Planning for multi-robot coverage seeks to determine collision-free paths for a fleet of robots, enabling them to collectively observe points of interest in an environment. Persistent coverage is a variant of traditional coverage where coverage-levels in the environment decay over time. Thus, robots have to continuously revisit parts of the environment to maintain a desired coverage-level. Facilitating this in the real world demands we tackle numerous subproblems. While there exist standard solutions to these subproblems, there is no complete framework that addresses all of their individual challenges as a whole in a practical setting. We adapt and combine these solutions to present a planning framework for persistent coverage with multiple unmanned aerial vehicles (UAVs). Specifically, we run a continuous loop of goal assignment and globally deconflicting, kinodynamic path planning for multiple UAVs. We evaluate our framework in simulation as well as the real world. In particular, we demonstrate that (i) our framework exhibits graceful coverage given sufficient resources, we maintain persistent coverage; if resources are insufficient (e.g., having too few UAVs for a given size of the enviornment), coverage-levels decay slowly and (ii) planning with global deconfliction in our framework incurs a negligibly higher price compared to other weaker, more local collision-checking schemes. (Video: https://youtu.be/aqDs6Wymp5Q)

Proactively perceiving others' intentions is a crucial skill to effectively interact in unstructured, dynamic and novel environments. This work proposes a first step towards embedding this skill in support robots for search and rescue missions. Predicting the responders' intentions, indeed, will enable exploration approaches which will identify and prioritise areas that are more relevant for the responder and, thus, for the task, leading to the development of safer, more robust and efficient joint exploration strategies. More specifically, this paper presents an active intention recognition paradigm to perceive, even under sensory constraints, not only the target's position but also the first responder's movements, which can provide information on his/her intentions (e.g. reaching the position where he/she expects the target to be). This mechanism is implemented by employing an extension of Monte-Carlo-based planning techniques for partially observable environments, where the reward function is augmented with an entropy reduction bonus. We test in simulation several configurations of reward augmentation, both information theoretic and not, as well as belief state approximations and obtain substantial improvements over the basic approach.

Active Learning methods create an optimized and labeled training set from unlabeled data. We introduce a novel Online Active Deep Learning method for Medical Image Analysis. We extend our MedAL active learning framework to present new results in this paper. Experiments on three medical image datasets show that our novel online active learning model requires significantly less labelings, is more accurate, and is more robust to class imbalances than existing methods. Our method is also more accurate and computationally efficient than the baseline model. Compared to random sampling and uncertainty sampling, the method uses 275 and 200 (out of 768) fewer labeled examples, respectively. For Diabetic Retinopathy detection, our method attains a 5.88% accuracy improvement over the baseline model when 80% of the dataset is labeled, and the model reaches baseline accuracy when only 40% is labeled.

We study the risk of minimum-norm interpolants of data in a Reproducing Kernel Hilbert Space where kernel is defined as a function of the inner product. Our upper bounds on the risk are of a multiple-descent shape for the various scalings of d = n^\alpha, \alpha\in(0,1), for the input dimension d and sample size n. At the heart of our analysis is a study of spectral properties of the random kernel matrix restricted to a filtration of eigen-spaces of the population covariance operator. Since gradient flow on appropriately initialized wide neural networks converges to a minimum-norm interpolant, the analysis also yields estimation guarantees for these models.

This work aims at modeling how the meaning of gradable adjectives of size (`big', `small') can be learned from visually-grounded contexts. Inspired by cognitive and linguistic evidence showing that the use of these expressions relies on setting a threshold that is dependent on a specific context, we investigate the ability of multi-modal models in assessing whether an object is `big' or `small' in a given visual scene. In contrast with the standard computational approach that simplistically treats gradable adjectives as `fixed' attributes, we pose the problem as relational: to be successful, a model has to consider the full visual context. By means of four main tasks, we show that state-of-the-art models (but not a relatively strong baseline) can learn the function subtending the meaning of size adjectives, though their performance is found to decrease while moving from simple to more complex tasks. Crucially, models fail in developing abstract representations of gradable adjectives that can be used compositionally.

Nuclear segmentation in histology images is a challenging task due to significant variations in the shape and appearance of nuclei. One of the main hurdles in nuclear instance segmentation is overlapping nuclei where a smart algorithm is needed to separate each nucleus. In this paper, we introduce a proposal-free deep learning based framework to address these challenges. To this end, we propose a spatially-aware network (SpaNet) to capture spatial information in a multi-scale manner. A dual-head variation of the SpaNet is first utilized to predict the pixel-wise segmentation and centroid detection maps of nuclei. Based on these outputs, a single-head SpaNet predicts the positional information related to each nucleus instance. Spectral clustering method is applied on the output of the last SpaNet, which utilizes the nuclear mask and the Gaussian-like detection map for determining the connected components and associated cluster identifiers, respectively. The output of the clustering method is the final nuclear instance segmentation mask. We applied our method on a publicly available multi-organ data set and achieved state-of-the-art performance for nuclear segmentation.

--As more end devices are getting connected, the Internet will become more congested. Various congestion control techniques have been developed either on transport or network layers. Active Queue Management (AQM) is a paradigm that aims to mitigate the congestion on the network layer through active buffer control to avoid overflow. However, finding the right parameters for an AQM scheme is challenging, due to the complexity and dynamics of the networks. On the other hand, the Explicit Congestion Notification (ECN) mechanism is a solution that makes visible incipient congestion on the network layer to the transport layer. In this work, we propose to exploit the ECN information to improve AQM algorithms by applying Machine Learning techniques. Our intelligent method uses an artificial neural network to predict congestion and an AQM parameter tuner based on reinforcement learning. The evaluation results show that our solution can enhance the performance of deployed AQM, using the existing TCP congestion control mechanisms. Thanks to the proliferation of smart devices and the paradigm of Internet of Things (IoT), the demand for connections to the Internet is dramatically growing.

Combining the capabilities of the programmability of networks by SDN and discovering patterns by machine learning are utilized in security, traffic classification, QoS prediction, and network performance and has attracted the attention of researchers. In this work, we propose HyMER: a novel hybrid machine learning framework for traffic aware energy efficient routing in SDN which has supervised and reinforcement learning components. The supervised learning component consists of feature extraction, training, and testing. The reinforcement learning component learns from existing data or from scratch by iteratively interacting with the network environment. The framework is developed on POX controller and is evaluated on Mininet using Abiline, GEANT, and Nobel-Germany real-world topologies and dynamic traffic traces. Experimental results show that the supervised component achieves up to 70% feature size reduction and more than 80% accuracy in parameter prediction. The refine heuristics algorithm increases the accuracy of the prediction to 100% with 14X to 25X speedup as compared to the brute force method. The reinforcement learning module converges from 100 to 275 iterations and converges twice faster if applied on top of the supervised component. Moreover, HyMER achieves up to 10 watts per switch power saving, 30% link saving, 2 hops decrease in average path length.

The U.S. water distribution system contains thousands of miles of pipes constructed from different materials, and of various sizes, and age. These pipes suffer from physical, environmental, structural and operational stresses, causing deterioration which eventually leads to their failure. Pipe deterioration results in increased break rates, reduced hydraulic capacity, and detrimental impacts on water quality. Therefore, it is crucial to use accurate models to forecast deterioration rates along with estimating the remaining useful life of the pipes to implement essential interference plans in order to prevent catastrophic failures. This paper discusses a computational model that forecasts the RUL of water pipes by applying Artificial Neural Networks (ANNs) as well as Adaptive Neural Fuzzy Inference System (ANFIS). These models are trained and tested acquired field data to identify the significant parameters that impact the prediction of RUL. It is concluded that, on average, with approximately 10\% of wall thickness loss in existing cast iron, ductile iron, asbestos-cement, and steel water pipes, the reduction of the remaining useful life is approximately 50%

In this work we use Recurrent Neural Networks and Multilayer Perceptrons to predict NYSE, NASDAQ and AMEX stock prices from historical data. We experiment with different architectures and compare data normalization techniques. Then, we leverage those findings to question the efficient-market hypothesis through a formal statistical test.