Vehicle classification in distributed sensor networks

By Marco F. Duarte, Y. Hu. 2004

573 citations recorded by the source corpus.

The task of classifying the types of moving vehicles in a distributed, wireless sensor network is investigated. Specifically, based on an extensive real world experiment, we have compiled a data set that consists of 820 MByte raw time series data, 70 MByte of preprocessed, extracted spectral feature vectors, and baseline classification results using the maximum likelihood classifier. The purpose of this paper is to detail the data collection procedure, the feature extraction and pre-processing steps, and baseline classifier development. The database is available for download at http://www.ece.wisc.edu/~sensit starting on July 2003.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Networks and Communications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Networks and Communications

Citations in the corpus

Fair Resource Allocation in Federated Learning (2019, methodology): “We then investigate a Vehicle dataset consisting of acoustic, seismic, and infrared sensor data collected from a distributed network of 23 sensors [8].”
Fully Decentralized Joint Learning of Personalized Models and Collaboration Graphs (2019, background): “, 2013), Vehicle Sensor (Duarte and Hu, 2004) (K = 23, D = 100), Computer Buyers (K = 190, D = 14) and School (Goldstein, 1991) (K = 140, D = 17).”
Federated Multi-Task Learning (2017, background): “• Vehicle Sensor6: Acoustic, seismic, and infrared sensor data collected from a distributed network of 23 sensors, deployed with the aim of classifying vehicles driving by a segment of road [13].”
Distributed Multi-Task Learning (2015, methodology): “We considered the vehicle classification problem in distributed sensor networks [33] with 3 binary classifica-”
Local Differential Privacy-Based Federated Learning for Internet of Things (2020, methodology): “These mechanisms effectively preserve the privacy when collecting data records and computing accurate statistics in various data analysis tasks, including estimating the mean frequency and complex machine learning tasks such as linear regression, logistic regression, and SVM classiﬁcation.”
Large Scale Spectral Clustering with Landmark-Based Representation (2011, methodology): “Seismic A data set initially built for the task of classifying the types of moving vehicles in a distributed, wireless sensor network (Duarte and Hu 2004).”
Approaches to Multisensor Data Fusion in Target Tracking: A Survey (2006, background): “Duarte and Hu [121] relied on each sensor classifying the target and then classifications were centrally fused, leaving a large computational effort at the node.”
Large Scale Spectral Clustering Via Landmark-Based Sparse Representation (2015, background): “4) Seismic: A data set initially built for the task of classifying the types of moving vehicles in a distributed, wireless sensor network [10].”
Tilted Empirical Risk Minimization (2020, methodology): “Here, we compare TERM with q-FFL in their setup on the vehicle dataset [16] consisting of data collected from 23 distributed sensors (hence 23 devices).”
A line in the sand: a wireless sensor network for target detection, classification, and tracking (2004, methodology): “By way of contrast, Duarte et al. [6] describes a classifier in which each sensor extracts feature vectors based on its own readings and passes them through a local pattern classifier.”
Selecting Near-Optimal Learners via Incremental Data Allocation (2015, background): “2011); SUSY (Baldi, Sadowski, and Whiteson 2014); and VehicleSensIT (Duarte and Hu 2004).”
Vertical Federated Learning: Concepts, Advances, and Challenges (2022, methodology): “NUSWIDE and Vehicle datasets consist of multi-modal features that can naturally simulate the two-party VFL scenario, whereas other datasets require manual partition.”
Variational Federated Multi-Task Learning (2019, unknown): “[14].”
Semi-Supervised Learning of Class Balance under Class-Prior Change by Distribution Matching (2012, methodology): “2 Real-World Application Finally, we demonstrate the usefulness of the proposed approach in a real-world problem of military vehicle classification from geophone recordings (Duarte and Hu, 2004).”
Visualization of wormholes in sensor networks (2004, background): “Army [8], the sensors are deployed at an interval of 30 − 40m.”
End-to-End Learning of Decision Trees and Forests (2019, background): “On SensIT and Protein we perform better than or on par with the Non-greedy approach proposed in Norouzi et al. (2015b).”