Assessing Neural Network Approaches for Solar Radiation Estimates Using Limited Climatic Data in the Mediterranean Sea

Bellido-Jiménez, Juan Antonio; Estévez, Javier; García‐Marín, A. P.

doi:10.3390/ecas2020-08116

Cited by 5 publications

(6 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the study's limitations include the need for training data and the lack of validation on real-world applications. Later, other researchers focused on improving solar radiation estimation models in agriculture meteorology due to limited data availability and low data quality [20]. Several neural network models (SVM, Extreme Learning Machine, CNN, and LSTM) were developed and tested in Southern Spain using different input variable configurations.…”

Section: Related Workmentioning

confidence: 99%

“…The dataset used in this study was obtained from a previous researcher's online database [22]. The dataset consisted of EEG recordings from 12 healthy male participants (19)(20)(21)(22)(23)(24) who completed a driving simulator task for up to 2 hours. EEG data from eight specific channels (O1, O2, Fp1, Fp2, P3, P4, F3, and F4) were selected from a Neuroscan device that had 30 electrodes and operated at a sampling rate of 1000 Hz.…”

Section: Data Acquisitionmentioning

confidence: 99%

See 1 more Smart Citation

A Robust Framework for Driver Fatigue Detection From Eeg Signals Using Enhancement of Modified Z-Score and Multiple Machine Learning Architectures

Abdubrani

Mustafa

Zahari

2023

IIUMEJ

View full text Add to dashboard Cite

Physiological signals, such as electroencephalogram (EEG), are used to observe a driver’s brain activities. A portable EEG system provides several advantages, including ease of operation, cost-effectiveness, portability, and few physical restrictions. However, it can be challenging to analyse EEG signals as they often contain various artefacts, including muscle activities, eye blinking, and unwanted noises. This study utilised an independent component analysis (ICA) approach to eliminate such unwanted signals from the unprocessed EEG data of 12 young, physically fit male participants between the ages of 19 and 24 who took part in a driving simulation. Furthermore, driver fatigue state detection was carried out using multichannel EEG signals obtained from O1, O2, Fp1, Fp2, P3, P4, F3, and F4. An enhanced modified z-score was utilised with features extracted from a time-frequency domain continuous wavelet transform (CWT) to elevate the reliability of driver fatigue classification. The proposed methodology offers several advantages. First, multichannel EEG analysis improves the accuracy of sleep stage detection, which is vital for accurate driver fatigue detection. Second, an enhanced modified z-score in feature extraction is more robust than conventional z-score techniques, making it more effective for removing outlier values and improving classification accuracy. Third, the proposed approach for detecting driver fatigue employs multiple machine learning classifiers, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Artificial Neural Networks (ANNs) that utilise Long Short-Term Memory (LSTM), and also machine learning techniques like Support Vector Machines (SVM). The evaluation of five classifiers was performed through 5-fold cross-validation. The outcomes indicate that the suggested framework attains exceptional precision in identifying driver fatigue, with an average accuracy rate of 96.07%. Among the classifiers, the ANN classifier achieved the most significant precision of 99.65%, and the SVM classifier ranked second with an accuracy of 97.89%. Based on the results of the receiver operating characteristic (ROC) and area under the curve (AUC) analysis, it was observed that all the classifiers had an outstanding performance, with an average AUC value of 0.95. This study’s contribution lies in presenting a comprehensive and effective framework that can accurately detect driver fatigue from EEG signals. ABSTRAK: Isyarat fisiologi, seperti elektroencefalogram (EEG), digunakan bagi memerhati aktiviti otak pemandu. Sistem EEG mudah alih menyediakan beberapa kelebihan, termasuk kemudahan operasi, keberkesanan kos, mudah alih dan sedikit sekatan fizikal. Namun, isyarat EEG mungkin sukar dianalisis kerana ia sering mengandungi pelbagai artifak, termasuk aktiviti otot, mata berkedip dan bunyi yang tidak diingini. Kajian ini menggunakan pendekatan analisis komponen bebas (ICA) bagi membuang isyarat tidak diperlukan daripada data EEG yang belum diproses daripada 12 peserta lelaki muda, cergas fizikal berumur 19 hingga 24 tahun yang mengambil bahagian dalam simulasi pemanduan. Tambahan, pengesanan keadaan lesu pemandu telah dijalankan menggunakan isyarat EEG berbilang saluran yang diperoleh dari O1, O2, Fp1, Fp2, P3, P4, F3, dan F4. Penambah baik skor z digunakan dengan ciri diekstrak daripada transformasi wavelet berterusan (CWT) domain frekuensi masa bagi meningkatkan kebolehpercayaan klasifikasi keletihan pemandu. Metodologi yang dicadangkan menawarkan beberapa kelebihan. Pertama, analisis EEG berbilang saluran meningkatkan ketepatan pengesanan peringkat tidur, penting bagi pengesanan keletihan pemandu secara tepat. Kedua, penambah baik skor z dalam pengekstrak ciri adalah lebih teguh daripada teknik skor z konvensional, menjadikannya lebih berkesan bagi membuang unsur luaran dan meningkatkan ketepatan pengelasan. Ketiga, pendekatan yang dicadangkan bagi mengesan keletihan pemandu menggunakan pelbagai pengelas pembelajaran mesin, seperti Rangkaian Neural Konvolusi (CNN), Rangkaian Neural Berulang (RNN), Rangkaian Neural Buatan (ANN) yang menggunakan Memori Jangka Pendek Panjang (LSTM), dan juga teknik pembelajaran mesin seperti Mesin Vektor Sokongan (SVM). Penilaian lima pengelas dilakukan melalui pengesahan silang 5 kali ganda. Dapatan kajian menunjukkan cadangan rangka kerja ini mencapai ketepatan yang luar biasa dalam mengenal pasti keletihan pemandu, dengan kadar ketepatan purata 96.07%. Antara kesemua pengelas, pengelas ANN mencapai ketepatan paling ketara sebanyak 99.65%, dan pengelas SVM menduduki tempat kedua dengan ketepatan 97.89%. Berdasarkan keputusan analisis ciri operasi penerima (ROC) dan kawasan di bawah lengkung (AUC), didapati semua pengelas mempunyai prestasi cemerlang, dengan purata nilai AUC 0.95. Sumbangan kajian ini adalah terletak pada rangka kerja yang komprehensif dan berkesan mengesan keletihan pemandu secara tepat melalui isyarat EEG.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Data Acquisitionmentioning

confidence: 99%

A Robust Framework for Driver Fatigue Detection From Eeg Signals Using Enhancement of Modified Z-Score and Multiple Machine Learning Architectures

Abdubrani

Mustafa

Zahari

2023

IIUMEJ

View full text Add to dashboard Cite

show abstract

“…Moreover, several temperature-based variables have been calculated, such as EnergyT (the area below the intraday temperature in a whole day), HourminTx (the time when Tx occurs), HourminTn (the time when Tn occurs), HourminSunset (the time when sunset occurs), HourminSunrise (the time when sunrise occurs), es (mean saturation vapor pressure), ea (actual vapor pressure) and VPD (vapor pressure deficit), Tx-Tn, HourminSunset-HourminTx, and HourminSunrise-HourminTn. All the configurations assessed in this work contained Tx, Tn, Tx-Tn, and Ra as features due to their very high Pearson correlation (Figure 2), and the rest of the configurations were selected based on their Pearson correlation values and the previous results on these same locations regarding ET 0 and solar radiation [24][25][26] estimations. The 27 different assessed configurations are shown in Table 3.…”

Section: Study Area and Datasetmentioning

confidence: 99%

“…Moreover, this process can be extrapolated to 1D sequences of data such as time series datasets. One of the advantages of using convolutions is that they can obtain local features' relationships without the requirement of an extensive preprocessing method and can obtain outstanding results in ET 0 [14,36,37] and in other agro-climatic parameters [25,38,39].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

AgroML: An Open-Source Repository to Forecast Reference Evapotranspiration in Different Geo-Climatic Conditions Using Machine Learning and Transformer-Based Models

et al. 2022

Self Cite

View full text Add to dashboard Cite

Accurately forecasting reference evapotranspiration (ET0) values is crucial to improve crop irrigation scheduling, allowing anticipated planning decisions and optimized water resource management and agricultural production. In this work, a recent state-of-the-art architecture has been adapted and deployed for multivariate input time series forecasting (transformers) using past values of ET0 and temperature-based parameters (28 input configurations) to forecast daily ET0 up to a week (1 to 7 days). Additionally, it has been compared to standard machine learning models such as multilayer perceptron (MLP), random forest (RF), support vector machine (SVM), extreme learning machine (ELM), convolutional neural network (CNN), long short-term memory (LSTM), and two baselines (historical monthly mean value and a moving average of the previous seven days) in five locations with different geo-climatic characteristics in the Andalusian region, Southern Spain. In general, machine learning models significantly outperformed the baselines. Furthermore, the accuracy dramatically dropped when forecasting ET0 for any horizon longer than three days. SVM, ELM, and RF using configurations I, III, IV, and IX outperformed, on average, the rest of the configurations in most cases. The best NSE values ranged from 0.934 in Córdoba to 0.869 in Tabernas, using SVM. The best RMSE, on average, ranged from 0.704 mm/day for Málaga to 0.883 mm/day for Conil using RF. In terms of MBE, most models and cases performed very accurately, with a total average performance of 0.011 mm/day. We found a relationship in performance regarding the aridity index and the distance to the sea. The higher the aridity index at inland locations, the better results were obtained in forecasts. On the other hand, for coastal sites, the higher the aridity index, the higher the error. Due to the good performance and the availability as an open-source repository of these models, they can be used to accurately forecast ET0 in different geo-climatic conditions, helping to increase efficiency in tasks of great agronomic importance, especially in areas with low rainfall or where water resources are limiting for the development of crops.

show abstract

“…In this study, Bayesian optimization was used, due to its high popularity in new automated machine learning (AML) models [44][45][46][47] and its good performance in [34,48]. It was first introduced by Wang et al [43] as an algorithm, based on the Bayes theorem, to search the minimum/maximum function.…”

Section: Bayesian Optimizationmentioning

confidence: 99%

Assessing Machine Learning Models for Gap Filling Daily Rainfall Series in a Semiarid Region of Spain

2021

Self Cite

View full text Add to dashboard Cite

The presence of missing data in hydrometeorological datasets is a common problem, usually due to sensor malfunction, deficiencies in records storage and transmission, or other recovery procedures issues. These missing values are the primary source of problems when analyzing and modeling their spatial and temporal variability. Thus, accurate gap-filling techniques for rainfall time series are necessary to have complete datasets, which is crucial in studying climate change evolution. In this work, several machine learning models have been assessed to gap-fill rainfall data, using different approaches and locations in the semiarid region of Andalusia (Southern Spain). Based on the obtained results, the use of neighbor data, located within a 50 km radius, highly outperformed the rest of the assessed approaches, with RMSE (root mean squared error) values up to 1.246 mm/day, MBE (mean bias error) values up to −0.001 mm/day, and R2 values up to 0.898. Besides, inland area results outperformed coastal area in most locations, arising the efficiency effects based on the distance to the sea (up to an improvement of 63.89% in terms of RMSE). Finally, machine learning (ML) models (especially MLP (multilayer perceptron)) notably outperformed simple linear regression estimations in the coastal sites, whereas in inland locations, the improvements were not such significant.

show abstract

Assessing Neural Network Approaches for Solar Radiation Estimates Using Limited Climatic Data in the Mediterranean Sea

Cited by 5 publications

References 49 publications

A Robust Framework for Driver Fatigue Detection From Eeg Signals Using Enhancement of Modified Z-Score and Multiple Machine Learning Architectures

A Robust Framework for Driver Fatigue Detection From Eeg Signals Using Enhancement of Modified Z-Score and Multiple Machine Learning Architectures

AgroML: An Open-Source Repository to Forecast Reference Evapotranspiration in Different Geo-Climatic Conditions Using Machine Learning and Transformer-Based Models

Assessing Machine Learning Models for Gap Filling Daily Rainfall Series in a Semiarid Region of Spain

Contact Info

Product

Resources

About