Abstract: Rapid urbanization has made traffic accidents a health and development threat. Accurate urban accident forecasting improves police force pre-allocation and traffic administration and traveler route planning, minimizing injuries and damages. Off-the-shelf short-term accident forecasting…
Abstract: Repeated distance measure can solve many time series data mining problems. Similarity search, clustering, classification, anomaly detection, and segmentation are examples. For over two decades, the Dynamic Time Warping (DTW) distance measure has been…
Abstract: Data mining tasks have used nonnegative matrix factorization (NMF). Due to its high cost on large matrices, NMF acceleration is gaining popularity. However, since NMF is widely used in image and text analysis, it…
Abstract: GPS enabled massive spatiotemporal trajectories. Researchers used this growing trend to find human mobility patterns. Semantic absence, bias, and complexity still hinder semantic pattern extraction. To solve the above three problems, we invented and…
Abstract: Complex network analysis is difficult and has garnered attention. Representing nodes as low-dimensional dense vectors can help. However, citation and email networks change over time. Most recent embedding methods only embed static networks. Thus,…
Abstract: Information propagation, decision making, and emergency prevention depend on social media event popularity prediction. Existing methods only predict single attributes like messages, hashtags, and images, which are not enough to represent complex social event…
Abstract: SSE addresses data outsourcing privacy, operability, and confidentiality. Most SSE schemes assume the cloud is honest but curious. Not always. Even if a malicious cloud supported verification, integrity, or freshness checking, performance and security…
Abstract: Network motif discovery, community detection, and frequent subgraph mining require subgraph enumeration. Recent works parallelize subgraph enumeration using GPUs to accelerate execution. Set intersection operations take up to 95% of the processing time in…
Abstract: Big data applications generate massive amounts of high-dimensional, real-time, streaming data. These applications require effective and efficient data stream clustering. Well-known data stream clustering algorithms based on the popular online-offline framework still face major…
Abstract: Time-series shapelets, discriminative subsequences, are effective for time series classification (tsc). Tsc accuracy depends on shapelet quality. However, major research has focused on accurate models from some shapelet candidates. Existing studies use simple methods…
Abstract: Social media and bibliographic datasets can be graphed. Clustering graphs reveals data structure. Node attributes in attributed graphs can improve clustering. Attributed graph clustering methods typically separate structural and attribute similarity. This paper models…
Abstract: HINs are used to model information systems with multi-type objects and relations. Homogeneous graphs have one type of nodes and edges. Web search, link prediction, and clustering require measuring object similarities. HIN similarity measures…
WhatsApp us