In this work we propose an autoencoder based framework for simultaneous reconstruction and classification of biomedical signals. Previously these two tasks, reconstruction and classification were treated as separate problems. This is the first work to propose a combined framework to address the issue in a holistic fashion. Reconstruction techniques for biomedical signals for tele-monitoring are largely based on compressed sensing (CS) based method, these are designed techniques where the reconstruction formulation is based on some assumption regarding the signal. In this work, we propose a new paradigm for reconstruction we learn to reconstruct. An autoencoder can be trained for the same. But since the final goal is to analyze classify the signal we learn a linear classification map inside the autoencoder. The ensuing optimization problem is solved using the Split Bregman technique. Experiments have been carried out on reconstruction and classification of ECG arrhythmia classification and EEG seizure classification signals. Our proposed tool is capable of operating in a semi-supervised fashion. We show that our proposed method is better and more than an order magnitude faster in reconstruction than CS based methods; it is capable of real-time operation. Our method is also better than recently proposed classification methods. Significance: This is the first work offering an alternative to CS based reconstruction. It also shows that representation learning can yield better results than hand-crafted features for signal analysis.
Design of recommender systems aimed at achieving high prediction accuracy is a widely researched area. However, several studies have suggested the need for diversified recommendations, with acceptable level of accuracy, to avoid monotony and improve customers experience. However, increasing diversity comes with an associated reduction in recommendation accuracy; thereby necessitating an optimum tradeoff between the two. In this work, we attempt to achieve accuracy vs diversity balance, by exploiting available ratings and item metadata, through a single, joint optimization model built over the matrix completion framework. Most existing works, unlike our formulation, propose a 2 stage model, a heuristic item ranking scheme on top of an existing collaborative filtering technique. Experimental evaluation on a movie recommender system indicates that our model achieves higher diversity for a given drop in accuracy as compared to existing state of the art techniques.
Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to variations commonly encountered in image datasets. Using the basic discriminating autoencoder as a unit, we build a stacked architecture aimed at extracting relevant representation from the training data. The efficiency of our feature extraction algorithm ensures a high classification accuracy with even simple classification schemes like KNN (K-nearest neighbor). We demonstrate the superiority of our model for representation learning by conducting experiments on standard datasets for character/image recognition and subsequent comparison with existing supervised deep architectures like class sparse stacked autoencoder and discriminative deep belief network.
This work addresses the problem of estimating proton density and T1 maps from two partially sampled K-space scans such that the total acquisition time remains approximately the same as a single scan. Existing multi parametric non linear curve fitting techniques require a large number (8 or more) of echoes to estimate the maps resulting in prolonged (clinically infeasible) acquisition times. Our simulation results show that our method yields very accurate and robust results from only two partially sampled scans (total scan time being the same as a single echo MRI). We model PD and T1 maps to be sparse in some transform domain. The PD map is recovered via standard Compressed Sensing based recovery technique. Estimating the T1 map requires solving an analysis prior sparse recovery problem from non linear measurements, since the relationship between T1 values and intensity values or K space samples is not linear. For the first time in this work, we propose an algorithm for analysis prior sparse recovery for non linear measurements. We have compared our approach with the only existing technique based on matrix factorization from non linear measurements; our method yields considerably superior results.
Existing works based on latent factor models have focused on representing the rating matrix as a product of user and item latent factor matrices, both being dense. Latent (factor) vectors define the degree to which a trait is possessed by an item or the affinity of user towards that trait. A dense user matrix is a reasonable assumption as each user will like/dislike a trait to certain extent. However, any item will possess only a few of the attributes and never all. Hence, the item matrix should ideally have a sparse structure rather than a dense one as formulated in earlier works. Therefore we propose to factor the ratings matrix into a dense user matrix and a sparse item matrix which leads us to the Blind Compressed Sensing (BCS) framework. We derive an efficient algorithm for solving the BCS problem based on Majorization Minimization (MM) technique. Our proposed approach is able to achieve significantly higher accuracy and shorter run times as compared to existing approaches.
Evolutionary algorithms are metaheuristic techniques that derive inspiration from the natural process of evolution. They can efficiently solve (generate acceptable quality of solution in reasonable time) complex optimization (NP-Hard) problems. In this paper, automatic image enhancement is considered as an optimization problem and three evolutionary algorithms (Genetic Algorithm, Differential Evolution and Self Organizing Migration Algorithm) are employed to search for an optimum solution. They are used to find an optimum parameter set for an image enhancement transfer function. The aim is to maximize a fitness criterion which is a measure of image contrast and the visibility of details in the enhanced image. The enhancement results obtained using all three evolutionary algorithms are compared amongst themselves and also with the output of histogram equalization method.
In this paper we address the problem of recovering a matrix, with inherent low rank structure, from its lower dimensional projections. This problem is frequently encountered in wide range of areas including pattern recognition, wireless sensor networks, control systems, recommender systems, image/video reconstruction etc. Both in theory and practice, the most optimal way to solve the low rank matrix recovery problem is via nuclear norm minimization. In this paper, we propose a Split Bregman algorithm for nuclear norm minimization. The use of Bregman technique improves the convergence speed of our algorithm and gives a higher success rate. Also, the accuracy of reconstruction is much better even for cases where small number of linear measurements are available. Our claim is supported by empirical results obtained using our algorithm and its comparison to other existing methods for matrix recovery. The algorithms are compared on the basis of NMSE, execution time and success rate for varying ranks and sampling ratios.