A hierarchical temporal attention-based LSTM encoder-decoder model for individual mobility prediction.

Prediction of individual mobility is crucial in human mobility related applications. Whereas, existing research on individual mobility prediction mainly focuses on next location prediction and short-term dependencies between traveling locations. Long-term location sequence prediction is of great importance for long-time traffic planning and location advertising, and long-term dependencies exist as individual mobility regularity typically occurs daily and weekly. This paper proposes a novel hierarchical temporal attention-based LSTM encoder-decoder model for individual location sequence prediction. The proposed hierarchical attention mechanism captures both long-term and short-term dependencies underlying in individual longitudinal trajectories, and uncovers frequential and periodical mobility patterns in an interpretable manner by incorporating the calendar cycle of individual travel regularities into location prediction. More specifically, the hierarchical attention consists of local temporal attention to identify highly related locations in each day, and global temporal attention to discern important travel regularities over a week. Experiments on individual trajectory datasets with varying degree of traveling uncertainty demonstrate that our method outperforms four baseline methods on three evaluation metrics. In addition, we explore the interpretability of the proposed model in understanding individual daily, and weekly mobility patterns by visualizing the temporal attention weights and frequent traveling patterns associated with locations.

Clustering by measuring local direction centrality for data with heterogeneous density and weak connectivity.

Clustering is a powerful machine learning method for discovering similar patterns according to the proximity of elements in feature space. It is widely used in computer science, bioscience, geoscience, and economics. Although the state-of-the-art partition-based and connectivity-based clustering methods have been developed, weak connectivity and heterogeneous density in data impede their effectiveness. In this work, we propose a boundary-seeking Clustering algorithm using the local Direction Centrality (CDC). It adopts a density-independent metric based on the distribution of K-nearest neighbors (KNNs) to distinguish between internal and boundary points. The boundary points generate enclosed cages to bind the connections of internal points, thereby preventing cross-cluster connections and separating weakly-connected clusters. We demonstrate the validity of CDC by detecting complex structured clusters in challenging synthetic datasets, identifying cell types from single-cell RNA sequencing (scRNA-seq) and mass cytometry (CyTOF) data, recognizing speakers on voice corpuses, and testifying on various types of real-world benchmarks.

Insights From Y-STRs: Forensic Characteristics, Genetic Affinities, and Linguistic Classifications of Guangdong Hakka and She Groups.

Guangdong province is situated in the south of China with a population size of 113.46 million. Hakka is officially recognized as a branch of Han Chinese, and She is the official minority group in mainland China. There are approximately 25 million Hakka people who mainly live in the East and North regions of China, while there are only 0.7 million She people. The genetic characterization and forensic parameters of these two groups are poorly defined (She) or still need to be explored (Hakka). In this study, we have genotyped 475 unrelated Guangdong males (260 Hakka and 215 She) with Promega PowerPlex® Y23 System. A total of 176 and 155 different alleles were observed across all 23 Y-STRs for Guangdong Hakka (with a range of allele frequencies from 0.0038 to 0.7423) and Guangdong She (0.0047-0.8605), respectively. The gene diversity ranged from 0.4877 to 0.9671 (Guangdong Hakka) and 0.3277-0.9526 (Guangdong She), while the haplotype diversities were 0.9994 and 0.9939 for Guangdong Hakka and Guangdong She, with discrimination capacity values of 0.8885 and 0.5674, respectively. With reference to geographical and linguistic scales, the phylogenetic analyses showed us that Guangdong Hakka has a close relationship with Southern Han, and the genetic pool of Guangdong Hakka was influenced by surrounding Han populations. The predominant haplogroups of the Guangdong She group were O2-M122 and O2a2a1a2-M7, while Guangdong She clustered with other Tibeto-Burman language-speaking populations (Guizhou Tujia and Hunan Tujia), which shows us that the Guangdong She group is one of the branches of Tibeto-Burman populations and the Huonie dialect of She languages may be a branch of Tibeto-Burman language families.