Cruft

Abstract: Human context recognition (HCR), which involves determining a user’s current situation (or context), has long been an important task in context-aware systems. With the widespread ownership of smartphones, HCR methods that utilize signals from its built-in sensors have recently received increased attention. We propose Context Recognition under label Uncertainty using Fusion and Temporal Learning (CRUFT), a novel method to recognize a diverse set of smartphone user contexts, including long-term human activities, short-term human activities, and phone placement (pocket or bag in which the smartphone is carried). Context recognition is formulated as a multi-label classification task. CRUFT uses both handcrafted features and auto-learned deep learning features extracted from raw time-series data in two separate arms. The handcrafted arm includes a Multi-Layer Perceptron (MLP), while the raw data arm utilizes a Convolutional Neural Network (CNN) along with a Bi-Directional Long Short Term Memory (Bi-LSTM) model that exploits temporal correlations in the input stream. As smartphone sensor readings, assigned timestamps, and labels can be wrong sometimes, CRUFT integrates an uncertainty module. CRUFT outperforms the state-of-the-art baselines achieving 94.25% in overall Balanced Accuracy (BA), which improves the best performing baseline by 2.7%. Our detailed analyses demonstrate the non-trivial contributions of each component in CRUFT.

Abstract: This book sets down, in nearly 1,000 pages, the greater part of the war-time course given to U.S. officers at the Cruft Laboratory, Harvard University. The range of material included is necessarily very great and, as Prof. Chaffee has frankly stated in his foreword, "... the scope and the method of presentation of the material in this volume are not on a graduate level. . . ." Indeed, this could not possibly be so in a single volume which includes : A.c. vector theory ; bridge and other measurements ; transient analysis ; network theory ; wave-filters ; thermionic emission ; electron dynamics ; transmitter and receiver circuits ; gas-discharge tubes ; modulation theory ; timing, rectification and control circuits. The treatment is essentially technological and, in many places, merely descriptive. Electronic Circuits and Tubes By the Electronics Training Staff of the Cruft Laboratory, Harvard University. Pp. xxiv + 948. (New York and London : McGraw-Hill Book Co., Inc., 1947.) 45s.