Deep Learning in Human Activity Recognition with Wearable Sensors: A Review on Advances.

Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human-computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

Conductive Thread-Based Textile Sensor for Continuous Perspiration Level Monitoring.

Individual perspiration level indicates a person's physical status as well as their comfort level. Therefore, continuous perspiration level measurement enables people to monitor these conditions for applications including fitness assessment, athlete physical status monitoring, and patient/elderly care. Prior work on perspiration (sweat) sensing required the user either to be static or to wear the adhesive sensor directly on the skin, which limits users' mobility and comfort. In this paper, we present a novel conductive thread-based textile sensor that measures an individual's on-cloth sweat quantity. The sensor consists of three conductive threads. Each conductive thread is surrounded by a braided cotton cover. An additional braided cotton cover is placed outside the three conductive threads, holding them in a position that is stable for measurement. the sensor can be embedded at various locations on a person's clothing. When the person sweats, the cotton braids absorb the sweat and change the conductivity (resistance) between conductive threads. We used a voltage dividing circuit to measure this resistance as the sensor output (DC). We then conducted a sensor calibration to map this measured voltage to the quantity of electrolyte solution (with the same density as sweat) applied to the sensor. We used this sensor to measure individuals' perspiration quantity and infer their perceived perspiration levels. The system is able to limit the average prediction error to 0.4 levels when compared to five pre-defined perceived perspiration levels.

Analysis of 2D nanomaterial BC3 for COVID-19 biomarker ethyl butyrate sensor.

Ethyl butyrate (EB) was identified in recent research as a prominent biomarker of COVID-19, as concentrations of EB were higher in exhaled breath of COVID-19 patients. Electronic sensitivities of pristine, Al- and Si-doped BC3 nanosheets to the EB molecule were investigated in this study using density functional theory. It is found that the pure BC3 was ineffective in sensing EB due to low adsorption energy and sensitivity. Aluminum- and silicon-doped BC3 nanosheets were effective in forming a strong interaction with EB and were also sensitive. Our calculations show that the band gaps of the Al-doped and Si-doped BC3 sheets were significantly decreased upon EB adsorption, which increased the electrical conductance of the sheets and the sensitivity. However, Si-doped BC3 had a recovery time of almost 22 hours, making it less potent than Al-doped BC3, which had a recovery time of just 7.7 minutes. The shorter recovery time of the Al-doped BC3 sheet is due to its moderate adsorption energy of 25.8 kcal mol-1. These results can help facilitate the development of an EB biosensor for COVID-19 testing and other similar applications.

Standing in the glory or shadow of the past self: cultures differ in how much the past self affects current subjective well-being.

Research in the past 2 decades has made great strides in understanding cross-cultural differences in the correlates and causes of subjective well-being. On the basis of past findings on the cross-cultural differences in temporal perspectives of the self, the present research examined a cross-cultural difference in individuals' subjective well-being as a function of how positively they viewed their present and past selves. Study 1 showed that both European and Asian Americans had higher subjective well-being when they viewed their present selves more positively. However, positive evaluations of the past self were accompanied by higher subjective well-being only among Asian Americans. Study 2 showed that when induced to think positively (vs. negatively) of the present self, both European and Asian Americans judged their current lives more favorably. However, when led to view the past self positively (vs. negatively), only Asian Americans made more favorable judgments about their current lives.

Rheology of the gel formed in the California Mastitis Test.

The California Mastitis Test has previously been adapted for use in an inline, cow-side sensor and relies on the fact that the viscosity of the gel formed during the test is proportional to the somatic cell concentration. In this paper, the use of capillary and rotational viscometry was compared in light of the expected rheology of the gel formed during the test. It was found that the gel is non-Newtonian, but the initial phase of viscosity increase was not due to shear dependence, but rather due to the gelation reaction. The maximum apparent viscosity of the gel was shear dependent while the time it took to reach the maximum was not truly shear dependent, but was rather dependent on the degree of mixing during gelation. This was confirmed by introducing a delay time prior to viscosity measurement, in both capillary and rotational viscometry. It was found that by mixing the reagent and infected milk, then delaying viscosity measurement for 30 s, shortened the time it took to reach maximum viscosity by more than 60 s. The maximum apparent viscosity, however, was unaffected. It was found that capillary viscometry worked well to correlate relative viscosity with somatic cell count, but that it was sensitive to the reagent concentration. It can therefore be deduced that the rheology of the gel is complicated not only by it being non-Newtonian, but also by the strong dependence on test conditions. These make designing a successful sensor much more challenging.