3. Producción
Browse
59 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Depression Detection Using Audio-Visual Data and Artificial Intelligence: A Systematic Mapping Study(Springer, 2020-09-30)Major depression disorder is a mental issue that has been increasing in the last decade, in consequence, prediction or detection of this mental disorder in early stages is necessary. Artificial intelligence techniques have been developed in order to ease the diagnosis of different illnesses, including depression, using audio-visual information such as voice or video recordings and medical images. This research field is growing, and some organizations and descriptions are required. In the present work, a systematic mapping study was conducted in order to summarize the factors involved in depression detection such as artificial intelligence techniques, source of information, and depression scales. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Application of semantic segmentation with few labels in the detection of water bodies from PeruSat-1 satellite’s images(Copernicus Publications, 2020-11-06)Abstract. Remote sensing is widely used to monitor earth surfaces with the main objective of extracting information from it. Such is the case of water surface, which is one of the most affected extensions when flood events occur, and its monitoring helps in the analysis of detecting such affected areas, considering that adequately defining water surfaces is one of the biggest problems that Peruvian authorities are concerned with. In this regard, semiautomatic mapping methods improve this monitoring, but this process remains a time-consuming task and into the subjectivity of the experts.In this work, we present a new approach for segmenting water surfaces from satellite images based on the application of convolutional neural networks. First, we explore the application of a U-Net model and then a transfer knowledge-based model. Our results show that both approaches are comparable when trained using an 680-labelled satellite image dataset; however, as the number of training samples is reduced, the performance of the transfer knowledge-based model, which combines high and very high image resolution characteristics, is improved. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Dimensionality reduction via an orthogonal autoencoder approach for hyperspectral image classification(International Society for Photogrammetry and Remote Sensing, 2020-08-06)Abstract. Nowadays, the increasing amount of information provided by hyperspectral sensors requires optimal solutions to ease the subsequent analysis of the produced data. A common issue in this matter relates to the hyperspectral data representation for classification tasks. Existing approaches address the data representation problem by performing a dimensionality reduction over the original data. However, mining complementary features that reduce the redundancy from the multiple levels of hyperspectral images remains challenging. Thus, exploiting the representation power of neural networks based techniques becomes an attractive alternative in this matter. In this work, we propose a novel dimensionality reduction implementation for hyperspectral imaging based on autoencoders, ensuring the orthogonality among features to reduce the redundancy in hyperspectral data. The experiments conducted on the Pavia University, the Kennedy Space Center, and Botswana hyperspectral datasets evidence such representation power of our approach, leading to better classification performances compared to traditional hyperspectral dimensionality reduction algorithms. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Más allá de los datos: decidir bien no es cuestión de cantidad, sino de teoría(Pontificia Universidad Católica del Perú. Departamento Académico de Ciencias de la Gestión, 2026-05)El crecimiento exponencial del volumen de datos y la adopción masiva de herramientas analíticas e inteligencia artificial han consolidado la toma de decisiones basada en datos como un enfoque dominante en los ámbitos empresarial y público. Sin embargo, la ausencia de un marco teórico sólido constituye un riesgo crítico, ya que propicia interpretaciones sesgadas y decisiones subóptimas. La presente nota académica analiza el rol de la teoría como elemento estructurador en el proceso analítico y destaca su función en la formulación de problemas, la selección de algoritmos y la interpretación de resultados. A partir de una revisión de conceptos y de evidencia ilustrativa, se argumenta que la interacción entre la teoría y los datos es necesaria para transformar la información en conocimiento válido y generalizable. Asimismo, se examinan los desafíos asociados al uso intensivo de herramientas estadísticas, particularmente en contextos en los que predomina una comprensión instrumental por encima de una comprensión fundamentada. Se concluye que el fortalecimiento de la formación teórica y del pensamiento crítico es una condición necesaria para mejorar la calidad de la toma de decisiones y su impacto en contextos complejos. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Artificial intelligence model based on Grey clustering for integral analysis of industrial hygiene risk(Science and Information Organization, 2021-01-01)The article proposes a model with an artificial intelligence approach that integrates risks through the Grey Clustering method applying the "Triangulation of center-point based on Whitening functions -CTWF", for this, the data established is standard data (minimum standards that the four workshops of a company in the industrial sector must meet) and sampled data (real data obtained in the field) to test the grey classes. In this study, the different types of risks (lighting, noise and hand-arm vibration) were globally evaluated and analyzed in the four workshops of a heavy machinery maintenance services company in the industrial sector (welding shop, hydraulic shop, machine shop 1 and machine shop 2), located in Lima, Peru. According to the results obtained from the level of hygienic quality in each workshop, the welding workshop is at a very poor-quality level, while the others are at a good and very good level; regarding the four workshops, it was determined that the noise level is not recommended as they do not meet the minimum required standards. Therefore, control measures were proposed in the four workshops where the level of irrigation is bad and very bad. This study will benefit companies in the industrial sector that need to analyze the level of hygienic quality in their work areas with a global approach in order to apply control measures with prevention, protection of health and physical integrity of workers. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Grey clustering method for water quality assessment to determine the impact of mining company, Peru(Science and Information Organization, 2021-01-01)Mining operations have a significant impact on environment, where the quality of water is an important affected issue that need to be controlled. In that way, the Grey Clustering Method based on center-point triangular whitenization weight (CTWF), is an artificial intelligence criterion that evaluates water samples according to selected parameters, in order to realize an effective water quality assessment. In the present study, the analysis is made on the Crisnejas River Basin, by using fifteen monitoring points based on an investigation realized by the National Water Authority (ANA) in 2019, based on the Peruvian law (ECA) about water quality standards. The results reveal that almost all of the monitoring points on the Crisnejas River Basin were classified as “irrigation of vegetables unrestricted”, but only one point was classified as “animal drink”, which is ubicated in an urbanized area. This implies that mining discharges are being well treated by the company, but another deal is the contamination generated in towns. Further, the present study might be helpful to audit processes made by the state or companies, to justify the quality of surface waters using a more accurate methodology. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Multi-view data augmentation to improve wound segmentation on 3D surface model by deep learning(Institute of Electrical and Electronics Engineers Inc., 2021-01-01)Wound area segmentation really progressed with the emergence of deep learning, due to its robustness in uncontrolled lighting and no need to design hand-crafted features but two limits have still to be overcome: firstly, its performance relies on the size and quality of the training dataset in the medical field, where data annotation is costly and time-consuming; secondly the accuracy of the segmentation depends highly on the camera distance and angle and moreover perspective effects prevent measuring real surfaces in single views. To address concurrently these two issues, we propose to apply multi-view modeling: an image sequence is acquired around the wound site and enables wound 3D reconstruction. Then, a segmentation step is run to extract roughly the wound from the background in each view and to select the best view with an original strategy. This view provides the most accurate segmentation and the real wound bed area even on non planar wounds. Finally, this segmentation is backprojected in each view to generate a complete set of well annotated real images to reinforce the learning step of the neural network. In our experiments, we compare several strategies to select the best view in the image sequence. The proposed method, tested on a dataset of 270 images, outperforms standard deep learning approach based on a single view, as recorded with DICE index and IoU score which rise respectively from 36.53% to 86.3% and 29.48% to 77.09% for the wound class to achieve an overall DICE and IoU score of 93.04% and 86.61% including background class. These results attest to the robustness of our method and its improved accuracy in the wound segmentation task. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Light-field imaging reconstruction using deep learning enabling intelligent autonomous transportation system(Institute of Electrical and Electronics Engineers Inc., 2021-05-27)Light-field (LF) cameras, also known as plenoptic cameras, permit the recording of the 4D LF distribution of target scenes. However, many times, surface errors of a microlens array (MLA) are responsible for degradation in the images captured by a plenoptic camera. Additionally, the limited pixel count of the sensor can cause missing parallax information. The aforementioned issues are crucial for creating accurate maps for Intelligent Autonomous Transport System (IATS), because they cause loss of LF information, and need to be addressed. To tackle this problem, a learning-based framework by directly simulating the LF distribution is proposed. A high-dimensional convolution layer with densely sampled LFs in 4D space and considering a soft activation function based on ReLU segmentation correction is used to generate a superresolution (SR) LF image, improving the convergence rate in the deep learning network. Experimental results show that our proposed LF image reconstruction framework outperforms the existing state-of-the-art approaches; specifically, it is effective for learning the LF distribution and generating high-quality LF images. Different image quality assessment methods are used to evaluate the performance of the proposed framework, such as PSNR, SSIM, IWSSIM, FSIM, GFM, MDFM, and HDR-VDP. Additionally, the computational efficiency was evaluated in terms of number of parameters and FLOPs, and experimental results demonstrated that our proposed framework reached the highest performance in most of the datasets used. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Light field image quality enhancement by a lightweight deformable deep learning framework for intelligent transportation systems(MDPI AG, 2021-05-02)Light field (LF) imaging has multi-view properties that help to create many applications that include auto-refocusing, depth estimation and 3D reconstruction of images, which are required particularly for intelligent transportation systems (ITSs). However, cameras can present a limited angular resolution, becoming a bottleneck in vision applications. Thus, there is a challenge to incorporate angular data due to disparities in the LF images. In recent years, different machine learning algorithms have been applied to both image processing and ITS research areas for different purposes. In this work, a Lightweight Deformable Deep Learning Framework is implemented, in which the problem of disparity into LF images is treated. To this end, an angular alignment module and a soft activation function into the Convolutional Neural Network (CNN) are implemented. For performance assessment, the proposed solution is compared with recent state-of-the-art methods using different LF datasets, each one with specific characteristics. Experimental results demonstrated that the proposed solution achieved a better performance than the other methods. The image quality results obtained outperform state-of-the-art LF image reconstruction methods. Furthermore, our model presents a lower computational complexity, decreasing the execution time. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A lightweight intelligent intrusion detection system for industrial internet of things using deep learning algorithms(Wiley, 2021-12-11)With the substantial industrial growth, the industrial internet of things (IIoT) and many IoT avenues have emerged. However, the existing industrial architectures are still inefficient to deal with advanced security issues due to the distributed and distensible nature of the network IIoT communication networks. Therefore, solutions for improving intelligent decision‐making actions to the IIoT are sorely necessary. Thus, in this paper, the main cybersecurity attacks are predicted by applying a deep learning model. The various security and integrity features such as the DoS, malevolent operation, data type probing, spying, scanning, intrusion detection, brute force, web attacks, and wrong setup is analysed and detected by a novel sparse evolutionary training (SET) based prediction model. To scrutinize the conduct of the proposed SET‐based prediction model, evaluation parameters, such as, precision, accuracy, recall, and F1 score are measured and compared to other state‐of‐the‐art algorithms, in which the proposed SET‐based model achieved an average accuracy of 0.99% for an average testing time of 2.29 ms. Results reveal that the proposed model improved the attack detection accuracy by an average of 6.25% when compared with the other state‐of‐the‐art machine learning models in a real scenario of IoT security in Industry 4.0.