Persona: Moreno Álvarez, Sergio
Cargando...
Dirección de correo electrónico
ORCID
0000-0002-1858-9920
Fecha de nacimiento
Proyectos de investigación
Unidades organizativas
Puesto de trabajo
Apellidos
Moreno Álvarez
Nombre de pila
Sergio
Nombre
8 resultados
Resultados de la búsqueda
Mostrando 1 - 8 de 8
Publicación Heterogeneous gradient computing optimization for scalable deep neural networks(Springer, 2022) Moreno Álvarez, Sergio; Paoletti, Mercedes Eugenia; Rico Gallego, Juan Antonio; Haut, Juan M.; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0002-4264-7473; https://orcid.org/0000-0001-6701-961XNowadays, data processing applications based on neural networks cope with the growth in the amount of data to be processed and with the increase in both the depth and complexity of the neural networks architectures, and hence in the number of parameters to be learned. High-performance computing platforms are provided with fast computing resources, including multi-core processors and graphical processing units, to manage such computational burden of deep neural network applications. A common optimization technique is to distribute the workload between the processes deployed on the resources of the platform. This approach is known as data-parallelism. Each process, known as replica, trains its own copy of the model on a disjoint data partition. Nevertheless, the heterogeneity of the computational resources composing the platform requires to unevenly distribute the workload between the replicas according to its computational capabilities, to optimize the overall execution performance. Since the amount of data to be processed is different in each replica, the influence of the gradients computed by the replicas in the global parameter updating should be different. This work proposes a modification of the gradient computation method that considers the different speeds of the replicas, and hence, its amount of data assigned. The experimental results have been conducted on heterogeneous high-performance computing platforms for a wide range of models and datasets, showing an improvement in the final accuracy with respect to current techniques, with a comparable performance.Publicación Cloud-Based Analysis of Large-Scale Hyperspectral Imagery for Oil Spill Detection(IEEE, 2024) Haut, Juan M.; Moreno Álvarez, Sergio; Pastor Vargas, Rafael; Pérez García, Ámbar; Paoletti, Mercedes Eugenia; https://orcid.org/0000-0001-6701-961X; https://orcid.org/0000-0002-4089-9538; https://orcid.org/0000-0002-2943-6348; https://orcid.org/0000-0003-1030-3729Spectral indices are of fundamental importance in providing insights into the distinctive characteristics of oil spills, making them indispensable tools for effective action planning. The normalized difference oil index (NDOI) is a reliable metric and suitable for the detection of coastal oil spills, effectively leveraging the visible and near-infrared (VNIR) spectral bands offered by commercial sensors. The present study explores the calculation of NDOI with a primary focus on leveraging remotely sensed imagery with rich spectral data. This undertaking necessitates a robust infrastructure to handle and process large datasets, thereby demanding significant memory resources and ensuring scalability. To overcome these challenges, a novel cloud-based approach is proposed in this study to conduct the distributed implementation of the NDOI calculation. This approach offers an accessible and intuitive solution, empowering developers to harness the benefits of cloud platforms. The evaluation of the proposal is conducted by assessing its performance using the scene acquired by the airborne visible infrared imaging spectrometer (AVIRIS) sensor during the 2010 oil rig disaster in the Gulf of Mexico. The catastrophic nature of the event and the subsequent challenges underscore the importance of remote sensing (RS) in facilitating decision-making processes. In this context, cloud-based approaches have emerged as a prominent technological advancement in the RS field. The experimental results demonstrate noteworthy performance by the proposed cloud-based approach and pave the path for future research for fast decision-making applications in scalable environments.Publicación Federated learning meets remote sensing(ELSEVIER, 2024-12-01) Moreno Álvarez, Sergio; Paoletti, Mercedes Eugenia; Sanchez Fernandez, Andres J.; Rico Gallego, Juan Antonio; han, lirong; Haut, Juan M.; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0001-6743-3570; https://orcid.org/0000-0002-4264-7473; https://orcid.org/0000-0002-8613-7037; https://orcid.org/0000-0001-6701-961XRemote sensing (RS) imagery provides invaluable insights into characterizing the Earth’s land surface within the scope of Earth observation (EO). Technological advances in capture instrumentation, coupled with the rise in the number of EO missions aimed at data acquisition, have significantly increased the volume of accessible RS data. This abundance of information has alleviated the challenge of insufficient training samples, a common issue in the application of machine learning (ML) techniques. In this context, crowd-sourced data play a crucial role in gathering diverse information from multiple sources, resulting in heterogeneous datasets that enable applications to harness a more comprehensive spatial coverage of the surface. However, the sensitive nature of RS data requires ensuring the privacy of the complete collection. Consequently, federated learning (FL) emerges as a privacy-preserving solution, allowing collaborators to combine such information from decentralized private data collections to build efficient global models. This paper explores the convergence between the FL and RS domains, specifically in developing data classifiers. To this aim, an extensive set of experiments is conducted to analyze the properties and performance of novel FL methodologies. The main emphasis is on evaluating the influence of such heterogeneous and disjoint data among collaborating clients. Moreover, scalability is evaluated for a growing number of clients, and resilience is assessed against Byzantine attacks. Finally, the work concludes with future directions and serves as the opening of a new research avenue for developing efficient RS applications under the FL paradigm. The source code is publicly available at https://github.com/hpc-unex/FLmeetsRS.Publicación Hyperspectral Image Analysis Using Cloud-Based Support Vector Machines(Springer, 2024) Haut, Juan M.; Franco Valiente, José M.; Paoletti, Mercedes Eugenia; Moreno Álvarez, Sergio; Pardo-Diaz, Alfonso; https://orcid.org/0000-0001-6701-961X; https://orcid.org/0000-0002-3880-6697; https://orcid.org/0000-0003-1030-3729Hyperspectral image processing techniques involve time-consuming calculations due to the large volume and complexity of the data. Indeed, hyperspectral scenes contain a wealth of spatial and spectral information thanks to the hundreds of narrow and continuous bands collected across the electromagnetic spectrum. Predictive models, particularly supervised machine learning classifiers, take advantage of this information to predict the pixel categories of images through a training set of real observations. Most notably, the Support Vector Machine (SVM) has demonstrate impressive accuracy results for image classification. Notwithstanding the performance offered by SVMs, dealing with such a large volume of data is computationally challenging. In this paper, a scalable and high-performance cloud-based approach for distributed training of SVM is proposed. The proposal address the overwhelming amount of remote sensing (RS) data information through a parallel training allocation. The implementation is performed over a memory-efficient Apache Spark distributed environment. Experiments are performed on a benchmark of real hyperspectral scenes to show the robustness of the proposal. Obtained results demonstrate efficient classification whilst optimising data processing in terms of training times.Publicación A Comprehensive Survey of Imbalance Correction Techniques for Hyperspectral Data Classification(IEEE, 2023) Paoletti, Mercedes Eugenia; Mogollón Gutiérrez, Óscar; Moreno Álvarez, Sergio; Sancho, José Carlos; Haut, Juan M.; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0003-2980-9236; https://orcid.org/0000-0002-4584-6945; https://orcid.org/0000-0001-6701-961XLand-cover classification is an important topic for remotely sensed hyperspectral (HS) data exploitation. In this regard, HS classifiers have to face important challenges, such as the high spectral redundancy, as well as noise, present in the data, and the fact that obtaining accurate labeled training data for supervised classification is expensive and time-consuming. As a result, the availability of large amounts of training samples, needed to alleviate the so-called Hughes phenomenon, is often unfeasible in practice. The class-imbalance problem, which results from the uneven distribution of labeled samples per class, is also a very challenging factor for HS classifiers. In this article, a comprehensive review of oversampling techniques is provided, which mitigate the aforementioned issues by generating new samples for the minority classes. More specifically, this article pursues a twofold objective. First, it reviews the most relevant oversampling methods that can be adopted according to the nature of HS data. Second, it provides a comprehensive experimental study and comparison, which are useful to derive practical conclusions about the performance of oversampling techniques in different HS image-based applications.Publicación Cloud Implementation of Extreme Learning Machine for Hyperspectral Image Classification(IEEE, 2023) Haut, Juan M.; Moreno Álvarez, Sergio; Moreno Ávila, Enrique; Ayma Quirita, Victor Andrés; Pastor Vargas, Rafael; Paoletti, Mercedes Eugenia; https://orcid.org/0000-0001-6701-961X; https://orcid.org/0000-0003-2987-2761; https://orcid.org/0000-0002-4089-9538; https://orcid.org/0000-0003-1030-3729Classifying remotely sensed hyperspectral images (HSIs) became a computationally demanding task given the extensive information contained throughout the spectral dimension. Furthermore, burgeoning data volumes compound inherent computational and storage challenges for data processing and classification purposes. Given their distributed processing capabilities, cloud environments have emerged as feasible solutions to handle these hurdles. This encourages the development of innovative distributed classification algorithms that take full advantage of the processing capabilities of such environments. Recently, computational-efficient methods have been implemented to boost network convergence by reducing the required training calculations. This letter develops a novel cloud-based distributed implementation of the extreme learning machine ( CC-ELM ) algorithm for efficient HSI classification. The proposal implements a fault-tolerant and scalable computing design while avoiding traditional batch-based backpropagation. CC-ELM has been evaluated over state-of-the-art HSI classification benchmarks, yielding promising results and proving the feasibility of cloud environments for large remote sensing and HSI data volumes processing. The code available at https://github.com/mhaut/scalable-ELM-HSIPublicación Heterogeneous model parallelism for deep neural networks(ELSEVIER, 2021-06-21) Moreno Álvarez, Sergio; Haut, Juan M.; Paoletti, Mercedes Eugenia; Rico Gallego, Juan Antonio; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0002-4264-7473Deep neural networks (DNNs) have transformed computer vision, establishing themselves as the current state-of-the-art for image processing. Nevertheless, the training of current large DNN models is one of the main challenges to be solved. In this sense, data-parallelism has been the most widespread distributed training strategy since it is easy to program and can be applied to almost all cases. However, this solution suffers from several limitations, such as its high communication requirements and the memory constraints when training very large models. To overcome these limitations model-parallelism has been proposed, solving the most substantial problems of the former strategy. However, describing and implementing the parallelization of the training of a DNN model across a set of processes deployed on several devices is a challenging task. Current proposed solutions assume a homogeneous distribution, being impractical when working with devices of different computational capabilities, which is quite common on high performance computing platforms. To address previous shortcomings, this work proposes a novel model-parallelism technique considering heterogeneous platforms, where a load balancing mechanism between uneven devices of an HPC platform has been implemented. Our proposal takes advantage of the Google Brain’s Mesh-TensorFlow for convolutional networks, splitting computing tensors across filter dimension in order to balance the computational load of the available devices. Conducted experiments show an improvement in the exploitation of heterogeneous computational resources, enhancing the training performance. The code is available on: https://github.com/mhaut/HeterogeneusModelDNN.Publicación Enhancing Distributed Neural Network Training Through Node-Based Communications(IEEE, 2023) Moreno Álvarez, Sergio; Paoletti, Mercedes Eugenia; Cavallaro, Gabriele; Haut, Juan M.; https://orcid.org/0000-0003-1030-3729; https://orcid.org/0000-0002-3239-9904; https://orcid.org/0000-0001-6701-961XThe amount of data needed to effectively train modern deep neural architectures has grown significantly, leading to increased computational requirements. These intensive computations are tackled by the combination of last generation computing resources, such as accelerators, or classic processing units. Nevertheless, gradient communication remains as the major bottleneck, hindering the efficiency notwithstanding the improvements in runtimes obtained through data parallelism strategies. Data parallelism involves all processes in a global exchange of potentially high amount of data, which may impede the achievement of the desired speedup and the elimination of noticeable delays or bottlenecks. As a result, communication latency issues pose a significant challenge that profoundly impacts the performance on distributed platforms. This research presents node-based optimization steps to significantly reduce the gradient exchange between model replicas whilst ensuring model convergence. The proposal serves as a versatile communication scheme, suitable for integration into a wide range of general-purpose deep neural network (DNN) algorithms. The optimization takes into consideration the specific location of each replica within the platform. To demonstrate the effectiveness, different neural network approaches and datasets with disjoint properties are used. In addition, multiple types of applications are considered to demonstrate the robustness and versatility of our proposal. The experimental results show a global training time reduction whilst slightly improving accuracy. Code: https://github.com/mhaut/eDNNcomm.