Search Results (8)

The Peace–Athabasca Delta (PAD) in northern Alberta is one of the world’s largest inland freshwater deltas and is home to many species of fish, mammals, and birds. Over the past five decades, the PAD has experienced prolonged dry periods in between rare floods, accompanied by a reduction in the area comprised of lakes and ponds that provide a habitat for aquatic life. In the Peace sector of the PAD, this likely resulted from a reduced frequency of spring flooding caused by major ice jams that form in the lower Peace River. There is debate in the literature regarding the factors that promote or inhibit the formation of such ice jams, deriving from physical process studies, paleolimnological studies, and—recently—statistical analysis founded in logistic regression. Logistic regression attempts to quantify ice-jam flood (IJF) probability, given the values of assumed explanatory variables, involve considerable uncertainty. Herein, different sources of uncertainty are examined and their effects on statistical inferences are evaluated. It is shown that epistemic uncertainty can be addressed by selecting direct explanatory variables, such as breakup flow and ice cover thickness, rather than through more convenient, albeit weak, proxies that rely on winter precipitation and degree-days of frost. Structural uncertainty, which derives from the unknown mathematical relationship between IJF probability and the selected explanatory variables, leads to different probability predictions for different assumed relationships but does not modify assessments of statistical significance. The uncertainty associated with the relatively small sample size (number of years of record) may be complicated by known physical constraints on IJF occurrence. Overall, logistic regression corroborates physical understanding that points to breakup flow and freezeup level as primary controls of IJF occurrence. Additional influences, related to the thermal decay of the ice cover and the flow gradient during the advance of the breakup front towards the PAD, are difficult to quantify at present. Progress requires increased monitoring of processes and an enhanced numerical modelling capability. Full article

Background and Objectives: Burn injuries range from minor medical issues to severe, life-threatening conditions. The severity and location of the burn dictate its treatment; while minor burns might be treatable at home, severe burns necessitate medical intervention, sometimes in specialized burn centers with extended follow-up care. This study aims to leverage artificial intelligence (AI)/machine learning (ML) to forecast potential adverse effects in burn patients. Methods: This retrospective analysis considered burn patients admitted to Chi Mei Medical Center from 2010 to 2019. The study employed 14 features, comprising supplementary information like prior comorbidities and laboratory results, for building models for predicting graft surgery, a prolonged hospital stay, and overall adverse effects. Overall, 70% of the data set trained the AI models, with the remaining 30% reserved for testing. Three ML algorithms of random forest, LightGBM, and logistic regression were employed with evaluation metrics of accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). Results: In this research, out of 224 patients assessed, the random forest model yielded the highest AUC for predictions related to prolonged hospital stays (>14 days) at 81.1%, followed by the XGBoost (79.9%) and LightGBM (79.5%) models. Besides, the random forest model of the need for a skin graft showed the highest AUC (78.8%), while the random forest model and XGBoost model of the occurrence of adverse complications both demonstrated the highest AUC (87.2%) as well. Based on the best models with the highest AUC values, an AI prediction system is designed and integrated into hospital information systems to assist physicians in the decision-making process. Conclusions: AI techniques showcased exceptional capabilities for predicting a prolonged hospital stay, the need for a skin graft, and the occurrence of overall adverse complications for burn patients. The insights from our study fuel optimism for the inception of a novel predictive model that can seamlessly meld with hospital information systems, enhancing clinical decisions and bolstering physician–patient dialogues. Full article

A good night’s sleep is of the utmost importance for the seamless execution of our cognitive capabilities. Unfortunately, the research shows that one-third of the US adult population is severely sleep deprived. With college students as our focused group, we devised a contactless, unobtrusive mechanism to detect sleep patterns, which, contrary to existing sensor-based solutions, does not require the subject to put on any sensors on the body or buy expensive sleep sensing equipment. We named this mechanism Packets-to-Predictions(P2P) because we leverage the WiFi MAC layer traffic collected in the home and university environments to predict “sleep” and “awake” periods. We first manually established that extracting such patterns is feasible, and then, we trained various machine learning models to identify these patterns automatically. We trained six machine learning models—K nearest neighbors, logistic regression, random forest classifier, support vector classifier, gradient boosting classifier, and multilayer perceptron. K nearest neighbors gave the best performance with 87% train accuracy and 83% test accuracy. Full article

Facilitating solid waste separating behavior at home continues to be a challenge for municipal programs in emerging economies. Large cities concentrate the generation of solid waste and, in Latin America, a great percentage of this waste is not re-used. Therefore, in this research, we explore the drivers motivating solid waste separation at home in Lima. We applied 450 surveys in two municipalities of Lima and analyzed the results through Structural Equation Modeling (SEM). The results demonstrate that attitude, perception of technical knowledge, and availability of physical space influence solid waste separation behavior. Additionally, the mediating role of intention between solid waste separation attitude and behavior is demonstrated. Municipal solid waste recycling programs in emerging economies tend to focus on educational and motivational actions, without giving due importance to space at home in order to manage solid waste. The lack of urban equipment and the limited availability of space at home introduce barriers that limit solid waste separating behaviors in emerging economies. Full article

Recent years have seen the rapid adoption of Internet of Things (IoT) technologies, where billions of physical devices are interconnected to provide data sensing, computing and actuating capabilities. IoT-based systems have been extensively deployed across various sectors, such as smart homes, smart cities, smart transport, smart logistics and so forth. Newer paradigms such as edge computing are developed to facilitate computation and data intelligence to be performed closer to IoT devices, hence reducing latency for time-sensitive tasks. However, IoT applications are increasingly being deployed in remote and difficult to reach areas for edge computing scenarios. These deployment locations make upgrading application and dealing with software failures difficult. IoT applications are also increasingly being deployed as containers which offer increased remote management ability but are more complex to configure. This paper proposes an approach for effectively managing, updating and re-configuring container-based IoT software as efficiently, scalably and reliably as possible with minimal downtime upon the detection of software failures. The approach is evaluated using docker container-based IoT application deployments in an edge computing scenario. Full article

Electrochemically based technologies are rapidly moving from the laboratory to bedside applications and wearable devices, like in the field of cardiovascular disease. Major efforts have focused on the biosensor component in contrast with those employed in creating more suitable detection algorithms for long-term real-world monitoring solutions. The calibration curve procedure presents major limitations in this context. The objective is to propose a new algorithm, compliant with current clinical guidelines, which can overcome these limitations and contribute to the development of trustworthy wearable or telemonitoring solutions for home-based care. A total of 123 samples of phosphate buffer solution were spiked with different concentrations of troponin, the gold standard method for the diagnosis of the acute coronary syndrome. These were classified as normal or abnormal according to established clinical cut-off values. Off-the-shelf screen-printed electrochemical sensors and cyclic voltammetry measurements (sweep between −1 and 1 V in a 5 mV step) was performed to characterize the changes on the surface of the biosensor and to measure the concentration of troponin in each sample. A logistic regression model was developed to accurately classify these samples as normal or abnormal. The model presents high predictive performance according to specificity (94%), sensitivity (92%), precision (92%), recall (92%), negative predictive value (94%) and F-score (92%). The area under the curve of the precision-recall curve is 97% and the positive and negative likelihood ratios are 16.38 and 0.082, respectively. Moreover, high discriminative power is observed from the discriminate odd ratio (201) and the Youden index (0.866) values. The promising performance of the proposed algorithm suggests its capability to overcome the limitations of the calibration curve procedure and therefore its suitability for the development of trustworthy home-based care solutions. Full article

The eruption of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) (corona virus disease, COVID-19) in Wuhan, China, and its global spread has led to an exponentially growing number of infected patients, currently exceeding over 6.6 million and over 390,000 deaths as of the 5th of June 2020. In this pandemic situation, health systems have been put under stress, and the demand for personal protective equipment (PPE) exceeded the delivery capabilities of suppliers. To address this issue, 3D printing was identified as a possible solution to quickly produce PPE items such as face shields, mask straps, masks, valves, and ear savers. Around the world, companies, universities, research institutions, and private individuals/hobbyists stepped into the void, using their 3D printers to support hospitals, doctors, nursing homes, and even refugee camps by providing them with PPE. In Germany, the makervsvirus movement took up the challenge and connected thousands of end users, makers, companies, and logistic providers for the production and supply of face shields, protective masks, and ear savers. The Karlsruhe Institute of Technology (KIT) also joined the makervsvirus movement and used its facilities to print headbands for face shield assemblies and ear savers. Within this paper, the challenges and lessons learned from the quick ramp up of a research laboratory to a production site for medium-sized batches of PPE, the limitations in material supply, selection criteria for suitable models, quality measures, and future prospects are reported and conclusions drawn. Full article

Sensors utilize a large number of heterogeneous technologies for a varied set of application environments. The sheer number of devices involved requires that this Internet be the Future Internet, with a core network based on IPv6 and a higher scalability in order to be able to address all the devices, sensors and things located around us. This capability to connect through IPv6 devices, sensors and things is what is defining the so-called Internet of Things (IoT). IPv6 provides addressing space to reach this ubiquitous set of sensors, but legacy technologies, such as X10, European Installation Bus (EIB), Controller Area Network (CAN) and radio frequency ID (RFID) from the industrial, home automation and logistic application areas, do not support the IPv6 protocol. For that reason, a technique must be devised to map the sensor and identification technologies to IPv6, thus allowing homogeneous access via IPv6 features in the context of the IoT. This paper proposes a mapping between the native addressing of each technology and an IPv6 address following a set of rules that are discussed and proposed in this work. Specifically, the paper presents a technology-dependent IPv6 addressing proxy, which maps each device to the different subnetworks built under the IPv6 prefix addresses provided by the internet service provider for each home, building or user. The IPv6 addressing proxy offers a common addressing environment based on IPv6 for all the devices, regardless of the device technology. Thereby, this offers a scalable and homogeneous solution to interact with devices that do not support IPv6 addressing. The IPv6 addressing proxy has been implemented in a multi-protocol Sensors 2013, 13 6688 card and evaluated successfully its performance, scalability and interoperability through a protocol built over IPv6. Full article