Academic literature on the topic 'U-NET CNN'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'U-NET CNN.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "U-NET CNN"
1
Sariturk, Batuhan, and Dursun Zafer Seker. "A Residual-Inception U-Net (RIU-Net) Approach and Comparisons with U-Shaped CNN and Transformer Models for Building Segmentation from High-Resolution Satellite Images." Sensors 22, no. 19 (October 8, 2022): 7624. http://dx.doi.org/10.3390/s22197624.
Full textAbstract:
Building segmentation is crucial for applications extending from map production to urban planning. Nowadays, it is still a challenge due to CNNs’ inability to model global context and Transformers’ high memory need. In this study, 10 CNN and Transformer models were generated, and comparisons were realized. Alongside our proposed Residual-Inception U-Net (RIU-Net), U-Net, Residual U-Net, and Attention Residual U-Net, four CNN architectures (Inception, Inception-ResNet, Xception, and MobileNet) were implemented as encoders to U-Net-based models. Lastly, two Transformer-based approaches (Trans U-Net and Swin U-Net) were also used. Massachusetts Buildings Dataset and Inria Aerial Image Labeling Dataset were used for training and evaluation. On Inria dataset, RIU-Net achieved the highest IoU score, F1 score, and test accuracy, with 0.6736, 0.7868, and 92.23%, respectively. On Massachusetts Small dataset, Attention Residual U-Net achieved the highest IoU and F1 scores, with 0.6218 and 0.7606, and Trans U-Net reached the highest test accuracy, with 94.26%. On Massachusetts Large dataset, Residual U-Net accomplished the highest IoU and F1 scores, with 0.6165 and 0.7565, and Attention Residual U-Net attained the highest test accuracy, with 93.81%. The results showed that RIU-Net was significantly successful on Inria dataset. On Massachusetts datasets, Residual U-Net, Attention Residual U-Net, and Trans U-Net provided successful results.
2
Choi, Keong-Hun, and Jong-Eun Ha. "Edge Detection based-on U-Net using Edge Classification CNN." Journal of Institute of Control, Robotics and Systems 25, no. 8 (August 31, 2019): 684–89. http://dx.doi.org/10.5302/j.icros.2019.19.0119.
Full text
3
Di Benedetto, Alessandro, Margherita Fiani, and Lucas Matias Gujski. "U-Net-Based CNN Architecture for Road Crack Segmentation." Infrastructures 8, no. 5 (May 6, 2023): 90. http://dx.doi.org/10.3390/infrastructures8050090.
Full textAbstract:
Many studies on the semantic segmentation of cracks using the machine learning (ML) technique can be found in the relevant literature. To date, the results obtained are quite good, but often the accuracy of the trained model and the results obtained are evaluated using traditional metrics only, and in most cases, the goal is to detect only the occurrence of cracks. Particular attention should be paid to the thickness of the segmented crack since, in road pavement maintenance, the width of the crack is the main parameter and is the one that characterizes the severity levels. The aim of our study is to optimize the crack segmentation process through the implementation of a modified U-Net model-based algorithm. For this, the Crack500 dataset is used, and then the results are compared with those obtained from the U-Net algorithm, which is currently found to be the most accurate and performant in the literature. The results are promising and accurate, as the findings on the shape and width of the segmented cracks are very close to reality.
4
Djohar, Muhammad Awaludin, Anita Desiani, Dewi Lestari Dwi Putri, Des Alwine Zayanti, Ali Amran, Irmeilyana Irmeilyana, and Novi Rustiana Dewi. "Segmentasi Citra Hati Menggunakan Metode Convolutional Neural Network dengan Arsitektur U-Net." JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING 6, no. 1 (July 23, 2022): 221–34. http://dx.doi.org/10.31289/jite.v6i1.6751.
Full textAbstract:
IAbnormalities in the liver can be used to identify the occurrence of disorders of the liver, one of which is called liver cancer. To detect abnormalities in the liver, segmentation is needed to take part of the liver that is affected. Segmentation of the liver is usually done manually with x-rays. . This manual detection is quite time consuming to get the results of the analysis. Segmentation is a technique in the image processing process that allocates images into objects and backgrounds. Deep learning applications can be used to help segment medical images. One of the deep learning methods that is widely used for segmentation is U-Net CNN. U-Net CNN has two parts encoder and decoder which are used for image segmentation. This research applies U-Net CNN to segment the liver data image. The performance results of the application of U-Net CNN on the liver image are very goodAccuracy performance obtained is 99%, sensitivity is 99%. The specificity is 99%, the F1-Score is 98%, the Jacard coefficient is 96.46% and the DSC is 98%. The performance achieved from the application of U-Net CNN on average is above 95%, it can be concluded that the application of U-Net CNN is very good and robust in segmenting abnormalities in the liver. This study only discusses the segmentation of the liver image. The results obtained have not been applied to the classification of types of disorders that exist in the liver yet. Further research can apply the segmentation results from the application of U-Net CNN in the problem of classifying types of liver disorders
5
Miron, Casian, Laura Ioana Grigoras, Radu Ciucu, and Vasile Manta. "Eye Image Segmentation Method Based on the Modified U-Net CNN Architecture." Bulletin of the Polytechnic Institute of Iași. Electrical Engineering, Power Engineering, Electronics Section 67, no. 2 (June 1, 2021): 41–52. http://dx.doi.org/10.2478/bipie-2021-0010.
Full textAbstract:
Abstract The paper presents a new eye image segmentation method used to extract the pupil contour based on the modified U-Net CNN architecture. The analysis was performed using two databases which contain IR images with a spatial resolution of 640x480 pixels. The first database was acquired in our laboratory and contains 400 eye images and the second database is a selection of 400 images from the publicly available CASIA Iris Lamp database. The results obtained by applying the segmentation based on the CNN architecture were compared to manually-annotated ground truth data. The results obtained are comparable to the state of the art. The purpose of the paper is to present the implementation of a robust segmentation algorithm based on the U-Net convolutional neural network that can be used in eye tracking applications such as human computer interface, communication devices for people with disabilities, marketing research or clinical studies. The proposed method improves uppon existing U-Net CNN architectures in terms of efficiency, by reducing the total number of parameters used from 31 millions to 38k. The advantages of using a number of parameters approximatly 815 times lower than the original U-Net CNN architecture are reduced computing resources consumption and a lower inference time.
6
Sariturk, Batuhan, Damla Kumbasar, and Dursun Zafer Seker. "Comparative Analysis of Different CNN Models for Building Segmentation from Satellite and UAV Images." Photogrammetric Engineering & Remote Sensing 89, no. 2 (February 1, 2023): 97–105. http://dx.doi.org/10.14358/pers.22-00084r2.
Full textAbstract:
Building segmentation has numerous application areas such as urban planning and disaster management. In this study, 12 CNN models (U-Net, FPN, and LinkNet using EfficientNet-B5 backbone, U-Net, SegNet, FCN, and six Residual U-Net models) were generated and used for building segmentation. Inria Aerial Image Labeling Data Set was used to train models, and three data sets (Inria Aerial Image Labeling Data Set, Massachusetts Buildings Data Set, and Syedra Archaeological Site Data Set) were used to evaluate trained models. On the Inria test set, Residual-2 U-Net has the highest F1 and Intersection over Union (IoU) scores with 0.824 and 0.722, respectively. On the Syedra test set, LinkNet-EfficientNet-B5 has F1 and IoU scores of 0.336 and 0.246. On the Massachusetts test set, Residual-4 U-Net has F1 and IoU scores of 0.394 and 0.259. It has been observed that, for all sets, at least two of the top three models used residual connections. Therefore, for this study, residual connections are more successful than conventional convolutional layers.
7
Erdem, Firat, Nuri Erkin Ocer, Dilek Kucuk Matci, Gordana Kaplan, and Ugur Avdan. "Apricot Tree Detection from UAV-Images Using Mask R-CNN and U-Net." Photogrammetric Engineering & Remote Sensing 89, no. 2 (February 1, 2023): 89–96. http://dx.doi.org/10.14358/pers.22-00086r2.
Full textAbstract:
Monitoring trees is necessary to manage and take inventory of forests, monitor plants in urban areas, distribute vegetation, monitor change, and establish sensitive and renewable agricultural systems. This study aims to automatically detect, count, and map apricot trees in an orthophoto, covering an area of approximately 48 ha on the ground surface using two different algorithms based on deep learning. Here, Mask region-based convolutional neural network (Mask R-CNN) and U-Net models were run together with a dilation operator to detect apricot trees in UAV images, and the performances of the models were compared. Results show that Mask R-CNN operated in this way performs better in tree detection, counting, and mapping tasks compared to U-Net. Mask R-CNN with the dilation operator achieved a precision of 98.7%, recall of 99.7%, F1 score of 99.1%, and intersection over union (IoU) of 74.8% for the test orthophoto. U-Net, on the other hand, has achieved a recall of 93.3%, precision of 97.2%, F1 score of 95.2%, and IoU of 58.3% when run with the dilation operator. Mask R-CNN was able to produce successful results in challenging areas. U-Net, on the other hand, showed a tendency to overlook existing trees rather than generate false alarms.
8
K.Narasimha Rao, Kesani Prudhvidhar Reddy, Gopavarapu Sai Satya Sreekar, and Gade Gopinath Reddy. "Retinal blood vessels segmentation using CNN algorithm." international journal of engineering technology and management sciences 7, no. 3 (2023): 499–504. http://dx.doi.org/10.46647/ijetms.2023.v07i03.70.
Full textAbstract:
The precise identification of blood vessels in fundus is crucial for diagnosing fundus diseases. In order to address the issues of inaccurate segmentation and low precision in conventional retinal image analysis for segmentation methods, a new approach was developed.The suggested method merges the U-Net and Dense-Net approaches and aims to enhance vascular feature information. To achieve this, the method employs several techniques such asHistogram equalization with limited contrast enhancement, median filtering, normalization of data, and morphological transformation. Furthermore, to correct artifacts, the method utilizes adaptive gamma correction. Next, randomly selected image blocks are utilized as training data to expand the data and enhance the generalization capability. The Dice loss function was optimized using stochastic gradient descent to improve the accuracy of segmentation, and ultimately, the Dense-U-net model was used for performing the segmentation. The algorithm achieved specificity, accuracy, sensitivity, and AUC of 0.9896, 0.9698, 0.7931, and 0.8946 respectively, indicating significant improvement in vessel segmentation accuracy, particularly in identifying small vessels.
9
Lutsenko, V. S., and A. E. Shukhman. "SEGMENTATION OF MEDICAL IMAGES BY CONVOLUTIONAL NEURAL NETWORKS." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 216 (June 2022): 40–50. http://dx.doi.org/10.14489/vkit.2022.06.pp.040-050.
Full textAbstract:
Our study briefly discusses the architectures of convolutional neural networks (CNN), their advantages and disadvantages. The features of the architecture of the convolutional neural network U-net are described. An analysis of the CNN U-net was carried out, based on the analysis, a rationale was given for choosing the CNN U-net as the main architecture for using and building subsequent created and analyzed models of cert neural networks to solve the problem of segmentation of medical images. The analysis of architectures of convolutional neural networks, which can be used as convolutional layers in CNN U-net, has been carried out. Based on the analysis, three architectures of convolutional neural networks were selected and described suitable for use as convolutional layers in CNN U-net. Using CNN U-net and three selected convolutional neural networks (“resnet34”, “inceptionv3” and “vgg16”), three neural network models for medical image segmentation were created. The training and testing of the created models of neural networks was carried out. Based on the results of training and testing, an analysis of the obtained indicators was carried out. Experiments were carried out with each of the three constructed models (segmentation of images from the validation set was performed and segmented images were presented). Based on the testing indicators and empirical data obtained from the results of the experiments, the most suitable neural network model created for solving the problem of medical image segmentation was determined. The algorithm for segmentation of medical images has been improved. An algorithm is described that uses the predictions of all created models of neural networks, which demonstrated a more accurate result than each of the considered models separately.
10
Younisse, Remah, Rawan Ghnemat, and Jaafer Al Saraireh. "Fine-tuning U-net for medical image segmentation based on activation function, optimizer and pooling layer." International Journal of Electrical and Computer Engineering (IJECE) 13, no. 5 (October 1, 2023): 5406. http://dx.doi.org/10.11591/ijece.v13i5.pp5406-5417.
Full textAbstract:
<span lang="EN-US">U-net convolutional neural network (CNN) is a famous architecture developed to deal with medical images. Fine-tuning CNNs is a common technique used to enhance their performance by selecting the building blocks which can provide the ultimate results. This paper introduces a method for tuning U-net architecture to improve its performance in medical image segmentation. The experiment is conducted using an x-ray image segmentation approach. The performance of U-net CNN in lung x-ray image segmentation is studied with different activation functions, optimizers, and pooling-bottleneck-layers. The analysis focuses on creating a method that can be applied for tuning U-net, like CNNs. It also provides the best activation function, optimizer, and pooling layer to enhance U-net CNN’s performance on x-ray image segmentation. The findings of this research showed that a U-net architecture worked supremely when we used the LeakyReLU activation function and average pooling layer as well as RMSProb optimizer. The U-net model accuracy is raised from 89.59 to 93.81% when trained and tested with lung x-ray images and uses the LeakyReLU activation function, average pooling layer, and RMSProb optimizer. The fine-tuned model also enhanced accuracy results with three other datasets.</span>
Dissertations / Theses on the topic "U-NET CNN"
1
Scotti, Alessandro. "Sviluppo e validazione di un nuovo approccio basato su reti neurali convoluzionali 3D per la valutazione della progressione della malattia policistica renale autosomica dominante." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Find full textAbstract:
La Malattia Policistica Renale Autosomica Dominante (ADPKD) è una malattia ereditaria caratterizzata dal progressivo sviluppo, all'interno di entrambi i reni, di numerose cisti che, sostituendosi al tessuto funzionante, determinano nel giro di alcuni anni, una insufficienza renale. Una precisa valutazione della progressione della malattia è necessaria per stabilire prontamente quale sia la terapia più appropriata e la sua efficacia. Tale valutazione si basa principalmente su tecniche di imaging, che permettono di ispezionare visivamente le crescite renali anomale e di quantificarle attraverso misurazioni. Ad oggi il volume totale del rene (TKV) è considerato il miglior biomarcatore per la valutazione della progressione della malattia in quanto lo sviluppo delle cisti causa a sua volta una espansione del rene stesso. Il calcolo del TKV è strettamente correlato ad una corretta segmentazione del rene malato. L'obiettivo principale del lavoro di tesi è la progettazione e la validazione sperimentale di tecniche in grado di eseguire la segmentazione completamente automatica di reni, al fine di valutare correttamente la progressione dell'ADPKD. In particolare, è stata progettata una soluzione basata su una rete convoluzionale tridimensionale con lo scopo di eseguire in maniera del tutto automatica la segmentazione renale per il calcolo del TKV. La rete realizzata è stata testata su 5 fold calcolando per ciascuno i valori medi del coefficiente di Dice, sensibilità e specificità ottenuti confrontando le maschere generate dalla rete e le maschere realizzate manualmente e considerate come ground truth. I risultati ottenuti sono stati soddisfacenti e paragonabili ad altre tecniche gia in precedenza validate.
2
Hellgren, Robin, and Martin Axelsson. "An evaluation of using a U-Net CNN with a random forest pre-screener : On a dataset of hand-drawn maps provided by länsstyrelsen i Jönköping." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-20003.
Full textAbstract:
Much research has been done on the use of machine learning to extract features such as buildings, lakes et cetera from satellite imagery, and while this dataset is valuable for many use cases, it is limited to time periods in which satellites were used. Historical maps have a much greater range of available time periods but the viability of using machine learning to extract data from these has not been investigated to any great extent. This case study uses a real-world use case to show the efficacy of using a U-Net convolutional neural network to extract features drawn on hand-drawn maps. By implementing a random forest as a pre-screener to the U-Net the goal was to filter out noise that could lead to false positives. By filtering out the noise the hope was to increase the accuracy of the U-Net. The pre-screener in this study has not performed well on the dataset and has not improved the performance of the U-Net. The U-Nets ability to extrapolate the location of features not explicitly drawn on the map was not clearly established. The results of this study show that the U-Net CNN could be an invaluable tool for quickly extracting data from this typically cumbersome data source, allowing for easier access to a wealth of data. The fields of archeology and climate science would find this especially useful.
3
Vincenzi, Fabian. "Reti neurali convoluzionali per il miglioramento di immagini tomografiche ad angoli limitati." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/22199/.
Full textAbstract:
Nel corso della tesi verrà presentata una rete neurale convoluzionale e un suo utilizzo per la ricostruzione di immagini CT (Computed Tomography) a bassa dose. Delle CNN viene approfondita una rete RED-CNN e una rete U-Net. Dopo che vengono affrontati questi argomenti sono presenti dei test effettuati per avere la rete più efficace possibile.
4
Berezina, Polina. "Enhancing Hurricane Damage Assessment from Satellite Images Using Deep Learning." The Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu1587554383454681.
Full text
5
Díaz, Pinto Andrés Yesid. "Machine Learning for Glaucoma Assessment using Fundus Images." Doctoral thesis, Universitat Politècnica de València, 2019. http://hdl.handle.net/10251/124351.
Full textAbstract:
[ES] Las imágenes de fondo de ojo son muy utilizadas por los oftalmólogos para la evaluación de la retina y la detección de glaucoma. Esta patología es la segunda causa de ceguera en el mundo, según estudios de la Organización Mundial de la Salud (OMS).
En esta tesis doctoral, se estudian algoritmos de aprendizaje automático (machine learning) para la evaluación automática del glaucoma usando imágenes de fondo de ojo. En primer lugar, se proponen dos métodos para la segmentación automática. El primer método utiliza la transformación Watershed Estocástica para segmentar la copa óptica y posteriormente medir características clínicas como la relación Copa/Disco y la regla ISNT. El segundo método es una arquitectura U-Net que se usa específicamente para la segmentación del disco óptico y la copa óptica.
A continuación, se presentan sistemas automáticos de evaluación del glaucoma basados en redes neuronales convolucionales (CNN por sus siglas en inglés). En este enfoque se utilizan diferentes modelos entrenados en ImageNet como clasificadores automáticos de glaucoma, usando fine-tuning. Esta nueva técnica permite detectar el glaucoma sin segmentación previa o extracción de características. Además, este enfoque presenta una mejora considerable del rendimiento comparado con otros trabajos del estado del arte.
En tercer lugar, dada la dificultad de obtener grandes cantidades de imágenes etiquetadas (glaucoma/no glaucoma), esta tesis también aborda el problema de la síntesis de imágenes de la retina. En concreto se analizaron dos arquitecturas diferentes para la síntesis de imágenes, las arquitecturas Variational Autoencoder (VAE) y la Generative Adversarial Networks (GAN). Con estas arquitecturas se generaron imágenes sintéticas que se analizaron cualitativa y cuantitativamente, obteniendo un rendimiento similar a otros trabajos en la literatura.
Finalmente, en esta tesis se plantea la utilización de un tipo de GAN (DCGAN) como alternativa a los sistemas automáticos de evaluación del glaucoma presentados anteriormente. Para alcanzar este objetivo se implementó un algoritmo de aprendizaje semi-supervisado.[CAT] Les imatges de fons d'ull són molt utilitzades pels oftalmòlegs per a l'avaluació de la retina i la detecció de glaucoma. Aquesta patologia és la segona causa de ceguesa al món, segons estudis de l'Organització Mundial de la Salut (OMS). En aquesta tesi doctoral, s'estudien algoritmes d'aprenentatge automàtic (machine learning) per a l'avaluació automàtica del glaucoma usant imatges de fons d'ull. En primer lloc, es proposen dos mètodes per a la segmentació automàtica. El primer mètode utilitza la transformació Watershed Estocàstica per segmentar la copa òptica i després mesurar característiques clíniques com la relació Copa / Disc i la regla ISNT. El segon mètode és una arquitectura U-Net que s'usa específicament per a la segmentació del disc òptic i la copa òptica. A continuació, es presenten sistemes automàtics d'avaluació del glaucoma basats en xarxes neuronals convolucionals (CNN per les sigles en anglès). En aquest enfocament s'utilitzen diferents models entrenats en ImageNet com classificadors automàtics de glaucoma, usant fine-tuning. Aquesta nova tècnica permet detectar el glaucoma sense segmentació prèvia o extracció de característiques. A més, aquest enfocament presenta una millora considerable del rendiment comparat amb altres treballs de l'estat de l'art. En tercer lloc, donada la dificultat d'obtenir grans quantitats d'imatges etiquetades (glaucoma / no glaucoma), aquesta tesi també aborda el problema de la síntesi d'imatges de la retina. En concret es van analitzar dues arquitectures diferents per a la síntesi d'imatges, les arquitectures Variational Autoencoder (VAE) i la Generative adversarial Networks (GAN). Amb aquestes arquitectures es van generar imatges sintètiques que es van analitzar qualitativament i quantitativament, obtenint un rendiment similar a altres treballs a la literatura. Finalment, en aquesta tesi es planteja la utilització d'un tipus de GAN (DCGAN) com a alternativa als sistemes automàtics d'avaluació del glaucoma presentats anteriorment. Per assolir aquest objectiu es va implementar un algoritme d'aprenentatge semi-supervisat.
[EN] Fundus images are widely used by ophthalmologists to assess the retina and detect glaucoma, which is, according to studies from the World Health Organization (WHO), the second cause of blindness worldwide. In this thesis, machine learning algorithms for automatic glaucoma assessment using fundus images are studied. First, two methods for automatic segmentation are proposed. The first method uses the Stochastic Watershed transformation to segment the optic cup and measures clinical features such as the Cup/Disc ratio and ISNT rule. The second method is a U-Net architecture focused on the optic disc and optic cup segmentation task. Secondly, automated glaucoma assessment systems using convolutional neural networks (CNNs) are presented. In this approach, different ImageNet-trained models are fine-tuned and used as automatic glaucoma classifiers. These new techniques allow detecting glaucoma without previous segmentation or feature extraction. Moreover, it improves the performance of other state-of-art works. Thirdly, given the difficulty of getting large amounts of glaucoma-labelled images, this thesis addresses the problem of retinal image synthesis. Two different architectures for image synthesis, the Variational Autoencoder (VAE) and Generative Adversarial Networks (GAN) architectures, were analysed. Using these models, synthetic images that were qualitative and quantitative analysed, reporting state-of-the-art performance, were generated. Finally, an adversarial model is used to create an alternative automatic glaucoma assessment system. In this part, a semi-supervised learning algorithm was implemented to reach this goal.
The research derived from this doctoral thesis has been supported by the Generalitat Valenciana under the scholarship Santiago Grisolía [GRISOLIA/2015/027].
Díaz Pinto, AY. (2019). Machine Learning for Glaucoma Assessment using Fundus Images [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/124351
TESIS
6
Sousa, Joana Vale Amaro de. "Lung Segmentation in CT Images: A CNN U-Net hybrid approach on a cross-cohort dataset." Master's thesis, 2021. https://hdl.handle.net/10216/137790.
Full textBooks on the topic "U-NET CNN"
1
Tse, Peter U. Two Types of Libertarian Free Will Are Realized in the Human Brain. Oxford University Press, 2018. http://dx.doi.org/10.1093/oso/9780190460723.003.0010.
Full textAbstract:
In Chapter 10, Peter U. Tse describes various developments in neuroscience that reveal how volitional mental events can be causal within a physicalist paradigm and argues that two types of libertarian free will are realized in the human brain. He takes as his foundation a new understanding of the neural code that emphasizes rapid synaptic resetting over the traditional emphasis of neural spiking. Such a neural code is an instance of “criterial causation,” which requires modifying standard interventionist conceptions of causation. This new view of the neural code, Tse argues, also provides a way out of self-causation arguments against the possibility of mental causation. Finally, Tse maintains that only if there is a second-order free will or meta-free will—do brains have the capacity to both have chosen otherwise and to have meta-chosen otherwise.
2
Białowąs, Sylwester, ed. Experimental design and biometric research. Toward innovations. Wydawnictwo Uniwersytetu Ekonomicznego w Poznaniu, 2021. http://dx.doi.org/10.18559/978-83-8211-079-1.
Full textAbstract:
This e-book aims to present the most critical aspects of knowledge about using experiments in economics and practical tools for using them. The topic is extended to the more advanced and increasing in popularity area of biometric research. The book is divided into three parts mirroring experimentation. The first part provides theoretical background and tips about organising own research. The chapter is concluded with a guide focused on writing a research report in APA style. This part includes an example of the actual research report. The next part has two chapters, and both are guided tours allowing to plan and conduct eye-tracking research and electrodermal activity research (EDA). The chapters contain details about preparing experiments, conducting them, using the dedicated software to analyse collected data and interpreting the default charts. The last part is devoted to the data analysis and is universal, goes beyond the biometric experiments. There are three chapters in this part covering the standard procedures used in the analysis of experiments. The first part includes tests for one hypothesis: parametric t-test and One-Way ANOVA and non-parametric siblings: Mann Whitney U test and Kruskal-Wallis test. The next part describes tests allowing testing more hypotheses: ANOVA without repetition and ANOVA with repetitions. Furthermore, the last chapter deals with dependent samples, which are a popular approach in experiments. This part describes the dependent sample t-test and Wilcoxon test. The effect sizes calculations are included; each test is shown with screenshots from SPSS and some additional screenshots from Excel. This approach allows following the procedure step by step. The examples help easily understand procedures and interpretations; they were chosen from areas of sustainability and innovations to match the general idea of the e-books series prepared within the CENETSIE program. The book contains texts that can be useful in the teaching process. It can be helpful in graduate programs in economics and business schools. Programs of doctoral schools cab benefit from this book as well.
3
Skupio, Rafał. Zastosowanie nieinwazyjnych pomiarów rdzeni wiertniczych do zwiększenia informacji na temat parametrów skał zbiornikowych. Instytut Nafty i Gazu - Państwowy Instytut Badawczy, 2022. http://dx.doi.org/10.18668/pn2022.237.
Full textAbstract:
The research carried out in the monograph aimed to create a measurement and interpretation system which is to obtain reliable results of well logging with the accuracy of laboratory measurements. Continuous core measurements allow for the generation of logging results without the impact of the borehole and facilitate the depth matching of the core to well log data. Four main chapters can be distinguished in this work: research methodology with a description of the devices used; partial results of core measurements made on various types of rocks; a proposal for a research system, and comprehensive data interpretation for selected boreholes. The methodological part concerned the description of the equipment for continuous measurements of cores in the field of natural gamma radioactivity (K, U, Th) with the application for bulk density measurements using the gamma-gamma method, X-ray fl uorescence spectrometers (XRF) for measuring the chemical composition of rocks and computed tomography (CT) for imaging of the core structure as well as determination of radiological density in Hounsfi eld units (HU). Rock studies were carried out on material representing formations of diff erent lithologies, such as shales, sandstones, limestones, dolomites, anhydrite, siltstones and heterolithic sandstone-siltstone-claystone complexes. The results of measurements made using individual methods have been described in detail and compared with the results of laboratory measurements and well logging data. Test measurements with data processing and interpretation were made on the cores from five boreholes (T-1, O-4, Pt-1, L-7, P-5H), whereas a comprehensive interpretation of the results was carried out for three other boreholes (J-1, P-4, T-2). The new methodology of spectral gamma measurements made it possible to obtain precise concentrations of potassium, uranium and thorium in rocks with high and low radioactivity. The results made it possible to standardise the archival gamma-ray logs made with the Russian-type probes from imp/min to API standard units and to obtain data on the content of K, U, and Th in the core intervals. Using the Cs-137 source in the device for the gamma equipment made it possible to carry out measurements of the bulk density in g/cm3 units. The lithological interpretation based on XRF measurements and mineralogical-chemical models allowed to obtain logs with increased resolution and a more signifi cant number of minerals than was the case with the interpretation of the well logging. In addition, it has been shown that the XRF measurement methodology can be used during the geosteering procedure. The results of the core tests using the CT computed tomography method were presented in combined images and continuous curves of density in HU units. The experience and the presentation of the full scope of measurement and interpretation workflow allowed to propose a procedure for conducting a full range of analyses, considering various types of material provided for research. The procedure considers the full range of analyses as well as the measurements of selected parameters depending on the client’s needs. Keywords: petrophysics, core analyses, XRF spectrometry, computed tomography, gamma profiling, lithological interpretation
4
Los ancestrales juegos y deportes de pelota maya en Mesoamérica contemporánea. Universidad Libre sede principal, 2022. http://dx.doi.org/10.18041/978-628-7580-08-4.
Full textAbstract:
Ver, contemplar, mirar u observar, son al parecer palabras sinónimas que sin embargo denotan significados disímiles al considerar los factores que intervienen en cada uno de estos actos. Las diferencias se van estableciendo de acuerdo con ciertos niveles de implicación, entre aquello que es objeto de curiosidad y quienes sobre este enfocan su atención. Los factores que contribuyen a profundizar o no esta interacción, se corresponden con el potencial de asombro irradiado desde el objeto, tanto como por el interés y/o capacidad de asombro que voluntariamente desplieguen las personas que se le acercan. Sin embargo, a estos factores se suman otras condiciones relacionadas con las experiencias previas de las personas potencialmente expectantes, las historias y transformaciones de aquello que funge como objeto de interés, así como los momentos y contextos en que tienen ocasión unos actos. De acuerdo a ello, quien presencia puede interactuar momentáneamente y desaparecer, pero también tiene la posibilidad de establecer una interacción basada en comparaciones con otras experiencias previas, o dejar fluir su asombro para configurar algo memorable. El acto de contemplar tendría dos posibilidades de traducción. Por ejemplo, al idioma kaqchikel, que es una de las 30 variantes mayences: B’ochinïk que se relaciona con una acción de persuasión y nik’onïk que se relaciona con una supervisión, un observar más allá, no con un carácter vigilante como lo sugeriría la expresión castellana. En ambos casos se implica un ejercicio activo. El acto contemplativo sugiere entonces una alteridad desde la cual es posible determinar la mayor o menor cercanía o distancia en relación con unas otras alteridades. Pero este acto que se sugiere tan inherente a la calidad que poseemos como seres vivientes presenta ciertas condicionantes que terminan por reflejar el momento, el contexto, el poder, el dominio y otras circunstancias desde las cuales se transforma otra subjetividad y sus actos, en meros objetos. Es de esta forma, cómo la humanidad, a través de la creación e imposición de ciertos “acuerdos”, ha venido definiendo lo desconocido como exótico, y en ese orden se le objetiviza para aprehenderle, desecharle o usarle. De lo exótico se puede hacer un espectáculo, pero también un lugar de catarsis propia que en el acto puede conllevar a hacerle desaparecer para limpiar aquello extraño que no encuadra. Entendiendo entonces, que contemplar va más allá del acto de entretener la mirada, esta investigación se concentra de manera genérica en los juegos de pelota mesoamericana, pero específicamente los que han ido recreando algunos grupos y personas en tierras mayas de México y Guatemala. Si bien los formatos en que circulan se remiten, en principio a espectáculos artísticos y deportivos, es importante tener en cuenta que son resultados de fuertes transformaciones operadas por los primeros observadores foráneos con poder para comunicarlos al mundo occidental. Pero gracias a las arquitecturas erigidas por las antiguas culturas asentadas en la vasta región conocida hoy como Mesoamérica, y que implicaron grandes creaciones artísticas asociadas, ahora sabemos que no todos los informes escriturales y visuales realizados a partir de la incursión europea se correspondían con un ejercicio de contemplación desde la alteridad. Estas arquitecturas fueron dispuestas de una manera favorable para la presentación de actos públicos variados, entre los cuales figuraban los juegos de pelota. Entonces, la noción actual de espectáculo no resultaba ajena en aquellos tiempos, lo cual desvirtúa que las formas de jugar actualmente sean tajantemente atribuibles a la influencia de los deportes y otras puestas en escena propuestas para complacer las miradas foráneas. Entonces, la presente investigación, no se remite a estudiar el fenómeno del espectáculo en tantos deportes o puestas en escena de juegos de pelota reinventados. Aunque sean estas las fuentes inmediatas a disposición, el foco de análisis es sobre aquello que sus participantes identifican, en unos casos como ritual asociado a las formas de vivir hoy la espiritualidad, en otros casos como deporte organizado, así como espacio formativo para las generaciones jóvenes. Con esta finalidad es necesario hacer una historiografía de estas prácticas, que dispersadas en Abya Yala1 desde tiempos antiguos se vinieron transformando conforme a las eventualidades propias en unos momentos, e impuestas desde cuando incursiona la historia oficialmente contada por voces, para las que resultó complejo establecer niveles de alteridad a la altura de lo que encontraron. Quienes practican actualmente los juegos, acudieron a múltiples estrategias para recordar los movimientos, las ritualidades y las formas de presentarse como ajpitzanel o ajetzanela’ (la persona que juega pelota en idioma Kaqchikel). Quienes promueven la práctica contemporánea de los juegos de pelota en Mesoamérica han decidido incorporar elementos de las competiciones deportivas que caracterizan al mundo moderno, pero también han encontrado formas para aprovechar la aceptación actual de las diversidades étnicas, cuyo fenómeno apenas va completando un baktún. Se plantean estrategias para difundirlos, promoverlos y masificarlos, pero también realizan lecturas novedosas que se debaten entre las complejas imposiciones nacionalistas y los ejercicios autorreflexivos. De esta manera, vienen proponiendo un panorama de alternativas que además de fungir como objetos observables, incitan a su práctica, más allá de la dimensión como espectáculo escénico practicado por profesionales. Pero dada la antigüedad y laberintos históricos que soportaron quienes en tiempos ancestrales lo practicaron el ejercicio de poner en juego la pelota mesoamericana nuevamente, ha implicado ejercicios de consulta en las fuentes disponibles. Además de la singularidad de los movimientos necesarios para impulsar una pelota maciza de hule con cadera, muslos, glúteos o antebrazos, los actuales juegos mayas del chaaj, pok ta pok y chajchaay proponen situaciones paradójicas que fluctúan entre las identidades étnicas, los nacionalismos, las tendencias New Age y las instrumentalizaciones identitarias, entre otras. Cuando son concebidas desde estas paradojas, las actuales iniciativas son blanco de críticas que se resguardan en esencialismos academicistas, perspectiva desde la cual también resulta incoherente su rechazo, pues han sido fuente principal desde donde han abrevado muchas de las iniciativas actuales. De esta manera, se desnuda la construcción hegemónica de las etnicidades desde una contemplación íntima que va más allá de un espectáculo para turistas, denotando unas nuevas conciencias que transitan invisibles para quien mira al otro cuando en apariencia se exhibe. El presente trabajo ofrenda un registro y análisis sobre las iniciativas locales y nacionales, gubernamentales y académicas, públicas y privadas, a partir de un acercamiento que reúne enfoques de varias disciplinas. En esa medida, contribuye al conocimiento sobre la vigencia actual de los antiguos juegos de pelota que, debido a su constante transformación y adaptación, se comunican y posicionan en contextos contemporáneos. Demuestra también algunos factores de la polémica provocada alrededor de los preceptos que determinan los usos de los juegos como patrimonios y herencias, cuando las transformaciones que operan sobre los juegos encasillados como “tradicionales”, muchas veces están en beneficio del espectáculo, y sus intereses económicos paulatinamente trascienden por algunas iniciativas. URI
Book chapters on the topic "U-NET CNN"
1
Kumaravelan, Umashankar, and M. Nivedita. "Localized Super Resolution for Foreground Images Using U-Net and MR-CNN." In Lecture Notes in Electrical Engineering, 25–39. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-19-7169-3_3.
Full text
2
Sharma, Utkarsh, Nimish Nigam, Ujjawal Kumar, Vinay Kumar, Sadanand Yadav, Ashish Pandey, and Rakesh Kumar Singh. "Abnormality Detection in Heart Using Combination of CNN, RNN and U-Net." In VLSI, Communication and Signal Processing, 135–46. Singapore: Springer Nature Singapore, 2023. http://dx.doi.org/10.1007/978-981-99-0973-5_10.
Full text
3
Konopczyński, Tomasz, Ron Heiman, Piotr Woźnicki, Paweł Gniewek, Marie-Cécilia Duvernoy, Oskar Hallatschek, and Jürgen Hesser. "Instance Segmentation of Densely Packed Cells Using a Hybrid Model of U-Net and Mask R-CNN." In Artificial Intelligence and Soft Computing, 626–35. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-61401-0_58.
Full text
4
Maqsood, Sarmad, Robertas Damasevicius, and Faisal Mehmood Shah. "An Efficient Approach for the Detection of Brain Tumor Using Fuzzy Logic and U-NET CNN Classification." In Computational Science and Its Applications – ICCSA 2021, 105–18. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-86976-2_8.
Full text
5
Chelle-Michou, Cyril, and Urs Schaltegger. "U–Pb Dating of Mineral Deposits: From Age Constraints to Ore-Forming Processes." In Isotopes in Economic Geology, Metallogenesis and Exploration, 37–87. Cham: Springer International Publishing, 2023. http://dx.doi.org/10.1007/978-3-031-27897-6_3.
Full textAbstract:
AbstractThe timing and duration of ore-forming processes are amongst the key parameters required in the study of mineral systems. After more than a century of technical developments, innovations and investigation, the U–Pb system arguably is the most mature radioisotopic system in our possession to conduct absolute dating of a wide range of minerals across geological environments and metallogenic processes. Here, we review the basics of U–Pb geochronology, the key historic developments of the method, and the most commonly used analytical techniques (including data reduction, Pb-correction, uncertainty propagation and data presentation) and minerals while pointing out their respective advantages, weaknesses and potential pitfalls. We also highlight critical aspects that need to be considered when interpreting a date into the age of a geological process (including field and petrographic constraints, open-system behavior, handling and interpretation of uncertainties). While U–Pb geochronology is strongly biased toward zircon dating, we strive to highlight the great diversity of minerals amenable to U–Pb dating (more than 16 mineral species) in the context of mineral systems, and the variety of geological events they can potentially date (magmatism, hydrothermal activity, ore-formation, cooling, etc.). Finally, through two case studies we show (1) how multi-mineral geochronological studies have been used to bracket and decipher the age of multiple geological events associated with the world-class Witwatersrand gold province, and (2) how rather than the absolute age, the duration and rate of the mineralizing event at porphyry copper deposits opens new avenues to understand ore-forming processes and the main controls on the size of such deposits. The improving precision, accuracy and spatial resolution of analyses in tandem with high-quality field and petrographic observations, numerical modelling and geochemical data, will continue to challenge paradigms of ore-forming processes and contribute significant breakthroughs in ore deposit research and potentially to the development of new exploration tools.
6
Zhang, Jindan, Jun Cai, Ying Su, Qingyou He, and Xinyue Lin. "Research and Development and Pilot Application of Innovative Technology of Prefabricated Concrete." In Lecture Notes in Civil Engineering, 226–37. Singapore: Springer Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-1260-3_20.
Full textAbstract:
AbstractRelying on the prefabricated construction project of a university in Guangxi, the standardization design of the building structure is proposed for the low standardization of prefabricated building design and serious conflicts in on-site construction, and the reinforced U-shaped ring is especially proposed for the problem of node collision in site construction. Advanced connection technologies such as buckle connection and steel slot connection and new components such as laminated truss floor slabs and corrugated pipe through-hole prefabricated columns. At the same time, BIM technology is used to verify the technical scheme. The result shows: the standardization degree of the integrated design of building structure proposed in the article High, can significantly improve the design and production efficiency, and the use of new connection technology and new components can effectively reduce the collision of steel bars and facilitate construction.
7
Hogan, Ciarán, and Ganesh Sistu. "Automatic Vehicle Ego Body Extraction for Reducing False Detections in Automated Driving Applications." In Communications in Computer and Information Science, 264–75. Cham: Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-26438-2_21.
Full textAbstract:
AbstractFisheye cameras are extensively employed in autonomous vehicles due to their wider field of view, which produces a complete 360-degree image of the vehicle with a minimum number of sensors. The drawback of having a broader field of view is that it may include undesirable portions of the vehicle’s ego body in its perspective. Due to objects’ reflections on the car body, this may produce false positives in perception systems. Processing ego vehicle pixels also uses up unnecessary computing power. Unexpectedly, there is no literature on this relevant practical problem. To our knowledge, this is the first attempt to discuss the significance of autonomous ego body extraction for automobile applications that are crucial for safety. We also proposed a simple deep learning model for identifying the vehicle’s ego-body. This model would enable us to eliminate any pointless processing of the car’s bodywork, eliminate the potential for pedestrians or other objects to be mistakenly detected in the car’s ego-body reflection, and finally, check to see if the camera is mounted incorrectly. The proposed network is a U-Net model with a Res-Net50 encoder pre-trained on ImageNet and trained for binary semantic segmentation on vehicle ego-body data. Our training data is an internal Valeo dataset with 10K samples collected by three separate car lines across Europe. This proposed network could then be integrated into the vehicles existing perception system by extracting the ego-body contour data and supplying this to the other algorithms which then ignore the area outside the contour coordinates. The proposed network can run at set intervals to save computing power and to check if the camera is misaligned by comparing the new contour data to the previous data.
8
Sikdar, Debosmita, Ivy Kanungo, and Dipanwita Das. "Microbial Enzymes: A Summary Focusing on Biotechnology Prospective for Combating Industrial Pollutants." In Proceedings of the Conference BioSangam 2022: Emerging Trends in Biotechnology (BIOSANGAM 2022), 70–76. Dordrecht: Atlantis Press International BV, 2022. http://dx.doi.org/10.2991/978-94-6463-020-6_8.
Full textAbstract:
AbstractEnvironmental issues are growing at an alarming rate and addressing the same is the need of the hour. Hazardous industrial pollutants and discharges are adding to the misery. Therefore, new ideas and technologies are being created and adopted to deal with ever increasing conservational troubles. Due to the burning issue of environmental pollution rising daily, a paradigm shift towards more sustainable and greener has to be pondered on. Microbial enzymes are such versatile, useful and beneficial weapons those can be exploited to combat the above-mentioned issues. In this aspect various works have been done and different sources of isolation of microbes and their fermentation process for procuring enzymes from them have been investigated in detail in those work. Pualsa Jagdish et al.’s work (2013) from Viva College, Virar, and Maharashtra entails that Lipase enzyme was procured from curd and waste oil was used as substrate. Lipase was produced by Lactobacillus sp. Whose lipolytic activity was calculated to be 0.082 U/mg. This enzyme if isolated under favorable conditions can be used to be applied for various industrial purposes in order to suppress the pollution rate and reduced the dependency on market-based chemicals and reagents those are highly dangerous and harmful. Work of Ashutosh Nema et al. (2019) [1], talks about the use of lipase enzyme as well as proteases are used as catalysts in biodiesel production as an effective and economical approach. According to Wu et al., large scale productions of protease have been achieved from Aspergillus species for their application in food and beverage industries. Alkaline proteases were reported to be produced under solid state fermentation processes by A. flavus and A. oryzae. Ikram-Ul-Haq and Mukhtar (2015) [2] stated that Penicillium sp. Alkaline proteases were generated under both solid state and submerged fermentation. The Mucor sp. of fungi can produce protease for milk clotting and can substitute rennin in the cheese making industry. Fungal enzymes are commonly used in industries over bacterial enzymes due to various technical reasons such as the feasibility of gaining enzymes at a high concentration in the fermentation medium and easier downstream processing. This way it can be encapsulated that microbial enzymes are savior in the field of pollution remediation and replacer of harsh and hazardous chemicals for carrying out various industrial applications.
9
Yildirim, Kemal, Sami Al-Nawaiseh, Sophia Ehlers, Lukas Schießer, Michael Storck, Tobias Brix, Nicole Eter, and Julian Varghese. "U-Net-Based Segmentation of Current Imaging Biomarkers in OCT-Scans of Patients with Age Related Macular Degeneration." In Caring is Sharing – Exploiting the Value in Data for Health and Innovation. IOS Press, 2023. http://dx.doi.org/10.3233/shti230315.
Full textAbstract:
Age-related macular degeneration (AMD) is the leading cause of blindness in the Western world. In this work, the non-invasive imaging technique spectral domain optical coherence tomography (SD-OCT) is used to acquire retinal images, which are then analyzed using deep learning techniques. The authors trained a convolutional neural network (CNN) using 1300 SD-OCT scans annotated by trained experts for the presence of different biomarkers associated with AMD. The CNN was able to accurately segment these biomarkers and the performance was further enhanced through transfer learning with weights from a separate classifier, trained on a large external public OCT dataset to distinguish between different types of AMD. Our model is able to accurately detect and segment AMD biomarkers in OCT scans, which suggests that it could be useful for prioritizing patients and reducing ophthalmologists’ workloads.
10
Islam, Mohammad Tariqul, Ferdaus Ahmed, Mowafa Househ, and Tanvir Alam. "Optical Disc Segmentation from Retinal Fundus Images Using Deep Learning." In Studies in Health Technology and Informatics. IOS Press, 2023. http://dx.doi.org/10.3233/shti230576.
Full textAbstract:
The optical disc in the human retina can reveal important information about a person’s health and well-being. We propose a deep learning-based approach to automatically identify the region in human retinal images that corresponds to the optical disc. We formulated the task as an image segmentation problem that leverages multiple public-domain datasets of human retinal fundus images. Using an attention-based residual U-Net, we showed that the optical disc in a human retina image can be detected with more than 99% pixel-level accuracy and around 95% in Matthew’s Correlation Coefficient. A comparison with variants of UNet with different encoder CNN architectures ascertains the superiority of the proposed approach across multiple metrics.
Conference papers on the topic "U-NET CNN"
1
Zhang, Chengzhu, and Yuxiang Xing. "CT artifact reduction via U-net CNN." In Image Processing, edited by Elsa D. Angelini and Bennett A. Landman. SPIE, 2018. http://dx.doi.org/10.1117/12.2293903.
Full text
2
Ghanshala, Anshul, Aakarshan Chauhan, Manoj Diwakar, and Sachin Sharma. "Brain Tumor Detection Using U-Net and 3D CNN Architecture." In 2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS). IEEE, 2022. http://dx.doi.org/10.1109/icccis56430.2022.10037660.
Full text
3
Liu, Yang, and Wei Yang. "Automatic liver segmentation using U-net in the assistance of CNN." In 2020 International Conference on Intelligent Computing, Automation and Systems (ICICAS). IEEE, 2020. http://dx.doi.org/10.1109/icicas51530.2020.00083.
Full text
4
Suman, Abdulla Al, Yash Khemchandani, Md Asikuzzaman, Alexandra Louise Webb, Diana M. Perriman, Murat Tahtali, and Mark R. Pickering. "Evaluation of U-Net CNN Approaches for Human Neck MRI Segmentation." In 2020 Digital Image Computing: Techniques and Applications (DICTA). IEEE, 2020. http://dx.doi.org/10.1109/dicta51227.2020.9363385.
Full text
5
Hsu, Aaron W., and Rodrigo Girão Serrão. "U-Net CNN in APL: Exploring Zero-Framework, Zero-Library Machine Learning." In ARRAY '23: 9th ACM SIGPLAN International Workshop on Libraries, Languages and Compilers for Array Programming. New York, NY, USA: ACM, 2023. http://dx.doi.org/10.1145/3589246.3595371.
Full text
6
Sushma, B., C. K. Raghavendra, and J. Prashanth. "CNN based U-Net with Modified Skip Connections for Colon Polyp Segmentation." In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC). IEEE, 2021. http://dx.doi.org/10.1109/iccmc51019.2021.9418037.
Full text
7
Li, Yuqin, Zhengang Jiang, Ke Zhang, Weili Shi, Fei He, and Jianhua Liu. "Dense-U-Net: A novel densely connected CNN for lung fields segmentation." In 2020 International Conference on Virtual Reality and Visualization (ICVRV). IEEE, 2020. http://dx.doi.org/10.1109/icvrv51359.2020.00035.
Full text
8
Nour, Abdala, Sherif Saad, and Boubakeur Boufama. "Prostate biomedical images segmentation and classification by using U-NET CNN model." In BCB '21: 12th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. New York, NY, USA: ACM, 2021. http://dx.doi.org/10.1145/3459930.3471169.
Full text
9
Wang, Yinglong, and Lyu Zhou. "A Lung Nodule Detector Based on U-Net and 3D-CNN Model." In 2021 IEEE International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI). IEEE, 2021. http://dx.doi.org/10.1109/cei52496.2021.9574604.
Full text
10
HAN, GUILAI, WEI LIU, BENGUO YU, XIAOLING LI, LU LIU, and HAIXIA LI. "The Detection and Recognition of Pulmonary Nodules Based on U-net and CNN." In CSAI 2020: 2020 4th International Conference on Computer Science and Artificial Intelligence. New York, NY, USA: ACM, 2020. http://dx.doi.org/10.1145/3445815.3445838.
Full textReports on the topic "U-NET CNN"
1
Mevarech, Moshe, Jeremy Bruenn, and Yigal Koltin. Virus Encoded Toxin of the Corn Smut Ustilago Maydis - Isolation of Receptors and Mapping Functional Domains. United States Department of Agriculture, September 1995. http://dx.doi.org/10.32747/1995.7613022.bard.
Full textAbstract:
Ustilago maydis is a fungal pathogen of maize. Some strains of U. maydis encode secreted polypeptide toxins capable of killing other susceptible strains of U. maydis. Resistance to the toxins is conferred by recessive nuclear genes. The toxins are encoded by genomic segments of resident double-strande RNA viruses. The best characterized toxin, KP6, is composed of two polypeptides, a and b, which are not covalently linked. It is encoded by P6M2 dsRNA, which has been cloned, sequenced and expressed in a variety of systems. In this study we have shown that the toxin acts on the membranes of sensitive cells and that both polypeptides are required for toxin activity. The toxin has been shown to function by creating new pores in the cell membrane and disrupting ion fluxes. The experiments performed on artificial phospholipid bilayers indicated that KP6 forms large voltage-independent, cation-selective channels. Experiments leading to the resolution of structure-function relationship of the toxin by in vitro analysis have been initiated. During the course of this research the collaboration also yielded X-ray diffracion data of the crystallized a polypeptide. The effect of the toxin on the pathogen has been shown to be receptor-mediated. A potential receptor protein, identified in membrane fractions of sensitive cells, was subjected to tryptic hydrolysis followed by amino-acid analysis. The peptides obtained were used to isolate a cDNA fragment by reverse PCR, which showed 30% sequence homology to the human HLA protein. Analysis of other toxins secreted by U. maydis, KP1 and KP4, have demonstrated that, unlike KP6, they are composed of a single polypeptide. Finally, KP6 has been expressed in transgenic tobacco plants, indicating that accurate processing by Kex2p-like activity occurs in plants as well. Using tobacco as a model system, we determined that active antifungal toxins can be synthesized and targeted to the outside of transgenic plant cells. If this methodology can be applied to other agronomically crop species, then U. maydis toxins may provide a novel means for biological control of pathogenic fungi.
2
Downard, Alicia, Stephen Semmens, and Bryant Robbins. Automated characterization of ridge-swale patterns along the Mississippi River. Engineer Research and Development Center (U.S.), April 2021. http://dx.doi.org/10.21079/11681/40439.
Full textAbstract:
The orientation of constructed levee embankments relative to alluvial swales is a useful measure for identifying regions susceptible to backward erosion piping (BEP). This research was conducted to create an automated, efficient process to classify patterns and orientations of swales within the Lower Mississippi Valley (LMV) to support levee risk assessments. Two machine learning algorithms are used to train the classification models: a convolutional neural network and a U-net. The resulting workflow can identify linear topographic features but is unable to reliably differentiate swales from other features, such as the levee structure and riverbanks. Further tuning of training data or manual identification of regions of interest could yield significantly better results. The workflow also provides an orientation to each linear feature to support subsequent analyses of position relative to levee alignments. While the individual models fall short of immediate applicability, the procedure provides a feasible, automated scheme to assist in swale classification and characterization within mature alluvial valley systems similar to LMV.
3
Reine, Kevin. A literature review of beach nourishment impacts on marine turtles. Engineer Research and Development Center (U.S.), March 2022. http://dx.doi.org/10.21079/11681/43829.
Full textAbstract:
This Technical Report was developed by the U. S. Army Engineer Research and Development Center-Environmental Laboratory (ERDC-EL), to summarize the known impacts to nesting sea turtles along the Atlantic and Gulf Coasts resulting from beach nourishment. The U.S. Army Corps of Engineers (USACE) is responsible for maintaining the nation’s infrastructure to include ports and harbors through dredging of Federal navigation channels as well as shoreline stabilization. Shoreline stabilization through beach nourishment activities can provide opportunities for reductions in storm surge, flood control, and provide opportunities for residential growth, recreational activities, and coastal habitat restoration (Guilfoyle et al. 2019). Beach nourishment is an effective method for protection and enhancement of coastal development projects but may have detrimental impacts on marine life (e.g., nesting sea turtles and shorebirds). The objective of this Technical Report is to examine all elements of the beach nourishment process to include, active beach construction, entrainment of marine turtles in hopper dredges, beach protection and hard structures, beach profile features, compaction and shear resistance, artificial lighting, marine turtle nest relocation, and nesting habitat factors. Recommendations for mitigating and minimizing these impacts are provided.
4
Pulugurtha, Srinivas S., Abimbola Ogungbire, and Chirag Akbari. Modeling and Evaluating Alternatives to Enhance Access to an Airport and Meet Future Expansion Needs. Mineta Transportation Institute, April 2023. http://dx.doi.org/10.31979/mti.2023.2120.
Full textAbstract:
The continued growth of air travel calls for the incessant construction effort at many airports and their surroundings. Thus, there is a need to determine how airports can better manage existing infrastructure to accommodate this growth. This study, therefore, focuses on (1) investigating how changes in transportation infrastructure have affected travel time reliability (TTR) of the surrounding road network within the airport vicinity over time, and, (2) exploring selected unconventional intersection designs and proposing new inbound/outbound access routes from the nearby major roads to the airport. The efficiency of road networks that surrounds large airports is discussed using Charlotte Douglas International Airport (CLT) as the case study. Firstly, an assessment of how transportation projects impact link-level travel time reliability (TTR) was performed using historical data. Secondly, an assessment of how future transportation projects would affect the traffic in the airport vicinity was performed. A simulation network was developed using the Vissim software, where the peak-hour turning movement counts were used with the existing signal design to replicate and calibrate the base scenario. Unconventional intersection designs such as continuous flow intersections (CFI), mini-roundabouts, and restricted crossing U-turn (RCUT) intersections were considered along with selected bridge design options to determine the impact on TTR. The results were compared with the conventional signalized intersection design. The connectivity projects led to an increase in TTR measures at most of the links within its vicinity after the project’s completion of the project. Similarly, parking areas exhibited the same characteristics, including those used by ridesharing companies. The simulation model showed that unconventional designs like RCUT and direct entry-exit ramps effectively reduced delay as well as the number of stops, increasing our understanding of how expansion projects affect TTR and potentially improving infrastructure optimization.
5
Taylor. L51755 Development and Testing of an Advanced Technology Vibration Transmission. Chantilly, Virginia: Pipeline Research Council International, Inc. (PRCI), July 1996. http://dx.doi.org/10.55274/r0010124.
Full textAbstract:
Fiber optic sensors have been under development in industrial and government laboratories around the world for over a decade. The commercial market for fiber sensors for measuring parameters such as temperature, displacement, and liquid level is now estimated to exceed $100 M/year. Aside from the commercial interest, the U. S. Department of Defense has vigorously pursued the development of fiber gyroscopes and hydrophones. In spite of the high level of research and development activity, however, until recently fiber sensors had not been successfully applied in high-temperature engine environments. The goal of this effort is to develop and test high-temperature fiber optic sensors and show that they are suitable for monitoring vibration and other instabilities in gas turbine engines. The underlying technology developed during the course of PRCI projects PR- 219-9120 and PR-219-9225 during 1991-94 serves as the foundation for PR-240-9416. Transducers with the fiber optic Fabry-Perot interferometer (FFPI) configuration have been adapted for use in the turbomachinery environment.To ensure the survival of the FFPI sensors at high temperatures, two techniques for coating the fibers with metal have been developed: electroplating and vacuum deposition. Coated sensors have subsequently been embedded in aluminum and brass alloys. Experiments on a small Sargent Welch turbine engine have shown the high sensitivity of embedded FFPI strain sensors to vibration in rolling bearings. Data have been collected in both the time and frequency domain. A new accelerometer design in which a metal-coated fiber containing the FFPI element is soldered directly to a diaphragm in a stainless steel housing shows response similar to a piezoelectric accelerometer in shaker table tests. The high sensitivity of the FFPI accelerometer has been demonstrated in field tests in a Solar Centaur turbine engine, and the design has survived temperatures greater than 500�C in a test oven. A magnetometer with a physical configuration similar to that of the accelerometer has been used to measure the distance from the sensor head to a rotating shaft made of ferromagnetic material. This device, which functions as a proximity probe, has been used to monitor shaft rotation rate (keyphasor application) and as a shaft thrust position sensor. These results indicate the potential for performing critical measurements in turbine engines with FFPI sensors. They can measure acceleration, distance (proximity), strain (as it relates to bearing defect diagnosis), and gas pressure, and can operate at higher temperatures than conventional transducers.