Breathing rate (BR), minute ventilation (VE), and other respiratory parameters are essential for real-time patient monitoring in many acute health conditions, such as asthma. The clinical standard for measuring respiration, namely Spirometry, is hardly suitable for continuous use. Wearables can track many physiological signals, like ECG and motion, yet not respiration. Deriving respiration from other modalities has become an area of active research. In this work, we infer respiratory parameters from wearable ECG and wrist motion signals. We propose a modular and generalizable classification-regression pipeline to utilize available context information, such as physical activity, in learning context-conditioned inference models. Morphological and power domain novel features from the wearable ECG are extracted to use with these models. Exploratory feature selection methods are incorporated in this pipeline to discover application-specific interpretable biomarkers. Using data from 15 subjects, we evaluate two implementations of the proposed pipeline: for inferring BR and VE. Each implementation compares generalized linear model, random forest, support vector machine, Gaussian process regression, and neighborhood component analysis as contextual regression models. Permutation, regularization, and relevance determination methods are used to rank the ECG features to identify robust ECG biomarkers across models and activities. This work demonstrates the potential of wearable sensors not only in continuous monitoring, but also in designing biomarker-driven preventive measures.

Continuous learning seeks to perform the learning on the data that arrives from time to time. While prior works have demonstrated several possible solutions, these approaches require excessive training time as well as memory usage. This is impractical for applications where time and storage are constrained, such as edge computing. In this work, a novel training algorithm, regularized subspace approximation classifier (RSAC), is proposed to achieve lightweight continuous learning. RSAC contains a feature reduction module and classifier module with regularization. Extensive experiments show that RSAC is more efficient than prior continuous learning works and outperforms these works on various experimental settings.

In distributed second order optimization, a standard strategy is to average many local estimates, each of which is based on a small sketch or batch of the data. However, the local estimates on each machine are typically biased, relative to the full solution on all of the data, and this can limit the effectiveness of averaging. Here, we introduce a new technique for debiasing the local estimates, which leads to both theoretical and empirical improvements in the convergence rate of distributed second order methods. Our technique has two novel components: (1) modifying standard sketching techniques to obtain what we call a surrogate sketch; and (2) carefully scaling the global regularization parameter for local computations. Our surrogate sketches are based on determinantal point processes, a family of distributions for which the bias of an estimate of the inverse Hessian can be computed exactly. Based on this computation, we show that when the objective being minimized is $l_2$-regularized with parameter $\lambda$ and individual machines are each given a sketch of size $m$, then to eliminate the bias, local estimates should be computed using a shrunk regularization parameter given by $\lambda^{\prime}=\lambda\cdot(1-\frac{d_{\lambda}}{m})$, where $d_{\lambda}$ is the $\lambda$-effective dimension of the Hessian (or, for quadratic problems, the data matrix).

Recent few-shot learning works focus on training a model with prior meta-knowledge to fast adapt to new tasks with unseen classes and samples. However, conventional time-series classification algorithms fail to tackle the few-shot scenario. Existing few-shot learning methods are proposed to tackle image or text data, and most of them are neural-based models that lack interpretability. This paper proposes an interpretable neural-based framework, namely \textit{Dual Prototypical Shapelet Networks (DPSN)} for few-shot time-series classification, which not only trains a neural network-based model but also interprets the model from dual granularity: 1) global overview using representative time series samples, and 2) local highlights using discriminative shapelets. In particular, the generated dual prototypical shapelets consist of representative samples that can mostly demonstrate the overall shapes of all samples in the class and discriminative partial-length shapelets that can be used to distinguish different classes. We have derived 18 few-shot TSC datasets from public benchmark datasets and evaluated the proposed method by comparing with baselines. The DPSN framework outperforms state-of-the-art time-series classification methods, especially when training with limited amounts of data. Several case studies have been given to demonstrate the interpret ability of our model.

Artificial Intelligence (AI) is already ubiquitous in our day-to-day lives. From maps that find the optimal route, to Amazon, Netflix and Facebook who curate content and make recommendations tailored specifically to us. Your smartphone even understands voice commands and can perform tasks prompted by you. The technology is pervasive and is increasingly being applied in the education sector. Globally in the education sector, AI is being applied in tools that help develop learner skills, allow self-paced tailored learning, streamline assessment systems, and automate administrative activities.

Language is as important as expressions when reading emotion, a study has found -- meaning that being told someone looks'grumpy' can makes them seem grumpier. Researchers from Australia and the US asked volunteers to rate the emotions of people in either photographs or videos. The team found that when the participants were told that the subjects were feeling a specific emotion, this biased how they interpreted the expressions on show. The effect was most pronounced when dealing with angry, sad or scared faces -- as opposed to happy, disgusted, embarrassed, proud or surprised -- the team found. Language is as important as expressions when reading emotion, a study has found -- meaning that being told someone looks'grumpy' can makes them seem grumpier (stock image) 'The current studies demonstrate that language context alters the dimensional affective foundations that underlie our judgements of others' expressions,' the researchers wrote in their paper.

The mean, standard deviation, and 75% confidence interval values are maximum for the'Total Amount of Fines in Dollars' feature. The 25% and 50% confidence interval values are maximum for'Number of Certified Beds' and'Average Number of Residents Per Day' columns.

New developments and opportunities are opening up in artificial intelligence, says Paul Budde. I RECENTLY followed a "lunch box lecture", organised by the University of Sydney. The world is infatuated with artificial intelligence (AI), and understandably so, given its super-human ability to find patterns in big data as we all notice when using Google, Facebook, Amazon, eBay and so on. But the so-called "general intelligence" that humans possess remains elusive for AI. Interestingly, Professor Kuncic approached this topic from a physics perspective.

CSRE is providing a total of $300,000 in funding for the projects, with an additional $300,000 in matching and supplemental funding from other colleges, departments, and institutes. "Today's challenges to global, national, and individual security are numerous and complex," said CSRE Director James W. Houck, "and we are delighted to support these innovative and exciting initiatives." CSRE was established in 2017 to promote interdisciplinary research and education to protect people, infrastructure and institutions from the broad range of threats and hazards confronting society today. Contributing units include the Provost and Office of the Senior Vice President for Research, as well as the colleges of Agricultural Sciences, Earth and Mineral Sciences, Engineering, Information Sciences and Technology, and the Liberal Arts; Penn State Law and the School of International Affairs; Penn State Harrisburg; Applied Research Laboratory; Institute for Computational and Data Sciences; Institutes of Energy and the Environment; Huck Institutes of the Life Sciences; and the Social Sciences Research Institute. In its first three years, CSRE has provided over $633,000 in funding, augmented by an additional $581,000 from contributing units, to a total of 39 seed projects and faculty fellowships and hosted a number of guest speakers, workshops and other events.

Complex applications such as big data analytics involve different forms of coupling relationships that reflect interactions between factors related to technical, business (domain-specific) and environmental (including socio-cultural and economic) aspects. There are diverse forms of couplings embedded in poor-structured and ill-structured data. Such couplings are ubiquitous, implicit and/or explicit, objective and/or subjective, heterogeneous and/or homogeneous, presenting complexities to existing learning systems in statistics, mathematics and computer sciences, such as typical dependency, association and correlation relationships. Modeling and learning such couplings thus is fundamental but challenging. This paper discusses the concept of coupling learning, focusing on the involvement of coupling relationships in learning systems. Coupling learning has great potential for building a deep understanding of the essence of business problems and handling challenges that have not been addressed well by existing learning theories and tools. This argument is verified by several case studies on coupling learning, including handling coupling in recommender systems, incorporating couplings into coupled clustering, coupling document clustering, coupled recommender algorithms and coupled behavior analysis for groups.