Hsun Ping Hsieh

U-Air: when urban air quality inference meets big data

Information about urban air quality, e.g., the concentration of PM2.5, is of great importance to protect human health and control air pollution. While there are limited air-quality-monitor-stations in a city, air quality varies in urban spaces non-linearly and depends on multiple factors, such as meteorology, traffic volume, and land uses. In this paper, we infer the real-time and fine-grained air quality information throughout a city, based on the (historical and real-time) air quality data reported by existing monitor stations and a variety of data sources we observed in the city, such as meteorology, traffic flow, human mobility, structure of road networks, and point of interests (POIs). We propose a semi-supervised learning approach based on a co-training framework that consists of two separated classifiers. One is a spatial classifier based on an artificial neural network (ANN), which takes spatially-related features (e.g., the density of POIs and length of highways) as input to model the spatial correlation between air qualities of different locations. The other is a temporal classifier based on a linear-chain conditional random field (CRF), involving temporally-related features (e.g., traffic and meteorology) to model the temporal dependency of air quality in a location. We evaluated our approach with extensive experiments based on five real data sources obtained in Beijing and Shanghai. The results show the advantages of our method over four categories of baselines, including linear/Gaussian interpolations, classical dispersion models, well-known classification models like decision tree and CRF, and ANN.

Exploiting large-scale check-in data to recommend time-sensitive routes

Location-based services allow users to perform geo-spatial check-in actions, which facilitates the mining of the moving activities of human beings. This paper proposes to recommend time-sensitive trip routes, consisting of a sequence of locations with associated time stamps, based on knowledge extracted from large-scale check-in data. Given a query location with the starting time, our goal is to recommend a time-sensitive route. We argue a good route should consider (a) the popularity of places, (b) the visiting order of places, (c) the proper visiting time of each place, and (d) the proper transit time from one place to another. By devising a statistical model, we integrate these four factors into a goodness function which aims to measure the quality of a route. Equipped with the goodness measure, we propose a greedy method to construct the time-sensitive route for the query. Experiments on Gowalla datasets demonstrate the effectiveness of our model on detecting real routes and cloze test of routes, comparing with other baseline methods. We also develop a system TripRouter as a real-time demo platform.

Inferring Air Quality for Station Location Recommendation Based on Urban Big Data

This paper tries to answer two questions. First, how to infer real-time air quality of any arbitrary location given environmental data and historical air quality data from very sparse monitoring locations. Second, if one needs to establish few new monitoring stations to improve the inference quality, how to determine the best locations for such purpose? The problems are challenging since for most of the locations (>99%) in a city we do not have any air quality data to train a model from. We design a semi-supervised inference model utilizing existing monitoring data together with heterogeneous city dynamics, including meteorology, human mobility, structure of road networks, and point of interests (POIs). We also propose an entropy-minimization model to suggest the best locations to establish new monitoring stations. We evaluate the proposed approach using Beijing air quality data, resulting in clear advantages over a series of state-of-the-art and commonly used methods.

Linkit: A CALL System for Learning Chinese Characters, Words, and Phrases.

Teaching Chinese as a foreign language (TCFL) is increasingly becoming a mainstream profession and an independent academic discipline. However, there is little research in CALL targeting the Chinese language to date. This research attempts to show how a CALL system can be constructed following the unique properties of the Chinese language so it can benefit the learner maximally. First, we analyze student journals to identify problematic areas for British students learning Chinese as a foreign language, which seem to spread across levels of phonology, morphology, orthography, and vocabulary in an inextricable fashion. To address this issue, we designed a hierarchical network model linking levels of sound, syllables, characters, words, and phrases together in the form of nodes and connections. Current implementation of the model is a CALL system nicknamed Linkit, which can work alongside a textbook or a corpus, offering interconnected elements of the Chinese language such as the syllable, the character, the word, and the phrase on the same screen. The purpose of the design is for students to view a Chinese character not just as a character, but to see how it relates to other homophonic characters by appreciating the underlying phonological similarities and how the character can develop into a word or a phrase. We suggest that the emphasis on this type of continuity is a key factor in designing Chinese-specific CALL programs.

Measuring and Recommending Time-Sensitive Routes from Location-Based Data

Location-based services allow users to perform geospatial recording actions, which facilitates the mining of the moving activities of human beings. This article proposes to recommend time-sensitive trip routes consisting of a sequence of locations with associated timestamps based on knowledge extracted from large-scale timestamped location sequence data (e.g., check-ins and GPS traces). We argue that a good route should consider (a) the popularity of places, (b) the visiting order of places, (c) the proper visiting time of each place, and (d) the proper transit time from one place to another. By devising a statistical model, we integrate these four factors into a route goodness function that aims to measure the quality of a route. Equipped with the route goodness, we recommend time-sensitive routes for two scenarios. The first is about constructing the route based on the user-specified source location with the starting time. The second is about composing the route between the specified source location and the destination location given a starting time. To handle these queries, we propose a search method, Guidance Search, which consists of a novel heuristic satisfaction function that guides the search toward the destination location and a backward checking mechanism to boost the effectiveness of the constructed route. Experiments on the Gowalla check-in datasets demonstrate the effectiveness of our model on detecting real routes and performing cloze test of routes, comparing with other baseline methods. We also develop a system TripRouter as a real-time demo platform.

Mining and Planning Time-aware Routes from Check-in Data

Location-based services allow users to perform check-in actions, which not only record their geo-spatial activities, but also provide a plentiful source for data scientists to analyze and plan more accurate and useful geographical recommender system. In this paper, we present a novel Time-aware Route Planning (TRP) problem using location check-in data. The central idea is that the pleasure of staying at the locations along a route is significantly affected by their visiting time. Each location has its own proper visiting time due to the category, objective, and population. To consider the visiting time of locations into route planning, we develop a three-stage time-aware route planning framework. First, since there is usually either noise time on existing locations or no visiting information on new locations constructed, we devise an inference method, LocTimeInf, to predict and recover the location visiting time on routes. Second, we aim to find the representative and popular time-aware location-transition behaviors from user check-in data, and a Time-aware Transit Pattern Mining (TTPM) algorithm is proposed correspondingly. Third, based on the mined time-aware transit patterns, we develop a Proper Route Search (PR-Search) algorithm to construct the final time-aware routes for recommendation. Experiments on Gowalla check-in data exhibit the promising effectiveness and efficiency of the proposed methods, comparing to a series of competitors.

Mining Temporal Subgraph Patterns in Heterogeneous Information Networks

With an increasing interest in social network applications, finding frequent social interactions can help us to do disease modeling, cultural and information transmission and behavioral ecology. We model the social interactions among objects and people by a temporal heterogeneous information network, where a node in the network represents an individual, and an edge between two nodes denotes the interaction between two individuals in a certain time interval. As time goes by, lots of temporal heterogonous information networks at different time unit can be collect. In this work, we aim to mine frequent temporal social interactions (call patterns) exist in numerous temporal heterogonous information networks. We propose a novel algorithm, TSP-algorithm (Temporal Subgraph Patterns algorithm) to mine the patterns which contain temporal information and forms a connective subgraph. The proposed method recursively grows the patterns in a depth-first search manner. Since the TSP-algorithm only needs to scan the database once and does not generate unnecessary candidates, the experiment results show that the TSP-algorithm outperforms the modified Apriori on time-efficiency and memory usage in both synthetic and real datasets. Keywordssocial network mining; temporal subgraph patterns; heterogeous information network; closed frequent patterns;

Where You Go Reveals Who You Know: Analyzing Social Ties from Millions of Footprints

This paper aims to investigate how the geographical footprints of users correlate to their social ties. While conventional wisdom told us that the more frequently two users co-locate in geography, the higher probability they are friends, we find that in real geo-social data, Gowalla and Meetup, almost all of the user pairs with friendships had never met geographically. In this sense, can we discover social ties among users purely using their geographical footprints even if they never met? To study this question, we develop a two-stage feature engineering framework. The first stage is to characterize the direct linkages between users through their spatial co-locations while the second is to capture the indirect linkages between them via a co-location graph. Experiments conducted on Gowalla check-in data and Meetup meeting events exhibit not only the superiority of our feature model, but also validate the predictability (with 70% accuracy) of detecting social ties solely from user footprints.

Finding influential seed successors in social networks

In a dynamic social network, nodes can be removed from the network for some reasons, and consequently affect the behaviors of the network. In this paper, we tackle the challenge of finding a successor node for each removed seed node to maintain the influence spread in the network. Given a social network and a set of seed nodes for influence maximization, who are the best successors to be transferred the jobs of initial influence propagation if some seeds are removed from the network. To tackle this problem, we present and discuss five neighborhood-based selection heuristics, including degree, degree discount, overlapping, community bridge, and community degree. Experiments on DBLP co-authorship network show the effectiveness of devised heuristics.

TripRec: recommending trip routes from large scale check-in data

With location-based services, such as Foursquare and Gowalla, users can easily perform check-in actions anywhere and anytime. Such check-in data not only enables personal geospatial journeys but also serves as a fine-grained source for trip planning. In this work, we aim to collectively recommend trip routes by leveraging a large-scaled check-in data through mining the moving behaviors of users. A novel recommendation system, TripRec, is proposed to allow users to pecify starting/end and must-go locations. It further provides the flexibility to satisfy certain time constraint (i.e., the expected duration of the trip). By considering a sequence of check-in points as a route, we mine the frequent sequences with some ranking mechanism to achieve the goal. Our TripRec targets at travelers who are unfamiliar to the objective area/city and have time constraints in the trip.