Search

The natural gas tightly correlates with our everyday life. However, driven by gray incomes, some users are prone to stealing gas by refitting the equipment without permission. Especially for the boiler room users in winter, this phenomenon appears more rampant. Traditional gas-theft detection methods highly rely on the on-site inspection, where exists ineffective and randomness. In this paper, we propose a data-driven approach, named SVOC, to detect gas-theft suspects among boiler room users. Our approach consists of a scenario-based data quality detection algorithm, a deformation-based normality detection algorithm, and an One-Class Support Vector Machine (OCSVM) based anomaly detection algorithm. Specifically, considering the temporal proximity between the gas consumption and the outdoor temperature, the normality detection algorithm adopts a similarity-based deformation correlation to detect normal boiler room users out of abnormal ones. Then, we employ OCSVM as the anomaly detection algorithm to capture various features across multiple data sources, aiming to distinguish gas-theft suspects from the remaining irregular users. Here, the detected normal and abnormal users are fed into the OCSVM for training and prediction, respectively, which can overcome the label scarcity problem. We conduct extensive experiments on a real-world dataset during one heating season. The results demonstrate distinct advantages of our approach over various baselines.

Nowadays, many cities are suffering from air pollution problems, which endangered the health of the young and elderly for breathing problems. For supporting the government's policy-making and people's decision making, it is important to predict future fine-grained air quality. In this paper, we predict the air quality of the next 48 hours for each monitoring station and the daily average air quality of the next 7 days for a city, considering air quality data, meteorology data, and weather forecast data. Based on the domain knowledge about air pollution, we propose a deep neural network based approach, entitled DeepAir. Our approach consists of a deep distributed fusion network for station-level short-term prediction and a deep cascaded fusion network for the city-level long-term forecast. With the data transformation preprocessing, the former network adopts a neural distributed architecture to fuse heterogeneous urban data for simultaneously capturing the direct and indirect factors affecting air quality. The latter network takes a neural cascaded architecture to learn the dynamic influences from previously existing data and future predicted data on future air quality. We have deployed a real-time system on the cloud, providing fine-grained air quality forecasts for 300 $_+$ Chinese cities every hour. Our system mainly consists of three components: data crawler, task scheduler, and prediction model, which are implemented with a multi-task architecture to improve the system's efficiency and stability. Based on the datasets from three-year nine Chinese cities, experimental results demonstrate the advantages of our proposed method.

Real-time traffic monitoring becomes an essential part of an intelligent city. In recent years, the adoption of surveillance cameras is rapidly growing because they are helpful to manage and control the traffic. However, it is impossible to install cameras on every road in a city due to the high costs of deployment and maintenance. Given the information from limited surveillance cameras, can we infer the citywide traffic volume accurately? This is a challenging question because we have no historical data on the roads without cameras. In this paper, we propose a framework named CityVolInf to infer citywide traffic volume based on surveillance camera records. Our framework combines a semi-supervised learning-based similarity module with a novel simulation module to address the above challenges. While the similarity module focuses on spatiotemporal correlations of traffic volume between road segments, the simulation module utilizes incomplete trajectories to model transitions of traffic volume between adjacent road segments. Our framework bridges the conventional data-driven approach and transportation domain knowledge from the simulator. Extensive experiments on a real-world dataset, containing 405,370,631 camera records collected from 1,704 surveillance cameras over a period of 31 days in Jinan, China, demonstrate the effectiveness of CityVolInf compared with existing methods.

Gas theft of restaurants is a major concern in the gas industry, which causes revenue losses for gas companies and endangers the public safety seriously. Traditional methods of gas theft detection highly rely on active human efforts that are extremely ineffective. Thanks to the gas consumption data collected by smart meters, we can devise a data-driven method to tackle this issue. In this paper, we propose a gas-theft detection method msRank to discover suspicious restaurant users when only scarce labels are available. Our method contains three main components: 1)data pre-processing, which filters reading noises and excludes data-missing or zero-use users; 2)normal user modeling, which quantifies the self-stable seasonality of normal users and distinguishes them from unstable ones; and 3)gas-theft suspect detection, which discovers gas-theft suspects among unstable users by RankNet-based suspicion scoring on extracted deviation features. By using detected normal users as negative samples to train RankNet, the component of normal user modeling and that of gas-theft suspect detection are seamlessly connected, overcoming the problem of label scarcity. We conduct extensive experiments on three real-world datasets, and the results demonstrate advantages of our approach. We have deployed a system GasShield which provides a gas-theft suspect list weekly for a gas group in northern China.

Traffic volume estimation at the city scale is an important problem useful to many transportation operations and urban applications. This paper proposes a hybrid framework that integrates both state-of-art machine learning techniques and well-established traffic flow theory to estimate citywide traffic volume. In addition to typical urban context features extracted from multiple sources, we extract a special set of features from GPS trajectories based on the implications of traffic flow theory, which provide extra information on the speed-flow relationship. Using the network-wide speed information estimated from a travel speed estimation model, a volume related high level feature is first learned using an unsupervised graphical model. A volume re-interpretation model is then introduced to map the volume related high level feature to the predicted volume using a small amount of ground truth data for training. The framework is evaluated using a GPS trajectory dataset from 33,000 Beijing taxis and volume ground truth data obtained from 4,980 video clips. The results demonstrate effectiveness and potential of the proposed framework in citywide traffic volume estimation.

With the increasing vehicles on the road, it is becoming more and more important to sense citywide traffic, which is of great benefit to the government's policy-making and people's decision making. Currently, traffic speed and volume information are mostly derived from GPS trajectories data and volume sensor records respectively. Unfortunately, speed and volume information suffer from serious data missing problem. Speed can be absent at arbitrary road segment and time slot, while volume is only recorded by limited volume sensors. For modeling citywide traffic, inspired by the observations of missing patterns and prior knowledge about traffic, we propose a neural memorization and generalization approach to infer the missing speed and volume, which mainly consists of a memorization module for speed inference and a generalization module for volume inference. Considering the temporal closeness and period properties, memorization module takes advantage of neural multi-head self-attention architecture to memorize the intrinsic correlations from historical traffic information. Generalization module adopts neural key-value attention architecture to generalize the extrinsic dependencies among volume sensors by exploiting road contexts. We conduct extensive experiments on two real-world datasets in two cities, Guiyang and Jinan, and the experimental results consistently demonstrate the advantages of our approach. We have developed a real-time system on the cloud, entitled CityTraffic, providing citywide traffic speed and volume information and fine-grained pollutant emission of vehicles in Guiyang city.

Accompanying the rapid urbanization, many developing countries are suffering from serious air pollution problem. The demand for predicting future air quality is becoming increasingly more important to government's policy-making and people's decision making. In this paper, we predict the air quality of next 48 hours for each monitoring station, considering air quality data, meteorology data, and weather forecast data. Based on the domain knowledge about air pollution, we propose a deep neural network (DNN)-based approach (entitled DeepAir), which consists of a spatial transformation component and a deep distributed fusion network. Considering air pollutants' spatial correlations, the former component converts the spatial sparse air quality data into a consistent input to simulate the pollutant sources. The latter network adopts a neural distributed architecture to fuse heterogeneous urban data for simultaneously capturing the factors affecting air quality, e.g. meteorological conditions. We deployed DeepAir in our AirPollutionPrediction system, providing fine-grained air quality forecasts for 300+ Chinese cities every hour. The experimental results on the data from three-year nine Chinese-city demonstrate the advantages of DeepAir beyond 10 baseline methods. Comparing with the previous online approach in AirPollutionPrediction system, we have 2.4%, 12.2%, 63.2% relative accuracy improvements on short-term, long-term and sudden changes prediction, respectively.

Previous study has indicated that exposure to anesthesia in early development leads to neuro-apoptosis and is followed by long-term cognitive dysfunction. Given that larger numbers of pregnant women currently receive anesthesia during the first trimester, we wanted to mimic this process in vitro using mouse embryonic stem cells (mESCs) and to explore how different anesthetics affect the self-renewal of mESCs. In the present study, mESCs were exposed to dexmedetomidine, fentanyl, or remifentanil at clinical concentrations for 48 h. The mESCs were then analyzed for cell proliferation and apoptosis. Furthermore, we used flow cytometry to analyze the cell cycle and quantitative real-time polymerase chain reaction to detect the gene expression during the cell cycle as well as the relevant stemness markers. We found that prolonged anesthesia with dexmedetomidine or fentanyl significantly inhibited mESC proliferation, with fewer cell numbers as well as decreased expression of cyclin B and cyclin E mRNA compared to that in the control group; meanwhile, p21 and RB2 gene expression was increased. Additionally, increases or decreases in the proportion of cells in the G1 and S phases, respectively, were observed in the dexmedetomidine- and fentanyl-treated groups. These anesthetics also repressed the gene expression of mESC stemness makers such as Oct4 and Sox2. However, remifentanil seemed to have no significant influence on the self-renewal of mESCs. These results demonstrated that prolonged anesthesia with dexmedetomidine or fentanyl, but not remifentanil, inhibited mESC proliferation by blocking the G1 to S transition, and repressed the maintenance of mESC stemness.

The traffic volume on road segments is a vital property of the transportation efficiency. City-wide traffic volume information can benefit people with their everyday life, and help the government on better city planning. However, there are no existing methods that can monitor the traffic volume of every road, because they are either too expensive or inaccurate. Fortunately, nowadays we can collect a large amount of urban data which provides us the opportunity to tackle this problem. In this paper, we propose a novel framework to infer the city-wide traffic volume information with data collected by loop detectors and taxi trajectories. Although these two data sets are incomplete, sparse and from quite different domains, the proposed spatio-temporal semi-supervised learning model can take the full advantages of both data and accurately infer the volume of each road. In order to provide a better interpretation on the inference results, we also derive the confidence of the inference based on spatio-temporal properties of traffic volume. Real-world data was collected from 155 loop detectors and 6,918 taxis over a period of 17 days in Guiyang China. The experiments performed on this large urban data set demonstrate the advantages of the proposed framework on correctly inferring the traffic volume in a city-wide scale.

Chromoblastomycosis (CBM), one of the neglected tropical diseases, is hard to cure and easy to be recurrent. Many studies suggest that macrophage is involved in the pathogenesis of chromoblastomycosis and the fungicidal effect of 5-Aminolaevulinic Acid-Based Photodynamic Therapy (ALA-PDT) against F. monophora (one of the main causative agent of chromoblastomycosis) has shown great promise. However, the fungicidal ability of ALA-PDT to F. monophora is still controversial and the molecular mechanism and immune mechanism of ALA-PDT against F. monophora remains poorly documented. In the present work, ALA (5-Aminolaevulinic Acid) was employed as photosensitizer and a LED device was served as light source to investigate photodynamic effect on F. monophora conidia under different ALA-PDT conditions in a direct way. RAW264.7 was stimulated by conidia treated with ALA-PDT to study the photodynamic effect on F. monophora conidia in an indirect way. It was observed that ALA-PDT can inactivate F. monophora conidia directly in a concentration-dependent and dose-dependent manner. RAW264.7 was activated indirectly by photodynamically treated conidia. ALA-PDT can enhance the fungicidal ability of RAW264.7 and protect it from Infection-induced apoptosis in an indirect way. ROS generated by photodynamic treated conidia is associated with mitochondrial-related apoptosis in RAW264.7.The results of this investigation demonstrated that ALA-PDT inactivate F. monophora through two way: directly killing F. monophora conidia through ROS-dependent Oxidative damage; activating RAW264.7 in an indirect way.