Search results for "Recurrent Neural Network"
showing 10 items of 40 documents
Exploiting deep learning algorithms and satellite image time series for deforestation prediction
2022
In recent years, we have witnessed the emergence of Deep Learning (DL) methods, which have led to enormous progress in various fields such as automotive driving, computer vision, medicine, finances, and remote sensing data analysis. The success of these machine learning methods is due to the ever-increasing availability of large amounts of information and the computational power of computers. In the field of remote sensing, we now have considerable volumes of satellite images thanks to the large number of Earth Observation (EO) satellites orbiting the planet. With the revisit time of satellites over an area becoming shorter and shorter, it will probably soon be possible to obtain daily imag…
Preamble Transmission Prediction for mMTC Bursty Traffic : A Machine Learning based Approach
2020
The evolution of Internet of things (IoT) towards massive IoT in recent years has stimulated a surge of traffic volume among which a huge amount of traffic is generated in the form of massive machine type communications. Consequently, existing network infrastructure is facing challenges when handling rapidly growing traffic load, especially under bursty traffic conditions which may more often lead to congestion. By proactively predicting the occurrence of congestion, we can implement necessary means and conceivably avoid congestion. In this paper, we propose a machine learning (ML) based model for predicting successful preamble transmissions at a base station and subsequently forecasting th…
Two-days ahead prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the urban area of Palermo, Italy
2007
Abstract Artificial neural networks are functional alternative techniques in modelling the intricate vehicular exhaust emission dispersion phenomenon. Pollutant predictions are notoriously complex when using either deterministic or stochastic models, which explains why this model was developed using a neural network. Neural networks have the ability to learn about non-linear relationships between the used variables. In this paper a recurrent neural network (Elman model) based forecaster for the prediction of daily maximum concentrations of SO2, O3, PM10, NO2, CO in the city of Palermo is proposed. The effectiveness of the presented forecaster was tested using a time series recorded between …
Review on Higher-Order Neural Units to Monitor Cardiac Arrhythmia Patterns
2017
An electrocardiogram (ECG) is a non-invasive technique that checks for problems with the electrical activity of a patient’s heart. ECG is economical and extremely versatile. Some of its characteristics make it a very useful tool to detect cardiac pathologies. The ECG records a series of characteristic waves called PQRST; however, the QRS complex analysis enables the detection of a type of arrhythmia in an ECG. Technological developments enable the storage of a large amount of data, from which knowledge extraction is impossible without a powerful data processing tool; in particular, an adequate signal processing tool, whose output provides reliable parameters as a basis to make a precise cli…
On the Computational Complexity of Binary and Analog Symmetric Hopfield Nets
2000
We investigate the computational properties of finite binary- and analog-state discrete-time symmetric Hopfield nets. For binary networks, we obtain a simulation of convergent asymmetric networks by symmetric networks with only a linear increase in network size and computation time. Then we analyze the convergence time of Hopfield nets in terms of the length of their bit representations. Here we construct an analog symmetric network whose convergence time exceeds the convergence time of any binary Hopfield net with the same representation length. Further, we prove that the MIN ENERGY problem for analog Hopfield nets is NP-hard and provide a polynomial time approximation algorithm for this p…
RNN- and LSTM-Based Soft Sensors Transferability for an Industrial Process
2021
The design and application of Soft Sensors (SSs) in the process industry is a growing research field, which needs to mediate problems of model accuracy with data availability and computational complexity. Black-box machine learning (ML) methods are often used as an efficient tool to implement SSs. Many efforts are, however, required to properly select input variables, model class, model order and the needed hyperparameters. The aim of this work was to investigate the possibility to transfer the knowledge acquired in the design of a SS for a given process to a similar one. This has been approached as a transfer learning problem from a source to a target domain. The implementation of a transf…
Information Abstraction from Crises Related Tweets Using Recurrent Neural Network
2016
Social media has become an important open communication medium during crises. The information shared about a crisis in social media is massive, complex, informal and heterogeneous, which makes extracting useful information a difficult task. This paper presents a first step towards an approach for information extraction from large Twitter data. In brief, we propose a Recurrent Neural Network based model for text generation able to produce a unique text capturing the general consensus of a large collection of twitter messages. The generated text is able to capture information about different crises from tens of thousand of tweets summarized only in a 2000 characters text.
CORENup: a combination of convolutional and recurrent deep neural networks for nucleosome positioning identification
2020
Abstract Background Nucleosomes wrap the DNA into the nucleus of the Eukaryote cell and regulate its transcription phase. Several studies indicate that nucleosomes are determined by the combined effects of several factors, including DNA sequence organization. Interestingly, the identification of nucleosomes on a genomic scale has been successfully performed by computational methods using DNA sequence as input data. Results In this work, we propose CORENup, a deep learning model for nucleosome identification. CORENup processes a DNA sequence as input using one-hot representation and combines in a parallel fashion a fully convolutional neural network and a recurrent layer. These two parallel …
Deep Learning Architectures for DNA Sequence Classification
2016
DNA sequence classification is a key task in a generic computational framework for biomedical data analysis, and in recent years several machine learning technique have been adopted to successful accomplish with this task. Anyway, the main difficulty behind the problem remains the feature selection process. Sequences do not have explicit features, and the commonly used representations introduce the main drawback of the high dimensionality. For sure, machine learning method devoted to supervised classification tasks are strongly dependent on the feature extraction step, and in order to build a good representation it is necessary to recognize and measure meaningful details of the items to cla…
Mašīnmācīšanās pielietojums sporta notikumu prognozēšanā
2017
Dažādu notikumu prognozēšana cilvēcei ir vienmēr bijusi aktuāla. Mūsdienās ir attīstījušās tehnoloģijas, lai to būtu iespējams paveikt balstoties uz pagātnes datiem. Darbā tiek apskatīta sporta notikumu prognozēšana, konkrēti futbola maču iznākumi. Tiek apskatītas vairākas mašīnmācīšanās metodes, kas būtu piemērotākās šī uzdevuma veikšanai. Tiek realizēti un optimizēti divi multi-slāņu perceptrona tīkli un viens vairākkārtējā neironu tīkla, konkrēti LSTM algoritms. Ar tiem tiek veikta simulācija izmantojot reālus datus. Vienā no simulācijām tiek sasniegts pozitīvs rezultāts, sezonas laikā algoritms gūst 65% peļņu.