检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Pérez-Hernández, Francisco Rodríguez-Ortega, Jose Benhammou, Yassir Herrera, Francisco Tabik, Siham Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Granada18071 Spain

The detection of critical infrastructures in large territories represented by aerial and satellite images is of high importance in several fields such as in security, anomaly detection, land use planning and land use change detection. However, the detection of such infrastructures is complex as they have highly variable shapes and sizes, i.e., some infrastructures, such as electrical substations, are too small while others, such as airports, are too large. Besides, airports can have a surface area either small or too large with completely different shapes, which makes its correct detection challenging. As far as we know, these limitations have not been tackled yet in previous works. This paper presents (1) a smart Critical Infrastructure dataset, named CI-dataset, organised into two scales, small and large scales critical infrastructures and (2) a two-level resolution-independent critical infrastructure detection (DetDSCI) methodology that first determines the spatial resolution of the input image using a classification model, then analyses the image using the appropriate detector for that spatial resolution. The present study targets two representative classes, airports and electrical substations. Our experiments show that DetDSCI methodology achieves up to 37,53% F1 improvement with respect to Faster R-CNN, one of the most influential detection models. Copyright © 2021, The Authors. All rights reserved.

关键词： Large dataset

What is the best RNN-cell structure to forecast each time series behavior?

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Khaldi, Rohaifa Afia, Abdellatif El Chiheb, Raddouane Tabik, Siham Dept. of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain ENSIAS Mohammed V University of Rabat Rabat10170 Morocco

It is unquestionable that time series forecasting is of paramount importance in many fields. The most used machine learning models to address time series forecasting tasks are Recurrent Neural Networks (RNNs). Typically, those models are built using one of the three most popular cells, ELMAN, Long–Short Term Memory (LSTM), or Gated Recurrent Unit (GRU) cells, each cell has a different structure and implies a different computational cost. However, it is not clear why and when to use each RNN-cell structure. Actually, there is no comprehensive characterization of all the possible time series behaviors and no guidance on what RNN cell structure is the most suitable for each behavior. The objective of this study is twofold: it presents a comprehensive taxonomy of almost all-time series behaviors (deterministic, random-walk, nonlinear, longmemory, and chaotic), and provides insights into the best RNN cell structure for each time series behavior. We conducted two experiments: (1) The first experiment evaluates and analyzes the role of each component in the LSTM-Vanilla cell by creating 11 variants based on one alteration in its basic architecture (removing, adding, or substituting one cell component). (2) The second experiment evaluates and analyzes the performance of 20 possible RNN-cell structures. To evaluate, compare, and select the best model, different statistical metrics were used: error-based metrics, information criterion-based metrics, naïve-based metric, and direction change-based metric. To further improve our confidence in the models’ interpretation and selection, Friedman Wilcoxon–Holm signed-rank test was used. Our results advocate the usage and the exploration of the newly created RNN variant, named SLIM, in time series forecasting thanks to its high ability to accurately predict the different time series behaviors as well as its simple structural design that does not require expensive temporal and computing resources. Copyright © 2022, The Authors. All ri

关键词： Long short-term memory

Sentiment Analysis based Multi-person Multi-criteria Decision Making Methodology: Using Natural Language Processing and Deep Learning for Decision Aid

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zuheros, Cristina Martínez-Cámara, Eugenio Herrera-Viedma, Enrique Herrera, Francisco Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Granada18071 Spain

Decision making models are constrained by taking the expert evaluations with pre-defined numerical or linguistic terms. We claim that the use of sentiment analysis will allow decision making models to consider expert evaluations in natural language. Accordingly, we propose the Sentiment Analysis based Multi-person Multi-criteria Decision Making (SA-MpMcDM) methodology, which builds the expert evaluations from their natural language reviews, and even from their numerical ratings if they are available. The SA-MpMcDM methodology incorporates an end-to-end multi-task deep learning model for aspect based sentiment analysis, named DOC-ABSADeepL model, able to identify the aspect categories mentioned in an expert review, and to distill their opinions and criteria. The individual expert evaluations are aggregated via a criteria weighting through the attention of the experts. We evaluate the methodology in a restaurant decision problem, hence we build the TripR-2020 dataset of restaurant reviews, which we manually annotate and release. We analyze the SA-MpMcDM methodology in different scenarios using and not using natural language and numerical evaluations. The analysis shows that the combination of both sources of information results in a higher quality preference vector. Copyright © 2020, The Authors. All rights reserved.

关键词： Sentiment analysis

Challenges and Opportunities in Integration of Human and Autonomous systems

学校读者我要写书评

暂无评论

INCOSE International Symposium 2022年第S1期32卷 48-49页

作者： Sahar, Yotam Wagner, Michael Herrera, Francisco Hatwell, Julian Department of Industrial Engineering & Management Ariel University Ariel Israel Andalusian Research Institute in Data Science and Computational Intelligence DaSCI Institute Spain Birmingham City University United Kingdom

Simultaneously evolving deep reinforcement learning models using multifactorial optimization

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Martinez, Aritz D. Osaba, Eneko Ser, Javier Del Herrera, Francisco Derio Bizkaia48160 Spain University of the Basque Country Bilbao Bizkaia48013 Spain DaSCI Andalusian Institute of Data Science and Computational Intelligence University of Granada Granada18071 Spain

In recent years, Multifactorial Optimization (MFO) has gained a notable momentum in the research community. MFO is known for its inherent capability to efficiently address multiple optimization tasks at the same time, while transferring information among such tasks to improve their convergence speed. On the other hand, the quantum leap made by Deep Q Learning (DQL) in the Machine Learning field has allowed facing Reinforcement Learning (RL) problems of unprecedented complexity. Unfortunately, complex DQL models usually find it difficult to converge to optimal policies due to the lack of exploration or sparse rewards. In order to overcome these drawbacks, pre-trained models are widely harnessed via Transfer Learning, extrapolating knowledge acquired in a source task to the target task. Besides, meta-heuristic optimization has been shown to reduce the lack of exploration of DQL models. This work proposes a MFO framework capable of simultaneously evolving several DQL models towards solving interrelated RL tasks. Specifically, our proposed framework blends together the benefits of meta-heuristic optimization, Transfer Learning and DQL to automate the process of knowledge transfer and policy learning of distributed RL agents. A thorough experimentation is presented and discussed so as to assess the performance of the framework, its comparison to the traditional methodology for Transfer Learning in terms of convergence, speed and policy quality, and the intertask relationships found and exploited over the search process. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep learning

Deep Active Audio Feature Learning in Resource-Constrained Environments

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Mohaimenuzzaman, Md Bergmeir, Christoph Meyer, Bernd The Department of Data Science and AI Monash University ClaytonVIC3800 Australia The Data Science and Computational Intelligence Andalusian Institute DaSCI Andalucía Spain The Department of Computer Science and AI University of Granada Granada18071 Spain

The scarcity of labelled data makes training Deep Neural Network (DNN) models in bioacoustic applications challenging. In typical bioacoustics applications, manually labelling the required amount of data can be prohibitively expensive. To effectively identify both new and current classes, DNN models must continue to learn new features from a modest amount of fresh data. Active Learning (AL) is an approach that can help with this learning while requiring little labelling effort. Nevertheless, the use of fixed feature extraction approaches limits feature quality, resulting in underutilization of the benefits of AL. We describe an AL framework that addresses this issue by incorporating feature extraction into the AL loop and refining the feature extractor after each round of manual annotation. In addition, we use raw audio processing rather than spectrograms, which is a novel approach. Experiments reveal that the proposed AL framework requires 14.3%, 66.7%, and 47.4% less labelling effort on benchmark audio datasets ESC-50, UrbanSound8k, and InsectWingBeat, respectively, for a large DNN model and similar savings on a microcontroller-based counterpart. Furthermore, we showcase the practical relevance of our study by incorporating data from conservation biology projects. All codes are publicly available on GitHub. © 2023, CC BY.

关键词： Deep neural networks

Improved Deep Neural Network Performance Under Dynamic Programming Mode

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Cabello, Julia García Department of Applied Mathematics Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Spain

For Deep Neural Networks (DNN), the standard gradient-based algorithms may not be efficient because of the raised computational expense resulting from the increase in the number of layers. This paper offers an alternative to the classic training solutions: an in-depth study to find conditions under which the underlying ANN minimisation problem can be addressed from a Dynamic Programming (DP) perspective. Specifically, we prove that any ANN with monotonic activation is separable when regarded as a parametric function. Particularly, when the ANN is viewed as a network representation of a dynamical system (as a coupled cell network), we also prove that the transmission-of-signal law is separable provided the activation function is a monotone non-decreasing function. This strategy may have a positive impact on the performance of ANNs by improving their learning accuracy, particularly for DNNs. For our purposes, ANNs are also viewed as universal approximators of continuous functions and as abstract compositions of an even number of functions. This broader representation makes it easier to analyse them from many other perspectives (universal approximation issues, inverse problem solving) leading to a general improvement in knowledge on NNs and their performance. © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

Comprehensive Taxonomies of Nature- and Bio-inspired Optimization: Inspiration versus Algorithmic Behavior, Critical Analysis and Recommendations (from 2020 to 2024)

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Molina, Daniel Poyatos, Javier Del Ser, Javier Garcia, Salvador Hussain, Amir Herrera, Francisco Department of Computer Science and Artificial Intelligence DaSCI Andalusian Institute of Data Science and Computation Intelligence University of Granada Spain Spain Spain Edinburgh Napier University United Kingdom

In recent years, bio-inspired optimization has garnered significant attention in the literature. This algorithmic family mimics various biological processes observed in nature to effectively tackle complex optimization problems. The proliferation of nature- and bio-inspired algorithms, accompanied by a plethora of applications, tools, and guidelines, underscores the growing interest in this field. However, the exponential rise in the number of bio-inspired algorithms poses a challenge to the future trajectory of this research domain. Along the five versions of this document, the number of approaches grows incessantly, and where having a new biological description takes precedence over real problem-solving. This document, in its fifth revision since the original published version in [1], presents two comprehensive taxonomies. One is based on principles of biological similarity, and the other one is based on operational aspects associated with the iteration of population models that initially have a biological inspiration. Therefore, these taxonomies enable researchers to categorize existing algorithmic developments into well-defined classes, considering two criteria: the source of inspiration and the behavior exhibited by each algorithm. Using these taxonomies, we classify 518 algorithms based on nature-inspired and bio-inspired principles. Each algorithm within these categories is thoroughly examined, allowing for a critical synthesis of design trends and similarities, and identifying the most analogous classical algorithm for each proposal. From our analysis, we conclude that a poor relationship is often found between the natural inspiration of an algorithm and its behavior. Furthermore, similarities in terms of behavior between different algorithms are greater than what is claimed in their public disclosure: specifically, we show that more than one-fourth of the reviewed bio-inspired solvers are versions of classical algorithms. The conclusions from the analysis o

关键词： Iterative methods

Analyzing α-divergence in Gaussian Rate-Distortion-Perception Theory

学校读者我要写书评

暂无评论

Analyzing α-divergence in Gaussian Rate-Distortion-Percepti...

IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

作者： Martha V. Sourla Giuseppe Serra Photios A. Stavrou Marios Kountouris School of Electrical & Computer Engineering Technical University of Crete Chania Greece Communication Systems Department EURECOM France Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Spain

ISBN: (数字)9798350393187

ISBN: (纸本)9798350393194

The problem of the estimation of the information rate-distortion-perception function (RDPF), which is a relevant information-theoretic quantity in goal-oriented lossy compression and semantic information reconstruction, is investigated here. Specifically, we study the RDPF tradeoff for Gaussian sources subject to a mean-squared error (MSE) distortion and a perception measure that belongs to the family of α-divergences. Assuming a jointly Gaussian RDPF, which forms a convex optimization problem, we characterize an upper bound for which we find a parametric solution. We show that evaluating the optimal parameters of this parametric solution is equivalent to finding the roots of a reduced exponential polynomial of degree α. Additionally, we determine which disjoint sets contain each root, which enables us to evaluate them numerically using the well-known bisection method. Finally, we validate our analytical findings with numerical results and establish connections with existing results.

关键词： Wireless communication Upper bound Semantics Measurement uncertainty Estimation Distortion Polynomials Convex functions Distortion measurement Information theory

MultiCalib4DEB: A toolbox exploiting multimodal optimisation in Dynamic Energy Budget parameters calibration

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Robles, Juan Francisco Chica, Manuel Filgueira, Ramón Agüera, Antonio Damas, Sergio Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain Department of Benthic resources Norwegian Institute of Marine Research BergenNO-5817 Norway Department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence DaSCI University of Granada Granada18071 Spain Marine Affairs Program Life Sciences Centre Dalhousie University 1459 Oxford Street HalifaxNSB3H 4R2 Canada

1. Calibration is a crucial step for the validation of computational models and a challenging task to accomplish. 2. Dynamic Energy Budget (DEB) theory has experienced an exponential rise in the number of published papers, which in large part has been made possible by the DEBtool toolbox. Multimodal evolutionary optimisation could provide DEBtool with new capabilities, particularly relevant on the provisioning of equally optimal and diverse solutions. 3. In this paper we present MultiCalib4DEB, a MATLAB toolbox directly integrated into the existing DEBtool toolbox, which uses multimodal evolutionary optimisation algorithms to find multiple global and local optimal and diverse calibration solutions for DEB models. 4. MultiCalib4DEB adds powerful calibration mechanisms, statistical analysis, and visualisation methods to the DEBtool toolbox and provides a wide range of outputs, different calibration alternatives, and specific tools to strengthen the DEBtool calibration module and to aid DEBtool users to evaluate the performance of the calibration results. © 2023, CC BY-NC-ND.

关键词： Calibration