RESUMO
In ambient-assisted living facilitated by smart home systems, the recognition of daily human activities is of great importance. It aims to infer the household's daily activities from the triggered sensor observation sequences with varying time intervals among successive readouts. This paper introduces a novel deep learning framework based on embedding technology and graph attention networks, namely the time-oriented and location-oriented graph attention (TLGAT) networks. The embedding technology converts sensor observations into corresponding feature vectors. Afterward, TLGAT provides a sensor observation sequence as a fully connected graph to the model's temporal correlation as well as the sensor's location correlation among sensor observations and facilitates the feature representation of each sensor observation through receiving other sensor observations and weighting operations. The experiments were conducted on two public datasets, based on the diverse setups of sensor event sequence length. The experimental results revealed that the proposed method achieved favorable performance under diverse setups.
Assuntos
Atividades Cotidianas , Inteligência Ambiental , Humanos , Atividades HumanasRESUMO
The Internet of Medical Things (IoMT) aims to exploit the Internet-of-Things (IoT) techniques to provide better medical treatment scheme for patients with smart, automatic, timely, and emotion-aware clinical services. One of the IoMT instances is applying IoT techniques to sleep-aware smartphones or wearable devices' applications to provide better sleep healthcare services. As we all know, sleep is vital to our daily health. What is more, studies have shown a strong relationship between sleep difficulties and various diseases such as COVID-19. Therefore, leveraging IoT techniques to develop a longer lifetime sleep healthcare IoMT system, with a tradeoff between data transferring/processing speed and battery energy efficiency, to provide longer time services for bad sleep condition persons, especially the COVID-19 patients or survivors, is a meaningful research topic. In this study, we propose an IoT-enabled sleep data fusion networks (SDFN) module with a star topology Bluetooth network to fuse data of sleep-aware applications. A machine learning model is built to detect sleep events through an audio signal. We design two data reprocessing mechanisms running on our IoT devices to alleviate the data jam problem and save the IoT devices' battery energy. The experiments manifest that the presented module and mechanisms can save the energy of the system and alleviate the data jam problem of the device.
RESUMO
To meet the increasing demands of specific pathogen free (SPF) minipigs in biomedical researches, 8 pregnant Chinese Wuzhishan minipigs (WZSP) sows with clear background were chosen to obtain SPF WZSP by hysterectomy. At 111 ± 2 days of the pregnancy, piglets were aseptically taken out from the sows and artificially suckled for 40 to 45 days in the positive isolators. Then, the piglets defined as F0 were transferred to barrier environment and fed with standard feeds. The original SPF colony was formed for breeding by selected piglets from F0 group of 6-8 months old. Biological characteristics of SPF WZSP were collected and further compared to those of conventional (CV) WZSP, including growth performance, reproductive performance, hematology and blood biochemistry, and major pathogens detection. As a result, 61 F0 piglets were obtained from 8 candidate sows, and 55 out of them survived. After strictly selection, 35 F0 piglets were used to form the original SPF colony, which produced 14 litters of SPF piglets defined as F1. Piglet survival rates, growth performance, and reproductive performance of SPF WZSP were similar to CV WZSP. Some hematology and blood biochemistry parameters showed significant differences between SPF and CV WZSP. Eighteen kinds of pathogens were identified to be free in F0 and F1 SPF colony by repeated pathogen detections. In conclusion, we established a satisfied SPF WZSP colony maintaining original characteristics, free of controlled diseases, and being proved to be a suitable laboratory animal.
RESUMO
In order to meet the demands of experimental minipigs for biomedical researches, we have aimed at cultivating grazing Chinese Wuzhishan (WZS) minipigs and trying to make them useful and affordable since the 1990s. After more than ten years of captive cultivation following sound management practices and a rigorous selection program for fertility and litter size, we established an outbred WZS minipigs colony with a core group (14 males and 30 females) and an expanding group (20 males and 40 females). In 2010-2013 periods, extensive background data of this colony were recorded and analyzed. This paper was written to provide pertinent information about outbred WZS minipigs for producers, users, and others concerned with WZS minipigs. It contains physical characteristics, growth performance, productive performance, hematology and blood biochemistry, microsatellite analysis, organ coefficients, and carcass properties. Results show that WZS minipigs have characteristics of small body size, slow growth rate, long life cycle, high reproductive rate, and maintaining original genetic diversity. All data present that outbred WZS minipigs are suitable laboratory animal and model animal.
