Artificial vision systems are powerful tools for the automatic inspection of fruits and vegetables. Typical target applications of such systems include grading, quality estimation from external ...parameters or internal features, monitoring of fruit processes during storage or evaluation of experimental treatments. The capabilities of an artificial vision system go beyond the limited human capacity to evaluate long-term processes objectively or to appreciate events that take place outside the visible electromagnetic spectrum. Use of the ultraviolet or near-infrared spectra makes it possible to explore defects or features that the human eye is unable to see. Hyperspectral systems provide information about individual components or damage that can be perceived only at particular wavelengths and can be used as a tool to develop new computer vision systems adapted to particular objectives. In-line grading systems allow huge amounts of fruit or vegetables to be inspected individually and provide statistics about the batch. In general, artificial systems not only substitute human inspection but also improve on its capabilities. This work presents the latest developments in the application of this technology to the inspection of the internal and external quality of fruits and vegetables.
The essential oil (EO) extracted from bergamot peel (Citrus bergamia, Risso et Poiteau) is appreciated in perfumery and gastronomy. Notably, 90 % of the bergamot EO production is concentrated in the ...Province of Reggio Calabria (Southern Italy) under a protected designation of origin (PDO). The early estimation of EO content in fruits is fundamental to help farmers in their decision at harvesting period. The application of advanced modelling techniques based on artificial intelligence and digital device technology can contribute to this goal. This study proposes a method to estimate the EO content of fruits in the field using classification and regression models based on a deep learning approach in two cultivars: cv. “Fantastico” and cv. “Femminello”. The first step was to capture images of the fruit in the Red, Green, and Blue colours (RGB) using a mid-range smartphone camera and a portable inspection chamber designed and developed for this study. The acquisition of the images was carried out in the field. The fruits were collected and transported to the laboratory, where the EO was extracted using steam hydrodistillation. Custom-built convolutional neural networks (CNN) and three transfer learning models (VGG-16, VGG-19, and Xception architectures) were trained and applied for classification (among different discrete levels of oil content) and regression (to predict the EO content). The classification results showed an accuracy of 0.795 and 0.797 on the test samples of the two cultivars separately, while the best regression model achieved a minimum mean squared error of 0.12 and 0.04 for each cultivar, respectively. The results showed the effectiveness of the approach tested and how modelling each variety independently can lead to better performance for the CNNs tested.
Display omitted
•New portable inspection chamber to acquire reproducible colour images in the field.•Essential oil of bergamot estimated for first time using a non-destructive method.•A custom CNN and three transfer learning models were trained.•Classification and regression methods have been applied to two bergamot cultivars.•Cultivar-based and a general models showed effective at classifying test samples.
The aim of this paper is to investigate the impact of two trading strategies (exporting and importing) on total factor productivity (TFP) and the potential complementarity/substitutability effects of ...these strategies. In order to assess these effects, robust estimates of TFP are obtained using a general method of moments approach that explicitly determines the ability of a firm's trading experience to affect productivity. Data from the Annual Manufacturing Survey spanning from 2007 to 2016 is used for Colombian manufacturing firms. Our estimation results suggest that, regardless of the technological intensity of the industry in which the firm operates, active trading strategies (exporting only, importing only, both importing and exporting) pay positive rewards in terms of productivity. Nevertheless, whilst positive (complementary) synergies are found between exporting and importing for firms in med/high‐tech sectors, for firms operating in low‐tech and med/low‐tech sectors, importing and exporting appear to be substitutes.
This paper analyses the involvement of small firms in international trade activities by identifying the comprehensive impact of innovation. Specifically, we study how innovation introduced by these ...firms determines the entrepreneurial decision-making process regarding whether to engage in exporting and/or importing. Our results confirm the interrelation of firms’ exporting and importing decisions and consequently, these two decisions should be jointly estimated when analysing the influence incurred by the introduction of alternative types of innovation (product, process, and organizational/managerial innovation) on said decisions. Furthermore, findings show complementarity between types of innovation to be relevant in explaining export and import decisions made by SMEs. Specifically, cumulative effects as a result of combining product and process innovation, as well as of product, process and organizational innovation, are highly significant in explaining export decisions, while in the case of imports, the combination of product and organizational innovation is shown to be significant. These findings lead to major policy and managerial implications regarding the promotion of SMEs’ participation in international trade flows through alternative innovation strategies.
Mango fruit are sensitive and can easily develop brown spots after suffering mechanical stress during postharvest handling, transport and marketing. The manual inspection of this fruit used today ...cannot detect the damage in very early stages of maturity and to date no automatic tool capable of such detection has been developed, since current systems based on machine vision only detect very visible damage. The application of hyperspectral imaging to the postharvest quality inspection of fruit is relatively recent and research is still underway to find a method of estimating internal properties or detecting invisible damage. This work describes a new system to evaluate mechanically induced damage in the pericarp of ‘Manila’ mangos at different stages of ripeness based on the analysis of hyperspectral images. Images of damaged and intact areas of mangos were acquired in the range 650–1100 nm using a hyperspectral computer vision system and then analysed to select the most discriminating wavelengths for distinguishing and classifying the two zones. Eleven feature-selection methods were used and compared to determine the wavelengths, while another five classification methods were used to segment the resulting multispectral images and classify the skin of the mangos as sound or damaged. A 97.9% rate of correct classification of pixels was achieved on the third day after the damage had been caused using k-Nearest Neighbours and the whole spectra and the figure dropped to 91.4% when only the most discriminant bands were used.
•Non-destructive system to automate the detection of early mechanical damage in mangos.•Eleven feature selection methods were compared to determine important wavelengths.•Five methods were compared to segment multispectral images in selected wavelengths.•Optimum results were achieved after the third day from the moment of the damage.•Results achieved 98% of correct classification of sound and damaged pixels using k-NN.
This paper examines the impact of different types of innovation on the business performance of small and medium-sized enterprises (SMEs) using a multi-dimensional analytical approach. Based on a wide ...sample of Spanish SMEs, our results highlight the existence of positive impacts of innovation on financial and operational dimensions of business performance, and the significant differences in these impacts depending on the type of innovation and the performance indicator considered. Our findings are relevant for managers and innovation decision-makers when designing innovation strategies to foster the business performance of SMEs. Additionally, the multi-faceted nature of the link between innovation and business outcomes in SMEs reveals that making the right innovation decision is crucial in securing the desired performance outcomes in a context of limited resources for innovation.
Abstract
Summary
We describe a novel computational method for genotyping repeats using sequence graphs. This method addresses the long-standing need to accurately genotype medically important loci ...containing repeats adjacent to other variants or imperfect DNA repeats such as polyalanine repeats. Here we introduce a new version of our repeat genotyping software, ExpansionHunter, that uses this method to perform targeted genotyping of a broad class of such loci.
Availability and implementation
ExpansionHunter is implemented in C++ and is available under the Apache License Version 2.0. The source code, documentation, and Linux/macOS binaries are available at https://github.com/Illumina/ExpansionHunter/.
Supplementary information
Supplementary data are available at Bioinformatics online.
•A policy instrument broadly used to foster firms’ R&D spending are tax incentives.•In Spain only a fraction of firms spending in R&D are regular tax credits claimants.•Using a duration model, our ...data exhibits persistence in claiming R&D tax credits.•Results are consistent with negative duration dependence in claiming R&D tax credits.•The number of product innovations depends positively on R&D tax credit persistence.
Despite the generosity of its tax system, Spain is far from EU countries in terms of R&D spending and innovation outcomes. A policy instrument commonly used to foster firms’ R&D investment are tax incentives. The use of this instrument is not generalized in firms spending on R&D, and only a fraction of firms are regular claimants. This paper investigates whether persistence in using tax credits is positively related to product innovations, beyond R&D investments. We consider that firms investing in qualified R&D and using tax credits regularly are likely to be firms aiming at innovating. By contrast, occasional tax credit users may be firms investing in R&D for different reasons, such as exploiting a business opportunity, or reducing their corporate tax burden, so that they may not prioritize innovating. Using a sample of Spanish manufacturing firms spanning 2001–2014, we first estimate persistence using a duration model accounting for firm observed and unobserved heterogeneity. Our results are consistent with negative duration dependence, indicating that the probability of ceasing in claiming tax credits decreases with the passage of time. Second, we estimate a count-data model and find that the number of product innovations positively depends on tax credit persistence only for SMEs.