ABSTRACT
End-to-end deep learning models are increasingly applied to safety-critical human activity recognition (HAR) applications, e.g., healthcare monitoring and smart home control, to reduce developer burden and increase the performance and robustness of prediction models. However, integrating HAR models in safety-critical applications requires trust, and recent approaches have aimed to balance the performance of deep learning models with explainable decision-making for complex activity recognition. Prior works have exploited the compositionality of complex HAR (i.e., higher-level activities composed of lower-level activities) to form models with symbolic interfaces, such as concept-bottleneck architectures, that facilitate inherently interpretable models. However, feature engineering for symbolic concepts-as well as the relationship between the concepts-requires precise annotation of lower-level activities by domain experts, usually with fixed time windows, all of which induce a heavy and error-prone workload on the domain expert. In this paper, we introduce X-CHAR , an eXplainable Complex Human Activity Recognition model that doesn't require precise annotation of low-level activities, offers explanations in the form of human-understandable, high-level concepts, while maintaining the robust performance of end-to-end deep learning models for time series data. X-CHAR learns to model complex activity recognition in the form of a sequence of concepts. For each classification, X-CHAR outputs a sequence of concepts and a counterfactual example as the explanation. We show that the sequence information of the concepts can be modeled using Connectionist Temporal Classification (CTC) loss without having accurate start and end times of low-level annotations in the training dataset-significantly reducing developer burden. We evaluate our model on several complex activity datasets and demonstrate that our model offers explanations without compromising the prediction accuracy in comparison to baseline models. Finally, we conducted a mechanical Turk study to show that the explanations provided by our model are more understandable than the explanations from existing methods for complex activity recognition.
ABSTRACT
Smart ear-worn devices (called earables) are being equipped with various onboard sensors and algorithms, transforming earphones from simple audio transducers to multi-modal interfaces making rich inferences about human motion and vital signals. However, developing sensory applications using earables is currently quite cumbersome with several barriers in the way. First, time-series data from earable sensors incorporate information about physical phenomena in complex settings, requiring machine-learning (ML) models learned from large-scale labeled data. This is challenging in the context of earables because large-scale open-source datasets are missing. Secondly, the small size and compute constraints of earable devices make on-device integration of many existing algorithms for tasks such as human activity and head-pose estimation difficult. To address these challenges, we introduce Auritus an extendable and open-source optimization toolkit designed to enhance and replicate earable applications. Auritus serves two primary functions. Firstly, Auritus handles data collection, pre-processing, and labeling tasks for creating customized earable datasets using graphical tools. The system includes an open-source dataset with 2.43 million inertial samples related to head and full-body movements, consisting of 34 head poses and 9 activities from 45 volunteers. Secondly, Auritus provides a tightly-integrated hardware-in-the-loop (HIL) optimizer and TinyML interface to develop lightweight and real-time machine-learning (ML) models for activity detection and filters for head-pose tracking. To validate the utlity of Auritus, we showcase three sample applications, namely fall detection, spatial audio rendering, and augmented reality (AR) interfacing. Auritus recognizes activities with 91% leave 1-out test accuracy (98% test accuracy) using real-time models as small as 6-13 kB. Our models are 98-740× smaller and 3-6% more accurate over the state-of-the-art. We also estimate head pose with absolute errors as low as 5 degrees using 20kB filters, achieving up to 1.6× precision improvement over existing techniques. We make the entire system open-source so that researchers and developers can contribute to any layer of the system or rapidly prototype their applications using our dataset and algorithms.
ABSTRACT
Owing to the emergence of better characteristics such as parallelism, low power consumption and data compactness, DNA computing has drawn great attention in recent years. In this study, the authors realise an arithmetic and logic unit (ALU) using deoxyribonucleic acid (DNA). Inputs and outputs of the proposed ALU keep the logical reversibility in computation processes. The proposed ALU is capable of performing four logical (AND, OR, EX-OR and NOT) with three arithmetic (addition, subtraction and multiplication) operations. They use DNA-based multiplexer to carry out final output. Compared to silicon-based computation, the proposed ALU is faster and requires less space and power due to parallelism, replication properties, compactness and formation of DNA strands. However, compared to one existing DNA-based system, fewer signals are required in each step. Besides, another existing DNA-based ALU requires five complex biological steps to compute, whereas the proposed ALU requires three biological steps. Also, the time complexities of that existing system are O(mln2n) for addition and subtraction operations; O(m) for logical operations and O(m(ln2n)(2)) for multiplication operation, while the proposed system has O(1) for logical operations and O(n) for others; here n is the number of bits and m is the number of test tubes for operands.
