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

Super-Resolution (SR) is a technique that has been exhaustively exploited and incorporates strategic aspects to image processing. As quantum computers gradually evolve and provide unconditional proof of computational advantage at solving intractable problems over their classical counterparts, quantum computing emerges with the compelling prospect to offer exponential speedup to process computationally expensive operations, such as the ones verified in SR imaging.

In this paper, we propose a novel person verification system based on footfall signatures using Gaussian Mixture Model-Universal Background Model (GMM-UBM). Ground vibration generated by footfall of an individual is used as a biometric modality. We conduct extensive experiments to compare the proposed technique with various baselines of footfall based person verification. The system is evaluated on an indigenous dataset containing 7750 footfall events of twenty subjects.

The clinical analysis of magnetic resonance (MR) can be accelerated through the undersampling in the k-space (Fourier domain). Deep learning techniques have been recently received considerable interest for accelerating MR imaging (MRI). In this paper, a deep learning method for accelerating MRI is presented, which is able to reconstruct undersampled MR images obtained by reducing the k-space data in the direction of the phase encoding.

A successful recommender system interacts with users and learns their preferences. This is crucial in order to provide accurate recommendations. In this paper, a Weighted Ordered Probit Collaborative Kalman filter is proposed for hotel rating prediction. Since potential changes may occur in hotel services or accommodation conditions, a hotel popularity may be volatile through time. A weighted ordered probit model is introduced to capture this latent trend about each hotel popularity through time.

The growing edge computing paradigm, notably the vision of the internet-of-things (IoT), calls for a new epitome of lightweight algorithms. Currently, the most successful models that learn from temporal data, which is prevalent in IoT applications, stem from the field of deep learning. However, these models evince extended training times and heavy resource requirements, prohibiting training in constrained environments. To address these concerns, we employ deep stochastic neural networks from the reservoir computing paradigm.

Unit sphere-constrained quadratic optimization has been studied extensively over the past decades. While state-of-art algorithms for solving this problem often rely on relaxation or approximation techniques, there has been little research into scalable first-order methods that tackle the problem in its original form. These first-order methods are often more well-suited for the big data setting. In this paper, we provide a novel analysis of the simple projected gradient descent method for minimizing a quadratic over a sphere.

Online banking activities are constantly growing and are likely to become even more common as digital banking platforms evolve. One side effect of this trend is the rise in attempted fraud. However, there is very little work in the literature on online banking fraud detection. We propose an attention based architecture for classifying online banking transactions as either fraudulent or genuine. The proposed method allows transparency to its decision by identifying the most important transactions in the sequence and the most informative features in each transaction.

Compressive spectral imaging (CSI) acquires random projections of a spectral scene. Typically, before applying any post-processing task, e.g. clustering, it is required a computationally expensive reconstruction of the underlying 3D scene. Therefore, several works focus on improving the reconstruction quality by adaptively designing the sensing matrix aiming at better post-processing results. Instead, this paper proposes a hierarchical adaptive approach to design a sensing matrix of the single-pixel camera, such that pixel clustering can be performed in the compressed domain.

The supervised learning paradigm is limited by the cost - and sometimes the impracticality - of data collection and labeling in multiple domains. Self-supervised learning, a paradigm which exploits the structure of unlabeled data to create learning problems that can be solved with standard supervised approaches, has shown great promise as a pretraining or feature learning approach in fields like computer vision and time series processing. In this work, we present self-supervision strategies that can be used to learn informative representations from multivariate time series.