Taesup Moon

Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks

We propose the use of deep convolutional neural networks (DCNNs) for human detection and activity classification based on Doppler radar. Previously, proposed schemes for these problems remained in the conventional supervised learning paradigm that relies on the design of handcrafted features. Whereas these schemes attained high accuracy, the requirement for domain knowledge of each problem limits the scalability of the proposed schemes. In this letter, we present an alternative deep learning approach. We apply the DCNN, one of the most successful deep learning algorithms, directly to a raw micro-Doppler spectrogram for both human detection and activity classification problem. The DCNN can jointly learn the necessary features and classification boundaries using the measured data without employing any explicit features on the micro-Doppler signals. We show that the DCNN can achieve accuracy results of 97.6% for human detection and 90.9% for human activity classification.

IntervalRank: isotonic regression with listwise and pairwise constraints

Ranking a set of retrieved documents according to their relevance to a given query has become a popular problem at the intersection of web search, machine learning, and information retrieval. Recent work on ranking focused on a number of different paradigms, namely, pointwise, pairwise, and list-wise approaches. Each of those paradigms focuses on a different aspect of the dataset while largely ignoring others. The current paper shows how a combination of them can lead to improved ranking performance and, moreover, how it can be implemented in log-linear time. The basic idea of the algorithm is to use isotonic regression with adaptive bandwidth selection per relevance grade. This results in an implicitly-defined loss function which can be minimized efficiently by a subgradient descent procedure. Experimental results show that the resulting algorithm is competitive on both commercial search engine data and publicly available LETOR data sets.

RNNDROP: A novel dropout for RNNS in ASR

Recently, recurrent neural networks (RNN) have achieved the state-of-the-art performance in several applications that deal with temporal data, e.g., speech recognition, handwriting recognition and machine translation. While the ability of handling long-term dependency in data is the key for the success of RNN, combating over-fitting in training the models is a critical issue for achieving the cutting-edge performance particularly when the depth and size of the network increase. To that end, there have been some attempts to apply the dropout, a popular regularization scheme for the feed-forward neural networks, to RNNs, but they do not perform as well as other regularization scheme such as weight noise injection. In this paper, we propose rnnDrop, a novel variant of the dropout tailored for RNNs. Unlike the existing methods where dropout is applied only to the non-recurrent connections, the proposed method applies dropout to the recurrent connections as well in such a way that RNNs generalize well. Our experiments show that rnnDrop is a better regularization method than others including weight noise injection. Namely, when deep bidirectional long short-term memory (LSTM) RNNs were trained with rnnDrop as acoustic models for phoneme and speech recognition, they significantly outperformed the current state-of-the-arts; we achieved the phoneme error rate of 16.29% on the TIMIT core test set for phoneme recognition and the word error rate of 5.53% on the Wall Street Journal (WSJ) dataset, dev93, for speech recognition, which are the best reported results on both of the datasets.

Discrete Denoising With Shifts

We introduce S-DUDE, a new algorithm for denoising discrete memoryless channel (DMC)-corrupted data. The algorithm, which generalizes the recently introduced DUDE (discrete universal denoiser), aims to compete with a genie that has access, in addition to the noisy data, also to the underlying clean data, and that can choose to switch, up to m times, between sliding-window denoisers in a way that minimizes the overall loss. When the underlying data form an individual sequence, we show that the S-DUDE performs essentially as well as this genie, provided that m is sublinear in the size of the data. When the clean data are emitted by a piecewise stationary process, we show that the S-DUDE achieves the optimum distribution-dependent performance, provided that the same sublinearity condition is imposed on the number of switches. To further substantiate the universal optimality of the S-DUDE, we show that when the number of switches is allowed to grow linearly with the size of the data, any (sequence of) scheme(s) fails to compete in the above sense. Using dynamic programming, we derive an efficient implementation of the S-DUDE, which has complexity (time and memory) growing linearly with the data size and the number of switches m . Preliminary experimental results are presented, suggesting that S-DUDE has the capacity to improve on the performance attained by the original DUDE in applications where the nature of the data abruptly changes in time (or space), as is often the case in practice.

An Online Learning Framework for Refining Recency Search Results with User Click Feedback

Traditional machine-learned ranking systems for Web search are often trained to capture stationary relevance of documents to queries, which have limited ability to track nonstationary user intention in a timely manner. In recency search, for instance, the relevance of documents to a query on breaking news often changes significantly over time, requiring effective adaptation to user intention. In this article, we focus on recency search and study a number of algorithms to improve ranking results by leveraging user click feedback. Our contributions are threefold. First, we use commercial search engine sessions collected in a random exploration bucket for reliable offline evaluation of these algorithms, which provides an unbiased comparison across algorithms without online bucket tests. Second, we propose an online learning approach that reranks and improves the search results for recency queries near real-time based on user clicks. This approach is very general and can be combined with sophisticated click models. Third, our empirical comparison of a dozen algorithms on real-world search data suggests importance of a few algorithmic choices in these applications, including generalization across different query-document pairs, specialization to popular queries, and near real-time adaptation of user clicks for reranking.

Universal FIR MMSE Filtering

We consider the problem of causal estimation, i.e., filtering, of a real-valued signal corrupted by zero mean, time-independent, real-valued additive noise, under the mean-squared error (MSE) criterion. We build a universal filter whose per-symbol squared error, for every bounded underlying signal, is essentially as small as that of the best finite-duration impulse response (FIR) filter of a given order. We do not assume a stochastic mechanism generating the underlying signal, and assume only that the variance of the noise is known to the filter. The regret of the expected MSE of our scheme is shown to decay as O(logn/n), where n is the length of the signal. Moreover, we present a stronger concentration result which guarantees the performance of our scheme not only in expectation, but also with high probability. Our result implies a conventional stochastic setting result, i.e., when the underlying signal is a stationary process, our filter achieves the performance of the optimal FIR filter. We back our theoretical findings with several experiments showcasing the potential merits of our universal filter in practice. Our analysis combines tools from the problems of universal filtering and competitive online regression.

Micro-Doppler Based Classification of Human Aquatic Activities via Transfer Learning of Convolutional Neural Networks

Accurate classification of human aquatic activities using radar has a variety of potential applications such as rescue operations and border patrols. Nevertheless, the classification of activities on water using radar has not been extensively studied, unlike the case on dry ground, due to its unique challenge. Namely, not only is the radar cross section of a human on water small, but the micro-Doppler signatures are much noisier due to water drops and waves. In this paper, we first investigate whether discriminative signatures could be obtained for activities on water through a simulation study. Then, we show how we can effectively achieve high classification accuracy by applying deep convolutional neural networks (DCNN) directly to the spectrogram of real measurement data. From the five-fold cross-validation on our dataset, which consists of five aquatic activities, we report that the conventional feature-based scheme only achieves an accuracy of 45.1%. In contrast, the DCNN trained using only the collected data attains 66.7%, and the transfer learned DCNN, which takes a DCNN pre-trained on a RGB image dataset and fine-tunes the parameters using the collected data, achieves a much higher 80.3%, which is a significant performance boost.

User behavior driven ranking without editorial judgments

We explore the potential of using users click-through logs where no editorial judgment is available to improve the ranking function of a vertical search engine. We base our analysis on the Cumulate Relevance Model, a user behavior model recently proposed as a way to extract relevance signal from click-through logs. We propose a novel way of directly learning the ranking function, effectively by-passing the need to have explicit editorial relevance label for each query-document pair. This approach potentially adjusts more closely the ranking function to a variety of user behaviors both at the individual and at the aggregate levels. We investigate two ways of using behavioral model; First, we consider the parametric approach where we learn the estimates of document relevance and use them as targets for the machine learned ranking schemes. In the second, functional approach, we learn a function that maximizes the behavioral model likelihood, effectively by-passing the need to estimate a substitute for document labels. Experiments using user session data collected from a commercial vertical search engine demonstrate the potential of our approach. While in terms of DCG, the editorial model out-perform the behavioral one, online experiments show that the behavioral model is on par --if not superior-- to the editorial model. To our knowledge, this is the first report in the Literature of a competitive behavioral model in a commercial setting

Regularization and Kernelization of the Maximin Correlation Approach

Robust classification becomes challenging when each class consists of multiple subclasses. Examples include multi-font optical character recognition and automated protein function prediction. In correlation-based nearest-neighbor classification, the maximin correlation approach (MCA) provides the worst-case optimal solution by minimizing the maximum misclassification risk through an iterative procedure. Despite the optimality, the original MCA has drawbacks that have limited its wide applicability in practice. That is, the MCA tends to be sensitive to outliers, cannot effectively handle nonlinearities in datasets, and suffers from having high computational complexity. To address these limitations, we propose an improved solution, named regularized MCA (R-MCA). We first reformulate MCA as a quadratically constrained linear programming (QCLP) problem, incorporate regularization by introducing slack variables in the primal problem of the QCLP, and derive the corresponding Lagrangian dual. The dual formulation enables us to apply the kernel trick to R-MCA, so that it can better handle nonlinearities. Our experimental results demonstrate that the regularization and kernelization make the proposed R-MCA more robust and accurate for various classification tasks than the original MCA. Furthermore, when the data size or dimensionality grows, R-MCA runs substantially faster by solving either the primal or dual (whichever has a smaller variable dimension) of the QCLP.

Competitive On-line Linear FIR MMSE Filtering

We consider the problem of causal estimation, i.e., filtering, of a real-valued signal corrupted by zero mean, i.i.d., real-valued additive noise under the mean square error (MSE) criterion. We build a competitive on-line filtering algorithm whose normalized cumulative MSE, for every bounded underlying signal, is asymptotically as small as the best linear finite-duration impulse response (FIR) filter of order d. We do not assume any stochastic mechanism in generating the underlying signal, and assume only the variance of the noise is known to the filter. The regret of our scheme is shown to decay in the order of O (log n/n), where n is the length of the signal. Moreover, we present a concentration of the average square error of our scheme to that of the best d-th order linear FIR filter. Our analysis combines tools from the problems of universal filtering and competitive on-line regression.