Learning Individual Behavior Using Sensor Data: The Case of Global Positioning System Traces and Taxi Drivers

2020 ◽  
Vol 31 (4) ◽  
pp. 1301-1321
Author(s):  
Yingjie Zhang ◽  
Beibei Li ◽  
Ramayya Krishnan
Keyword(s):  
Information Sharing ◽  
Bayesian Learning ◽  
Sensor Data ◽  
Local Market ◽  
Data Set ◽  
Taxi Drivers ◽  
Individual Level ◽  
Market Expansion ◽  
Aggregate Information ◽  
Efficient Information

In this study, using a Bayesian learning model with a rich data set consisting of 2 million fine-grained GPS observations, we study the role of information observable by or made available to taxi drivers in enabling them to learn the distribution of demand for their services over space and time. We find significant differences between new and experienced drivers in both learning behavior and driving decisions. Drivers benefit significantly from their ability to learn from not only information directly observable in the local market but also aggregate information on demand flows across markets. Interestingly, our policy simulations indicate that information that is noisy at the individual level becomes valuable when aggregated across relevant spatial and temporal dimensions. Moreover, we find that the value of information does not increase monotonically with the scale and frequency of information sharing. Our results also provide important evidence that efficient information sharing can lead to a welfare increase because of potential market expansion. Efficient information sharing can bring additional income-generating opportunities that could be unfulfilled. Overall, this study not only explains driver decision-making behavior but also provides taxi companies with an implementable information-sharing strategy to improve overall market efficiency.

Individual Differences in the Neural Dynamics of Response Inhibition

2019 ◽  
Vol 31 (12) ◽  
pp. 1976-1996 ◽  
Author(s):  
M. Fiona Molloy ◽  
Giwon Bahg ◽  
Zhong-Lin Lu ◽  
Brandon M. Turner
Keyword(s):  
Individual Differences ◽  
Cognitive Control ◽  
Response Inhibition ◽  
Bayesian Models ◽  
Accurate Estimation ◽  
Hierarchical Bayesian ◽  
Hierarchical Bayesian Models ◽  
Data Set ◽  
Individual Level ◽  
Aggregate Information

Response inhibition is a widely studied aspect of cognitive control that is particularly interesting because of its applications to clinical populations. Although individual differences are integral to cognitive control, so too is our ability to aggregate information across a group of individuals, so that we can powerfully generalize and characterize the group's behavior. Hence, an examination of response inhibition would ideally involve an accurate estimation of both group- and individual-level effects. Hierarchical Bayesian analyses account for individual differences by simultaneously estimating group and individual factors and compensate for sparse data by pooling information across participants. Hierarchical Bayesian models are thus an ideal tool for studying response inhibition, especially when analyzing neural data. We construct hierarchical Bayesian models of the fMRI neural time series, models assuming hierarchies across conditions, participants, and ROIs. Here, we demonstrate the advantages of our models over a conventional generalized linear model in accurately separating signal from noise. We then apply our models to go/no-go and stop signal data from 11 participants. We find strong evidence for individual differences in neural responses to going, not going, and stopping and in functional connectivity across the two tasks and demonstrate how hierarchical Bayesian models can effectively compensate for these individual differences while providing group-level summarizations. Finally, we validated the reliability of our findings using a larger go/no-go data set consisting of 179 participants. In conclusion, hierarchical Bayesian models not only account for individual differences but allow us to better understand the cognitive dynamics of response inhibition.

scholarly journals A remote sensing derived data set of 100 million individual tree crowns for the National Ecological Observatory Network

eLife ◽  
2021 ◽  
Vol 10 ◽  
Author(s):  
Ben G Weinstein ◽  
Sergio Marconi ◽  
Stephanie A Bohlman ◽  
Alina Zare ◽  
Aditya Singh ◽  
...  
Keyword(s):  
United States ◽  
Remote Sensing ◽  
Spatial Location ◽  
The United States ◽  
Sensor Data ◽  
Data Set ◽  
Individual Tree ◽  
Individual Level ◽  
Remote Sensing Techniques ◽  
Individual Trees

Forests provide biodiversity, ecosystem, and economic services. Information on individual trees is important for understanding forest ecosystems but obtaining individual-level data at broad scales is challenging due to the costs and logistics of data collection. While advances in remote sensing techniques allow surveys of individual trees at unprecedented extents, there remain technical challenges in turning sensor data into tangible information. Using deep learning methods, we produced an open-source data set of individual-level crown estimates for 100 million trees at 37 sites across the United States surveyed by the National Ecological Observatory Network’s Airborne Observation Platform. Each canopy tree crown is represented by a rectangular bounding box and includes information on the height, crown area, and spatial location of the tree. These data have the potential to drive significant expansion of individual-level research on trees by facilitating both regional analyses and cross-region comparisons encompassing forest types from most of the United States.

Human Activity Recognition using Fourier Transform Inspired Deep Learning Combination Model

2019 ◽  
Vol 9 (1) ◽  
pp. 16-31
Author(s):  
Kyungkoo Jun
Keyword(s):  
Fourier Transform ◽  
Deep Learning ◽  
Short Term Memory ◽  
Window Size ◽  
Sensor Data ◽  
Data Sets ◽  
Data Set ◽  
Proposed Model ◽  
Testing Data ◽  
Labeling Scheme

Background & Objective: This paper proposes a Fourier transform inspired method to classify human activities from time series sensor data. Methods: Our method begins by decomposing 1D input signal into 2D patterns, which is motivated by the Fourier conversion. The decomposition is helped by Long Short-Term Memory (LSTM) which captures the temporal dependency from the signal and then produces encoded sequences. The sequences, once arranged into the 2D array, can represent the fingerprints of the signals. The benefit of such transformation is that we can exploit the recent advances of the deep learning models for the image classification such as Convolutional Neural Network (CNN). Results: The proposed model, as a result, is the combination of LSTM and CNN. We evaluate the model over two data sets. For the first data set, which is more standardized than the other, our model outperforms previous works or at least equal. In the case of the second data set, we devise the schemes to generate training and testing data by changing the parameters of the window size, the sliding size, and the labeling scheme. Conclusion: The evaluation results show that the accuracy is over 95% for some cases. We also analyze the effect of the parameters on the performance.

scholarly journals Automatic Identification of Upper Extremity Rehabilitation Exercise Type and Dose Using Body-Worn Sensors and Machine Learning: A Pilot Study

2021 ◽  
pp. 158-166
Author(s):  
Noah Balestra ◽  
Gaurav Sharma ◽  
Linda M. Riek ◽  
Ania Busza
Keyword(s):  
Machine Learning ◽  
Upper Extremity ◽  
Sensor Data ◽  
Inpatient Setting ◽  
Accelerometer Data ◽  
Data Set ◽  
Machine Learning Classification ◽  
Exercise Type ◽  
Exercise Dose ◽  
Rehabilitation Exercises

<b><i>Background:</i></b> Prior studies suggest that participation in rehabilitation exercises improves motor function poststroke; however, studies on optimal exercise dose and timing have been limited by the technical challenge of quantifying exercise activities over multiple days. <b><i>Objectives:</i></b> The objectives of this study were to assess the feasibility of using body-worn sensors to track rehabilitation exercises in the inpatient setting and investigate which recording parameters and data analysis strategies are sufficient for accurately identifying and counting exercise repetitions. <b><i>Methods:</i></b> MC10 BioStampRC® sensors were used to measure accelerometer and gyroscope data from upper extremities of healthy controls (<i>n</i> = 13) and individuals with upper extremity weakness due to recent stroke (<i>n</i> = 13) while the subjects performed 3 preselected arm exercises. Sensor data were then labeled by exercise type and this labeled data set was used to train a machine learning classification algorithm for identifying exercise type. The machine learning algorithm and a peak-finding algorithm were used to count exercise repetitions in non-labeled data sets. <b><i>Results:</i></b> We achieved a repetition counting accuracy of 95.6% overall, and 95.0% in patients with upper extremity weakness due to stroke when using both accelerometer and gyroscope data. Accuracy was decreased when using fewer sensors or using accelerometer data alone. <b><i>Conclusions:</i></b> Our exploratory study suggests that body-worn sensor systems are technically feasible, well tolerated in subjects with recent stroke, and may ultimately be useful for developing a system to measure total exercise “dose” in poststroke patients during clinical rehabilitation or clinical trials.

scholarly journals Outlier Detection Transilience-Probabilistic Model for Wind Tunnels Based on Sensor Data

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2532
Author(s):  
Encarna Quesada ◽  
Juan J. Cuadrado-Gallego ◽  
Miguel Ángel Patricio ◽  
Luis Usero
Keyword(s):  
Anomaly Detection ◽  
Outlier Detection ◽  
Research Work ◽  
Industrial Sector ◽  
Sensor Data ◽  
Correct Selection ◽  
Wind Tunnels ◽  
Data Set ◽  
First Case ◽  
Anomaly Analysis

Anomaly Detection research is focused on the development and application of methods that allow for the identification of data that are different enough—compared with the rest of the data set that is being analyzed—and considered anomalies (or, as they are more commonly called, outliers). These values mainly originate from two sources: they may be errors introduced during the collection or handling of the data, or they can be correct, but very different from the rest of the values. It is essential to correctly identify each type as, in the first case, they must be removed from the data set but, in the second case, they must be carefully analyzed and taken into account. The correct selection and use of the model to be applied to a specific problem is fundamental for the success of the anomaly detection study and, in many cases, the use of only one model cannot provide sufficient results, which can be only reached by using a mixture model resulting from the integration of existing and/or ad hoc-developed models. This is the kind of model that is developed and applied to solve the problem presented in this paper. This study deals with the definition and application of an anomaly detection model that combines statistical models and a new method defined by the authors, the Local Transilience Outlier Identification Method, in order to improve the identification of outliers in the sensor-obtained values of variables that affect the operations of wind tunnels. The correct detection of outliers for the variables involved in wind tunnel operations is very important for the industrial ventilation systems industry, especially for vertical wind tunnels, which are used as training facilities for indoor skydiving, as the incorrect performance of such devices may put human lives at risk. In consequence, the use of the presented model for outlier detection may have a high impact in this industrial sector. In this research work, a proof-of-concept is carried out using data from a real installation, in order to test the proposed anomaly analysis method and its application to control the correct performance of wind tunnels.

scholarly journals Remaining Useful Life Prediction Using Temporal Convolution with Attention

AI ◽  
2021 ◽  
Vol 2 (1) ◽  
pp. 48-70
Author(s):  
Wei Ming Tan ◽  
T. Hui Teo
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Time Series Data ◽  
Remaining Useful Life ◽  
Sensor Data ◽  
Series Data ◽  
Multiple Time ◽  
Data Set ◽  
Form Complex ◽  
Useful Life

Prognostic techniques attempt to predict the Remaining Useful Life (RUL) of a subsystem or a component. Such techniques often use sensor data which are periodically measured and recorded into a time series data set. Such multivariate data sets form complex and non-linear inter-dependencies through recorded time steps and between sensors. Many current existing algorithms for prognostic purposes starts to explore Deep Neural Network (DNN) and its effectiveness in the field. Although Deep Learning (DL) techniques outperform the traditional prognostic algorithms, the networks are generally complex to deploy or train. This paper proposes a Multi-variable Time Series (MTS) focused approach to prognostics that implements a lightweight Convolutional Neural Network (CNN) with attention mechanism. The convolution filters work to extract the abstract temporal patterns from the multiple time series, while the attention mechanisms review the information across the time axis and select the relevant information. The results suggest that the proposed method not only produces a superior accuracy of RUL estimation but it also trains many folds faster than the reported works. The superiority of deploying the network is also demonstrated on a lightweight hardware platform by not just being much compact, but also more efficient for the resource restricted environment.

Avenues to News and Diverse News Exposure Online: Comparing Direct Navigation, Social Media, News Aggregators, Search Queries, and Article Hyperlinks

2021 ◽  
pp. 194016122110091
Author(s):  
Magdalena Wojcieszak ◽  
Ericka Menchen-Trevino ◽  
Joao F. F. Goncalves ◽  
Brian Weeks
Keyword(s):  
Social Media ◽  
Search Engines ◽  
Direct Access ◽  
Data Set ◽  
Individual Level ◽  
News Sources ◽  
Internet Users ◽  
News Websites ◽  
The Us ◽  
Social Media Platforms

The online environment dramatically expands the number of ways people can encounter news but there remain questions of whether these abundant opportunities facilitate news exposure diversity. This project examines key questions regarding how internet users arrive at news and what kinds of news they encounter. We account for a multiplicity of avenues to news online, some of which have never been analyzed: (1) direct access to news websites, (2) social networks, (3) news aggregators, (4) search engines, (5) webmail, and (6) hyperlinks in news. We examine the extent to which each avenue promotes news exposure and also exposes users to news sources that are left leaning, right leaning, and centrist. When combined with information on individual political leanings, we show the extent of dissimilar, centrist, or congenial exposure resulting from each avenue. We rely on web browsing history records from 636 social media users in the US paired with survey self-reports, a unique data set that allows us to examine both aggregate and individual-level exposure. Visits to news websites account for about 2 percent of the total number of visits to URLs and are unevenly distributed among users. The most widespread ways of accessing news are search engines and social media platforms (and hyperlinks within news sites once people arrive at news). The two former avenues also increase dissimilar news exposure, compared to accessing news directly, yet direct news access drives the highest proportion of centrist exposure.

Personalized Priority Policies in Call Centers Using Past Customer Interaction Information

2021 ◽  
Author(s):  
Brett Alan Hathaway ◽  
Seyed Morteza Emadi ◽  
Vinayak Deshpande
Keyword(s):  
Customer Service ◽  
Operations Management ◽  
Bayesian Learning ◽  
Structural Model ◽  
Call Centers ◽  
Waiting Times ◽  
Operational Performance ◽  
System Throughput ◽  
History Data ◽  
Individual Level

To increase revenue or improve customer service, companies are increasingly personalizing their product or service offerings based on their customers' history of interactions. In this paper, we show how call centers can improve customer service by implementing personalized priority policies. Under personalized priority policies, managers use customer contact history to predict individual-level caller abandonment and redialing behavior and prioritize them based on these predictions to improve operational performance. We provide a framework for how companies can use individual-level customer history data to capture the idiosyncratic preferences and beliefs that impact caller abandonment and redialing behavior and quantify the improvements to operational performance of these policies by applying our framework using caller history data from a real-world call center. We achieve this by formulating a structural model that uses a Bayesian learning framework to capture how callers’ past waiting times and abandonment/redialing decisions affect their current abandonment and redialing behavior and use our data to impute the callers’ underlying primitives such as their rewards for service, waiting costs, and redialing costs. These primitives allow us to simulate caller behavior under a variety of personalized priority policies and hence, collect relevant operational performance measures. We find that, relative to the first-come, first-served policy, our proposed personalized priority policies have the potential to decrease average waiting times by up to 29% or increase system throughput by reducing the percentage of service requests lost to abandonment by up to 6.3%. This paper was accepted by Vishaul Gaur, operations management.

scholarly journals Social connectedness and political behavior

2017 ◽  
Vol 4 (3) ◽  
pp. 205316801771917 ◽  
Author(s):  
Jack Lyons Reilly
Keyword(s):  
Social Networks ◽  
Political Behavior ◽  
Political Ideology ◽  
Social Connectedness ◽  
Local Environment ◽  
Social Environments ◽  
Data Set ◽  
Individual Level ◽  
Nationally Representative ◽  
Socially Isolated

One of the focal points of social networks research has been the process by which individuals utilize information and cues from their social networks and communities to form political attitudes and make decisions about how and when to participate in politics. Not all individuals, however, have large social networks or are strongly connected to their local social environments. Furthermore, despite concerns about rising social isolation in American society, the role that relatively socially disconnected individuals play in politics is not well understood. Using a nationally representative data set with information about communities, social networks, and individual-level variables, this paper examines social connectedness and political behavior. Those who are more socially isolated, it is found, are neither more conservative nor liberal on any particular political issues, but clearly participate in politics less than individuals who are well connected to those around them. Finally, while individual political ideology is not correlated with isolation, the contextual influence of the local environment on individual preferences is correlated with social connectedness. When compared with well connected citizens, individuals who are more isolated are less likely to have their vote choices influenced by those around them. Individual social connectedness conditions the effect of contextual social influence.

scholarly journals Intersecting social-capital and perceived-efficacy perspectives to explain underperformance in community-based monitoring

Evaluation ◽  
2017 ◽  
Vol 23 (3) ◽  
pp. 339-357 ◽  
Author(s):  
Sara Dewachter ◽  
Nathalie Holvoet
Keyword(s):  
Social Capital ◽  
Information Sharing ◽  
Information Network ◽  
Community Based ◽  
Perceived Efficacy ◽  
Leadership Efficacy ◽  
Efficient Information ◽  
Social Capital Perspective ◽  
The Village ◽  
Efficacy Profile

While community-based monitoring is becoming increasingly commonplace, evidence as to its functioning remains inconsistent. Based on Ugandan village network and survey data, this article studies community-based monitoring from a social-capital and perceived-efficacy perspective. From a social-capital perspective, the prospects for community-based monitoring look promising as there is a high social-capital stock and an efficient information-sharing network galvanizing information for a few key individuals. The dominant efficacy profiles are also encouraging as there is an abundance of ‘followers’ (with high belief in collective capabilities) and some ‘leaders’ for collective action (with high belief in individual and collective capabilities). And yet, few community-based monitoring activities are undertaken. Our article shows that only the intersection of both theoretical lenses explains the underperformance in community-based monitoring, as those actors who are central in the information-sharing network do not have a ‘leadership’ efficacy profile while those who are ‘leaders’ are not central in the village information network.

Sign in / Sign up

Export Citation Format

Share Document