Suchergebnisse

El glaucoma es una de las principales causas de ceguera. Cambia la morfología del nervio óptico. La copa es la región central del disco óptico. El CDR (relación del diámetro de la copa y el disco) es un indicador del estado de la enfermedad. Un CDR normal se encuentra entre 0.3 y 0.4. A mayor CDR Glaucoma más avanzado. En este trabajo se pretende demostrar la viabilidad de los algoritmos en los que la forma del disco y la copa son aproximadamente círculos. En estos casos el número de parámetros es mucho menor y, al menos, en nuestras pruebas iniciales la aproximación es más realista que con las formas originales para su implementación en aprendizaje profundo. ; Glaucoma is one of the main causes of blindness. It changes the morphology of the optic nerve. The cup is the central region of the optical disc. The CDR (ratio of the diameter of the cup and disc) is an indicator of the state of the disease. A normal CDR is between 0.3 and 0.4. A higher CDR more advanced glaucoma. In this work we try to demonstrate the viability of algorithms in which the shape of the disc and the cup are approximately circles. In these cases, the number of parameters is much lower and, at least, in our initial tests the approach is sometimes more realistic than with the original forms for a Deep learning implementation. ; NPP project funded by SAIT (2015-2018) ; Spanish government grant European Regional Development Fund COFNET TEC2016-77785-P

Hyperglycemia is a complication of diabetes (high blood sugar). This condition causes biochemical alterations in the cells of the body, which may lead to structural and functional problems throughout the body, including the eye. Diabetes retinopathy (DR) is a type of retinal degeneration induced by long-term diabetes that may lead to blindness. propose our deep learning method for the early detection of retinopathy using an efficient net B1 model and using the APTOS 2019 dataset. we used the Gaussian filter as one of the most significant image-processing algorithms. It recognizes edges in the dataset and reduces superfluous noise. We will enlarge the retina picture to 224×224 (the Efficient Net B1 standard) and utilize data augmentation methods to enhance the dataset photographs, and balance the dataset (which was quite uneven), to avoid overfitting. By using Transfer learning we save training time by using a previously learned deep CNN and transfer learning weights. In this research, EfficientNetB1 is compared against Xception, InceptionV3, MobileNet, and ResNet50 as a deep transfer learning model. The proposed model's accuracy, precision, recall, and f1-score are all examined. The EfficientNetB1 model outperforms all others in terms of overall testing accuracy (86.1%), sensitivity (87.24%), precision (97.6%), and F1-Score (89.32 percent). This approach might help physicians diagnose Diabetic Retinopathy earlier.

This presentation was aimed to explore the growing opportunities to merge two booming fields: deep learning and autonomous vehicles, from a technical point of view. It addressed some Intelligent Systems Laboratory (Universidad Carlos III de Madrid, Spain) developments in this line of research, such as an obstacle detection framework using convolutional neural networks (CNNs). Furthermore, it presented a large number of challenging driving-related tasks that were expected to become tractable through this new approach, with the focus on the strong requirements posed by the upcoming self-driving systems. This presentation was part of the 6th LSI Ph.D. Meeting, which was held on 14 Jun 2016 at the Escuela Politécnica Superior of the Universidad Carlos III de Madrid. It was published on Zenodo as an exercise within the THOR Bootcamp on Open Data, organized on 16 Nov 2016. ; Research supported by the Spanish Government through the CICYT projects (TRA2015-63708-R and TRA2013-48314-C3-1-R), and the Comunidad de Madrid through SEGVAUTO-TRIES (S2013/MIT-2713). The Tesla K40 used for this research was donated by the NVIDIA Corporation.

Opium poppies are a major source of traditional drugs, which are not only harmful to physical and mental health, but also threaten the economy and society. Monitoring poppy cultivation in key regions through remote sensing is therefore a crucial task ; the location coordinates of poppy parcels represent particularly important information for their eradication by local governments. We propose a new methodology based on deep learning target detection to identify the location of poppy parcels and map their spatial distribution. We first make six training datasets with different band combinations and slide window sizes using two ZiYuan3 (ZY3) remote sensing images and separately train the single shot multibox detector (SSD) model. Then, we choose the best model and test its performance using 225 km2 verification images from Lao People&rsquo ; s Democratic Republic (Lao PDR), which exhibits a precision of 95% for a recall of 85%. The speed of our method is 4.5 km2/s on 1080TI Graphics Processing Unit (GPU). This study is the first attempt to monitor opium poppies with the deep learning method and achieve a high recognition rate. Our method does not require manual feature extraction and provides an alternative way to rapidly obtain the exact location coordinates of opium poppy cultivation patches.

Now a days, Twitter posts more than 400 million tweets every day can disclose real-world details as events grow. Event detection is a method to find real events which occur over time and space. Recent social media networks, such as Face Book, Instagram, Whatsapp and Twitter have been widely documented in real time. In the case of an earthquake, for example, people report earthquake-related information instantly, which allows the earthquake to be quickly detected. In this paper, we have developed a data filter based on functions like keywords, numbers and context. Every user feed is viewed as a sensor and such sensor selection provides a device capable of alerting registered users immediately. Using word embedding models, tweets are converted into numerical vectors. Tweets are classified into political, criminal, social, medical, disaster and miscellaneous predefined classes. Classification task is done by using long short-term memory networks (LSTM). A large number of tweets for the creation and testing of our proposed model are obtained via the Twitter API endpoint, which is marked as an effective technique.

Finding an appropriate environment representation is a crucial problem in robotics. 3D data has been recently used thanks to the advent of low cost RGB-D cameras. We propose a new way to represent a 3D map based on the information provided by an expert. Namely, the expert is the output of a Convolutional Neural Network trained with deep learning techniques. Relying on such information, we propose the generation of 3D maps using individual semantic labels, which are associated with environment objects or semantic labels. So, for each label we are provided with a partial 3D map whose data belong to the 3D perceptions, namely point clouds, which have an associated probability above a given threshold. The final map is obtained by registering and merging all these partial maps. The use of semantic labels provide us a with way to build the map while recognizing objects. ; This work has been supported by the Spanish Government TIN2016-76515-R Grant, supported with Feder funds, and by grant of Vicerrectorado de Investigación y Transferencia de Conocimiento para el fomento de la I+D+i en la Universidad de Alicante 2016.

Many emerging social sites, famous forums, review sites, and many bloggers generate huge amount of data in the form of user sentimental reviews, emotions, opinions, arguments, viewpoints etc. about different social events, products, brands, and politics, movies etc. Sentiments expressed by the users has great effect on readers, political images, online vendors. So the data present in scattered and unstructured manner needs to be managed properly and in this context sentiment analysis has got attention at very large level. Sentiment analysis can be defined as organization of the text which is used to understand the mindsets or feelings expressed in the form of different manners such as negative, positive, neutral, not satisfactory etc. This paper explains the implementation and accuracy of sentiment analysis using Tensor flow and python with any kind of text data. It works on embedding, LSTM and Sigmoid layers and finds the accuracy of data in iterative manner for better result