Imagine Industrial IoT as the nervous system of a company: it is a network of sensors that collects valuable information from all corners of a production plant and stores it in a repository for data analysis and exploitation. This network is necessary to measure and obtain data in order to make informed decisions. We always talk about making good decisions based on reliable information, but although it may sound obvious, it is not always that easy to achieve that goal. In this article, we will go a bit beyond IoT and will focus on the data and how to leverage it with AIoT and data analytics. We'll be discussing specifically the analysis phase, the process that turns data first into information and then into knowledge (sometimes also referred to as business logic). In the end, however, we won't stray far from the core subject of IoT, because for us IoT without Big Data is meaningless.

This paper proposes an efficient way to reduce usage or predict the future needs of appliances or power consumption by using the weather information data . Over the last few years, activity recognition in the smart home has become an active research area due to the wide range of human centric-applications. IoT brings together everything at home under one umbrella which has the potential to monitor and remote control such as air conditioning, alarm system, lighting, heating, ventilation, telephone system, tv, etc. To enhance our comfort and security with low energy consumption and energy management is one of the IoT use cases with which energy being sent out or consumed can be monitored. One can monitor each of the IoT appliances and how much power each of the devices is consuming, and easily switch between energy-efficient appliances across the day. In this case study we are going to focus on predicting the future energy consumption with the past data so that we can manage our day to day usage of appliances at home.

Electric vehicles have the potential to substantially reduce carbon emissions, but car companies are running out of materials to make batteries. One crucial component, nickel, is projected to cause supply shortages as early as the end of this year. Scientists recently discovered four new materials that could potentially help--and what may be even more intriguing is how they found these materials: the researchers relied on artificial intelligence to pick out useful chemicals test from a list of more than 300 options. And they are not the only humans turning to A.I. for scientific inspiration. Creating hypotheses has long been a purely human domain.

Mixed-signal analog/digital circuits emulate spiking neurons and synapses with extremely high energy efficiency, an approach known as "neuromorphic engineering". However, analog circuits are sensitive to process-induced variation among transistors in a chip ("device mismatch"). For neuromorphic implementation of Spiking Neural Networks (SNNs), mismatch causes parameter variation between identically-configured neurons and synapses. Each chip exhibits a different distribution of neural parameters, causing deployed networks to respond differently between chips. Current solutions to mitigate mismatch based on per-chip calibration or on-chip learning entail increased design complexity, area and cost, making deployment of neuromorphic devices expensive and difficult. Here we present a supervised learning approach that produces SNNs with high robustness to mismatch and other common sources of noise. Our method trains SNNs to perform temporal classification tasks by mimicking a pre-trained dynamical system, using a local learning rule from non-linear control theory. We demonstrate our method on two tasks requiring memory, and measure the robustness of our approach to several forms of noise and mismatch. We show that our approach is more robust than common alternatives for training SNNs. Our method provides robust deployment of pre-trained networks on mixed-signal neuromorphic hardware, without requiring per-device training or calibration.

In this paper, we address two key challenges in deep reinforcement learning setting, sample inefficiency and slow learning, with a dual NN-driven learning approach. In the proposed approach, we use two deep NNs with independent initialization to robustly approximate the action-value function in the presence of image inputs. In particular, we develop a temporal difference (TD) error-driven learning approach, where we introduce a set of linear transformations of the TD error to directly update the parameters of each layer in the deep NN. We demonstrate theoretically that the cost minimized by the error-driven learning (EDL) regime is an approximation of the empirical cost and the approximation error reduces as learning progresses, irrespective of the size of the network. Using simulation analysis, we show that the proposed methods enables faster learning and convergence and requires reduced buffer size (thereby increasing the sample efficiency).

Learning controllers that reproduce legged locomotion in nature have been a long-time goal in robotics and computer graphics. While yielding promising results, recent approaches are not yet flexible enough to be applicable to legged systems of different morphologies. This is partly because they often rely on precise motion capture references or elaborate learning environments that ensure the naturality of the emergent locomotion gaits but prevent generalization. This work proposes a generic approach for ensuring realism in locomotion by guiding the learning process with the spring-loaded inverted pendulum model as a reference. Leveraging on the exploration capacities of Reinforcement Learning (RL), we learn a control policy that fills in the information gap between the template model and full-body dynamics required to maintain stable and periodic locomotion. The proposed approach can be applied to robots of different sizes and morphologies and adapted to any RL technique and control architecture. We present experimental results showing that even in a model-free setup and with a simple reactive control architecture, the learned policies can generate realistic and energy-efficient locomotion gaits for a bipedal and a quadrupedal robot. And most importantly, this is achieved without using motion capture, strong constraints in the dynamics or kinematics of the robot, nor prescribing limb coordination. We provide supplemental videos for qualitative analysis of the naturality of the learned gaits.

Airborne magnetic data are commonly used to produce preliminary geological maps. Machine learning has the potential to partly fulfill this task rapidly and objectively, as geological mapping is comparable to a semantic segmentation problem. Because this method requires a high-quality dataset, we developed a data augmentation workflow that uses a 3D geological and magnetic susceptibility model as input. The workflow uses soft-constrained Multi-Point Statistics, to create many synthetic 3D geological models, and Sequential Gaussian Simulation algorithms, to populate the models with the appropriate magnetic distribution. Then, forward modeling is used to compute the airborne magnetic responses of the synthetic models, which are associated with their counterpart surficial lithologies. A Gated Shape Convolutional Neural Network algorithm was trained on a generated synthetic dataset to perform geological mapping of airborne magnetic data and detect lithological contacts. The algorithm also provides attention maps highlighting the structures at different scales, and clustering was applied to its high-level features to do a semi-supervised segmentation of the area. The validation conducted on a portion of the synthetic dataset and data from adjacent areas shows that the methodology is suitable to segment the surficial geology using airborne magnetic data. Especially, the clustering shows a good segmentation of the magnetic anomalies into a pertinent geological map. Moreover, the first attention map isolates the structures at low scales and shows a pertinent representation of the original data. Thus, our method can be used to produce preliminary geological maps of good quality and new representations of any area where a geological and petrophysical 3D model exists, or in areas sharing the same geological context, using airborne magnetic data only.

Network load balancers are important components in data centers to provide scalable services. Workload distribution algorithms are based on heuristics, e.g., Equal-Cost Multi-Path (ECMP), Weighted-Cost Multi-Path (WCMP) or naive machine learning (ML) algorithms, e.g., ridge regression. Advanced ML-based approaches help achieve performance gain in different networking and system problems. However, it is challenging to apply ML algorithms on networking problems in real-life systems. It requires domain knowledge to collect features from low-latency, high-throughput, and scalable networking systems, which are dynamic and heterogenous. This paper proposes Aquarius to bridge the gap between ML and networking systems and demonstrates its usage in the context of network load balancers. This paper demonstrates its ability of conducting both offline data analysis and online model deployment in realistic systems. The results show that the ML model trained and deployed using Aquarius improves load balancing performance yet they also reveals more challenges to be resolved to apply ML for networking systems.

Copulas are a powerful tool for modeling multivariate distributions as they allow to separately estimate the univariate marginal distributions and the joint dependency structure. However, known parametric copulas offer limited flexibility especially in high dimensions, while commonly used non-parametric methods suffer from the curse of dimensionality. A popular remedy is to construct a tree-based hierarchy of conditional bivariate copulas. In this paper, we propose a flexible, yet conceptually simple alternative based on implicit generative neural networks. The key challenge is to ensure marginal uniformity of the estimated copula distribution. We achieve this by learning a multivariate latent distribution with unspecified marginals but the desired dependency structure. By applying the probability integral transform, we can then obtain samples from the high-dimensional copula distribution without relying on parametric assumptions or the need to find a suitable tree structure. Experiments on synthetic and real data from finance, physics, and image generation demonstrate the performance of this approach.

Artifact removal is an integral component of cinematic scientific visualization, and is especially challenging with big datasets in which artifacts are difficult to define. In this paper, we describe a method for creating cloud artifact masks which can be used to remove artifacts from satellite imagery using a combination of traditional image processing together with deep learning based on U-Net. Compared to previous methods, our approach does not require multi-channel spectral imagery but performs successfully on single-channel Digital Elevation Models (DEMs). DEMs are a representation of the topography of the Earth and have a variety applications including planetary science, geology, flood modeling, and city planning.