Tackling unbalanced datasets for yellow and brown rust detection in wheat.

This study evaluates the efficacy of hyperspectral data for detecting yellow and brown rust in wheat, employing machine learning models and the SMOTE (Synthetic Minority Oversampling Technique) augmentation technique to tackle unbalanced datasets. Artificial Neural Network (ANN), Support Vector Machine (SVM), Random Forest (RF), and Gaussian Naïve Bayes (GNB) models were assessed. Overall, SVM and RF models showed higher accuracies, particularly when utilizing SMOTE-enhanced datasets. The RF model achieved 70% accuracy in detecting yellow rust without data alteration. Conversely, for brown rust, the SVM model outperformed others, reaching 63% accuracy with SMOTE applied to the training set. This study highlights the potential of spectral data and machine learning (ML) techniques in plant disease detection. It emphasizes the need for further research in data processing methodologies, particularly in exploring the impact of techniques like SMOTE on model performance.

Determinación de tiempos quirúrgicos estándar de los procedimientos más comunes de cirugía general y su probabilidad de extensión para eficientizar la programación de cirugías / Estimation of the standard surgical times of the most common general surgery procedures and the probability of extending them to make surgery scheduling more efficient

RESUMEN Objetivo: Determinar los tiempos quirúrgicos estándar de los cuatro procedimientos más comunes en cirugía general (hernioplastia inguinal unilateral, hernioplastia inguinal bilateral, hernioplastia umbilical y colecistectomía) de un hospital de segundo nivel y calcular la probabilidad de extensión de cada uno de los procedimientos. La eficiencia es un fenómeno ampliamente estudiado en el ámbito económico, pues hace referencia a la necesidad de menor cantidad de factores para la producción de un determinado nivel de bienes y servicios, por ello, es de vital importancia incluirlo en el ámbito quirúrgico. Materiales y métodos: Estudio observacional, descriptivo y retrospectivo. Se utilizaron los registros de quirófano de un hospital de segundo nivel del año 2017 al 2019 del servicio de Cirugía General. A partir de esta información, se estandarizó el tiempo necesario para cada procedimiento mediante la media de cada uno (hernioplastia umbilical, hernioplastia inguinal unilateral o bilateral y colecistectomía). Se calculó la probabilidad de extensión de las cirugías tomando en consideración los datos obtenidos y el intervalo de confianza. Resultados: Para el procedimiento de hernioplastia inguinal unilateral se obtuvo una media de 76 min (IC 95,00 %: 72-80 min, DE 23); en hernioplastia inguinal bilateral, una media de 104,38 min (IC 95,00 %: 91-116 min, DE 41,7); en hernioplastia umbilical, una media de 59,31 min (IC 95,00 %: 54-63 min, DE 29,9), y en colecistectomía, una media de 85,735 min (IC 95,00 %: 83-88 min). La probabilidad de que se programen tres cirugías y todas estén a tiempo (límite superior del IC) es de 92,69 %, la probabilidad de que se programen tres cirugías y todas se prolonguen es de 0,0016 % (límite inferior del IC). Conclusiones: Es posible realizar la planeación de las cirugías programadas mediante el uso de tiempos quirúrgicos estandarizados. Se requiere contar con estadística actualizada de los procedimientos quirúrgicos (promedios del tiempo de realización de cada procedimiento), ya que es posible detectar y supervisar de manera más precisa la dinámica de quirófano mediante la detección de las áreas de oportunidad, de esta manera, se eficientizará el tiempo de quirófano para beneficio de los sistemas de salud y los pacientes.

ABSTRACT Objective: To determine the standard surgical times of the four most common general surgery procedures (unilateral inguinal hernioplasty, bilateral inguinal hernioplasty, umbilical hernioplasty and cholecystectomy) in a second-level hospital and to estimate the probability of extending the time of each of the procedures. Efficiency is a widely studied subject in economics. It involves the need for fewer elements in the production of a certain level of goods and services. Therefore, it is extremely important to consider it in the field of surgery. Materials and methods: An observational, descriptive and retrospective study. It used the operating room records from 2017 to 2019 of the General Surgery service in a second-level hospital. Based on this information, the time required for each procedure was standardized using the mean for each one (umbilical hernioplasty, unilateral or bilateral inguinal hernioplasty and cholecystectomy). The probability of extending surgical times was estimated based on the obtained data and confidence interval. Results: The mean for unilateral inguinal hernioplasty was 76 min (95.00 % CI: 72-80 min, SD 23), for bilateral inguinal hernioplasty 104.38 min (95.00 % CI: 91-116 min, SD 41.7), for umbilical hernioplasty 59.31 min (95.00 % CI: 54-63 min, SD 29.99) and for cholecystectomy 85.735 min (95.00 % CI: 83-88 min). The probability of scheduling three surgical interventions and completing all of them on time (upper limit of the CI) is 92.69 %, and the probability of scheduling three surgical interventions and extending the time of all of them is 0.0016 % (lower limit of the CI). Conclusions: Planning scheduled operations using standardized surgical times is feasible. Updated statistics on surgical procedures (average time for each procedure) are required since it is possible to more accurately detect and supervise operating room dynamics by identifying opportunity areas. This will make operating room time more efficient for the benefit of health care systems and patients.

Reducing environmental exposure to PPPs in super-high density olive orchards using UAV sprayers.

The increasing demand for optimizing the use of agricultural resources will require the adoption of cutting-edge technologies and precision farming management. Unmanned Aerial Vehicle (UAV) sprayers seem promising due to their potential to perform precision or spot spraying, particularly in woody crop environments where total surface spraying is unnecessary. However, incorporating this technology is limited by the lack of scientific knowledge about the environmental risks associated with UAV sprayers and the strict legal framework. Nonetheless, these spraying systems' characteristic downwash airflow and the limited swath width can potentially mitigate drift in hedgerow crops. During our study we performed comparative studies aimed to compare the airborne drift, soil, and crop depositions between a conventional orchard sprayer and a UAV sprayer in a commercial superhigh-density orchard in the South Iberian Peninsula in 2022. Our findings reveal that, in superhigh-density olive orchards, the UAV sprayer presents a substantial reduction in airborne drift, while soil depositions showed no significant differences compared to those of a conventional terrestrial orchard sprayer. Crop depositions were significantly lower when utilizing the UAV sprayer. These results suggest that introducing UAV spraying technology in Mediterranean agricultural systems, under specific scenarios, can effectively reduce the environmental impact of crop spraying and encourage the responsible use of plant protection products (PPPs).

Intelligent Fruit Yield Estimation for Orchards Using Deep Learning Based Semantic Segmentation Techniques-A Review.

Smart farming employs intelligent systems for every domain of agriculture to obtain sustainable economic growth with the available resources using advanced technologies. Deep Learning (DL) is a sophisticated artificial neural network architecture that provides state-of-the-art results in smart farming applications. One of the main tasks in this domain is yield estimation. Manual yield estimation undergoes many hurdles such as labor-intensive, time-consuming, imprecise results, etc. These issues motivate the development of an intelligent fruit yield estimation system that offers more benefits to the farmers in deciding harvesting, marketing, etc. Semantic segmentation combined with DL adds promising results in fruit detection and localization by performing pixel-based prediction. This paper reviews the different literature employing various techniques for fruit yield estimation using DL-based semantic segmentation architectures. It also discusses the challenging issues that occur during intelligent fruit yield estimation such as sampling, collection, annotation and data augmentation, fruit detection, and counting. Results show that the fruit yield estimation employing DL-based semantic segmentation techniques yields better performance than earlier techniques because of human cognition incorporated into the architecture. Future directions like customization of DL architecture for smart-phone applications to predict the yield, development of more comprehensive model encompassing challenging situations like occlusion, overlapping and illumination variation, etc., were also discussed.

A Cloud-Based Environment for Generating Yield Estimation Maps From Apple Orchards Using UAV Imagery and a Deep Learning Technique.

Farmers require accurate yield estimates, since they are key to predicting the volume of stock needed at supermarkets and to organizing harvesting operations. In many cases, the yield is visually estimated by the crop producer, but this approach is not accurate or time efficient. This study presents a rapid sensing and yield estimation scheme using off-the-shelf aerial imagery and deep learning. A Region-Convolutional Neural Network was trained to detect and count the number of apple fruit on individual trees located on the orthomosaic built from images taken by the unmanned aerial vehicle (UAV). The results obtained with the proposed approach were compared with apple counts made in situ by an agrotechnician, and an R2 value of 0.86 was acquired (MAE: 10.35 and RMSE: 13.56). As only parts of the tree fruits were visible in the top-view images, linear regression was used to estimate the number of total apples on each tree. An R2 value of 0.80 (MAE: 128.56 and RMSE: 130.56) was obtained. With the number of fruits detected and tree coordinates two shapefile using Python script in Google Colab were generated. With the previous information two yield maps were displayed: one with information per tree and another with information per tree row. We are confident that these results will help to maximize the crop producers' outputs via optimized orchard management.

Low-Cost Three-Dimensional Modeling of Crop Plants.

Plant modeling can provide a more detailed overview regarding the basis of plant development throughout the life cycle. Three-dimensional processing algorithms are rapidly expanding in plant phenotyping programmes and in decision-making for agronomic management. Several methods have already been tested, but for practical implementations the trade-off between equipment cost, computational resources needed and the fidelity and accuracy in the reconstruction of the end-details needs to be assessed and quantified. This study examined the suitability of two low-cost systems for plant reconstruction. A low-cost Structure from Motion (SfM) technique was used to create 3D models for plant crop reconstruction. In the second method, an acquisition and reconstruction algorithm using an RGB-Depth Kinect v2 sensor was tested following a similar image acquisition procedure. The information was processed to create a dense point cloud, which allowed the creation of a 3D-polygon mesh representing every scanned plant. The selected crop plants corresponded to three different crops (maize, sugar beet and sunflower) that have structural and biological differences. The parameters measured from the model were validated with ground truth data of plant height, leaf area index and plant dry biomass using regression methods. The results showed strong consistency with good correlations between the calculated values in the models and the ground truth information. Although, the values obtained were always accurately estimated, differences between the methods and among the crops were found. The SfM method showed a slightly better result with regard to the reconstruction the end-details and the accuracy of the height estimation. Although the use of the processing algorithm is relatively fast, the use of RGB-D information is faster during the creation of the 3D models. Thus, both methods demonstrated robust results and provided great potential for use in both for indoor and outdoor scenarios. Consequently, these low-cost systems for 3D modeling are suitable for several situations where there is a need for model generation and also provide a favourable time-cost relationship.

Evaluation of Over-The-Row Harvester Damage in a Super-High-Density Olive Orchard Using On-Board Sensing Techniques.

New super-high-density (SHD) olive orchards designed for mechanical harvesting using over-the-row harvesters are becoming increasingly common around the world. Some studies regarding olive SHD harvesting have focused on the effective removal of the olive fruits; however, the energy applied to the canopy by the harvesting machine that can result in fruit damage, structural damage or extra stress on the trees has been little studied. Using conventional analyses, this study investigates the effects of different nominal speeds and beating frequencies on the removal efficiency and the potential for fruit damage, and it uses remote sensing to determine changes in the plant structures of two varieties of olive trees (‘Manzanilla Cacereña’ and ‘Manzanilla de Sevilla’) planted in SHD orchards harvested by an over-the-row harvester. ‘Manzanilla de Sevilla’ fruit was the least tolerant to damage, and for this variety, harvesting at the highest nominal speed led to the greatest percentage of fruits with cuts. Different vibration patterns were applied to the olive trees and were evaluated using triaxial accelerometers. The use of two light detection and ranging (LiDAR) sensing devices allowed us to evaluate structural changes in the studied olive trees. Before- and after-harvest measurements revealed significant differences in the LiDAR data analysis, particularly at the highest nominal speed. The results of this work show that the operating conditions of the harvester are key to minimising fruit damage and that a rapid estimate of the damage produced by an over-the-row harvester with contactless sensing could provide useful information for automatically adjusting the machine parameters in individual olive groves in the future.

Optical Sensing to Determine Tomato Plant Spacing for Precise Agrochemical Application: Two Scenarios.

The feasibility of automated individual crop plant care in vegetable crop fields has increased, resulting in improved efficiency and economic benefits. A systems-based approach is a key feature in the engineering design of mechanization that incorporates precision sensing techniques. The objective of this study was to design new sensing capabilities to measure crop plant spacing under different test conditions (California, USA and Andalucía, Spain). For this study, three different types of optical sensors were used: an optical light-beam sensor (880 nm), a Light Detection and Ranging (LiDAR) sensor (905 nm), and an RGB camera. Field trials were conducted on newly transplanted tomato plants, using an encoder as a local reference system. Test results achieved a 98% accuracy in detection using light-beam sensors while a 96% accuracy on plant detections was achieved in the best of replications using LiDAR. These results can contribute to the decision-making regarding the use of these sensors by machinery manufacturers. This could lead to an advance in the physical or chemical weed control on row crops, allowing significant reductions or even elimination of hand-weeding tasks.