Sorry, you need to enable JavaScript to visit this website.

We present an approach for detecting application level protocols over a wireless communications link, without the need for demodulation or decryption. Our detector is suitable for diverse radio types, since only simple external signal features are used as inputs. We show that the Profile Hidden Markov Model (PHMM) is well suited to this task, due to the probabilistic nature of the wireless channel and the discrete nature of application level traffic. We include results evaluating the detection performance for two application protocols in 802.11 in the presence of background traffic.

Multilayer graphs are commonly used for representing different relations between entities and handling heterogeneous data processing tasks. New challenges arise in multilayer graph clustering for assigning clusters to a common multilayer node set and for combining information from each layer. This paper presents a theoretical framework for multilayer spectral graph clustering of the nodes via convex layer aggregation.

This paper addresses the problem of learning a discriminative dictionary from training signals. Given a structured dictionary, each atom of which has its corresponding label, one signal should be mainly constructed by its closely associated atoms. Besides the representations for the same class ought to be very close to form a cluster. Thus we present out-of-label suppression dictionary model with cluster regularization to amplify the discriminative power. Upon out-of-label suppression, we don't adopt $l_0$-norm or $l_1$-norm for regularization.

We define micro hand gesture recognition system as which uses micro dynamic hand gestures within a time interval for classification and recognition to achieve human-machine interaction. Our Project Hug (Hand-Ultrasonic-Gesture), with ultrasonic active sensing, pulsed radar signal processing, and time-sequence pattern recognition is presented in this paper for micro hand gesture recognition. We leverage one single channel to detect both range and velocity precisely, reducing the hardware complexity.

This report describes a method which is implemented for the IEEE signal Processing Cup 2016, that is to extract power signatures from a given media signal and identify where the signal was recorded in order to be used for forensic applications.
The primary task of this project was to design a system which can identify the captured location of a given multimedia sample based on the Electrical network frequency signals (ENF) signal embedded in it.

Partial face recognition is a problem that often arises in practical settings and applications. We propose a sparse representation-based algorithm for this problem. Our method firstly trains a dictionary and the classifier parameters in a supervised dictionary learning framework and then aligns the partially observed test image and seeks for the sparse representation with respect to the training data alternatively to obtain its label. We also analyze the performance limit of sparse representation-based classification algorithms on partial observations.

This presentation introduces a Deep Learning model that performs classification of the Audio Scene in the subway environment. The final goal is to detect Screams and Shouts for surveillance purposes. The model is a combination of Deep Belief Network and Deep Neural Network, (generatively pre-trained within the DBN framework and fine-tuned discriminatively within the DNN framework), and is trained on a novel database of pseudo-real signals collected in the Paris metro.

In this paper, we present Discriminant Correlation Analysis (DCA), a feature level fusion technique that incorporates the class associations in correlation analysis of the feature sets. DCA performs an effective feature fusion by maximizing the pair-wise correlations across the two feature sets, and at the same time, eliminating the between-class correlations and restricting the correlations to be within classes.

Recently, sparse representation based classification has been widely used in pattern recognition. Most of existing methods exploit the recovered representation coefficients to reconstruct the inputs, and the classwise reconstruction errors are used to identify the class of the sample based on the subspace assumption. Different from the reconstruction pipeline, an assignment framework is built on the representation coefficients in this paper.