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

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.

Deep-learning based speech enhancement systems have offered tremendous gains, where the best performing approaches use long short-term memory (LSTM) recurrent neural networks (RNNs) to model temporal speech correlations. These models, however, do not consider the frequency-level correlations within a single time frame, as spectral dependencies along the frequency axis are often ignored. This results in inaccurate frequency responses that negatively affect perceptual quality and intelligibility. We propose a deep-learning approach that considers temporal and frequency-level dependencies.

After their triumph in various classification, recognition and segmentation problems, deep learning and convolutional networks are now making great strides in different inverse problems of imaging. Magnetic resonance image (MRI) reconstruction is an important imaging inverse problem, where deep learning methodologies are starting to make impact. In this work we will develop a new Convolutional Neural Network (CNN) based variant for MRI reconstruction. The developed algorithm is based on the recently proposed deep cascaded CNN (DC-CNN) structure.

Non-maximum suppression (NMS) is a post-processing step in almost every visual object detector. Its goal is to drastically prune the number of overlapping detected candidate regions-of-interest (ROIs) and replace them with a single, more spatially accurate detection. The default algorithm (Greedy NMS) is fairly simple and suffers from drawbacks, due to its need for manual tuning. Recently, NMS has been improved using deep neural networks that learn how to solve a spatial overlap-based detections rescoring task in a supervised manner, where only ROI coordinates are exploited as input.

In recent years, deep metric learning has achieved promising results in learning high dimensional semantic feature embeddings where the spatial relationships of the feature vectors match the visual similarities of the images. Similarity search for images is performed by determining the vectors with the smallest distances to a query vector. However, high retrieval quality does not depend on the actual distances of the feature vectors, but rather on the ranking order of the feature vectors from similar images.