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

Time-delay estimation is an essential building block of many signal processing applications. This paper follows up on earlier work for acoustic source localization and time delay estimation using pattern recognition techniques; it presents high performance results obtained with supervised training of neural networks which challenge the state of the art and compares its performance to that of well-known methods such as the Generalized Cross-Correlation or Adaptive Eigenvalue Decomposition.

Estimating accurate number of interested objects from a given image is a challenging yet important task. Significant efforts have been made to address this problem and achieve great progress, yet counting number of ground objects from remote sensing images is barely studied. In this paper, we are interested in counting dense objects from remote sensing images. Compared with object counting in natural scene, this task is challenging in following factors: large scale variation, complex cluttered background and orientation arbitrariness.

Estimating accurate number of interested objects from a given image is a challenging yet important task. Significant efforts have been made to address this problem and achieve great progress, yet counting number of ground objects from remote sensing images is barely studied. In this paper, we are interested in counting dense objects from remote sensing images. Compared with object counting in natural scene, this task is challenging in following factors: large scale variation, complex cluttered background and orientation arbitrariness.

Our work has focused on detecting Mild Cognitive Impairment (MCI) by developing Serious Games (SG) on mobile devices, distinct from games marketed as 'brain training' which claim to maintain mental acuity. One game, WarCAT, captures players' moves during the game to infer processes of strategy recognition, learning, and memory. The purpose of our game is to use the generated game-play data combined with machine learning (ML) to help detect MCI. MCI is difficult to detect for several reasons.

We explore the resistance of deep learning methods for radio fingerprinting to MAC ID spoofing. We demonstrate that classifying transmission slices enables classification of a transmission with a fixed-length input deep classifier, enhances shift-invariance, and, most importantly, makes the classifier resistant to MAC ID spoofing. This is a consequence of the fact that the classifier does not learn to use the MAC ID to classifying among transmissions, but relies on other inherent discriminating signals, e.g., device imperfections.

Air pollution is the leading environmental health hazard globally due to various sources which include factory emissions, car exhaust and cooking stoves. As a precautionary measure, air pollution forecast serves as the basis for taking effective pollution control measures, and accurate air pollution forecasting has become an important task. In this paper, we forecast fine-grained ambient air quality information for 5 prominent locations in Delhi based on the historical and realtime ambient air quality and meteorological data reported by Central Pollution Control board.

Abstract—To satisfy the strict latency requirement of Ultra Reliable Low Latency Communications (URLLC) traffic, it is usually scheduled on resources occupied by enhanced Mobile Broadband (eMBB) transmissions at the expense of a highly degraded eMBB spectral efficiency (SE). In this paper, we propose a back propagation neural network (BPNN) based punctured scheduling scheme to address the URLLC placement problem on eMBB traffic within mini-slots.

Glandular morphology is used by pathologists to assess the malignancy of different adenocarcinomas. This process involves conducting gland segmentation task. The common approach in specialised domains, such as medical imaging, is to design complex architectures in a multi-task learning setup. Generally, these approaches rely on substantial postprocessing efforts. Moreover, a predominant notion is that general purpose models are not suitable for gland instance segmentation. We analyse the behaviour of two architectures: SA-FCN and Mask R-CNN.

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.