Whereas a large number of empirical studies have been devoted to analyzing consumer demand for dietary energy (or dietary quantity), much less attention has been paid to the demand for dietary quality, an equally important aspect of food security. To address this gap in the literature, this paper uses data from a nationally representative household expenditure survey conducted in Bangladesh in 2000 on the food acquisition behavior of 7,440 households over a two week period. Two indicators of dietary quality are employed: household protein availability and household diet diversity. Using two-stage least squares regression to correct for the endogeneity of income, we find significant roles of income, education, gender of household head, and prices of key foods. The determination of dietary quality in the country has a strong gender dimension. While male education plays a positive role, female education is found to have a substantially stronger influence. Further, female household headship is associated with lower dietary quality than male headship. Given the crucial roles of income and education in increasing access to a high quality diet, the results call for the continued implementation of well targeted poverty reduction and education programs. Promoting female education and addressing the unique constraints faced by female headed households with respect to diet quality could be a significant policy instrument for government and non-government organizations in addressing food insecurity in Bangladesh.

Thermal images are mainly used to detect the presence of people at night or in bad lighting conditions, but perform poorly at daytime. To solve this problem, most state-of-theart techniques employ a fusion network that uses features from paired thermal and color images. Instead, we propose to augment thermal images with their saliency maps, to serve as an attention mechanism for the pedestrian detector especially during daytime. We investigate how such an approach results in improved performance for pedestrian detection using only thermal images, eliminating the need for paired color images. For our experiments, we train the Faster R-CNN for pedestrian detection and report the added effect of saliency maps generated using static and deep methods (PiCA-Net and R 3 -Net). Our best performing model results in an absolute reduction of miss rate by 13.4% and 19.4% over the baseline in day and night images respectively. We also annotate and release pixel level masks of pedestrians on a subset of the KAIST Multispectral Pedestrian Detection dataset, which is a first publicly available dataset for salient pedestrian detection.

Identifying episodes of significant stress is a challenging problem with implications for personal health and interface adaptation. We present the results of a study comparing multiple modalities of minimally intrusive stress sensing in real-world environments, collected from seven participants as they carried out their everyday activities over a ten-day period. We compare the data streams produced by sensors and self-report measures, in addition to asking the participants, themselves, to reflect on the accuracy and completeness of the data that had been collected. Finally, we describe the range of participant experiences-both positive and negative-as they reported their everyday stress levels. As a result of this study, we demonstrate that voice-based stress sensing tracks with electrodermal activity and self-reported stress measures in real-world environments and we identify limitations of various sensing approaches.

The aim of the study herein reported was to review mobile health (mHealth) technologies and explore their use to monitor and mitigate the effects of the COVID-19 pandemic. Methods: A Task Force was assembled by recruiting individuals with expertise in electronic Patient-Reported Outcomes (ePRO), wearable sensors, and digital contact tracing technologies. Its members collected and discussed available information and summarized it in a series of reports. Results: The Task Force identified technologies that could be deployed in response to the COVID-19 pandemic and would likely be suitable for future pandemics. Criteria for their evaluation were agreed upon and applied to these systems. Conclusions: mHealth technologies are viable options to monitor COVID-19 patients and be used to predict symptom escalation for earlier intervention. These technologies could also be utilized to monitor individuals who are presumed noninfected and enable prediction of exposure to SARS-CoV-2, thus facilitating the prioritization of diagnostic testing.