Examinando por Autor "Almeida, Aitor"

Mostrando 1 - 8 de 8
  • Miniatura
    Ítem
    Analysing centralities for organisational role inference in online social networks
    (Elsevier Ltd, 2021-03) Sánchez Corcuera, Rubén; Bilbao Jayo, Aritz; Zulaika Zurimendi, Unai; Almeida, Aitor
    The intensive use of Online Social Networks (OSN) nowadays has made users expose more information without realising it. Malicious users or marketing agencies are now able to infer information that is not published on OSNs by using data from targets friends to use for their benefit. In this paper, the authors present a generalisable method capable of deducing the roles of employees of an organisation using their Twitter relationships and the features of the graph from their organisation. The authors also conduct an extensive analysis of the node centralities to study their roles in the inference of the different classes proposed. Derived from the experiments and the ablation study conducted to the centralities, the authors conclude that the latent features of the graph along with the directed relationships perform better than previously proposed methods when classifying the role of the employees of an organisation. Additionally, to evaluate the method, the authors also contribute with a new dataset consisting of three directed graphs (one for each organisation) representing the relationships between the employees obtained from Twitter.
  • Miniatura
    Ítem
    A critical analysis of an IoT—aware AAL system for elderly monitoring
    (Elsevier B.V., 2019-08) Almeida, Aitor; Mulero, Rubén; Rametta, Piercosimo; Urošević, Vladimir; Andrić, Marina; Patrono, Luigi
    A growing number of elderly people (65+ years old) are affected by particular conditions, such as Mild Cognitive Impairment (MCI) and frailty, which are characterized by a gradual cognitive and physical decline. Early symptoms may spread across years and often they are noticed only at late stages, when the outcomes remain irrevocable and require costly intervention plans. Therefore, the clinical utility of early detecting these conditions is of substantial importance in order to avoid hospitalization and lessen the socio-economic costs of caring, while it may also significantly improve elderly people's quality of life. This work deals with a critical performance analysis of an Internet of Things aware Ambient Assisted Living (AAL) system for elderly monitoring. The analysis is focused on three main system components: (i) the City-wide data capturing layer, (ii) the Cloud-based centralized data management repository, and (iii) the risk analysis and prediction module. Each module can provide different operating modes, therefore the critical analysis aims at defining which are the best solutions according to context's needs. The proposed system architecture is used by the H2020 City4Age project to support geriatricians for the early detection of MCI and frailty conditions.
  • No hay miniatura disponible
    Ítem
    Cross-environment activity recognition using word embeddings for sensor and activity representation
    (Elsevier B.V., 2020-12-22) Azkune, Gorka; Almeida, Aitor; Agirre, Eneko
    Cross-environment activity recognition in smart homes is a very challenging problem, specially for data-driven approaches. Currently, systems developed to work for a certain environment degrade substantially when applied to a new environment, where not only sensors, but also the monitored activities may be different. Some systems require manual labeling and mapping of the new sensor names and activities using an ontology. Ideally, given a new smart home, we would like to be able to deploy the system, which has been trained on other sources, with minimal manual effort and with acceptable performance. In this paper, we propose the use of neural word embeddings to represent sensor activations and activities, which comes with several advantages: (i) the representation of the semantic information of sensor and activity names, and (ii) automatically mapping sensors and activities of different environments into the same semantic space. Based on this novel representation approach, we propose two data-driven activity recognition systems: the first one is a completely unsupervised system based on embedding similarities, while the second one adds a supervised learning regressor on top of them. We compare our approaches with some baselines using four public datasets, showing that data-driven cross-environment activity recognition obtains good results even when sensors and activity labels significantly differ. Our results show promise for reducing manual effort, and are complementary to other efforts using ontologies.
  • Miniatura
    Ítem
    Embedding-based real-time change point detection with application to activity segmentation in smart home time series data
    (Elsevier Ltd, 2021-12-15) Bermejo Fernández, Unai; Almeida, Aitor; Bilbao Jayo, Aritz; Azkune, Gorka
    Human activity recognition systems are essential to enable many assistive applications. Those systems can be sensor-based or vision-based. When sensor-based systems are deployed in real environments, they must segment sensor data streams on the fly in order to extract features and recognize the ongoing activities. This segmentation can be done with different approaches. One effective approach is to employ change point detection (CPD) algorithms to detect activity transitions (i.e. determine when activities start and end). In this paper, we present a novel real-time CPD method to perform activity segmentation, where neural embeddings (vectors of continuous numbers) are used to represent sensor events. Through empirical evaluation with 3 publicly available benchmark datasets, we conclude that our method is useful for segmenting sensor data, offering significant better performance than state of the art algorithms in two of them. Besides, we propose the use of retrofitting, a graph-based technique, to adjust the embeddings and introduce expert knowledge in the activity segmentation task, showing empirically that it can improve the performance of our method using three graphs generated from two sources of information. Finally, we discuss the advantages of our approach regarding computational cost, manual effort reduction (no need of hand-crafted features) and cross-environment possibilities (transfer learning) in comparison to others.
  • Miniatura
    Ítem
    LWP-WL: link weight prediction based on CNNs and the Weisfeiler–Lehman algorithm
    (Elsevier Ltd, 2022-05-01) Zulaika Zurimendi, Unai; Sánchez Corcuera, Rubén; Almeida, Aitor; López de Ipiña González de Artaza, Diego
    We present a new technique for link weight prediction, the Link Weight Prediction Weisfeiler–Lehman (LWP-WL) method that learns from graph structure features and link relationship patterns. Inspired by the Weisfeiler–Lehman Neural Machine, LWP-WL extracts an enclosing subgraph for the target link and applies a graph labelling algorithm for weighted graphs to provide an ordered subgraph adjacency matrix into a neural network. The neural network contains a Convolutional Neural Network in the first layer that applies special filters adapted to the input graph representation. An extensive evaluation is provided that demonstrates an improvement over the state-of-the-art methods in several weighted graphs. Furthermore, we conduct an ablation study to show how adding different features to our approach improves our technique's performance. Finally, we also perform a study on the complexity and scalability of our algorithm. Unlike other approaches, LWP-WL does not rely on a specific graph heuristic and can perform well in different kinds of graphs.
  • No hay miniatura disponible
    Ítem
    Orfeon: an AIOps framework for the goal-driven operationalization of distributed analytical pipelines
    (Elsevier B.V., 2023-03) Díaz de Arcaya Serrano, Josu; Torre Bastida, Ana Isabel; Miñón Jiménez, Raúl; Almeida, Aitor
    The use of Artificial Intelligence solutions keeps raising in the business domain. However, this adoption has not brought the expected results to companies so far. There are several reasons that make Artificial Intelligence solutions particularly complicated to adopt by businesses, such as the knowledge gap between the data science and operations teams. In this paper, we tackle the operationalization of distributed analytical pipelines in heterogeneous production environments, which span across different computational layers. In particular, we present a system called Orfeon, which can leverage different objectives and yields an optimized deployment for these pipelines. In addition, we offer the mathematical formulation of the problem alongside the objectives in hand (i.e. resilience, performance, and cost). Next, we propose a scenario utilizing cloud and edge infrastructural devices, in which we demonstrate how the system can optimize these objectives, without incurring scalability issues in terms of time nor memory. Finally, we compare the usefulness of Orfeon with a variety of tools in the field of machine learning operationalization and conclude that it is able to outperform these tools under the analyzed criteria, making it an appropriate system for the operationalization of machine learning pipelines.
  • Miniatura
    Ítem
    Regularized online tensor factorization for sparse knowledge graph embeddings
    (Springer Science and Business Media Deutschland GmbH, 2023) Zulaika Zurimendi, Unai; Almeida, Aitor; López de Ipiña González de Artaza, Diego
    Knowledge Graphs represent real-world facts and are used in several applications; however, they are often incomplete and have many missing facts. Link prediction is the task of completing these missing facts from existing ones. Embedding models based on Tensor Factorization attain state-of-the-art results in link prediction. Nevertheless, the embeddings they produce can not be easily interpreted. Inspired by previous work on word embeddings, we propose inducing sparsity in the bilinear tensor factorization model, RESCAL, to build interpretable Knowledge Graph embeddings. To overcome the difficulties that stochastic gradient descent has when producing sparse solutions, we add l1 regularization to the learning objective by using the generalized Regularized Dual Averaging online optimization algorithm. The proposed method substantially improves the interpretability of the learned embeddings while maintaining competitive performance in the standard metrics.
  • Miniatura
    Ítem
    Towards more reliable and efficient inteligents environments
    (Universidad de Deusto, 2013-06-10) Almeida, Aitor; López de Ipiña González de Artaza, Diego; Facultad de Ingeniería; SISTEMAS DE INFORMACION
    El objetivo de los entornos inteligentes y los sistemas sensibles al contexto es mejorar la vida diaria de los usuarios haciéndose cargo de las actividades que se puedan automatizar de manera transparente, siendo completamente invisibles para el usuario. Para conseguir esto se deben alcanzar tres objetivos: a) las reacciones a los cambios en el contexto deben de ser lo más exactas posibles, b) las reacciones deben llevarse a cabo en un tiempo prudencial y c) los dispositivos computacionales deben de desaparecer en el entorno, convirtiéndose en invisibles. Estos objetivos pueden ser difíciles de alcanzar en ciertos casos. Para que las adaptaciones se lleven a cabo de manera exacta y eficiente, el modelo de contexto debe de ser lo más cercano posible a la realidad. Este modelo debe de proveer la expresividad necesaria para conseguir una inferencia más precisa y para adaptarse mejor a las necesidades de los usuarios. Por otro lado, conseguir reacciones rápidas y que los dispositivos estén integrados en el entorno son objetivos enfrentados. Integrar las capacidades computacionales en el entorno suele resultar en dispositivos más limitados, lo que a su vez acarrea mayores tiempos de inferencia. Esta tesis hace frente a estos problemas. Para crear un mejor modelo de contexto, se propone un nuevo mecanismo de razonamiento que integre la inferencia semántica con incertidumbre y vaguedad. Esto permitirá conseguir una mayor expresividad a la hora de modelar el contexto e incluirá además un mecanismo de fusión de datos que integrará las diferentes medidas en una visión global del entorno. Además se creará una estructura distribuida de razonamiento que permitirá alcanzar conclusiones en un menor tiempo y de manera más eficiente.