Reactive flows in porous media play an important role in our life and are crucial for many industrial, environmental and biomedical applications. Very often the concentration of the species at the inlet is known, and the so-called breakthrough curves, measured at the outlet, are the quantities which could be measured or computed numerically. The measurements and the simulations could be time-consuming and expensive, and machine learning and Big Data approaches can help to predict breakthrough curves at lower costs. Machine learning (ML) methods, such as Gaussian processes and fully-connected neural networks, and a tensor method, cross approximation, are well suited for predicting breakthrough curves. In this paper, we demonstrate their performance in the case of pore scale reactive flow in catalytic filters.
Although digital twins have recently emerged as a clear alternative for reliable asset representations, most of the solutions and tools available for the development of digital twins are tailored to specific environments. Furthermore, achieving reliable digital twins often requires the orchestration of technologies and paradigms such as machine learning, the Internet of Things, and 3D visualization, which are rarely seamlessly aligned. In this paper, we present a generic framework for the development of effective digital twins combining some of the aforementioned areas. In this open framework, digital twins can be easily developed and orchestrated with 3D connected visualizations, IoT data streams, and real-time machine-learning predictions. To demonstrate the feasibility of the framework, a use case in the Petrochemical Industry 4.0 has been developed.
A simple motion amplification algorithm suitable for real-time applications on mobile devices is presented. It is based on motion enhancement by moving average differencing (MEMAD), a temporal high-pass filter for video streams. MEMAD can amplify small moving objects or subtle motion in larger objects. It is computationally sufficiently simple to be implemented in real time on smartphones. In the specific implementation as an Android phone app, MEMAD is demonstrated on examples chosen such as to motivate applications in the engineering, biological, and medical sciences.
With the prospect of automating a number of chemical tasks with high fidelity, chemical language processing models are emerging at a rapid speed. Here, we present a cloud-based real-time platform that allows users to virtually screen molecules of interest. For this purpose, molecular embeddings inferred from a recently proposed large chemical language model, named MolFormer, are leveraged. The platform currently supports three tasks: nearest neighbor retrieval, chemical space visualization, and property prediction. Based on the functionalities of this platform and results obtained, we believe that such a platform can play a pivotal role in automating chemistry and chemical engineering research, as well as assist in drug discovery and material design tasks. A demo of our platform is provided at \url{www.ibm.biz/molecular_demo}.
New technologies and the availability of geospatial data have drawn attention to spatio-temporal biases present in society. For example: the COVID-19 pandemic highlighted disparities in the availability of broadband service and its role in the digital divide; the environmental justice movement in the United States has raised awareness to health implications for minority populations stemming from historical redlining practices; and studies have found varying quality and coverage in the collection and sharing of open-source geospatial data. Despite the extensive literature on machine learning (ML) fairness, few algorithmic strategies have been proposed to mitigate such biases. In this paper we highlight the unique challenges for quantifying and addressing spatio-temporal biases, through the lens of use cases presented in the scientific literature and media. We envision a roadmap of ML strategies that need to be developed or adapted to quantify and overcome these challenges -- including transfer learning, active learning, and reinforcement learning techniques. Further, we discuss the potential role of ML in providing guidance to policy makers on issues related to spatial fairness.
FullSubNet is our recently proposed real-time single-channel speech enhancement network that achieves outstanding performance on the Deep Noise Suppression (DNS) Challenge dataset. A number of variants of FullSubNet have been proposed recently, but they all focus on the structure design towards better performance and are rarely concerned with computational efficiency. This work proposes a new architecture named Fast FullSubNet dedicated to accelerating the computation of FullSubNet. Specifically, Fast FullSubNet processes sub-band speech spectra in the mel-frequency domain by using cascaded linear-to-mel full-band, sub-band, and mel-to-linear full-band models such that frequencies involved in the sub-band computation are vastly reduced. After that, a down-sampling operation is proposed for the sub-band input sequence to further reduce the computational complexity along the time axis. Experimental results show that, compared to FullSubNet, Fast FullSubNet has only 13% computational complexity and 16% processing time, and achieves comparable or even better performance.
In Federated Learning (FL), clients train a model locally and share it with a central aggregator to build a global model. Impermissibility to access client's data and collaborative training makes FL appealing for applications with data-privacy concerns such as medical imaging. However, these FL characteristics pose unprecedented challenges for debugging. When a global model's performance deteriorates, finding the round and the clients responsible is a major pain point. Developers resort to trial-and-error debugging with subsets of clients, hoping to increase the accuracy or let future FL rounds retune the model, which are time-consuming and costly. We design a systematic fault localization framework, FedDebug, that advances the FL debugging on two novel fronts. First, FedDebug enables interactive debugging of realtime collaborative training in FL by leveraging record and replay techniques to construct a simulation that mirrors live FL. FedDebug's {\em breakpoint} can help inspect an FL state (round, client, and global model) and seamlessly move between rounds and clients' models, enabling a fine-grained step-by-step inspection. Second, FedDebug automatically identifies the client responsible for lowering global model's performance without any testing data and labels--both are essential for existing debugging techniques. FedDebug's strengths come from adapting differential testing in conjunction with neurons activations to determine the precise client deviating from normal behavior. FedDebug achieves 100\% to find a single client and 90.3\% accuracy to find multiple faulty clients. FedDebug's interactive debugging incurs 1.2\% overhead during training, while it localizes a faulty client in only 2.1\% of a round's training time. With FedDebug, we bring effective debugging practices to federated learning, improving the quality and productivity of FL application developers.
In this paper, we present electromyography analysis of human activity - database 1 (EMAHA-DB1), a novel dataset of multi-channel surface electromyography (sEMG) signals to evaluate the activities of daily living (ADL). The dataset is acquired from 25 able-bodied subjects while performing 22 activities categorised according to functional arm activity behavioral system (FAABOS) (3 - full hand gestures, 6 - open/close office draw, 8 - grasping and holding of small office objects, 2 - flexion and extension of finger movements, 2 - writing and 1 - rest). The sEMG data is measured by a set of five Noraxon Ultium wireless sEMG sensors with Ag/Agcl electrodes placed on a human hand. The dataset is analyzed for hand activity recognition classification performance. The classification is performed using four state-ofthe-art machine learning classifiers, including Random Forest (RF), Fine K-Nearest Neighbour (KNN), Ensemble KNN (sKNN) and Support Vector Machine (SVM) with seven combinations of time domain and frequency domain feature sets. The state-of-theart classification accuracy on five FAABOS categories is 83:21% by using the SVM classifier with the third order polynomial kernel using energy feature and auto regressive feature set ensemble. The classification accuracy on 22 class hand activities is 75:39% by the same SVM classifier with the log moments in frequency domain (LMF) feature, modified LMF, time domain statistical (TDS) feature, spectral band powers (SBP), channel cross correlation and local binary patterns (LBP) set ensemble. The analysis depicts the technical challenges addressed by the dataset. The developed dataset can be used as a benchmark for various classification methods as well as for sEMG signal analysis corresponding to ADL and for the development of prosthetics and other wearable robotics.
We propose iterative algorithms to solve adversarial problems in a variety of supervised learning settings of interest. Our algorithms, which can be interpreted as suitable ascent-descent dynamics in Wasserstein spaces, take the form of a system of interacting particles. These interacting particle dynamics are shown to converge toward appropriate mean-field limit equations in certain large number of particles regimes. In turn, we prove that, under certain regularity assumptions, these mean-field equations converge, in the large time limit, toward approximate Nash equilibria of the original adversarial learning problems. We present results for nonconvex-nonconcave settings, as well as for nonconvex-concave ones. Numerical experiments illustrate our results.
Untethered miniaturized wireless neural sensor nodes with data transmission and energy harvesting capabilities call for circuit and system-level innovations to enable ultra-low energy deep implants for brain-machine interfaces. Realizing that the energy and size constraints of a neural implant motivate highly asymmetric system design (a small, low-power sensor and transmitter at the implant, with a relatively higher power receiver at a body-worn hub), we present Time-Domain Bi-Phasic Quasi-static Brain Communication (TD- BPQBC), offloading the burden of analog to digital conversion (ADC) and digital signal processing (DSP) to the receiver. The input analog signal is converted to time-domain pulse-width modulated (PWM) waveforms, and transmitted using the recently developed BPQBC method for reducing communication power in implants. The overall SoC consumes only 1.8{\mu}W power while sensing and communicating at 800kSps. The transmitter energy efficiency is only 1.1pJ/b, which is >30X better than the state-of-the-art, enabling a fully-electrical, energy-harvested, and connected in-brain sensor/stimulator node.