Grapevine bunch weight estimation using image-based features: comparing the predictive performance of number of visible berries and bunch area

Recent advances in machine vision technologies have provided a multitude of automatic tools for recognition and quantitative estimation of grapevine bunch features in 2D images. However, converting them into bunch weight (BuW) is still a big challenge. This paper aims to compare the explanatory power of the number of visible berries (#vBe) and the bunch area (BuA) in 2D images, in order to predict BuW. A set of 300 bunches from four grapevine cultivars were picked at harvest and imaged using a digital RGB camera. Then each bunch was manually assessed for several morphological attributes and, from each image, the #vBe was visually assessed while BuA was segmented using manual labelling combined with an image processing software. Single and multiple regression analysis between BuW and the image-based variables were performed and the obtained regression models were subsequently validated with two independent datasets.The high goodness of fit obtained for all the linear regression models indicates that either one of the image-based variables can be used as an accurate proxy of actual bunch weight and that a general model is also suitable. The comparison of the explanatory power of the two image-based attributes for predicting bunch weight showed that the models based on the predictor #vBe had a slightly lower coefficient of determination (R2) than the models based on BuA. The combination of the two image-based explanatory variables in a multiple regression model produced predictor models with similar or noticeably higher R2 than those obtained for single-predictor models. However, adding a second variable produced a higher and more generalised gain in accuracy for the simple regression models based on the predictor #vBe than for the models based on BuA. Our results recommend the use of the models based on the two image-based variables, as they were generally more accurate and robust than the single variable models. When the gains in accuracy produced by adding a second image-based feature are small, the option of using only a single predictor can be chosen; in such a case, our results indicate that BuA would be a more accurate and less cultivar-dependent option than the #vBe.

Implementation of machine learning techniques for the quasi real-time blind and electric lighting optimization in a controlled experimental facility

Machine Learning techniques have been recently investigated as an alternative to the use of physical simulations, aiming to improve the response time of daylight and electric lighting performance-predictions. In this study, daylight and electric lighting predictor models are derived from daylighting RADIANCE simulations, aiming to provide visual comfort to office room occupants, with a reduced use of electric lighting. The aim is to integrate an intelligent control scheme, that, implemented on a small embedded 32-bit computer (Raspberry Pi), interfaces a KNX system for a quasi-real-time optimization of the building parameters. The present research constitutes a step towards the broader goal of achieving a unified approach, in which the daylight and electric lighting predictor models would be integrated in a Model Predictive Control. A verification of the ML performance is carried-out by comparing the model predictions to data obtained in monitoring sessions in autumn, winter and spring 2020-2021, resulting in an average MAPE of 19.3%.

Assessment of an intervention to optimise antenatal management of women admitted with preterm labour and intact membranes using amniocentesis-based predictive risk models: study protocol for a randomised controlled trial (OPTIM-PTL Study)

IntroductionThe majority of women admitted with threatened preterm labour (PTL) do not delivery prematurely. While those with microbial invasion of the amniotic cavity (MIAC) represent the highest risk group, this is a condition that is not routinely ruled out since it requires amniocentesis. Identification of low-risk or high-risk cases might allow individualisation of care, that is, reducing overtreatment with corticosteroids and shorten hospital stay in low-risk women, while allowing early antibiotic therapy in those with MIAC. Benefits versus risks of amniocentesis-based predictor models of spontaneous delivery within 7 days and/or MIAC have not been evaluated.Methods and analysisThis will be a Spanish randomised, multicentre clinical trial in singleton pregnancies (23.0–34.6 weeks) with PTL, conducted in 13 tertiary centres. The intervention arm will consist in the use of amniocentesis-based predictor models: if low risk, hospital discharge within 24 hours of results with no further medication will be recommended. If high risk, antibiotics will be added to standard management. The control group will be managed according to standard institutional protocols, without performing amniocentesis for this indication. The primary outcome will be total antenatal doses of corticosteroids, and secondary outcomes will be days of maternal stay and the occurrence of clinical chorioamnionitis. A cost analysis will be undertaken. To observe a reduction from 90% to 70% in corticosteroid doses, a reduction in 1 day of hospital stay (SD of 2) and a reduction from 24% to 12% of clinical chorioamnionitis, a total of 340 eligible patients randomised 1 to 1 to each study arm is required (power of 80%, with type I error α=0.05 and two-sided test, considering a dropout rate of 20%). Randomisation will be stratified by gestational age and centre.Ethics and disseminationPrior to receiving approval from the Ethics Committee (HCB/2020/1356) and the Spanish Agency of Medicines and Medical Devices (AEMPS) (identification number: 2020-005-202-26), the trial was registered in the European Union Drug Regulating Authorities Clinical Trials database (2020-005202-26). AEMPS approved the trial as a low-intervention trial. All participants will be required to provide written informed consent. Findings will be disseminated through workshops, peer-reviewed publications and national/international conferences.Protocol versionV.4 10 May 2021.Trial registration numbersNCT04831086 and Eudract number 2020-005202-26.

Analisis Akurasi Model-Model Prediksi Financial Distress

This study aims to find the most accurate predictor model of financial distress. The company has the potential to go bankrupt. Bankruptcy can be predicted using an accurate predictor model as an early warning to anticipate financial distress. This research was conducted on the global retail industry which is included in Kantar's 2019 Top 30 Global Retails (EUR). The data in this study were taken from 60 annual reports for the 2018-2019 period and a sample of 30 on global retail companies. The accuracy rate is calculated by the number of correct predictions divided by the total data and multiplied by one hundred percent. This study compares four predictor models of financial distress, namely the Altman model, the Springate model, the Taffler model, and the Grover model. With the results of the study, the Grover model has the highest level of accuracy, which is 76.67%.

Determinant physical factors in the wheelchair tennis player

The objective of this research was to identify the most determining physical factors in the ranking position of wheelchair tennis players (WT). In a national camp, the nine best nationally ranked Spanish male WT players (38.35 ± 11.28 years, 63.77 ± 7.01 kg. weight) completed a test battery. Significantly higher correlations were observed in medicine ball throws, 5 and 20-metres sprints with racquet and in an agility test without racquet. In addition, the regression analysis identified two predictor models of the player's ranking position that included both the serve throw and the 5-metre racquet sprint. In conclusion, it is recommended that coaches and physical trainers include in their training programmes medicine ball exercises as well as acceleration drills over short distances.

Comparative assessment of severity and prognosis of acute pancreatitis through APACHE II and HAPS predictor models

Background: Acute pancreatitis is one of the leading causes of hospitalization amongst all gastrointestinal disorders with high burden of morbidity and mortality. Predicting the progression of AP in terms of course and outcome to determine suitable management strategy and level of care is challenging. A number of predictor models are developed to predict the severity of acute pancreatitis but they vary in their definitions of severity. HAPS have been proposed as a simple scoring tool for assessment of severity and prognosis of acute pancreatitis. Thus, the aim of present study was to investigate the usefulness of HAPS predictor model against APACHE II model.Methods: Current investigation was a hospital based prospective study conducted on 80 proven cases of acute pancreatitis at K. K. hospital, Uttar Pradesh. The serum amylase and lipase levels of all enrolled patients, were tested and measured at admission, and at 48 and 72 hours post admission. The pancreatitis-specific clinical investigations like; HAPS, APACHE II were calculated and assessed statistically in terms of sensitivity, specificity, positive and negative predictive values and accuracy.Results: The findings of present investigation revealed that amongst the two scoring systems, APACHE II was superior predictor model in terms of sensitivity and specificity for various outcomes like severe acute pancreatitis, hospital stay >7 days and in-hospital mortality. However, HAPS exhibited high specificity for all the outcomes.Conclusions: HAPS can be recommended as a useful tool for early evaluation of acute pancreatitis in patients specifically in primary care settings of developing countries like India.

No magic bullet: estimating anti-immigrant sentiment and social desirability bias with the item-count technique

Extant scholarship on attitudes toward immigration and immigrants relies mostly on direct survey items. Thus, little is known about the scope of social desirability bias, and even less about its covariates. In this paper, we use probability-based mixed-modes panel data collected in the Southern Spanish region of Andalusia to estimate anti-immigrant sentiment with both the item-count technique, also known as list experiment, and a direct question. Based on these measures, we gauge the size of social desirability bias, compute predictor models for both estimators of anti-immigrant sentiment, and pinpoint covariates of bias. For most respondent profiles, the item-count technique produces higher estimates of anti-immigrant sentiment than the direct question, suggesting that self-presentational concerns are far more ubiquitous than previously assumed. However, we also find evidence that among people keen to position themselves as all-out xenophiles, social desirability pressures persist in the list-experiment: the full scope of anti-immigrant sentiment remains elusive even in non-obtrusive measurement.