensive experiments on nine real datasets verify the effectiveness and efficiency of our proposed techniques.

With the pervasive availability of smart devices, billions of users' trajectories are recorded and collected. The aggregated human behaviors reveal users' interests and characteristics, becoming invaluable to reflect their demographic preference, i.e., gender, age, marital status and even personality, occupation. Occupation profiling from trajectory data is an attractive option for advertisement targeting and other applications, without severe privacy concerns. However, it carries great difficulties in sparsity and vagueness.

Location prediction is widely used to forecast users' next place to visit based on his/her mobility logs. It is an essential problem in location data processing, invaluable for surveillance, business, and personal applications. It is very challenging due to the sparsity issues of check-in data. An often ignored problem in recent studies is the variety across different check-in scenarios, which is becoming more urgent due to the increasing availability of more location check-in applications. In this paper, we propose a new feature fusion based prediction approach, GALLOP, i.e., GlobAL feature fused LOcation Prediction for different check-in scenarios. Based on the carefully designed feature extraction methods, we utilize a novel combined prediction framework. Specifically, we set out to utilize the density estimation model to profile geographical features, i.e., context information, the factorization method to extract collaborative information, and a graph structure to extract location transition patterns of users' temporal check-in sequence, i.e., content information. An empirical study on three different check-in datasets demonstrates impressive robustness and improvement of the proposed approach.

Electrocardiography is a common tool for detecting cardiovascular system diseases. In clinical, as the individual difference is an intrinsic feature of ECG, data distribution difference between training and testing data impacts on the accuracy of classifier. Automatic ECG classification satisfied clinical demand is urgently required. QRS is a main waves in a heartbeat. In this paper, we propose a complete framework for individual oriented QRS morphology variation analysis. The original signal is first preprocessed by re-sampling and smoothing, then symbolized by dynamic and static combined method. For similarity measure, an improved information entropy measure function based on the symbolic result is proposed and ECG domain knowledge is well utilized by the function. At last, the entropy function based unsupervised learning algorithm is presented for QRS complex similarity computation. Our algorithm dedicates to the individual data analysis combined with domain knowledge, which is free from any training data and more suitable for application. Comprehensive experiments show that the proposed entropy function achieves improvements over the general distance measure functions during QRS similarity measure. The clustering algorithm is effective at recognizing normal and abnormal QRS morphology.

Standard Electrocardiogram (ECG) database is prepared for testing the performance of automatic detection and classification algorithms. At present, there are three mainstream standard databases used by computer-aided ECG diagnosis researchers: MIT-BIH arrhythmia database, CSE multi-lead database and AHA database. By the progress of ECG in both equipment and diagnosis theory, fatal deficiency was found in these databases and a new one is needed for further studies. So Chinese Cardiovascular Disease Database (CCDD or CCD database), which contains 12-Lead ECG data and detailed features with diagnosis result is proposed. It is distinguished not only by improving the raw ECG data's technical parameters, but also introduces some morphology features. Investigation shows these features are utilized by experienced cardiologists effectively. CCDD is used in our group as well as aiming for other and others' projects in the future.