Leishmaniasis is part of a group of diseases called Neglected Tropical Diseases (NTDs) that affects poor and forgotten communities and reports more than 5,000 cases in regions like Brazil, Peru, and Colombia being categorized as endemic in these. In this study, we present a machine-learning model (Random Forest) to predict cases in the future and predict possible outbreaks using meteorological and epidemiological data of the province of la Convencion (Cusco - Peru). Understanding how climate variables affect leishmaniasis outbreaks is an important problem to help people to perform prevention systems. We used several techniques to obtain better metrics and improve our model performance such as synthetic data and hyperparameter optimization. Results showed two important climate factors to analyze and no outbreaks.

Research has shown the ineffectiveness of video surveillance operators in detecting crimes through security cameras, which is a challenge due to their physical limitations. On the other hand, it was shown that computer vision, although promising, faces difficulties in real-time crime detection due to the large amount of data needed to build reliable models. This study presents three key innovations: a gun dataset extracted from the Grand Theft Auto V game, a computer vision model trained on this data, and a video surveillance application that employs the model for automatic gun crime detection. The main challenge was to collect images representing various scenarios and angles to reinforce the computer vision model. The video editor of the Grand Theft Auto V game was used to obtain the necessary images. These images were used to train the model, which was implemented in a desktop applicat...

To this point, there has been extensive research investigating human-robot motion retargeting, but the vast majority of existing methods rely on sensors or multiple cameras to detect human poses and movements, while many other methods are not suitable for usage on real-time scenarios. The current paper presents an integrated solution for performing realtime human-to-robot pose retargeting utilizing only regular monocular images and video as input data. We use deep learning models to perform three-dimensional human pose estimation on the monocular images and video, after which we calculate a set of joint angles that the robot must utilize to reproduce the detected human pose as accurately as possible. We evaluate our solution on Softbank’s NAO robot and show that it is possible to reproduce promising approximations and imitations of human motions and poses on the NAO robot, although it ...

Deaf people generally face difficulties in their daily lives when they try to communicate with hearing people, this is due to the lack of sign language knowledge in the country. Deaf people have to go on their everyday lives in company of a interpreter to be able to communicate, even wanting to go to buy bread every morning becomes a challenge for them and being treated in health centers also becomes a challenge, a challenge which should not exist since they have the fundamental right to health. For that reason this paper attempts to present a system for dynamic sign recognition for Peruvian Sign Language and our main goal is to detect which model and processing technique is the most appropriate to solve this problem. So that this system can be used in deaf people everyday life and help them communicate. There have been many projects around the world trying to address this situation. How...

Road damage, such as potholes and cracks, represent a constant nuisance to drivers as they could potentially cause accidents and damages. Current pothole detection in Peru, is mostly manually operated and hardly ever use image processing technology. To combat this we propose a mobile application capable of real-time road damage detection and spatial mapping across a city. Three models are going to be trained and evaluated (Yolov5, Yolov8 and MobileNet v2) on a novel dataset which contains images from Lima, Peru. Meanwhile, the viability of crack detection through bounding box method will be put to the test, each model will be trained once with cracks annotations and without. The YOLOv5 model was the one with the best results, as it showed the best mAP50 across all of out experiments. It got 99.0% and 98.3% mAP50 with the dataset without crack and with crack annotations, correspondingly..

Every year, the increase in human-computer interaction is noticeable. This brings with it the evolution of computer vision to improve this interaction to make it more efficient and effective. This paper presents a CNN-based emotion face recognition model capable to be executed on mobile devices, in real time and with high accuracy. Different models implemented in other research are usually of large sizes, and although they obtained high accuracy, they fail to make predictions in an optimal time, which prevents a fluid interaction with the computer. To improve these, we have implemented a lightweight CNN model trained with the FER2013 dataset to obtain the prediction of seven basic emotions. Experimentation shows that our model achieves an accuracy of 66.52% in validation, can be stored in a 13.23MB file and achieves an average processing time of 14.39ms and 16.06ms, on a tablet and a pho...

Irrigation systems and their performance to efficiently accomplish their function have gained notoriety in recent years. Therefore, those systems are not capable of approaching many factors as water-saving and irrigation automation. Here we present a new irrigation system based on the IoT, analyzing the most important factors that involve an efficient irrigation process taking into consideration water usage and saving this resource. Thus, we developed a prototype using Arduino Uno which is connected to sensors that can lead a web application named HydroTi to determine when to irrigate and how much water to use. This function was enabled by Adafruit IO, a web service useful for IoT projects. To validate the effectiveness of this solution, we compared different irrigation types to determine that the automatic irrigation mode of HydroTi is better w.r.t. water consumption in Metropolitan Lim...

Transformer models have evolved natural language processing tasks in machine learning and set a new standard for the state of the art. Thanks to the self-attention component, these models have achieved significant improvements in text generation tasks (such as extractive and abstractive text summarization). However, research works involving text summarization and the legal domain are still in their infancy, and as such, benchmarks and a comparative analysis of these state of the art models is important for the future of text summarization of this highly specialized task. In order to contribute to these research works, the researchers propose a comparative analysis of different, fine-tuned Transformer models and datasets in order to provide a better understanding of the task at hand and the challenges ahead. The results show that Transformer models have improved upon the text summarizatio...

Research shows that data analysis and artificial intelligence applied to agriculture in Peru can help manage crop production and mitigate monetary losses. This work presents SmartAgro, a system based on pattern mining and classification techniques that takes information from multiple sources related to the agricultural process to extract knowledge and produce recommendations about the crop growth process. The problem we seek to mitigate with our system is the economic losses generated in Peruvian agriculture caused by poor crop planning. Our results show a high accuracy in regards to type of crop recommendation, and a knowledge base useful for agricultural planning.

In the current pandemic, people are looking to leave their houses less frequently to prevent getting infected, but the absence of an app that shows the necessary information before going to the supermarket forces people to look in different supermarkets for the products they want to buy, thus increasing their chances of catching the virus, not to mention the waste of money and time. DoremyS is an app that allows you to create shopping lists that indicate to the user which supermarket to visit to find every product in them; it uses Geolocation to recommend supermarkets that are near the user and Data Mining to recommend shopping lists based on the user's interests.

Deep learning models have shown that it is possible to train neural networks to dispense, to a lesser or greater extent, with the need for human intervention for the task of image animation, which helps to reduce not only the production time of these audiovisual pieces, but also presents benefits with respect to the economic investment they require to be made. However, these models suffer from two common problems: the animations they generate are of very low resolution and they require large amounts of training data to generate good results. To deal with these issues, this article introduces the architectural modification of a state-of-the-art image animation model integrated with a video super-resolution model to make the generated videos more visually pleasing to viewers. Although it is possible to train the animation models with higher resolution images, the time it would take to trai...

Depression is regarded as a widespread mental condition that affects people of all ages. It has a negative impact on a variety of aspects of life, including mood, vigor, and interests in enjoying activities. In the most severe cases, depression can also result in suicide. creating the chance for collaboration between mental health professionals and the use of technical tools to enhance the assessment of the severity of depression to offer the patient with an ideal clinical diagnosis and an appropriate referral to begin treatment. The COVID-19 epidemic in Peru has decreased face-to-face interaction and quick access to medical professionals, making it more difficult for patients’ mental health to be identified or treated effectively, which results in the disease becoming chronic, psychological suffering, and high costs associated with specialized care. The implementation of a technology ...

The article’s objective is to outline the application of a technological solution based on wearable technology that provides for the best possible monitoring of elderly patients with CoViD19. This is a pressing issue right now because the epidemic has caused numerous problems for senior patients. For example, because older persons are more susceptible to CoViD19, they must limit social contact or adhere to stricter lockdown protocols. In order to do this, a thorough assessment of the relevant scientific literature in the phases of planning, development, and analysis was conducted. The use of technology models in real time, the monitoring of CoViD19 symptoms, and the usage of IoT for geriatric patient monitoring are all topics covered in this paper. Our findings demonstrate the viability of our strategy.

In the health industry, the transparency of product data registration in the supply chain is a critical aspect in determining the source of genetic data. Various upcoming technologies, such as blockchain, can help with this challenge. Blockchain is a shared and immutable database that makes recording transactions and tracking assets in a commercial network easier. Currently, genetic information is regarded as a vital asset in the health sector, as more precise diagnostic samples in medical genomics enable improved treatments for patients suffering from a variety of disorders. Since actions connected to the storage or management of data might have several areas of vulnerability, this paper describes the development of a technological model employing Blockchain as technology to assure the protection of genetic information in the private health sector. Furthermore, unauthorized activities s...

Deception detection has always been of subject of interest. After all, determining if a person is telling the truth or not could be detrimental in many real-world cases. Current methods to discern deceptions require expensive equipment that need specialists to read and interpret them. In this article, we carry out an exhaustive comparison between 9 different facial landmark recognition based recurrent deep learning models trained on a recent man-made database used to determine lies, comparing them by accuracy and AUC. We also propose two new metrics that represent the validity of each prediction. The results of a 5-fold cross validation show that out of all the tested models, the Stacked GRU neural model has the highest AUC of.9853 and the highest accuracy of 93.69% between the trained models. Then, a comparison is done between other machine and deep learning methods and our proposed Sta...