Near-field microwave sensing technology enhanced with machine learning for the non-destructive evaluation of packaged food and beverage products.

In the food industry, the increasing use of automatic processes in the production line is contributing to the higher probability of finding contaminants inside food packages. Detecting these contaminants before sending the products to market has become a critical necessity. This paper presents a pioneering real-time system for detecting contaminants within food and beverage products by integrating microwave (MW) sensing technology with machine learning (ML) tools. Considering the prevalence of water and oil as primary components in many food and beverage items, the proposed technique is applied to both media. The approach involves a thorough examination of the MW sensing system, from selecting appropriate frequency bands to characterizing the antenna in its near-field region. The process culminates in the collection of scattering parameters to create the datasets, followed by classification using the Support Vector Machine (SVM) learning algorithm. Binary and multiclass classifications are performed on two types of datasets, including those with complex numbers and amplitude data only. High accuracy is achieved for both water-based and oil-based products.

Graduate medical education-led continuous assessment of burnout and learning environments to improve residents' wellbeing.

BACKGROUND: Promoting residents' wellbeing and decreasing burnout is a focus of Graduate Medical Education (GME). A supportive clinical learning environment is required to optimize residents' wellness and learning. OBJECTIVE: To determine if longitudinal assessments of burnout and learning environment as perceived by residents combined with applying continuous quality Model for Improvement and serial Plan, Do, Study, Act (PDSA) cycles to test interventions would improve residents' burnout. METHODS: From November 2017 to January 2020, 271 GME residents in internal medicine, general surgery, psychiatry, emergency medicine, family medicine and obstetrics and gynecology, were assessed over five cycles by Maslach Burnout Inventory (MBI), and by clinical learning environment factors (which included personal/social relationships, self-defined burnout, program burnout support, program back-up support, clinical supervision by faculty, and sleep difficulties). The results of the MBI and clinical learning environment factors were observed and analyzed to determine and develop indicated Institutional and individual program interventions using a Plan, Do, Study, Act process with each of the five cycles. RESULTS: The response rate was 78.34%. MBI parameters for all GME residents improved over time but were not statistically significant. Residents' positive perception of the clinical supervision by faculty was significantly and independently associated with improved MBI scores, while residents' self-defined burnout; and impaired personal relations perceptions were independently significantly associated with adverse MBI scores on liner regression. For all GME, significant improvements improved over time in residents' perception of impaired personal relationships (p < 0.001), self-defined burnout (p = 0.013), program burn-out support (p = 0.002) and program back-up support (p = 0.028). For the Internal Medicine Residency program, there were statistically significant improvements in all three MBI factors (p < 0.001) and in clinical learning environment measures (p = 0.006 to < 0.001). Interventions introduced during the PDSA cycles included organization-directed interventions (such as: faculty and administrative leadership recruitment, workflow interventions and residents' schedule optimization), and individual interventions (such as: selfcare, mentoring and resilience training). CONCLUSION: In our study, for all GME residents, clinical learning environment factors in contrast to MBI factors showed significant improvements. Residents' positive perception of the clinical learning environment was associated with improved burnout measures. Residents in separate programs responded differently with one program reaching significance in all MBI and clinical learning environment factors measured. Continuous wellbeing assessment of all GME residents and introduction of Institutional and individual program interventions was accomplished.

A comparative study on predicting influenza outbreaks using different feature spaces: application of influenza-like illness data from Early Warning Alert and Response System in Syria.

OBJECTIVE: An accurate forecasting of outbreaks of influenza-like illness (ILI) could support public health officials to suggest public health actions earlier. We investigated the performance of three different feature spaces in different models to forecast the weekly ILI rate in Syria using EWARS data from World Health Organization (WHO). Time series feature space was first used and we applied the seven models which are Naïve, Average, Seasonal naïve, drift, dynamic harmonic regression (Dhr), seasonal and trend decomposition using loess (STL) and TBATS. The Second feature space is like some state-of-the-art, which we named [Formula: see text] feature space. The third one, we proposed and named [Formula: see text] (YnWm) feature space. Machine learning (ML) and deep learning (DL) model were applied to the second and third feature spaces (generalized linear model (GLM), support vector regression (SVR), gradient boosting (GB), random forest (RF) and long short term memory (LSTM)). RESULTS: It was indicated that the LSTM model of four layers with [Formula: see text] feature space gave more accurate results than other models and reached the lowest MAPE of [Formula: see text] and the lowest RMSE of 0.01662. I hope that this modelling methodology can be applied in other countries and therefore help prevent and control influenza worldwide.