Falls are the top reason for fatal and non-fatal injuries among seniors. Existing solutions are based on wearable fall-alert sensors, but medical research has shown that they are ineffective, mostly because seniors do not wear them. These revelations have led to new passive sensors that infer falls by analyzing Radio Frequency (RF) signals in homes. Seniors can go about their lives as usual without the need to wear any device. While passive monitoring has made major advances, current approaches still cannot deal with the complexities of real-world scenarios. They typically train and test their classifiers on the same people in the same environments, and cannot generalize to new people or new environments. Further, they cannot separate motions from different people and can easily miss a fall in the presence of other motions. To overcome these limitations, we introduce Aryokee, an RF-based fall detection system that uses convolutional neural networks governed by a state machine. Aryokee works with new people and environments unseen in the training set. It also separates different sources of motion to increase robustness. Results from testing Aryokee with over 140 people performing 40 types of activities in 57 different environments show a recall of 94% and a precision of 92% in detecting falls.

No abstract

BigSMILES, a line notation for encapsulating the molecular structure of stochastic molecules such as polymers, was recently proposed as a compact and readable solution for writing macromolecules. While BigSMILES strings serve as useful identifiers for reconstructing the molecular connectivity for polymers, in general, BigSMILES allows the same polymer to be codified into multiple equally valid representations. Having a canonicalization scheme that eliminates the multiplicity would be very useful in reducing time-intensive tasks like structural comparison and molecular search into simple string-matching tasks. Motivated by this, in this work, two strategies for deriving canonical representations for linear polymers are proposed. In the first approach, a canonicalization scheme is proposed to standardize the expression of BigSMILES stochastic objects, thereby standardizing the expression of overall BigSMILES strings. In the second approach, an analogy between formal language theory and the molecular ensemble of polymer molecules is drawn. Linear polymers can be converted into regular languages, and the minimal deterministic finite automaton uniquely associated with each prescribed language is used as the basis for constructing the unique text identifier associated with each distinct polymer. Overall, this work presents algorithms to convert linear polymers into unique structure-based text identifiers. The derived identifiers can be readily applied in chemical information systems for polymers and other polymer informatics applications.

This paper proposes to address the word sense ambiguity issue in an unsupervised manner, where word sense representations are learned along a word sense selection mechanism given contexts. Prior work focused on designing a single model to deliver both mechanisms, and thus suffered from either coarse-grained representation learning or inefficient sense selection. The proposed modular approach, MUSE, implements flexible modules to optimize distinct mechanisms, achieving the first purely sense-level representation learning system with linear-time sense selection. We leverage reinforcement learning to enable joint training on the proposed modules, and introduce various exploration techniques on sense selection for better robustness. The experiments on benchmark data show that the proposed approach achieves the state-of-the-art performance on synonym selection as well as on contextual word similarities in terms of MaxSimC.

We provide a new approach to training neural models to exhibit transparency in a well-defined, functional manner. Our approach naturally operates over structured data and tailors the predictor, functionally, towards a chosen family of (local) witnesses. The estimation problem is setup as a co-operative game between an unrestricted predictor such as a neural network, and a set of witnesses chosen from the desired transparent family. The goal of the witnesses is to highlight, locally, how well the predictor conforms to the chosen family of functions, while the predictor is trained to minimize the highlighted discrepancy. We emphasize that the predictor remains globally powerful as it is only encouraged to agree locally with locally adapted witnesses. We analyze the effect of the proposed approach, provide example formulations in the context of deep graph and sequence models, and empirically illustrate the idea in chemical property prediction, temporal modeling, and molecule representation learning.