Human activity recognition (HAR) is a classification task that aims to classify human activities or predict human behavior by means of features extracted from sensors data. Typical HAR systems use wearable sensors and/or handheld and mobile devices with built-in sensing capabilities. Due to the widespread use of smartphones and to the inclusion of various sensors in all contemporary smartphones (e.g., accelerometers and gyroscopes), they are commonly used for extracting and collecting data from sensors and even for implementing HAR systems. When using mobile devices, e.g., smartphones, HAR systems need to deal with several constraints regarding battery, computation and memory. These constraints enforce the need of a system capable of managing its resources and maintain acceptable levels of classification accuracy. Moreover, several factors can influence activity recognition, such as classification models, sensors availability and size of data window for feature extraction, making stable accuracy a difficult task. In this paper, we present a semi-supervised classifier and a study regarding the influence of hyperparameter configuration in classification accuracy, depending on the user and the activities performed by each user. This study focuses on sensing data provided by the PAMAP2 dataset. Experimental results show that it is possible to maintain classification accuracy by adjusting hyperparameters, like window size and windows overlap factor, depending on user and activity performed. These experiments motivate the development of a system able to automatically adapt hyperparameter settings for the activity performed by each user.
Given a partially observable dynamic system and a diagnoser observing its evolution over time, diagnosability analysis formally verifies (at design time) if the diagnosis system will be able to infer (at runtime) the required information on the hidden part of the dynamic state. Diagnosability directly depends on the availability of observations, and can be guaranteed by different sets of sensors, possibly associated with different costs. In this paper, we tackle the problem of synthesizing observability requirements, i.e. automatically discovering a set of observations that is sufficient to guarantee diagnosability. We propose a novel approach with the following characterizing features. First, it fully covers a comprehensive formal framework for diagnosability analysis, and enables ranking configurations of observables in terms of cost, minimality, and diagnosability delay. Second, we propose two complementary algorithms for the synthesis of observables. Third, we describe an efficient implementation that takes full advantage of mature symbolic model checking techniques. The proposed approach is thoroughly evaluated over a comprehensive suite of benchmarks taken from the aerospace domain.
A configuration of training refers to the combinations of feature engineering, learner, and its associated hyperparameters. Given a set of configurations and a large dataset randomly split into training and testing set, we study how to efficiently identify the best configuration with approximately the highest testing accuracy when trained from the training set. To guarantee small accuracy loss, we develop a solution using confidence interval (CI)-based progressive sampling and pruning strategy. Compared to using full data to find the exact best configuration, our solution achieves more than two orders of magnitude speedup, while the returned top configuration has identical or close test accuracy.
Laser light can induce electronic excitations on metal surfaces. These excitations, or plasmons, are sensitive to the surface environment and are now routinely used in chemical and biological sensing applications. Dowran et al. show that the sensitivity of these plasmonic sensors can be enhanced by using quantum states of light. They replace the laser light (used in the classical configuration) with quantum light, in this case a twin beam of entangled photons; one beam is used as a reference and the other to excite the surface plasmons. They find an appreciable sensitivity enhancement in the quantum configuration.
Samsung's next flagship may feature some of the new camera technology it announced Wednesday. The manufacturer shared details on two new image sensors, the ISOCELL Fast 2L9 and the ISOCELL Slim 2X7. The Fast 2L9 has a 12-megapixel configuration with dual pixel technology. Likely ideal as a mid-range rear-facing camera sensor, it will enable features like bokeh effects and will apply improvements to quick focus and low light photography. The Slim 2X7 has a 24-megapixel configuration with Tetra Cell technology.