Kliknij ten link, aby zobaczyć inne rodzaje publikacji na ten temat: HYBRID CNN-RNN MODEL.
Artykuły w czasopismach na temat „HYBRID CNN-RNN MODEL”
Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych
Sprawdź 50 najlepszych artykułów w czasopismach naukowych na temat „HYBRID CNN-RNN MODEL”.
Przycisk „Dodaj do bibliografii” jest dostępny obok każdej pracy w bibliografii. Użyj go – a my automatycznie utworzymy odniesienie bibliograficzne do wybranej pracy w stylu cytowania, którego potrzebujesz: APA, MLA, Harvard, Chicago, Vancouver itp.
Możesz również pobrać pełny tekst publikacji naukowej w formacie „.pdf” i przeczytać adnotację do pracy online, jeśli odpowiednie parametry są dostępne w metadanych.
Przeglądaj artykuły w czasopismach z różnych dziedzin i twórz odpowiednie bibliografie.
1
Zaheer, Shahzad, Nadeem Anjum, Saddam Hussain, Abeer D. Algarni, Jawaid Iqbal, Sami Bourouis i Syed Sajid Ullah. "A Multi Parameter Forecasting for Stock Time Series Data Using LSTM and Deep Learning Model". Mathematics 11, nr 3 (22.01.2023): 590. http://dx.doi.org/10.3390/math11030590.
Pełny tekst źródłaStreszczenie:
Financial data are a type of historical time series data that provide a large amount of information that is frequently employed in data analysis tasks. The question of how to forecast stock prices continues to be a topic of interest for both investors and financial professionals. Stock price forecasting is quite challenging because of the significant noise, non-linearity, and volatility of time series data on stock prices. The previous studies focus on a single stock parameter such as close price. A hybrid deep-learning, forecasting model is proposed. The model takes the input stock data and forecasts two stock parameters close price and high price for the next day. The experiments are conducted on the Shanghai Composite Index (000001), and the comparisons have been performed by existing methods. These existing methods are CNN, RNN, LSTM, CNN-RNN, and CNN-LSTM. The generated result shows that CNN performs worst, LSTM outperforms CNN-LSTM, CNN-RNN outperforms CNN-LSTM, CNN-RNN outperforms LSTM, and the suggested single Layer RNN model beats all other models. The proposed single Layer RNN model improves by 2.2%, 0.4%, 0.3%, 0.2%, and 0.1%. The experimental results validate the effectiveness of the proposed model, which will assist investors in increasing their profits by making good decisions.
2
Ashraf, Mohsin, Fazeel Abid, Ikram Ud Din, Jawad Rasheed, Mirsat Yesiltepe, Sook Fern Yeo i Merve T. Ersoy. "A Hybrid CNN and RNN Variant Model for Music Classification". Applied Sciences 13, nr 3 (22.01.2023): 1476. http://dx.doi.org/10.3390/app13031476.
Pełny tekst źródłaStreszczenie:
Music genre classification has a significant role in information retrieval for the organization of growing collections of music. It is challenging to classify music with reliable accuracy. Many methods have utilized handcrafted features to identify unique patterns but are still unable to determine the original music characteristics. Comparatively, music classification using deep learning models has been shown to be dynamic and effective. Among the many neural networks, the combination of a convolutional neural network (CNN) and variants of a recurrent neural network (RNN) has not been significantly considered. Additionally, addressing the flaws in the particular neural network classification model, this paper proposes a hybrid architecture of CNN and variants of RNN such as long short-term memory (LSTM), Bi-LSTM, gated recurrent unit (GRU), and Bi-GRU. We also compared the performance based on Mel-spectrogram and Mel-frequency cepstral coefficient (MFCC) features. Empirically, the proposed hybrid architecture of CNN and Bi-GRU using Mel-spectrogram achieved the best accuracy at 89.30%, whereas the hybridization of CNN and LSTM using MFCC achieved the best accuracy at 76.40%.
3
Krishnan, V. Gokula, M. V. Vijaya Saradhi, T. A. Mohana Prakash, K. Gokul Kannan i AG Noorul Julaiha. "Development of Deep Learning based Intelligent Approach for Credit Card Fraud Detection". International Journal on Recent and Innovation Trends in Computing and Communication 10, nr 12 (31.12.2022): 133–39. http://dx.doi.org/10.17762/ijritcc.v10i12.5894.
Pełny tekst źródłaStreszczenie:
Credit card fraud (CCF) has long been a major concern of institutions of financial groups and business partners, and it is also a global interest to researchers due to its growing popularity. In order to predict and detect the CCF, machine learning (ML) has proven to be one of the most promising techniques. But, class inequality is one of the main and recurring challenges when dealing with CCF tasks that hinder model performance. To overcome this challenges, a Deep Learning (DL) techniques are used by the researchers. In this research work, an efficient CCF detection (CCFD) system is developed by proposing a hybrid model called Convolutional Neural Network with Recurrent Neural Network (CNN-RNN). In this model, CNN acts as feature extraction for extracting the valuable information of CCF data and long-term dependency features are studied by RNN model. An imbalance problem is solved by Synthetic Minority Over Sampling Technique (SMOTE) technique. An experiment is conducted on European Dataset to validate the performance of CNN-RNN model with existing CNN and RNN model in terms of major parameters. The results proved that CNN-RNN model achieved 95.83% of precision, where CNN achieved 93.63% of precision and RNN achieved 88.50% of precision.
4
Yu, Dian, i Shouqian Sun. "A Systematic Exploration of Deep Neural Networks for EDA-Based Emotion Recognition". Information 11, nr 4 (15.04.2020): 212. http://dx.doi.org/10.3390/info11040212.
Pełny tekst źródłaStreszczenie:
Subject-independent emotion recognition based on physiological signals has become a research hotspot. Previous research has proved that electrodermal activity (EDA) signals are an effective data resource for emotion recognition. Benefiting from their great representation ability, an increasing number of deep neural networks have been applied for emotion recognition, and they can be classified as a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), or a combination of these (CNN+RNN). However, there has been no systematic research on the predictive power and configurations of different deep neural networks in this task. In this work, we systematically explore the configurations and performances of three adapted deep neural networks: ResNet, LSTM, and hybrid ResNet-LSTM. Our experiments use the subject-independent method to evaluate the three-class classification on the MAHNOB dataset. The results prove that the CNN model (ResNet) reaches a better accuracy and F1 score than the RNN model (LSTM) and the CNN+RNN model (hybrid ResNet-LSTM). Extensive comparisons also reveal that our three deep neural networks with EDA data outperform previous models with handcraft features on emotion recognition, which proves the great potential of the end-to-end DNN method.
5
Behera, Bibhuti Bhusana, Binod Kumar Pattanayak i Rajani Kanta Mohanty. "Deep Ensemble Model for Detecting Attacks in Industrial IoT". International Journal of Information Security and Privacy 16, nr 1 (1.01.2022): 1–29. http://dx.doi.org/10.4018/ijisp.311467.
Pełny tekst źródłaStreszczenie:
In this research work, a novel IIoT attack detection framework is designed by following four major phases: pre-processing, imbalance processing, feature extraction, and attack detection. The attack detection is carried out using the projected ensemble classification framework. The projected ensemble classification framework encapsulates the recurrent neural network, CNN, and optimized bi-directional long short-term memory (BI-LSTM). The RNN and CNN in the ensemble classification framework is trained with the extracted features. The outcome acquired from RNN and CNN is utilized for training the optimized BI-LSTM model. The final outcome regarding the presence/absence of attacks in the industrial IoT is portrayed by the optimized BI-LSTM model. Therefore, the weight of BI-LSTM model is fine-tuned using the newly projected hybrid optimization model referred as cat mouse updated slime mould algorithm (CMUSMA). The projected hybrids the concepts of both the standard slime mould algorithm (SMA) and cat and mouse-based optimizer(CMBO), respectively.
6
Cheng, Yepeng, Zuren Liu i Yasuhiko Morimoto. "Attention-Based SeriesNet: An Attention-Based Hybrid Neural Network Model for Conditional Time Series Forecasting". Information 11, nr 6 (5.06.2020): 305. http://dx.doi.org/10.3390/info11060305.
Pełny tekst źródłaStreszczenie:
Traditional time series forecasting techniques can not extract good enough sequence data features, and their accuracies are limited. The deep learning structure SeriesNet is an advanced method, which adopts hybrid neural networks, including dilated causal convolutional neural network (DC-CNN) and Long-short term memory recurrent neural network (LSTM-RNN), to learn multi-range and multi-level features from multi-conditional time series with higher accuracy. However, they didn’t consider the attention mechanisms to learn temporal features. Besides, the conditioning method for CNN and RNN is not specific, and the number of parameters in each layer is tremendous. This paper proposes the conditioning method for two types of neural networks, and respectively uses the gated recurrent unit network (GRU) and the dilated depthwise separable temporal convolutional networks (DDSTCNs) instead of LSTM and DC-CNN for reducing the parameters. Furthermore, this paper presents the lightweight RNN-based hidden state attention module (HSAM) combined with the proposed CNN-based convolutional block attention module (CBAM) for time series forecasting. Experimental results show our model is superior to other models from the viewpoint of forecasting accuracy and computation efficiency.
7
Pawar, Mahendra Eknath, Rais Allauddin Mulla, Sanjivani H. Kulkarni, Sajeeda Shikalgar, Harikrishna B. Jethva i Gunvant A. Patel. "A Novel Hybrid AI Federated ML/DL Models for Classification of Soil Components". International Journal on Recent and Innovation Trends in Computing and Communication 10, nr 1s (10.12.2022): 190–99. http://dx.doi.org/10.17762/ijritcc.v10i1s.5823.
Pełny tekst źródłaStreszczenie:
The soil is the most fundamental component for the survival of any living thing that can be found on this planet. A little less than 41 percent of Indians are employed in agriculture, which accounts for approximately 19 percent of the country's gross domestic product. As is the case in every other industry, researchers and scientists in this one are exerting a lot of effort to enhance agricultural practices by utilising cutting-edge methods such as machine learning, artificial intelligence, big data, and so on. The findings of the study described in this paper are predicated on the assumption that the method of machine learning results in an improvement in the accuracy of the prediction of soil chemical characteristics. The correlations that were discovered as a result of this research are essential for comprehending the comprehensive approach to predicting the soil attributes using ML/DL models. A number of findings from previous study have been reported and analysed. A state of the art machine learning algorithm, including Logistic Regression, KNN, Support Vector Machine and Random Forest are implemented and compared. Additionally, the innovative Deep Learning Hybrid CNN-RF and VGG-RNN Model for Categorization of Soil Properties is also implemented along with CNN. An investigation into the significance of the selected category for nutritional categorization revealed that a multi-component technique provided the most accurate predictions. Both the CNN-RF and VGG-RNN models that were proposed were successful in classifying the soil with average accuracies of 95.8% and 97.9%, respectively, in the test procedures. A study was carried out in which the CNN-RF model, the VGG-RNN model, and five other machine learning and deep learning models were compared. The suggested VGG-RNN model achieved superior accuracy of classification and real-time durability, respectively.
8
UTKU, Anıl. "Kentsel Trafik Tahminine Yönelik Derin Öğrenme Tabanlı Verimli Bir Hibrit Model". Bilişim Teknolojileri Dergisi 16, nr 2 (30.04.2023): 107–17. http://dx.doi.org/10.17671/gazibtd.1167140.
Pełny tekst źródłaStreszczenie:
The traffic density problem has become one of the most important problems of urban life. The time and fuel spent due to traffic density is a significant loss for vehicle users and countries. Applications developed to reduce the time spent in traffic cannot make successful predictions about long-term traffic density. Traffic data obtained from cameras, sensors and mobile devices highlights the use of artificial intelligence technologies in order to solve the traffic management problem. In this study, a hybrid prediction model has been proposed by using CNN and RNN models for traffic density prediction. The proposed hybrid model has been tested using LR, RF, SVM, MLP, CNN, RNN and LSTM and Istanbul's traffic data for 2020. Experimental results showed that the proposed hybrid model has more successful results than the compared models. The proposed model has 0.929 R2 in the prediction of the number of vehicles passing through the junction, and 0.934 R2 in the prediction of the average speed of the vehicles passing through the junction.
9
Liang, Youzhi, Wen Liang i Jianguo Jia. "Structural Vibration Signal Denoising Using Stacking Ensemble of Hybrid CNN-RNN". Advances in Artificial Intelligence and Machine Learning 03, nr 02 (2023): 1110–22. http://dx.doi.org/10.54364/aaiml.2023.1165.
Pełny tekst źródłaStreszczenie:
Vibration signals have been increasingly utilized in various engineering fields for analysis and monitoring purposes, including structural health monitoring, fault diagnosis and damage detection, where vibration signals can provide valuable information about the condition and integrity of structures. In recent years, there has been a growing trend towards the use of vibration signals in the field of bioengineering. Activity-induced structural vibrations, particularly footstep-induced signals, are useful for analyzing the movement of biological systems such as the human body and animals, providing valuable information regarding an individual’s gait, body mass, and posture, making them an attractive tool for health monitoring, security, and human-computer interaction. However, the presence of various types of noise can compromise the accuracy of footstep-induced signal analysis. In this paper, we propose a novel ensemble model that leverages both the ensemble of multiple signals and of recurrent and convolutional neural network predictions. The proposed model consists of three stages: preprocessing, hybrid modeling, and ensemble. In the preprocessing stage, features are extracted using the Fast Fourier Transform and wavelet transform to capture the underlying physics-governed dynamics of the system and extract spatial and temporal features. In the hybrid modeling stage, a bi-directional LSTM is used to denoise the noisy signal concatenated with FFT results, and a CNN is used to obtain a condensed feature representation of the signal. In the ensemble stage, three layers of a fully-connected neural network are used to produce the final denoised signal. The proposed model addresses the challenges associated with structural vibration signals, which outperforms the prevailing algorithms for a wide range of noise levels, evaluated using PSNR, SNR, and WMAPE.
10
Zhang, Langlang, Jun Xie, Xinxiu Liu, Wenbo Zhang i Pan Geng. "Research on water quality prediction based on PE-CNN-GRU hybrid model". E3S Web of Conferences 393 (2023): 02014. http://dx.doi.org/10.1051/e3sconf/202339302014.
Pełny tekst źródłaStreszczenie:
Sewage treatment is a complex and nonlinear process. In this paper, a prediction method based on convolutional neural network (CNN) and gated recurrent unit (GRU) hybrid neural network is proposed for the prediction of dissolved oxygen concentration in sewage treatment. Firstly, akima 's method is used to complete the filling preprocessing of missing data, and then the integrated empirical mode decomposition (EEMD) algorithm is used to denoise the key factors of water quality data. Pearson correlation analysis is used to select better water quality parameters as the input of the model. Then, CNN is used to convolve the data sequence to extract the feature components of sewage data. Then, the CNN-GRU hybrid network is used to extract the feature components for sequence prediction, and then the predicted output value is obtained. The mean absolute error (MAE), root mean square error (RMSE) and mean square error (MSE) were used as evaluation criteria to analyze the prediction results of the model. By comparing with RNN model, LSTM model, GRU model and CNN-LSTM model, the results show that the PCA-EEMD-CNN-GRU (PE-CNN-GRU) hybrid model proposed in this paper has significantly improved the prediction accuracy of dissolved oxygen concentration.
11
Khamparia, Aditya, Babita Pandey, Shrasti Tiwari, Deepak Gupta, Ashish Khanna i Joel J. P. C. Rodrigues. "An Integrated Hybrid CNN–RNN Model for Visual Description and Generation of Captions". Circuits, Systems, and Signal Processing 39, nr 2 (11.11.2019): 776–88. http://dx.doi.org/10.1007/s00034-019-01306-8.
Pełny tekst źródła
12
Uly, Novem, Hendry Hendry i Ade Iriani. "CNN-RNN Hybrid Model for Diagnosis of COVID-19 on X-Ray Imagery". Digital Zone: Jurnal Teknologi Informasi dan Komunikasi 14, nr 1 (27.05.2023): 57–67. http://dx.doi.org/10.31849/digitalzone.v14i1.13668.
Pełny tekst źródłaStreszczenie:
Abstract
This research aims to implement deep learning in determining Covid-19 or normal cases using X-Ray imagery. The method used is CNN (ResNet50) and RNN (LSTM). The research phase begins with data collection, data preprocessing, method modeling, method testing and method evaluation. The data was taken from the kagle.com site with the amount of data used 1.000 images where 500 covid data and 500 normal data, the data is divided into 80% training data, 10% validation data and 10% test data. The results of the evaluation by calculating the ResNet50-LSTM confusion matrix have a value of 95% accuracy, 96% precision, 94% recall and 95% F1-score. At the method testing stage, the researcher got the results of the proposed method experiencing overfitting seen by the comparison of the loss values in the validation data which were not as good as the loss values of the training data. From the results of evaluation and method testing, research can be used as a recommendation in cases of Covid-19 or normal.
13
Arshad, Muhammad Zeeshan, Ankhzaya Jamsrandorj, Jinwook Kim i Kyung-Ryoul Mun. "Gait Events Prediction Using Hybrid CNN-RNN-Based Deep Learning Models through a Single Waist-Worn Wearable Sensor". Sensors 22, nr 21 (27.10.2022): 8226. http://dx.doi.org/10.3390/s22218226.
Pełny tekst źródłaStreszczenie:
Elderly gait is a source of rich information about their physical and mental health condition. As an alternative to the multiple sensors on the lower body parts, a single sensor on the pelvis has a positional advantage and an abundance of information acquirable. This study aimed to improve the accuracy of gait event detection in the elderly using a single sensor on the waist and deep learning models. Data were gathered from elderly subjects equipped with three IMU sensors while they walked. The input taken only from the waist sensor was used to train 16 deep-learning models including a CNN, RNN, and CNN-RNN hybrid with or without the Bidirectional and Attention mechanism. The groundtruth was extracted from foot IMU sensors. A fairly high accuracy of 99.73% and 93.89% was achieved by the CNN-BiGRU-Att model at the tolerance window of ±6 TS (±6 ms) and ±1 TS (±1 ms), respectively. Advancing from the previous studies exploring gait event detection, the model demonstrated a great improvement in terms of its prediction error having an MAE of 6.239 ms and 5.24 ms for HS and TO events, respectively, at the tolerance window of ±1 TS. The results demonstrated that the use of CNN-RNN hybrid models with Attention and Bidirectional mechanisms is promising for accurate gait event detection using a single waist sensor. The study can contribute to reducing the burden of gait detection and increase its applicability in future wearable devices that can be used for remote health monitoring (RHM) or diagnosis based thereon.
14
Gong, Liyun, Miao Yu, Vassilis Cutsuridis, Stefanos Kollias i Simon Pearson. "A Novel Model Fusion Approach for Greenhouse Crop Yield Prediction". Horticulturae 9, nr 1 (20.12.2022): 5. http://dx.doi.org/10.3390/horticulturae9010005.
Pełny tekst źródłaStreszczenie:
In this work, we have proposed a novel methodology for greenhouse tomato yield prediction, which is based on a hybrid of an explanatory biophysical model—the Tomgro model, and a machine learning model called CNN-RNN. The Tomgro and CNN-RNN models are calibrated/trained for predicting tomato yields while different fusion approaches (linear, Bayesian, neural network, random forest and gradient boosting) are exploited for fusing the prediction result of individual models for obtaining the final prediction results. The experimental results have shown that the model fusion approach achieves more accurate prediction results than the explanatory biophysical model or the machine learning model. Moreover, out of different model fusion approaches, the neural network one produced the most accurate tomato prediction results, with means and standard deviations of root mean square error (RMSE), r2-coefficient, Nash-Sutcliffe efficiency (NSE) and percent bias (PBIAS) being 17.69 ± 3.47 g/m2, 0.9995 ± 0.0002, 0.9989 ± 0.0004 and 0.1791 ± 0.6837, respectively.
15
Kang, Taehyung, Dae Yeong Lim, Hilal Tayara i Kil To Chong. "Forecasting of Power Demands Using Deep Learning". Applied Sciences 10, nr 20 (16.10.2020): 7241. http://dx.doi.org/10.3390/app10207241.
Pełny tekst źródłaStreszczenie:
The forecasting of electricity demands is important for planning for power generator sector improvement and preparing for periodical operations. The prediction of future electricity demand is a challenging task due to the complexity of the available demand patterns. In this paper, we studied the performance of the basic deep learning models for electrical power forecasting such as the facility capacity, supply capacity, and power consumption. We designed different deep learning models such as convolution neural network (CNN), recurrent neural network (RNN), and a hybrid model that combines both CNN and RNN. We applied these models to the data provided by the Korea Power Exchange. This data contains the daily recordings of facility capacity, supply capacity, and power consumption. The experimental results showed that the CNN model outperforms the other two models significantly for the three features forecasting (facility capacity, supply capacity, and power consumption).
16
Hasbullah, Sumayyah, Mohd Soperi Mohd Zahid i Satria Mandala. "Detection of Myocardial Infarction Using Hybrid Models of Convolutional Neural Network and Recurrent Neural Network". BioMedInformatics 3, nr 2 (15.06.2023): 478–92. http://dx.doi.org/10.3390/biomedinformatics3020033.
Pełny tekst źródłaStreszczenie:
Myocardial Infarction (MI) is the death of the heart muscle caused by lack of oxygenated blood flow to the heart muscle. It has been the main cause of death worldwide. The fastest way to detect MI is by using an electrocardiogram (ECG) device, which generates graphs of heartbeats morphology over a certain period of time. Patients with MI need fast intervention as delay will lead to worsening heart conditions or failure. To improve MI diagnosis, much research has been carried out to come up with a fast and reliable system to aid automatic MI detection and prediction from ECG readings. Recurrent Neural Network (RNN) with memory has produced more accurate results in predicting time series problems. Convolutional neural networks have also shown good results in terms of solving prediction problems. However, CNN models do not have the capability of remembering temporal information. This research proposes hybrid models of CNN and RNN techniques to predict MI. Specifically, CNN-LSTM and CNN-BILSTM models have been developed. The PTB XL dataset is used to train the models. The models predict ECG input as representing MI symptoms, healthy heart conditions or other cardiovascular diseases. Deep learning models offer automatic feature extraction, and our models take advantage of automatic feature extraction. The other superior models used their own feature extraction algorithm. This research proposed a straightforward architecture that depends mostly on the capability of the deep learning model to learn the data. Performance evaluation of the models shows overall accuracy of 89% for CNN LSTM and 91% for the CNN BILSTM model.
17
Rong, Guangzhi, Kaiwei Li, Yulin Su, Zhijun Tong, Xingpeng Liu, Jiquan Zhang, Yichen Zhang i Tiantao Li. "Comparison of Tree-Structured Parzen Estimator Optimization in Three Typical Neural Network Models for Landslide Susceptibility Assessment". Remote Sensing 13, nr 22 (20.11.2021): 4694. http://dx.doi.org/10.3390/rs13224694.
Pełny tekst źródłaStreszczenie:
Landslides pose a constant threat to the lives and property of mountain people and may also cause geomorphological destruction such as soil and water loss, vegetation destruction, and land cover change. Landslide susceptibility assessment (LSA) is a key component of landslide risk evaluation. There are many related studies, but few analyses and comparisons of models for optimization. This paper aims to introduce the Tree-structured Parzen Estimator (TPE) algorithm for hyperparameter optimization of three typical neural network models for LSA in Shuicheng County, China, as an example, and to compare the differences of predictive ability among the models in order to achieve higher application performance. First, 17 influencing factors of landslide multiple data sources were selected for spatial prediction, hybrid ensemble oversampling and undersampling techniques were used to address the imbalanced sample and small sample size problem, and the samples were randomly divided into a training set and validation set. Second, deep neural network (DNN), recurrent neural network (RNN), and convolutional neural network (CNN) models were adopted to predict the regional landslides susceptibility, and the TPE algorithm was used to optimize the hyperparameters respectively to improve the assessment capacity. Finally, to compare the differences and optimization effects of these models, several objective measures were applied for validation. The results show that the high-susceptibility regions mostly distributed in bands along fault zones, where the lithology is mostly claystone, sandstone, and basalt. The DNN, RNN, and CNN models all perform well in LSA, especially the RNN model. The TPE optimization significantly improves the accuracy of the DNN and CNN (3.92% and 1.52%, respectively), but does not improve the performance of the RNN. In summary, our proposed RNN model and TPE-optimized DNN and CNN model have robust predictive capability for landslide susceptibility in the study area and can also be applied to other areas containing similar geological conditions.
18
Sharma, Richa, Sudha Morwal i Basant Agarwal. "Entity-Extraction Using Hybrid Deep-Learning Approach for Hindi text". International Journal of Cognitive Informatics and Natural Intelligence 15, nr 3 (lipiec 2021): 1–11. http://dx.doi.org/10.4018/ijcini.20210701.oa1.
Pełny tekst źródłaStreszczenie:
This article presents a neural network-based approach to develop named entity recognition for Hindi text. In this paper, the authors propose a deep learning architecture based on convolutional neural network (CNN) and bi-directional long short-term memory (Bi-LSTM) neural network. Skip-gram approach of word2vec model is used in the proposed model to generate word vectors. In this research work, several deep learning models have been developed and evaluated as baseline systems such as recurrent neural network (RNN), long short-term memory (LSTM), Bi-LSTM. Furthermore, these baseline systems are promoted to a proposed model with the integration of CNN and conditional random field (CRF) layers. After a comparative analysis of results, it is verified that the performance of the proposed model (i.e., Bi-LSTM-CNN-CRF) is impressive. The proposed system achieves 61% precision, 56% recall, and 58% F-measure.
19
Guo, Yanan, Xiaoqun Cao, Bainian Liu i Kecheng Peng. "El Niño Index Prediction Using Deep Learning with Ensemble Empirical Mode Decomposition". Symmetry 12, nr 6 (1.06.2020): 893. http://dx.doi.org/10.3390/sym12060893.
Pełny tekst źródłaStreszczenie:
El Niño is an important quasi-cyclical climate phenomenon that can have a significant impact on ecosystems and societies. Due to the chaotic nature of the atmosphere and ocean systems, traditional methods (such as statistical methods) are difficult to provide accurate El Niño index predictions. The latest research shows that Ensemble Empirical Mode Decomposition (EEMD) is suitable for analyzing non-linear and non-stationary signal sequences, Convolutional Neural Network (CNN) is good at local feature extraction, and Recurrent Neural Network (RNN) can capture the overall information of the sequence. As a special RNN, Long Short-Term Memory (LSTM) has significant advantages in processing and predicting long, complex time series. In this paper, to predict the El Niño index more accurately, we propose a new hybrid neural network model, EEMD-CNN-LSTM, which combines EEMD, CNN, and LSTM. In this hybrid model, the original El Niño index sequence is first decomposed into several Intrinsic Mode Functions (IMFs) using the EEMD method. Next, we filter the IMFs by setting a threshold, and we use the filtered IMFs to reconstruct the new El Niño data. The reconstructed time series then serves as input data for CNN and LSTM. The above data preprocessing method, which first decomposes the time series and then reconstructs the time series, uses the idea of symmetry. With this symmetric operation, we extract valid information about the time series and then make predictions based on the reconstructed time series. To evaluate the performance of the EEMD-CNN-LSTM model, the proposed model is compared with four methods including the traditional statistical model, machine learning model, and other deep neural network models. The experimental results show that the prediction results of EEMD-CNN-LSTM are not only more accurate but also more stable and reliable than the general neural network model.
20
Mas-Pujol, Sergi, Esther Salamí i Enric Pastor. "RNN-CNN Hybrid Model to Predict C-ATC CAPACITY Regulations for En-Route Traffic". Aerospace 9, nr 2 (10.02.2022): 93. http://dx.doi.org/10.3390/aerospace9020093.
Pełny tekst źródłaStreszczenie:
Meeting the demand with the available airspace capacity is one of the most challenging problems faced by Air Traffic Management. Nowadays, this collaborative Demand–Capacity Balancing process often ends up enforcing Air Traffic Flow Management regulations when capacity cannot be adjusted. This process to decide if a regulation is needed is time consuming and relies heavily on human knowledge. This article studies three different Air Traffic Management frameworks aiming to improve the cost-efficiency for Flow Manager Positions and Network Manager operators when facing the detection of regulations. For this purpose, two already tested Deep Learning models are combined, creating different hybrid models. A Recurrent Neural Network is used to process scalar variables to extract the overall airspace characteristics, and a Convolutional Neural Network is used to process artificial images exhibiting the specific airspace configuration. The models are validated using historical data from two of the most regulated European regions, resulting in a novel framework that could be used across Air Traffic Control centers. For the best hybrid model, using a cascade architecture, an average accuracy of 88.45% is obtained, with an average recall of 92.16%, and an average precision of 86.85%, across different traffic volumes. Moreover, two different techniques for model explainability are used to provide a theoretical understanding of its behavior and understand the reasons behind the predictions.
21
Lapa, Paulo, Mauro Castelli, Ivo Gonçalves, Evis Sala i Leonardo Rundo. "A Hybrid End-to-End Approach Integrating Conditional Random Fields into CNNs for Prostate Cancer Detection on MRI". Applied Sciences 10, nr 1 (2.01.2020): 338. http://dx.doi.org/10.3390/app10010338.
Pełny tekst źródłaStreszczenie:
Prostate Cancer (PCa) is the most common oncological disease in Western men. Even though a growing effort has been carried out by the scientific community in recent years, accurate and reliable automated PCa detection methods on multiparametric Magnetic Resonance Imaging (mpMRI) are still a compelling issue. In this work, a Deep Neural Network architecture is developed for the task of classifying clinically significant PCa on non-contrast-enhanced MR images. In particular, we propose the use of Conditional Random Fields as a Recurrent Neural Network (CRF-RNN) to enhance the classification performance of XmasNet, a Convolutional Neural Network (CNN) architecture specifically tailored to the PROSTATEx17 Challenge. The devised approach builds a hybrid end-to-end trainable network, CRF-XmasNet, composed of an initial CNN component performing feature extraction and a CRF-based probabilistic graphical model component for structured prediction, without the need for two separate training procedures. Experimental results show the suitability of this method in terms of classification accuracy and training time, even though the high-variability of the observed results must be reduced before transferring the resulting architecture to a clinical environment. Interestingly, the use of CRFs as a separate postprocessing method achieves significantly lower performance with respect to the proposed hybrid end-to-end approach. The proposed hybrid end-to-end CRF-RNN approach yields excellent peak performance for all the CNN architectures taken into account, but it shows a high-variability, thus requiring future investigation on the integration of CRFs into a CNN.
22
Beseiso, Majdi. "Word and Character Information Aware Neural Model for Emotional Analysis". Recent Patents on Computer Science 12, nr 2 (25.02.2019): 142–47. http://dx.doi.org/10.2174/2213275911666181119112645.
Pełny tekst źródłaStreszczenie:
Background: Social media texts are often highly unstructured in accordance with the presence of hashtags, emojis and URLs occurring in abundance. Thus, a sentiment or emotion analysis on these kinds of texts becomes very difficult. The difficulty increases even more when such texts are in local languages like Arabic. Methods: This work utilizes novel deep learning architectures in the form of character-level Convolutional Neural Network (CNN) module and the word-level Recurrent Neural Network (RNN) module to produce a hybrid architecture that makes use of the character level analysis and the word level analysis to obtain state-of-the-art results on a totally new Arabic Emotions dataset. Results: The proposed method works the best among the traditional bag-of-words and Term Frequency and Inverse Document Frequency methods for emotion analysis. It also outperforms the state-of-the-art deep learning methods which are known to perform very well in an English corpus. Conclusion: The proposed deep end-to-end architecture utilizes the character level information from a text through the Character CNN Module and the word level information from a text through the Word-Level RNN Module.
23
Amer, Rusul, i Ahmed Al Tmeme. "Hybrid Deep Learning Model for Singing Voice Separation". MENDEL 27, nr 2 (21.12.2021): 44–50. http://dx.doi.org/10.13164/mendel.2021.2.044.
Pełny tekst źródłaStreszczenie:
Monaural source separation is a challenging issue due to the fact that there is only a single channel available; however, there is an unlimited range of possible solutions. In this paper, a monaural source separation model based hybrid deep learning model, which consists of convolution neural network (CNN), dense neural network (DNN) and recurrent neural network (RNN), will be presented. A trial and error method will be used to optimize the number of layers in the proposed model. Moreover, the effects of the learning rate, optimization algorithms, and the number of epochs on the separation performance will be explored. Our model was evaluated using the MIR-1K dataset for singing voice separation. Moreover, the proposed approach achieves (4.81) dB GNSDR gain, (7.28) dB GSIR gain, and (3.39) dB GSAR gain in comparison to current approaches
24
Zhang, Dong, i Qichuan Tian. "A Novel Fuzzy Optimized CNN-RNN Method for Facial Expression Recognition". Elektronika ir Elektrotechnika 27, nr 5 (27.10.2021): 67–74. http://dx.doi.org/10.5755/j02.eie.29648.
Pełny tekst źródłaStreszczenie:
Facial expression is one of the important ways of transferring emotion in interpersonal communication, and it has been widely used in many interpersonal communication systems. The traditional facial expression recognition methods are not intelligent enough to manage the model uncertainty. The deep learning method has obvious ability to deal with model uncertainty in the image recognition. The deep learning method is able to complete the facial expression work, but the recognition rate can be further improved by a hybrid learning strategy. In this paper, a Fuzzy optimized convolutional neural network-recurrent neural network (CNN-RNN) method for facial expression recognition is proposed to solve the problems of direct image convolution without image enhancement and simple convolution stack ignoring feature layer-by-layer convolution resulting in information loss. Firstly, each face image is scaled by the bilinear interpolation and the affine transformation is adopted to expand the image data to avoid the shortage of the data set. Then the feature map of the facial expression is extracted by the CNN with small information loss. To deal with the uncertainty in the feature map, the Fuzzy logic is employed to reduce the uncertainty by recognizing the highly nonlinear relationship between the features. Then the output of the Fuzzy model is fed with the RNN to classify different facial expression images. The recognition results based on the open datasets CK, Jaffe, and FER2013 show that the proposed Fuzzy optimized CNN-RNN method has a certain improvement in the recognition effect of different facial expression data sets compared with current popular algorithms.
25
Wang, Yu, Yining Sun, Zuchang Ma, Lisheng Gao i Yang Xu. "A Hybrid Model for Named Entity Recognition on Chinese Electronic Medical Records". ACM Transactions on Asian and Low-Resource Language Information Processing 20, nr 2 (23.04.2021): 1–12. http://dx.doi.org/10.1145/3436819.
Pełny tekst źródłaStreszczenie:
Electronic medical records (EMRs) contain valuable information about the patients, such as clinical symptoms, diagnostic results, and medications. Named entity recognition (NER) aims to recognize entities from unstructured text, which is the initial step toward the semantic understanding of the EMRs. Extracting medical information from Chinese EMRs could be a more complicated task because of the difference between English and Chinese. Some researchers have noticed the importance of Chinese NER and used the recurrent neural network or convolutional neural network (CNN) to deal with this task. However, it is interesting to know whether the performance could be improved if the advantages of the RNN and CNN can be both utilized. Moreover, RoBERTa-WWM, as a pre-training model, can generate the embeddings with word-level features, which is more suitable for Chinese NER compared with Word2Vec. In this article, we propose a hybrid model. This model first obtains the entities identified by bidirectional long short-term memory and CNN, respectively, and then uses two hybrid strategies to output the final results relying on these entities. We also conduct experiments on raw medical records from real hospitals. This dataset is provided by the China Conference on Knowledge Graph and Semantic Computing in 2019 (CCKS 2019). Results demonstrate that the hybrid model can improve performance significantly.
26
Roy, Bishwajit, Lokesh Malviya, Radhikesh Kumar, Sandip Mal, Amrendra Kumar, Tanmay Bhowmik i Jong Wan Hu. "Hybrid Deep Learning Approach for Stress Detection Using Decomposed EEG Signals". Diagnostics 13, nr 11 (1.06.2023): 1936. http://dx.doi.org/10.3390/diagnostics13111936.
Pełny tekst źródłaStreszczenie:
Stress has an impact, not only on a person’s physical health, but also on the ability to perform at the workplace in daily life. The well-established relation between psychological stress and its pathogeneses highlights the need for detecting psychological stress early, in order to prevent disease advancement and to save human lives. Electroencephalography (EEG) signal recording tools are widely used to collect these psychological signals/brain rhythms in the form of electric waves. The aim of the current research was to apply automatic feature extraction to decomposed multichannel EEG recordings, in order to efficiently detect psychological stress. The traditional deep learning techniques, namely the convolution neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU) and recurrent neural network (RNN) models, have been frequently used for stress detection. A hybrid combination of these techniques may provide improved performance, and can handle long-term dependencies in non-linear brain signals. Therefore, this study proposed an integration of deep learning models, called DWT-based CNN, BiLSTM, and two layers of a GRU network, to extract features and classify stress levels. Discrete wavelet transform (DWT) analysis was used to remove the non-linearity and non-stationarity from multi-channel (14 channel) EEG recordings, and to decompose them into different frequency bands. The decomposed signals were utilized for automatic feature extraction using the CNN, and the stress levels were classified using BiLSTM and two layers of GRU. This study compared five combinations of the CNN, LSTM, BiLSTM, GRU and RNN models with the proposed model. The proposed hybrid model performed better in classification accuracy compared to the other models. Therefore, hybrid combinations are appropriate for the clinical intervention and prevention of mental and physical problems.
27
Yadav, Omprakash, Rachael Dsouza, Rhea Dsouza i Janice Jose. "Soccer Action video Classification using Deep Learning". International Journal for Research in Applied Science and Engineering Technology 10, nr 6 (30.06.2022): 1060–63. http://dx.doi.org/10.22214/ijraset.2022.43929.
Pełny tekst źródłaStreszczenie:
Abstract: This paper proposes a deep learning approach for the classification of different soccer actions like Goal, Yellow Card and Soccer Juggling from an input soccer video. The approach used for the same included a Hybrid model which consisted of VGG16 CNN model and Bidirectional Long short-term memory (Bi-LSTM) a Recurrent Neural Network (RNN) model. Our approach involved manually annotating approximately 400 soccer clips from 3 action classes for training. Using the VGG16 model to extract the features from the frames of these clips and then training the bi-LSTM on the features obtained. Bi-LSTM being useful in predicting input sequence problems like videos. Keywords: Soccer Videos, Convolution Neural Networks (CNNs), Recurrent Neural Network (RNN), Bidirectional Long shortterm memory (Bi-LSTM)
28
Mekruksavanich, Sakorn, i Anuchit Jitpattanakul. "Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data". Electronics 10, nr 14 (14.07.2021): 1685. http://dx.doi.org/10.3390/electronics10141685.
Pełny tekst źródłaStreszczenie:
Sensor-based human activity recognition (S-HAR) has become an important and high-impact topic of research within human-centered computing. In the last decade, successful applications of S-HAR have been presented through fruitful academic research and industrial applications, including for healthcare monitoring, smart home controlling, and daily sport tracking. However, the growing requirements of many current applications for recognizing complex human activities (CHA) have begun to attract the attention of the HAR research field when compared with simple human activities (SHA). S-HAR has shown that deep learning (DL), a type of machine learning based on complicated artificial neural networks, has a significant degree of recognition efficiency. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) are two different types of DL methods that have been successfully applied to the S-HAR challenge in recent years. In this paper, we focused on four RNN-based DL models (LSTMs, BiLSTMs, GRUs, and BiGRUs) that performed complex activity recognition tasks. The efficiency of four hybrid DL models that combine convolutional layers with the efficient RNN-based models was also studied. Experimental studies on the UTwente dataset demonstrated that the suggested hybrid RNN-based models achieved a high level of recognition performance along with a variety of performance indicators, including accuracy, F1-score, and confusion matrix. The experimental results show that the hybrid DL model called CNN-BiGRU outperformed the other DL models with a high accuracy of 98.89% when using only complex activity data. Moreover, the CNN-BiGRU model also achieved the highest recognition performance in other scenarios (99.44% by using only simple activity data and 98.78% with a combination of simple and complex activities).
29
Farid, Ahmed Bahaa, Enas Mohamed Fathy, Ahmed Sharaf Eldin i Laila A. Abd-Elmegid. "Software defect prediction using hybrid model (CBIL) of convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM)". PeerJ Computer Science 7 (16.11.2021): e739. http://dx.doi.org/10.7717/peerj-cs.739.
Pełny tekst źródłaStreszczenie:
In recent years, the software industry has invested substantial effort to improve software quality in organizations. Applying proactive software defect prediction will help developers and white box testers to find the defects earlier, and this will reduce the time and effort. Traditional software defect prediction models concentrate on traditional features of source code including code complexity, lines of code, etc. However, these features fail to extract the semantics of source code. In this research, we propose a hybrid model that is called CBIL. CBIL can predict the defective areas of source code. It extracts Abstract Syntax Tree (AST) tokens as vectors from source code. Mapping and word embedding turn integer vectors into dense vectors. Then, Convolutional Neural Network (CNN) extracts the semantics of AST tokens. After that, Bidirectional Long Short-Term Memory (Bi-LSTM) keeps key features and ignores other features in order to enhance the accuracy of software defect prediction. The proposed model CBIL is evaluated on a sample of seven open-source Java projects of the PROMISE dataset. CBIL is evaluated by applying the following evaluation metrics: F-measure and area under the curve (AUC). The results display that CBIL model improves the average of F-measure by 25% compared to CNN, as CNN accomplishes the top performance among the selected baseline models. In average of AUC, CBIL model improves AUC by 18% compared to Recurrent Neural Network (RNN), as RNN accomplishes the top performance among the selected baseline models used in the experiments.
30
ÇAVDAR, İsmail, i Vahid FARYAD. "New Design of a Supervised Energy Disaggregation Model Based on the Deep Neural Network for a Smart Grid". Energies 12, nr 7 (29.03.2019): 1217. http://dx.doi.org/10.3390/en12071217.
Pełny tekst źródłaStreszczenie:
Energy management technology of demand-side is a key process of the smart grid that helps achieve a more efficient use of generation assets by reducing the energy demand of users during peak loads. In the context of a smart grid and smart metering, this paper proposes a hybrid model of energy disaggregation through deep feature learning for non-intrusive load monitoring to classify home appliances based on the information of main meters. In addition, a deep neural model of supervised energy disaggregation with a high accuracy for giving awareness to end users and generating detailed feedback from demand-side with no need for expensive smart outlet sensors was introduced. A new functional API model of deep learning (DL) based on energy disaggregation was designed by combining a one-dimensional convolutional neural network and recurrent neural network (1D CNN-RNN). The proposed model was trained on Google Colab’s Tesla graphics processing unit (GPU) using Keras. The residential energy disaggregation dataset was used for real households and was implemented in Tensorflow backend. Three different disaggregation methods were compared, namely the convolutional neural network, 1D CNN-RNN, and long short-term memory. The results showed that energy can be disaggregated from the metrics very accurately using the proposed 1D CNN-RNN model. Finally, as a work in progress, we introduced the DL on the Edge for Fog Computing non-intrusive load monitoring (NILM) on a low-cost embedded board using a state-of-the-art inference library called uTensor that can support any Mbed enabled board with no need for the DL API of web services and internet connectivity.
31
WEN, HAO, WENJIAN YU, YUANQING WU, SHUAI YANG i XIAOLONG LIU. "A SCALABLE HYBRID MODEL FOR ATRIAL FIBRILLATION DETECTION". Journal of Mechanics in Medicine and Biology 21, nr 05 (17.04.2021): 2140021. http://dx.doi.org/10.1142/s0219519421400212.
Pełny tekst źródłaStreszczenie:
In this work, a scalable hybrid model is proposed for the purpose of screening and continuous monitoring of atrial fibrillation (AF) using electrocardiogram (ECG) signals collected from wearable ECG devices. The time series of RR intervals (with units in seconds) extracted from the ECG signal is fed into a recurrent neural network (RNN), and the bandpass filtered and scaled signal itself is fed into a convolutional neural network (CNN). At the post-processing stage, these two predictions are merged. An additional logistic regression model using statistical features of “pseudo” PR interval sequence is applied to aid making the final prediction. The proposed model is trained and validated on several datasets from PhysioNet and achieves a precision of 98.28% and a specificity of 99.82% on a dataset collected from several PhysioNet databases. This hybrid model has already been deployed through a WeChat applet, providing services those using wearable ECG devices, thus helping the screening and continuous out-of-hospital monitoring of the disease of AF.
32
Rafi, Quazi Ghulam, Mohammed Noman, Sadia Zahin Prodhan, Sabrina Alam i Dip Nandi. "Comparative Analysis of Three Improved Deep Learning Architectures for Music Genre Classification". International Journal of Information Technology and Computer Science 13, nr 2 (8.04.2021): 1–14. http://dx.doi.org/10.5815/ijitcs.2021.02.01.
Pełny tekst źródłaStreszczenie:
Among the many music information retrieval (MIR) tasks, music genre classification is noteworthy. The categorization of music into different groups that came to existence through a complex interplay of cultures, musicians, and various market forces to characterize similarities between compositions and organize collections is known as a music genre. The past researchers extracted various hand-crafted features and developed classifiers based on them. But the major drawback of this approach was the requirement of field expertise. However, in recent times researchers, because of the remarkable classification accuracy of deep learning models, have used similar models for MIR tasks. Convolutional Neural Net- work (CNN), Recurrent Neural Network (RNN), and the hybrid model, Convolutional - Recurrent Neural Network (CRNN), are such prominently used deep learning models for music genre classification along with other MIR tasks and various architectures of these models have achieved state-of-the-art results. In this study, we review and discuss three such architectures of deep learning models, already used for music genre classification of music tracks of length of 29-30 seconds. In particular, we analyze improved CNN, RNN, and CRNN architectures named Bottom-up Broadcast Neural Network (BBNN) [1], Independent Recurrent Neural Network (IndRNN) [2] and CRNN in Time and Frequency dimensions (CRNN- TF) [3] respectively, almost all of the architectures achieved the highest classification accuracy among the variants of their base deep learning model. Hence, this study holds a comparative analysis of the three most impressive architectural variants of the main deep learning models that are prominently used to classify music genre and presents the three architecture, hence the models (CNN, RNN, and CRNN) in one study. We also propose two ways that can improve the performances of the RNN (IndRNN) and CRNN (CRNN-TF) architectures.
33
Dhar, Puja, Vijay Kumar Garg i Mohammad Anisur Rahman. "Enhanced Feature Extraction-based CNN Approach for Epileptic Seizure Detection from EEG Signals". Journal of Healthcare Engineering 2022 (16.03.2022): 1–14. http://dx.doi.org/10.1155/2022/3491828.
Pełny tekst źródłaStreszczenie:
One of the most common neurological disorders is epilepsy, which disturbs the nerve cell activity in the brain, causing seizures. Electroencephalography (EEG) signals are used to detect epilepsy and are considered standard techniques to diagnose epilepsy conditions. EEG monitors and records the brain activity of epilepsy patients, and these recordings are used in the diagnosis of epilepsy. However, extracting the information from the EEG recordings manually for detecting epileptic seizures is a difficult cumbersome, error-prone, and labor-intensive task. These negative attributes of the manual process increase the demand for implementing an automated model for the seizure detection process, which can classify seizure and nonseizures from EEG signals to help in the timely identification of epilepsy. Recently, deep learning (DL) and machine learning (ML) techniques have been used in the automatic detection of epileptic seizures because of their superior classification abilities. ML and DL algorithms can accurately classify different seizure conditions from large-scale EEG data and provide appropriate results for neurologists. This work presents a feature extraction-based convolutional neural network (CNN) to sense and classify different types of epileptic seizures from EEG signals. Different features are analyzed to classify seizures via EEG signals. Simulation analysis was managed to investigate the classification performance of the hybrid CNN-RNN model in terms of different achievement metrics such as accuracy, precision, recall, f1 score, and false-positive rate. The results validate the efficacy of the CNN-RNN model for seizure detection.
34
He, Yijuan, Jidong Lv, Hongjie Liu i Tao Tang. "Toward the Trajectory Predictor for Automatic Train Operation System Using CNN–LSTM Network". Actuators 11, nr 9 (31.08.2022): 247. http://dx.doi.org/10.3390/act11090247.
Pełny tekst źródłaStreszczenie:
The accurate trajectory of the train ahead with more dynamic behaviour, such as train position, speed, acceleration, etc., is the critical issue of virtual coupling for future railways, which can drastically reduce their headways and increase line capacity. This paper presents an integrated convolutional neural network (CNN) and long short-term memory (LSTM) hybrid model for the task of trajectory prediction. A CNN–LSTM hybrid algorithm has been proposed. The model employs CNN and LSTM to extract the spatial dimension feature of the trajectory and the long-term dependencies of train trajectory data, respectively. The proposed CNN–LSTM model has superiority in achieving collaborative data mining on spatiotemporal measurement data to simultaneously learn spatial and temporal features from phasor measurement unit data. Therefore, the high-precision prediction of the train trajectory prediction is achieved based on the sufficient fusion of the above features. We use real automatic train operation (ATO) collected data for experiments and compare the proposed method with recurrent neural networks (RNN), recurrent neural networks (GRU), LSTM, and stateful-LSTM models on the same data sets. Experimental results show that the prediction performance of long-term trajectories is satisfyingly accurate. The root mean square error (RMSE) error can be reduced to less than 0.21 m, and the hit rate achieves 93% when the time horizon increases to 4S, respectively.
35
Umair, Muhammad, Muhammad Zubair, Farhan Dawood, Sarim Ashfaq, Muhammad Shahid Bhatti, Mohammad Hijji i Abid Sohail. "A Multi-Layer Holistic Approach for Cursive Text Recognition". Applied Sciences 12, nr 24 (9.12.2022): 12652. http://dx.doi.org/10.3390/app122412652.
Pełny tekst źródłaStreszczenie:
Urdu is a widely spoken and narrated language in several South-Asian countries and communities worldwide. It is relatively hard to recognize Urdu text compared to other languages due to its cursive writing style. The Urdu text script belongs to a non-Latin cursive family script like Arabic, Hindi and Chinese. Urdu is written in several writing styles, among which ‘Nastaleeq’ is the most popular and widely used font style. A gap still poses a challenge for localization/detection and recognition of Urdu Nastaleeq text as it follows modified version of Arabic script. This research study presents a methodology to recognize and classify Urdu text in Nastaleeq font, regardless of the text position in the image. The proposed solution is comprised of a two-step methodology. In the first step, text detection is performed using the Connected Component Analysis (CCA) and Long Short-Term Memory Neural Network (LSTM). In the second step, a hybrid Convolution Neural Network and Recurrent Neural Network (CNN-RNN) architecture is deployed to recognize the detected text. The image containing Urdu text is binarized and segmented to produce a single-line text image fed to the hybrid CNN-RNN model, which recognizes the text and saves it in a text file. The proposed technique outperforms the existing ones by achieving an overall accuracy of 97.47%.
36
Moradzadeh, Arash, Sahar Zakeri, Waleed A. Oraibi, Behnam Mohammadi-Ivatloo, Zulkurnain Abdul-Malek i Reza Ghorbani. "Non-Intrusive Load Monitoring of Residential Loads via Laplacian Eigenmaps and Hybrid Deep Learning Procedures". Sustainability 14, nr 22 (11.11.2022): 14898. http://dx.doi.org/10.3390/su142214898.
Pełny tekst źródłaStreszczenie:
Today, introducing useful and practical solutions to residential load disaggregation as subsets of energy management has created numerous challenges. In this study, an intelligence hybrid solution based on manifold learning and deep learning applications is presented. The proposed solution presents a combined structure of Laplacian eigenmaps (LE), a convolutional neural network (CNN), and a recurrent neural network (RNN), called LE-CRNN. In the proposed model architecture, LE, with its high ability in dimensional reduction, transfers the salient features and specific values of power consumption curves (PCCs) of household electrical appliances (HEAs) to a low-dimensional space. Then, the combined model of CRNN significantly improves the structure of CNN in fully connected layers so that the process of identification and separation of the HEA type can be performed without overfitting problems and with very high accuracy. In order to implement the suggested model, two real-world databases have been used. In a separate scenario, a conventional CNN is applied to the data for comparing the performance of the suggested model with the CNN. The designed networks are trained and validated using the PCCs of HEAs. Then, the whole energy consumption of the building obtained from the smart meter is used for load disaggregation. The trained networks, which contain features extracted from PCCs of HEAs, prove that they can disaggregate the total power consumption for houses intended for the Reference Energy Disaggregation Data Set (REDD) and Almanac of Minutely Power Dataset (AMPds) with average accuracies (Acc) of 97.59% and 97.03%, respectively. Finally, in order to show the accuracy of the developed hybrid model, the obtained results in this study are compared with the results of similar works for the same datasets.
37
Bao, Zhengyi, Jiahao Jiang, Chunxiang Zhu i Mingyu Gao. "A New Hybrid Neural Network Method for State-of-Health Estimation of Lithium-Ion Battery". Energies 15, nr 12 (16.06.2022): 4399. http://dx.doi.org/10.3390/en15124399.
Pełny tekst źródłaStreszczenie:
Accurate estimation of lithium-ion battery state-of-health (SOH) is important for the safe operation of electric vehicles; however, in practical applications, the accuracy of SOH estimation is affected by uncertainty factors, including human operation, working conditions, etc. To accurately estimate the battery SOH, a hybrid neural network based on the dilated convolutional neural network and the bidirectional gated recurrent unit, namely dilated CNN-BiGRU, is proposed in this paper. The proposed data-driven method uses the voltage distribution and capacity changes in the extracted battery discharge curve to learn the serial data time dependence and correlation. This method can obtain more accurate temporal and spatial features of the original battery data, resulting higher accuracy and robustness. The effectiveness of dilated CNN-BiGRU for SOH estimation is verified on two publicly lithium-ion battery datasets, the NASA Battery Aging Dataset and Oxford Battery Degradation Dataset. The experimental results reveal that the proposed model outperforms the compared data-driven methods, e.g., CNN-series and RNN-series. Furthermore, the mean absolute error (MAE) and root mean square error (RMSE) are limited to within 1.9% and 3.3%, respectively, on the NASA Battery Aging Dataset.
38
Alrasheedi, Abdullah, i Abdulaziz Almalaq. "Hybrid Deep Learning Applied on Saudi Smart Grids for Short-Term Load Forecasting". Mathematics 10, nr 15 (28.07.2022): 2666. http://dx.doi.org/10.3390/math10152666.
Pełny tekst źródłaStreszczenie:
Despite advancements in smart grid (SG) technology, effective load forecasting utilizing big data or large-scale datasets remains a complex task for energy management, planning, and control. The Saudi SGs, in alignment with the Saudi Vision 2030, have been envisioned as future electrical grids with a bidirectional flow of power and data. To that end, data analysis and predictive models can enhance Saudi SG planning and control via artificial intelligence (AI). Recently, many AI methods including deep learning (DL) algorithms for SG applications have been published in the literature and have shown superior time series predictions compared with conventional prediction models. Current load-prediction research for the Saudi grid focuses on identifying anticipated loads and consumptions, on utilizing limited historical data and the behavior of the load’s consumption, and on conducting shallow forecasting models. However, little scientific proof on complex DL models or real-life application has been conducted by researchers; few articles have studied sophisticated large-scale prediction models for Saudi grids. This paper proposes hybrid DL methods to enhance the outcomes in Saudi SG load forecasting, to improve problem-relevant features, and to accurately predict complicated power consumption, with the goal of developing reliable forecasting models and of obtaining knowledge of the relationships between the various features and attributes in the Saudi SGs. The model in this paper utilizes a real dataset from the Jeddah and Medinah grids in Saudi Arabia for a full year, 2021, with a one-hour time resolution. A benchmark strategy using different conventional DL methods including artificial neural network, recurrent neural network (RNN), conventional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and different real datasets is used to verify the proposed models. The prediction results demonstrate the effectiveness of the proposed hybrid DL models, with CNN–GRU and CNN–RNN with NRMSE obtaining 1.4673% and 1.222% improvements, respectively, in load forecasting accuracy.
39
Tran Quang, Duy, i Sang Hoon Bae. "A Hybrid Deep Convolutional Neural Network Approach for Predicting the Traffic Congestion Index". Promet - Traffic&Transportation 33, nr 3 (31.05.2021): 373–85. http://dx.doi.org/10.7307/ptt.v33i3.3657.
Pełny tekst źródłaStreszczenie:
Traffic congestion is one of the most important issues in large cities, and the overall travel speed is an important factor that reflects the traffic status on road networks. This study proposes a hybrid deep convolutional neural network (CNN) method that uses gradient descent optimization algorithms and pooling operations for predicting the short-term traffic congestion index in urban networks based on probe vehicles. First, the input data are collected by the probe vehicles to calculate the traffic congestion index (output label). Then, a CNN that uses gradient descent optimization algorithms and pooling operations is applied to enhance its performance. Finally, the proposed model is chosen on the basis of the R-squared (R2) and root mean square error (RMSE) values. In the best-case scenario, the proposed model achieved an R2 value of 98.7%. In addition, the experiments showed that the proposed model significantly outperforms other algorithms, namely the ordinary least squares (OLS), k-nearest neighbors (KNN), random forest (RF), recurrent neural network (RNN), artificial neural network (ANN), and convolutional long short-term memory (ConvLSTM), in predicting traffic congestion index. Furthermore, using the proposed method, the time-series changes in the traffic congestion status can be reliably visualized for the entire urban network.
40
Hong, Taekeun, Jin-A. Choi, Kiho Lim i Pankoo Kim. "Enhancing Personalized Ads Using Interest Category Classification of SNS Users Based on Deep Neural Networks". Sensors 21, nr 1 (30.12.2020): 199. http://dx.doi.org/10.3390/s21010199.
Pełny tekst źródłaStreszczenie:
The classification and recommendation system for identifying social networking site (SNS) users’ interests plays a critical role in various industries, particularly advertising. Personalized advertisements help brands stand out from the clutter of online advertisements while enhancing relevance to consumers to generate favorable responses. Although most user interest classification studies have focused on textual data, the combined analysis of images and texts on user-generated posts can more precisely predict a consumer’s interests. Therefore, this research classifies SNS users’ interests by utilizing both texts and images. Consumers’ interests were defined using the Curlie directory, and various convolutional neural network (CNN)-based models and recurrent neural network (RNN)-based models were tested for our user interest classification system. In our hybrid neural network (NN) model, CNN-based classification models were used to classify images from users’ SNS postings while RNN-based classification models were used to classify textual data. The results of our extensive experiments show that the classification of users’ interests performed best when using texts and images together, at 96.55%, versus texts only, 41.38%, or images only, 93.1%. Our proposed system provides insights into personalized SNS advertising research and informs marketers on making (1) interest-based recommendations, (2) ranked-order recommendations, and (3) real-time recommendations.
41
Rajagukguk, Rial A., Raden A. A. Ramadhan i Hyun-Jin Lee. "A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power". Energies 13, nr 24 (15.12.2020): 6623. http://dx.doi.org/10.3390/en13246623.
Pełny tekst źródłaStreszczenie:
Presently, deep learning models are an alternative solution for predicting solar energy because of their accuracy. The present study reviews deep learning models for handling time-series data to predict solar irradiance and photovoltaic (PV) power. We selected three standalone models and one hybrid model for the discussion, namely, recurrent neural network (RNN), long short-term memory (LSTM), gated recurrent unit (GRU), and convolutional neural network-LSTM (CNN–LSTM). The selected models were compared based on the accuracy, input data, forecasting horizon, type of season and weather, and training time. The performance analysis shows that these models have their strengths and limitations in different conditions. Generally, for standalone models, LSTM shows the best performance regarding the root-mean-square error evaluation metric (RMSE). On the other hand, the hybrid model (CNN–LSTM) outperforms the three standalone models, although it requires longer training data time. The most significant finding is that the deep learning models of interest are more suitable for predicting solar irradiance and PV power than other conventional machine learning models. Additionally, we recommend using the relative RMSE as the representative evaluation metric to facilitate accuracy comparison between studies.
42
Selvarani, Renjith Vijayakumar, i Paul Subha Hency Jose. "A Label-Free Marker Based Breast Cancer Detection using Hybrid Deep Learning Models and Raman Spectroscopy". Trends in Sciences 20, nr 4 (22.01.2023): 6299. http://dx.doi.org/10.48048/tis.2023.6299.
Pełny tekst źródłaStreszczenie:
Breast Cancer (BC) is a serious menace to women’s health around the world. Early BC identification has been critically important for diagnosing protocol. Several classification methods for breast cancer were examined recently with various techniques, and Raman spectroscopy (RS) has become an effective approach for the identification of responsible metabolites. Moreover, the rapid and accurate classification of BC using RS necessitates active engagement in processing and analyzing Raman spectral data. This work aims to develop an efficient Hybrid Deep Learning (HDL) neural network model to differentiate breast cancer blood plasma from control samples and the spectral features obtained are used as spectral cancer markers for the detection of breast cancer. To find the optimum performing HDL model, several other HDL models were implemented to perform the binary classification of the Raman spectral signal. A total of 62199 Raman spectra generated from 26 blood plasma samples are evaluated in this study. Mainly 6 HDL methods, 1D-CNN-GRU, CNN-BiLSTM-AT, 1D-CNN-LSTM, GRU-LSTM, RNN-LSTM, and OGRU-LSTM are modeled to evaluate the performance of hybrid models to identify 2 classes of Raman spectral data. Comparative classification results show that the stacked 1D-CNN-GRU model outperforms well for breast cancer detection using the Raman spectral dataset than other prominent HDL architectures. The stacked 1D-CNN-GRUclassifier model achieved the highest classification accuracy (98.90 %), Cohen-kappa score (0.941), F1-score (0.969), and the lowermost number of test loss as 0.102776 and MSE (0.0230) indicating that the model outperforms other HDL classifiers. HIGHLIGHTS The potential of Raman spectroscopy in combination with hybrid deep learning (HDL) models to diagnose and classify cancerous or noncancerous samples, specifically blood plasma samples, based on chemical composition The implementation of data augmentation techniques to address underfitting and overfitting issues occur in the classification of spectral samples due to a lack of sufficient Raman spectral data The development of an efficient Hybrid Deep Learning (HDL) neural network model to differentiate breast cancer blood plasma from control samples and the use of spectral features as spectral cancer markers for breast cancer detection The evaluation of several HDL models for binary classification of Raman spectral signals, with the stacked 1D-CNN-GRU model achieving the highest classification accuracy and the lowest test losses The potential for this technique is to accurately classify breast cancerous samples and reduce the number of unnecessary excisional breast biopsies GRAPHICAL ABSTRACT
43
Chung, Jaewon, i Beakcheol Jang. "Accurate prediction of electricity consumption using a hybrid CNN-LSTM model based on multivariable data". PLOS ONE 17, nr 11 (23.11.2022): e0278071. http://dx.doi.org/10.1371/journal.pone.0278071.
Pełny tekst źródłaStreszczenie:
The stress placed on global power supply systems by the growing demand for electricity has been steadily increasing in recent years. Thus, accurate forecasting of energy demand and consumption is essential to maintain the lifestyle and economic standards of nations sustainably. However, multiple factors, including climate change, affect the energy demands of local, national, and global power grids. Therefore, effective analysis of multivariable data is required for the accurate estimation of energy demand and consumption. In this context, some studies have suggested that LSTM and CNN models can be used to model electricity demand accurately. However, existing works have utilized training based on either electricity loads and weather observations or national metrics e.g., gross domestic product, imports, and exports. This binary segregation has degraded forecasting performance. To resolve this shortcoming, we propose a CNN-LSTM model based on a multivariable augmentation approach. Based on previous studies, we adopt 1D convolution and pooling to extract undiscovered features from temporal sequences. LSTM outperforms RNN on vanishing gradient problems while retaining its benefits regarding time-series variables. The proposed model exhibits near-perfect forecasting of electricity consumption, outperforming existing models. Further, state-level analysis and training are performed, demonstrating the utility of the proposed methodology in forecasting regional energy consumption. The proposed model outperforms other models in most areas.
44
Geng, Boting. "Open Relation Extraction in Patent Claims with a Hybrid Network". Wireless Communications and Mobile Computing 2021 (28.04.2021): 1–7. http://dx.doi.org/10.1155/2021/5547281.
Pełny tekst źródłaStreszczenie:
Research on relation extraction from patent documents, a high-priority topic of natural language process in recent years, is of great significance to a series of patent downstream applications, such as patent content mining, patent retrieval, and patent knowledge base constructions. Due to lengthy sentences, crossdomain technical terms, and complex structure of patent claims, it is extremely difficult to extract open triples with traditional methods of Natural Language Processing (NLP) parsers. In this paper, we propose an Open Relation Extraction (ORE) approach with transforming relation extraction problem into sequence labeling problem in patent claims, which extract none predefined relationship triples from patent claims with a hybrid neural network architecture based on multihead attention mechanism. The hybrid neural network framework combined with Bi-LSTM and CNN is proposed to extract argument phrase features and relation phrase features simultaneously. The Bi-LSTM network gains long distance dependency features, and the CNN obtains local content feature; then, multihead attention mechanism is applied to get potential dependency relationship for time series of RNN model; the result of neural network proposed above applied to our constructed open patent relation dataset shows that our method outperforms both traditional classification algorithms of machine learning and the-state-of-art neural network classification models in the measures of Precision, Recall, and F1.
45
Al Duhayyim, Mesfer, Hanan Abdullah Mengash, Radwa Marzouk, Mohamed K. Nour, Hany Mahgoub, Fahd Althukair i Abdullah Mohamed. "Hybrid Rider Optimization with Deep Learning Driven Biomedical Liver Cancer Detection and Classification". Computational Intelligence and Neuroscience 2022 (30.06.2022): 1–11. http://dx.doi.org/10.1155/2022/6162445.
Pełny tekst źródłaStreszczenie:
Biomedical engineering is the application of the principles and problem-solving methods of engineering to biology along with medicine. Computation intelligence is the study of design of intelligent agents which are systems acting perceptively. The computation intelligence paradigm offers more advantages to the enhancement and maintenance of the field of biomedical engineering. Liver cancer is the major reason of mortality worldwide. Earlier-stage diagnosis and treatment might increase the survival rate of liver cancer patients. Manual recognition of the cancer tissue is a time-consuming and difficult task. Hence, a computer-aided diagnosis (CAD) is employed in decision making procedures for accurate diagnosis and effective treatment. In contrast to classical image-dependent “semantic” feature evaluation from human expertise, deep learning techniques could learn feature representation automatically from sample images using convolutional neural network (CNN). This study introduces a Hybrid Rider Optimization with Deep Learning Driven Biomedical Liver Cancer Detection and Classification (HRO-DLBLCC) model. The proposed HRO-DLBLCC model majorly focuses on the identification of liver cancer in the medical images. To do so, the proposed HRO-DLBLCC model employs preprocessing in two stages, namely, Gabor filtering (GF) based noise removal and watershed transform based segmentation. In addition, the proposed HRO-DLBLCC model involves NAdam optimizer with DenseNet-201 based feature extractor to generate an optimal set of feature vectors. Finally, the HRO algorithm with recurrent neural network–long short-term memory (RNN-LSTM) model is applied for liver cancer classification, in which the hyperparameters of the RNN-LSTM model are tuned by the use of HRO algorithm. The HRO-DLBLCC model is experimentally validated and compared with existing models. The experimental results assured the promising performance of the HRO-DLBLCC model over recent approaches.
46
Song, Fuquan, Heying Ding, Yongzheng Wang, Shiming Zhang i Jinbiao Yu. "A Well Production Prediction Method of Tight Reservoirs Based on a Hybrid Neural Network". Energies 16, nr 6 (21.03.2023): 2904. http://dx.doi.org/10.3390/en16062904.
Pełny tekst źródłaStreszczenie:
Tight reservoirs have poor physical properties: low permeability and strong heterogeneity, which makes it difficult to predict productivity. Accurate prediction of oil well production plays a very important role in the exploration and development of oil and gas reservoirs, and improving the accuracy of production prediction has always been a key issue in reservoir characterization. With the development of artificial intelligence, high-performance algorithms make reliable production prediction possible from the perspective of data. Due to the high cost and large error of traditional seepage theory formulas in predicting oil well production, this paper establishes a horizontal well productivity prediction model based on a hybrid neural network method (CNN-LSTM), which solves the limitations of traditional methods and produces accurate predictions of horizontal wells’ daily oil production. In order to prove the effectiveness of the model, compared with the prediction results of BPNN, RBF, RNN and LSTM, it is concluded that the error results of the CNN-LSTM prediction model are 67%, 60%, 51.3% and 28% less than those of the four models, respectively, and the determination coefficient exceeds 0.95. The results show that the prediction model based on a hybrid neural network can accurately reflect the dynamic change law of production, which marks this study as a preliminary attempt of the application of this neural network method in petroleum engineering, and also provides a new method for the application of artificial intelligence in oil and gas field development.
47
Altalak, Maha, Mohammad Ammad uddin, Amal Alajmi i Alwaseemah Rizg. "Smart Agriculture Applications Using Deep Learning Technologies: A Survey". Applied Sciences 12, nr 12 (10.06.2022): 5919. http://dx.doi.org/10.3390/app12125919.
Pełny tekst źródłaStreszczenie:
Agriculture is considered an important field with a significant economic impact in several countries. Due to the substantial population growth, meeting people’s dietary needs has become a relevant concern. The transition to smart agriculture has become inevitable to achieve these food security goals. In recent years, deep learning techniques, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), have been intensely researched and applied in various fields, including agriculture. This study analyzed the recent research articles on deep learning techniques in agriculture over the previous five years and discussed the most important contributions and the challenges that have been solved. Furthermore, we investigated the agriculture parameters being monitored by the internet of things and used them to feed the deep learning algorithm for analysis. Additionally, we compared different studies regarding focused agriculture area, problems solved, the dataset used, the deep learning model used, the framework used, data preprocessing and augmentation method, and results with accuracy. We concluded in this survey that although CNN provides better results, it lacks in early detection of plant diseases. To cope with this issue, we proposed an intelligent agriculture system based on a hybrid model of CNN and SVM, capable of detecting and classifying plant leaves disease early.
48
Lee, Chien-Hsing, Phuong Nguyen Thanh, Chao-Tsung Yeh i Ming-Yuan Cho. "Three-Phase Load Prediction-Based Hybrid Convolution Neural Network Combined Bidirectional Long Short-Term Memory in Solar Power Plant". International Transactions on Electrical Energy Systems 2022 (16.09.2022): 1–15. http://dx.doi.org/10.1155/2022/2870668.
Pełny tekst źródłaStreszczenie:
The economic renewable energy generations have been rapidly developed because of the sharp reduction in the costs of solar panels. It is imperative to forecast the three-phase load power for more effective energy planning and optimization in a smart solar microgrid installed on a building in the Linyuan District, Taiwan. To alleviate this problem, this article proposes a convolution neural network bidirectional long short-term memory (CNN-Bi-LSTM) to accurately predict the short-term three-phase load power in building the energy management system in the smart solar microgrid with the collected data from advanced metering infrastructure (AMI), which have not been investigated before. The three-phase load-predicting methodology is developed using weather parameters and different collected data from AMI. The project evaluates the performance of the CNN-Bi-LSTM model by utilizing hyper-parameter optimization to attain the optimum parameters. The prediction models are trained based on hourly historical input features, selected based on the Pearson correlation coefficient. The performances’ optimal structure CNN-Bi-LSTM are validated and compared with the bidirectional LSTM (Bi-LSTM), LSTM, the Gated Recurrent Unit (GRU), and the recurrent neural network (RNN) models. The obtained optimized structure of CNN-Bi-LSTM demonstrates the effectiveness of the proposed models in the short-term prediction of three-phase load power in a smart solar microgrid for building with a maximum enhancement of 68.36% and 8.81% average MSE, and 30.26% and 36.36% average MAE during the testing and validating operations.
49
Jishan, Md Asifuzzaman, Khan Raqib Mahmud, Abul Kalam Al Azad, Md Shahabub Alam i Anif Minhaz Khan. "Hybrid deep neural network for Bangla automated image descriptor". International Journal of Advances in Intelligent Informatics 6, nr 2 (12.07.2020): 109. http://dx.doi.org/10.26555/ijain.v6i2.499.
Pełny tekst źródłaStreszczenie:
Automated image to text generation is a computationally challenging computer vision task which requires sufficient comprehension of both syntactic and semantic meaning of an image to generate a meaningful description. Until recent times, it has been studied to a limited scope due to the lack of visual-descriptor dataset and functional models to capture intrinsic complexities involving features of an image. In this study, a novel dataset was constructed by generating Bangla textual descriptor from visual input, called Bangla Natural Language Image to Text (BNLIT), incorporating 100 classes with annotation. A deep neural network-based image captioning model was proposed to generate image description. The model employs Convolutional Neural Network (CNN) to classify the whole dataset, while Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) capture the sequential semantic representation of text-based sentences and generate pertinent description based on the modular complexities of an image. When tested on the new dataset, the model accomplishes significant enhancement of centrality execution for image semantic recovery assignment. For the experiment of that task, we implemented a hybrid image captioning model, which achieved a remarkable result for a new self-made dataset, and that task was new for the Bangladesh perspective. In brief, the model provided benchmark precision in the characteristic Bangla syntax reconstruction and comprehensive numerical analysis of the model execution results on the dataset.
50
Khortsriwong, Nonthawat, Promphak Boonraksa, Terapong Boonraksa, Thipwan Fangsuwannarak, Asada Boonsrirat, Watcharakorn Pinthurat i Boonruang Marungsri. "Performance of Deep Learning Techniques for Forecasting PV Power Generation: A Case Study on a 1.5 MWp Floating PV Power Plant". Energies 16, nr 5 (22.02.2023): 2119. http://dx.doi.org/10.3390/en16052119.
Pełny tekst źródłaStreszczenie:
Recently, deep learning techniques have become popular and are widely employed in several research areas, such as optimization, pattern recognition, object identification, and forecasting, due to the advanced development of computer programming technologies. A significant number of renewable energy sources (RESs) as environmentally friendly sources, especially solar photovoltaic (PV) sources, have been integrated into modern power systems. However, the PV source is highly fluctuating and difficult to predict accurately for short-term PV output power generation, leading to ineffective system planning and affecting energy security. Compared to conventional predictive approaches, such as linear regression, predictive-based deep learning methods are promising in predicting short-term PV power generation with high accuracy. This paper investigates the performance of several well-known deep learning techniques to forecast short-term PV power generation in the real-site floating PV power plant of 1.5 MWp capacity at Suranaree University of Technology Hospital, Thailand. The considered deep learning techniques include single models (RNN, CNN, LSTM, GRU, BiLSTM, and BiGRU) and hybrid models (CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU). Five-minute resolution data from the real floating PV power plant is used to train and test the deep learning models. Accuracy indices of MAE, MAPE, and RMSE are applied to quantify errors between actual and forecasted values obtained from the different deep learning techniques. The obtained results show that, with the same training dataset, the performance of the deep learning models differs when testing under different weather conditions and time horizons. The CNN-BiGRU model offers the best performance for one-day PV forecasting, while the BiLSTM model is the most preferable for one-week PV forecasting.