Medication non-adherence is a prevalent, complex problem. Failure to follow medication schedules may lead to major health complications, including death. Proper medication adherence is thus required in order to gain the greatest possible drug benefit during a patient’s treatment. Interventions have been proven to improve medication adherence if deviations are detected. This review focuses on recent advances in the field of technology-based medication adherence approaches and pays particular attention to their technical monitoring aspects. The taxonomy space of this review spans multiple techniques including sensor systems, proximity sensing, vision systems, and combinations of these. As each technique has unique advantages and limitations, this work describes their trade-offs in accuracy, energy consumption, acceptability and user’s comfort, and user authentication.

Oral hygiene is very important for a healthy life. Proper toothbrushing is one of the most important measures against dental problems. Poor toothbrushing methods can lead to tooth decay and other gum diseases. Unfortunately, many people do not brush their teeth properly and there is very limited technology available to assist them in compliance with the standard toothbrushing procedure. Sensor-based human activity recognition techniques have seen tremendous growth recently and are being used in various applications. In this work, we treat the compliance to the standard toothbrushing method as an activity recognition problem. We divide the toothbrushing activity into 16 sub-activities and use a machine learning model to recognize those activities. We introduce an off-body sensing solution that uses a detachable Inertial Measurement Unit (IMU), attached to the handle of the brush. The sensor captures the movements of the brush while reaching different parts of the teeth. Then a machine learning pipeline is trained to predict the brushing of different parts of the teeth. We evaluated the performance of the proposed approach in real-world scenarios and performed experiments with 10 different users. We collected our own data set and compared our approach with the wearable-based approach. The results show that our approach performs better than wearable-based approaches and can recognize the toothbrushing activities with 97.15% accuracy. We also evaluated our model for different types of brushes (manual and electric) and the results show that the proposed approach can work independently from the brush types.

Medication non-adherence is a prevalent, complex problem. Failure to follow medication schedules may lead to major health complications, which could reduce quality of life. Proper medication adherence is thus required in order to gain the greatest possible drug benefit during a patient’s treatment. Interventions have been proven to improve medication adherence if deviations are detected. This review focuses on recent advances in the field of technology-based medication adherence approaches and pays particular attention to their technical monitoring aspects. The taxonomy space of this review spans multiple techniques including sensor systems, proximity sensing, vision systems, and combinations of these. As each technique has unique advantages and limitations, this work describes their trade-offs in accuracy, energy consumption, acceptability and user’s comfort, and user authentication.

The novel coronavirus that causes the now well-known COVID-19 illness has affected the whole world as the number of daily reported cases has exceeded 250,000. The spread trend of the virus across the globe has varied from one country to another, mainly because of each government’s response. In this article, we discuss the statistics of the cases in Iraq and provide a projection model based on the current situation and government interventions. Using daily reported cases data from February 24, 2020--July 31, 2020, we report 6-week-ahead projections of daily cases, critical cases, and deaths. Specifically, we propose a simple machine learning-based model based on Gaussian Process regression to project the future trend of COVID-19 in Iraq. This work aims to aid the Iraqi government by providing a statistical tool to provide future estimates of the suspected and death cases resulting from COVID-19 and make strategic decisions.

The Internet of Things (IoT) offers transformative potential when combined with Machine Learning (ML), but labeling diverse IoT data remains challenging. To address this, we introduce SenseScape Testbed, an IoT experimentation platform for indoor environments with wireless sensor nodes, robots, and location-tracking nodes. This testbed enables IoT applications such as human activity recognition and indoor mobility tracking, supporting energy efficiency, occupant comfort, and context representation while providing a versatile environment for labeling and testing to advance ML algorithms tailored for IoT applications.

Timeseries partitioning is an essential step in most machine-learning driven, sensor-based IoT applications. This paper introduces a sample-efficient, robust, time-series segmentation model and algorithm. We show that by learning a representation specifically with the segmentation objective based on maximum mean discrepancy (MMD), our algorithm can robustly detect time-series events across different applications. Our loss function allows us to infer whether consecutive sequences of samples are drawn from the same distribution (null hypothesis) and determines the change-point between pairs that reject the null hypothesis (i.e., come from different distributions). We demonstrate its applicability in a real-world IoT deployment for ambient-sensing based activity recognition. Moreover, while many works on change-point detection exist in the literature, our model is significantly simpler and can be fully trained in 9-93 seconds on average with little variation in hyperparameters for data across different applications. We empirically evaluate Cadence on four popular change point detection (CPD) datasets where Cadence matches or outperforms existing CPD techniques.