Longitudinal human behavior modeling has received increasing attention over the years due to its widespread applications to patient monitoring, dietary and lifestyle recommendations, and just-in-time intervention for at-risk individuals (e.g., problematic drug users and struggling students), to name a few. Using in-the-moment health data collected via ubiquitous devices (e.g., smartphones and smartwatches), this multidisciplinary field focuses on developing predictive models for certain health or well-being outcomes (e.g., depression and stress) in the short future given the time series of individual behaviors (e.g., resting heart rate, sleep quality, and current feelings). Yet, most existing models on these data, which we refer to as ubiquitous health data, do not achieve adequate accuracy. The latest works that yielded promising results have yet to consider realistic aspects of ubiquitous health data (e.g., containing features of different types and high rate of missing values) and the consumption of various resources (e.g., computing power, time, and cost). Given these two shortcomings, it is dubious whether these studies could translate to realistic settings. In this paper, we propose MuHBoost, a multi-label boosting method for addressing these shortcomings, by leveraging advanced methods in large language model (LLM) prompting and multi-label classification (MLC) to jointly predict multiple health or well-being outcomes. Because LLMs can hallucinate when tasked with answering multiple questions simultaneously, we also develop two variants of MuHBoost that alleviate this issue and thereby enhance its predictive performance. We conduct extensive experiments to evaluate MuHBoost and its variants on 13 health and well-being prediction tasks defined from four realistic ubiquitous health datasets. Our results show that our three developed methods outperform all considered baselines across three standard MLC metrics, demonstrating their effectiveness while ensuring resource efficiency.

This work presents a novel application of electromagnetic wave sensor in healthcare domain. Clotting of blood, also known as coagulation is a serious concern giving rise to cardiovascular disorders. Venous thromboembolism, clot formation of blood within veins, blocks sufficient amount of blood from reaching different parts of the body, like arms and legs. Similar phenomenon occurring in arteries, arterial thrombosis, can cause heart attacks or brain strokes from preventing enough quantity of blood circulating through brain and heart. Heparin is an important drug used to avoid certain clotting of blood, during or after surgical operations where there are more chances of such formation due to cuts being made into body organs. In this work, a bespoke planar electromagnetic wave sensor, designed to resonate in a specific manner, was used to detect heparin level in blood samples. The hairpin resonator sensor was able to distinguish between varying concentrations of heparin in fixed volume of blood by means of electromagnetic wave spectroscopy. This real-time and non-invasive monitoring of blood, containing heparin, can aid towards administration of correct doses of heparin and to ensure that they are maintained in a controlled manner.

This work reports on using X-ray fluorescent method to detect heavy metals in soils of Rozdil State Mining and Chemical Enterprise Sirka, which is included in a list of the top 100 companies for causing environmental pollution in Ukraine. This work has established qualitative and quantitative composition of chemical elements in the soils near to flotation tailings using the X-ray fluorescent analyzer. The metal content was defined in soils near flotation tailings, including: - Zinc, Arsenic (Class 1, high risk). - Nickel, Copper, Chrome, Manganese (Class 2, moderate risk). - Iron, Strontium (Class 3, low risk). As a result of laboratory tests it was found that with increasing distance from the pollutants the amount of heavy metals in the soil decreases. Beginning from a distance of 10 m and more have disappeared in the soil pollutants such as Stannum, Barium and Niobium and other pollutants.

New methods and means to improve the accuracy of the computer system to control the ecological status of water environment are reported. These are based on interference-free measurement of the time parameters of multiple reflected ultrasonic signals in the two reference and study environments.

The intensive use of antibiotics for human treatment and disease prevention in livestock and agriculture has led to the global threat of antibiotic resistance. To prevent the contamination of antibiotic residues through wastewater treatment plants, this paper assesses the feasibility of using UV-Vis spectrophotometer and low-frequency impedance analysis for detecting specific antibiotics in water. The change in the optical absorbance of the solutions was recorded with the spectrophotometer and the change in the values of capacitance was recorded using impedance analyser. In all cases these were dependent on the type of antibiotic and its concentration in water. The efficiency of the sensing methods in detecting different antibiotics at different concentrations is analyzed throughout the paper.