Machinery for potato harvesting: a state-of-the-art review.

Potatoes are the fourth most important crop for human consumption. In the 18 century, potatoes saved the European population from starvation, and since then, it has become one of the primary crops cultivated in countries such as Spain, France, Germany, Ukraine and the United Kingdom. Potato production worldwide reached 368.8 million tonnes in 2019, 371.1 million tonnes in 2020, and 376.1 million tonnes in 2021, with production expected to grow alongside the worldwide population. However, the agricultural sector is currently suffering from urbanization. With the next generation of farmers relocating to cities, there is a diminishing and ageing agricultural workforce. Consequently, farms urgently need innovation, particularly from a technology perspective. As a result, this work is focused on reviewing the worldwide developments in potato harvesting, with an emphasis on mechatronics, the use of intelligent systems and the opportunities that arise from applications utilising the Internet of Things (IoT). Our work covers worldwide scientific publications in the last five years, sustained by public data made available from different governments. We end our review by providing a discussion on the future trends derived from our analysis.

Machine learning assisted remote forestry health assessment: a comprehensive state of the art review.

Forests are suffering water stress due to climate change; in some parts of the globe, forests are being exposed to the highest temperatures historically recorded. Machine learning techniques combined with robotic platforms and artificial vision systems have been used to provide remote monitoring of the health of the forest, including moisture content, chlorophyll, and nitrogen estimation, forest canopy, and forest degradation, among others. However, artificial intelligence techniques evolve fast associated with the computational resources; data acquisition, and processing change accordingly. This article is aimed at gathering the latest developments in remote monitoring of the health of the forests, with special emphasis on the most important vegetation parameters (structural and morphological), using machine learning techniques. The analysis presented here gathered 108 articles from the last 5 years, and we conclude by showing the newest developments in AI tools that might be used in the near future.

Inteligencia artificial en otorrinolaringología: estado actual y perspectivas a futuro / Artificial intelligence in otolaryngology: current status and future perspectives

La inteligencia artificial posee una larga historia, llena de innovaciones que han dado como resultado diferentes recursos diagnósticos de alto rendimiento, que se encuentran disponibles actualmente. En este artículo se presenta una revisión sobre la inteligencia artificial y sus aplicaciones en medicina. El trabajo se centra en la especialidad de otorrinolaringología con el objetivo de informar a la comunidad médica la importancia y las aplicaciones más destacadas en los diferentes procesos diagnósticos dentro de la especialidad. Incluimos una sección para el análisis del estado actual de la inteligencia artificial en otorrinolaringología en Chile, así como los desafíos a enfrentar a futuro para utilizar la inteligencia artificial en la práctica médica diaria.

Artificial intelligence has a long history full of innovations that have resulted in different high-performance diagnostic resources currently available. This work has reviewed the artificial intelligence definition and its applications to medicine. We focused our review on otolaryngology's specialty to inform the medical community of the importance and the most relevant applications in the different diagnostic processes. We include an analysis of the current state of artificial intelligence in otolaryngology in Chile, and the challenges to be faced in the future to use artificial intelligence into daily medical practice.

Passive Landmark Geometry Optimization and Evaluation for Reliable Autonomous Navigation in Mining Tunnels Using 2D Lidars.

Autonomous navigation in mining tunnels is challenging due to the lack of satellite positioning signals and visible natural landmarks that could be exploited by ranging systems. Solutions requiring stable power feeds for locating beacons and transmitters are not accepted because of accidental damage risks and safety requirements. Hence, this work presents an autonomous navigation approach based on artificial passive landmarks, whose geometry has been optimized in order to ensure drift-free localization of mobile units typically equipped with lidar scanners. The main contribution of the approach lies in the design and optimization of the landmarks that, combined with scan matching techniques, provide a reliable pose estimation in modern smoothly bored mining tunnels. A genetic algorithm is employed to optimize the landmarks' geometry and positioning, thus preventing that the localization problem becomes ill-posed. The proposed approach is validated both in simulation and throughout a series of experiments with an industrial skid-steer CAT 262C robotic excavator, showing the feasibility of the approach with inexpensive passive and low-maintenance landmarks. The results show that the optimized triangular and symmetrical landmarks improve the positioning accuracy by 87.5% per 100 m traveled compared to the accuracy without landmarks. The role of optimized artificial landmarks in the context of modern smoothly bored mining tunnels should not be understated. The results confirm that without the optimized landmarks, the localization error accumulates due to odometry drift and that, contrary to the general intuition or belief, natural tunnel features alone are not sufficient for unambiguous localization. Therefore, the proposed approach ensures grid-based SLAM techniques can be implemented to successfully navigate in smoothly bored mining tunnels.

Color Dependence Analysis in a CNN-Based Computer-Aided Diagnosis System for Middle and External Ear Diseases.

Artificial intelligence-assisted otologic diagnosis has been of growing interest in the scientific community, where middle and external ear disorders are the most frequent diseases in daily ENT practice. There are some efforts focused on reducing medical errors and enhancing physician capabilities using conventional artificial vision systems. However, approaches with multispectral analysis have not yet been addressed. Tissues of the tympanic membrane possess optical properties that define their characteristics in specific light spectra. This work explores color wavelengths dependence in a model that classifies four middle and external ear conditions: normal, chronic otitis media, otitis media with effusion, and earwax plug. The model is constructed under a computer-aided diagnosis system that uses a convolutional neural network architecture. We trained several models using different single-channel images by taking each color wavelength separately. The results showed that a single green channel model achieves the best overall performance in terms of accuracy (92%), sensitivity (85%), specificity (95%), precision (86%), and F1-score (85%). Our findings can be a suitable alternative for artificial intelligence diagnosis systems compared to the 50% of overall misdiagnosis of a non-specialist physician.

Computer-aided diagnosis of external and middle ear conditions: A machine learning approach.

In medicine, a misdiagnosis or the absence of specialists can affect the patient's health, leading to unnecessary tests and increasing the costs of healthcare. In particular, the lack of specialists in otolaryngology in third world countries forces patients to seek medical attention from general practitioners, whom might not have enough training and experience for making correct diagnosis in this field. To tackle this problem, we propose and test a computer-aided system based on machine learning models and image processing techniques for otoscopic examination, as a support for a more accurate diagnosis of ear conditions at primary care before specialist referral; in particular, for myringosclerosis, earwax plug, and chronic otitis media. To characterize the tympanic membrane and ear canal for each condition, we implemented three different feature extraction methods: color coherence vector, discrete cosine transform, and filter bank. We also considered three machine learning algorithms: support vector machine (SVM), k-nearest neighbor (k-NN) and decision trees to develop the ear condition predictor model. To conduct the research, our database included 160 images as testing set and 720 images as training and validation sets of 180 patients. We repeatedly trained the learning models using the training dataset and evaluated them using the validation dataset to thus obtain the best feature extraction method and learning model that produce the highest validation accuracy. The results showed that the SVM and k-NN presented the best performance followed by decision trees model. Finally, we performed a classification stage -i.e., diagnosis- using testing data, where the SVM model achieved an average classification accuracy of 93.9%, average sensitivity of 87.8%, average specificity of 95.9%, and average positive predictive value of 87.7%. The results show that this system might be used for general practitioners as a reference to make better decisions in the ear pathologies diagnosis.

LFuji-air dataset: Annotated 3D LiDAR point clouds of Fuji apple trees for fruit detection scanned under different forced air flow conditions.

This article presents the LFuji-air dataset, which contains LiDAR based point clouds of 11 Fuji apples trees and the corresponding apples location ground truth. A mobile terrestrial laser scanner (MTLS) comprised of a LiDAR sensor and a real-time kinematics global navigation satellite system was used to acquire the data. The MTLS was mounted on an air-assisted sprayer used to generate different air flow conditions. A total of 8 scans per tree were performed, including scans from different LiDAR sensor positions (multi-view approach) and under different air flow conditions. These variability of the scanning conditions allows to use the LFuji-air dataset not only for training and testing new fruit detection algorithms, but also to study the usefulness of the multi-view approach and the application of forced air flow to reduce the number of fruit occlusions. The data provided in this article is related to the research article entitled "Fruit detection, yield prediction and canopy geometric characterization using LiDAR with forced air flow" [1].

Foliar Moisture Content from the Spectral Signature for Wildfire Risk Assessments in Valparaíso-Chile.

Fuel moisture content (FMC) proved to be one of the most relevant parameters for controlling fire behavior and risk, particularly at the wildland-urban interface (WUI). Data relating FMC to spectral indexes for different species are an important requirement identified by the wildfire safety community. In Valparaíso, the WUI is mainly composed of Eucalyptus Globulus and Pinus Radiata-commonly found in Mediterranean WUI areas-which represent the 97.51% of the forests plantation inventory. In this work we study the spectral signature of these species under different levels of FMC. In particular, we analyze the behavior of the spectral reflectance per each species at five dehydration stages, obtaining eighteen spectral indexes related to water content and, for Eucalyptus Globulus, the area of each leave-associated with the water content-is also computed. As the main outcome of this research, we provide a validated linear regression model associated with each spectral index and the fuel moisture content and moisture loss, per each species studied.

Design and evaluation of sound-based electronic football soccer training system for visually impaired athletes.

BACKGROUND: Several countries encourage the practice of football for rehabilitation and social inclusion purposes. For visually impaired people, football is purely sound-based, where the ball and the players are constantly emitting sounds for localization purposes in the field. However, the task of shooting the ball requires of a non-visually impaired extra person, behind the goal (known as caller), whom is punching the four corner of such goal to help the athletes. The presence of the caller restricts the self-sufficiency of the players. This work addresses such problem, by presenting a goal for visually impaired players with the aim of enhancing their self-sufficiency. MATERIALS AND METHODS: The electronic goal is designed with four functionalities for training purposes, by returning sound-based feedback of its position and the places where the ball has impacted. The system is validated with seven volunteers from Chilean Football Soccer National Team. A questionnaire was answered by the players before and after the tests to statically validate the proposed device. RESULTS: The presented system is portable and designed following a modular criterion suitable for visually impaired people self-assembling. From a test of 350 shootings, the electronic goal showed to enhance the shooting assertiveness from 82 to 92%, and the accuracy from 20 to 56% compared to the traditional caller. CONCLUSIONS: The electronic goal showed to enhance the self-sufficiency of athletes, by improving their assertiveness in shooting training. Nevertheless, and according to the responses to the questionnaires, the system needs improvements in its portability and handling.

Ultra wide-band localization and SLAM: a comparative study for mobile robot navigation.

In this work, a comparative study between an Ultra Wide-Band (UWB) localization system and a Simultaneous Localization and Mapping (SLAM) algorithm is presented. Due to its high bandwidth and short pulses length, UWB potentially allows great accuracy in range measurements based on Time of Arrival (TOA) estimation. SLAM algorithms recursively estimates the map of an environment and the pose (position and orientation) of a mobile robot within that environment. The comparative study presented here involves the performance analysis of implementing in parallel an UWB localization based system and a SLAM algorithm on a mobile robot navigating within an environment. Real time results as well as error analysis are also shown in this work.

Analysis of different feature selection criteria based on a covariance convergence perspective for a SLAM algorithm.

This paper introduces several non-arbitrary feature selection techniques for a Simultaneous Localization and Mapping (SLAM) algorithm. The feature selection criteria are based on the determination of the most significant features from a SLAM convergence perspective. The SLAM algorithm implemented in this work is a sequential EKF (Extended Kalman filter) SLAM. The feature selection criteria are applied on the correction stage of the SLAM algorithm, restricting it to correct the SLAM algorithm with the most significant features. This restriction also causes a decrement in the processing time of the SLAM. Several experiments with a mobile robot are shown in this work. The experiments concern the map reconstruction and a comparison between the different proposed techniques performance. The experiments were carried out at an outdoor environment composed by trees, although the results shown herein are not restricted to a special type of features.