No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Robustness of vehicle identification via trajectory dynamics to noisy measurements and malicious attacks
Time Series Classification (TSC) is an important and challenging problem in data mining. With the increase of time series data availability, hundreds of TSC algorithms have been proposed. Among these methods, only a few have considered Deep Neural Networks (DNNs) to perform this task. This is surprising as deep learning has seen very successful applications in the last years. DNNs have indeed revolutionized the field of computer vision especially with the advent of novel deeper architectures such as Residual and Convolutional Neural Networks. Apart from images, sequential data such as text and audio can also be processed with DNNs to reach state-of-the-art performance for document classification and speech recognition. In this article, we study the current state-of-the-art performance of deep learning algorithms for TSC by presenting an empirical study of the most recent DNN architectures for TSC. We give an overview of the most successful deep learning applications in various time series domains under a unified taxonomy of DNNs for TSC. We also provide an open source deep learning framework to the TSC community where we implemented each of the compared approaches and evaluated them on a univariate TSC benchmark (the UCR/UEA archive) and 12 multivariate time series datasets. By training 8730 deep learning models on 97 time series datasets, we propose the most exhaustive study of DNNs for TSC to date.
With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks (DNNs) have been recently found vulnerable to well-designed input samples called adversarial examples. Adversarial perturbations are imperceptible to human but can easily fool DNNs in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying DNNs in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples for DNNs, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples. In addition, three major challenges in adversarial examples and the potential solutions are discussed.
We introduce the use of rectified linear units (ReLU) as the classification function in a deep neural network (DNN). Conventionally, ReLU is used as an activation function in DNNs, with Softmax function as their classification function. However, there have been several studies on using a classification function other than Softmax, and this study is an addition to those. We accomplish this by taking the activation of the penultimate layer $h_{n - 1}$ in a neural network, then multiply it by weight parameters $\theta$ to get the raw scores $o_{i}$. Afterwards, we threshold the raw scores $o_{i}$ by $0$, i.e. $f(o) = \max(0, o_{i})$, where $f(o)$ is the ReLU function. We provide class predictions $\hat{y}$ through argmax function, i.e. argmax $f(x)$.
Short-term traffic forecasting based on deep learning methods, especially long short-term memory (LSTM) neural networks, has received much attention in recent years. However, the potential of deep learning methods in traffic forecasting has not yet fully been exploited in terms of the depth of the model architecture, the spatial scale of the prediction area, and the predictive power of spatial-temporal data. In this paper, a deep stacked bidirectional and unidirectional LSTM (SBU- LSTM) neural network architecture is proposed, which considers both forward and backward dependencies in time series data, to predict network-wide traffic speed. A bidirectional LSTM (BDLSM) layer is exploited to capture spatial features and bidirectional temporal dependencies from historical data. To the best of our knowledge, this is the first time that BDLSTMs have been applied as building blocks for a deep architecture model to measure the backward dependency of traffic data for prediction. The proposed model can handle missing values in input data by using a masking mechanism. Further, this scalable model can predict traffic speed for both freeway and complex urban traffic networks. Comparisons with other classical and state-of-the-art models indicate that the proposed SBU-LSTM neural network achieves superior prediction performance for the whole traffic network in both accuracy and robustness.
We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy preprocessing on the raw data or feature crafting. The proposed Fully Convolutional Network (FCN) achieves premium performance to other state-of-the-art approaches and our exploration of the very deep neural networks with the ResNet structure is also competitive. The global average pooling in our convolutional model enables the exploitation of the Class Activation Map (CAM) to find out the contributing region in the raw data for the specific labels. Our models provides a simple choice for the real world application and a good starting point for the future research. An overall analysis is provided to discuss the generalization capability of our models, learned features, network structures and the classification semantics.
The code and extended experiment results are available at https://github.com/cauchyturing/UCR_Time_Series_Classification_Deep_Learning_Baseline
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
The explosive popularity of transportation network companies (TNCs) in the last decade has imposed dramatic disruptions on the taxi industry, but not all the impacts are beneficial. For instance, studies have shown taxi capacity utilization rate is lower than 50% in five major U.S. cities. With the availability of taxi data, this study finds the taxi utilization rate is around 40% in June 2019 (normal scenario) and 35% in June 2020 (COVID 19 scenario) in the city of Chicago, U.S. Powered by recent advances in the deep learning of capturing non-linear relationships and the availability of datasets, a real-time taxi trip optimization strategy with dynamic demand prediction was designed using long short-term memory (LSTM) architecture to maximize the taxi utilization rate. The algorithms are tested in both scenarios—normal time and COVID 19 time—and promising results have been shown by implementing the strategy, with around 19% improvement in mileage utilization rate in June 2019 and 74% in June 2020 compared with the baseline without any optimizations. Additionally, this study investigated the impacts of COVID 19 on the taxi service in Chicago.
In this article, we assess the string stability of seven 2018 model year
adaptive cruise control
(ACC) equipped vehicles that are widely available in the US market. Seven distinct vehicle models from two different vehicle makes are analyzed using data collected from more than 1,200 miles of driving in car-following experiments with ACC engaged by the follower vehicle. The resulting dataset is used to identify the parameters of a linear second order delay differential equation model that approximates the behavior of the black box ACC systems. The string stability of the data-fitted model associated with each vehicle is assessed, and the main finding is that all seven vehicle models have string unstable ACC systems. For one commonly available vehicle model that offers ACC as a standard feature on all trim levels, we validate the string stability finding with a multi-vehicle homogeneousplatoon experiment in which all vehicles are the same year, make, and model. In this test, an initial disturbance of 6 mph is amplified to a 25 mph disturbance, at which point the last vehicle in the platoon is observed to disengage the ACC. The data collected in the driving experiments is made available, representing the largest publicly available comparative driving dataset on ACC equipped vehicles.
Dynamic state estimation plays a critical role in achieving real-time wide-area monitoring of power systems. On the other hand, false data injection (FDI) attacks are substantial threats, which can undesirably ruin the state estimation results. To tackle the foregoing problem, an effective Secure Hybrid Dynamic State Estimation (SHDSE) approach which involves a dynamic model of the attack vector is proposed in this paper. In the proposed method, an initial estimation of the system states is first obtained using a designed Unknown Input Observer (UIO). Subsequently, based on the system and UIO models and the initial estimations of the states, a dynamic model for the attack vector is extracted. Ultimately, the attack model is augmented with the main system model for co-estimation of the attack and the system states using a Kalman Filter (KF). The onset of the FDI attack is rapidly detected by the accurate estimation of the attack vector. The effectiveness of the proposed approach is demonstrated under different FDI attack scenarios by a thorough theoretical analysis as well as simulations on IEEE 14-bus and 57-bus test systems. In order to show that the proposed method can keep up with typical scan rates of commercial Phasor Measurement Units (PMUs), a series of Software-in-the-Loop (SIL) experiments are also conducted and the real-time feasibility of the proposed approach is guaranteed.
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 dif- ferent classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implemen- tation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called dropout that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry
Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets. © 2014 Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever and Ruslan Salakhutdinov.
We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 dif-ferent classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make train-ing faster, we used non-saturating neurons and a very efficient GPU implemen-tation of the convolution operation. To reduce overfitting in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
Recurrent neural networks (RNNs) are a powerful model for sequential
data. End-to-end training methods such as Connectionist Temporal
Classification make it possible to train RNNs for sequence labelling
problems where the input-output alignment is unknown. The combination of
these methods with the Long Short-term Memory RNN architecture has
proved particularly fruitful, delivering state-of-the-art results in
cursive handwriting recognition. However RNN performance in speech
recognition has so far been disappointing, with better results returned
by deep feedforward networks. This paper investigates \emph{deep
recurrent neural networks}, which combine the multiple levels of
representation that have proved so effective in deep networks with the
flexible use of long range context that empowers RNNs. When trained
end-to-end with suitable regularisation, we find that deep Long
Short-term Memory RNNs achieve a test set error of 17.7% on the TIMIT
phoneme recognition benchmark, which to our knowledge is the best
recorded score.
The purpose of this study was to investigate the effect of a noise injection method on the "overfitting" problem of artificial neural networks (ANNs) in two-class classification tasks. The authors compared ANNs trained with noise injection to ANNs trained with two other methods for avoiding overfitting: weight decay and early stopping. They also evaluated an automatic algorithm for selecting the magnitude of the noise injection. They performed simulation studies of an exclusive-or classification task with training datasets of 50, 100, and 200 cases (half normal and half abnormal) and an independent testing dataset of 2000 cases. They also compared the methods using a breast ultrasound dataset of 1126 cases. For simulated training datasets of 50 cases, the area under the receiver operating characteristic curve (AUC) was greater (by 0.03) when training with noise injection than when training without any regularization, and the improvement was greater than those from weight decay and early stopping (both of 0.02). For training datasets of 100 cases, noise injection and weight decay yielded similar increases in the AUC (0.02), whereas early stopping produced a smaller increase (0.01). For training datasets of 200 cases, the increases in the AUC were negligibly small for all methods (0.005). For the ultrasound dataset, noise injection had a greater average AUC than ANNs trained without regularization and a slightly greater average AUC than ANNs trained with weight decay. These results indicate that training ANNs with noise injection can reduce overfitting to a greater degree than early stopping and to a similar degree as weight decay.
Tracking vehicle trajectories and fuel rates in oscillatory traffic
- wu
A novel clustering approach to identify vehicles equipped with adaptive cruise control in a vehicle trajectory data
- M Khajeh-Hosseini
- A Talebpour
Classification of car-following dynamics via deep learning. under review
- T Li
- Raphael Stern
Tracking vehicle trajectories and fuel rates in oscillatory traffic
- F Wu
- R Stern
- S Cui
- M L Delle Monache
- R Bhadani
- M Bunting