In the present work, a novel methodology for error detection in automatic weather stations has been implemented. Time series acquired from two highly correlated stations with a station under analysis are utilised to o...
详细信息
In the present work, a novel methodology for error detection in automatic weather stations has been implemented. Time series acquired from two highly correlated stations with a station under analysis are utilised to obtain a 24-h air temperature forecast that allows to know if a station register erroneous measurements. Four models to obtain a reliable forecast have been analysed, auto-regressive integrated moving average, Long Short-Term Memory (LSTM), LSTM stacked and a convolutional LSTM model with uncertainty error reduction. The analysis carried out exhibits a significant success with the methodology for three stations reaching error values between 0.98 degrees C and 1.50 degrees C and correlation coefficients between 0.72 and 0.81.
This paper proposes MP-SENet, a novel Speech Enhancement Network which directly denoises Magnitude and Phase spectra in parallel. The proposed MP-SENet adopts a codec architecture in which the encoder and decoder are ...
详细信息
This paper proposes MP-SENet, a novel Speech Enhancement Network which directly denoises Magnitude and Phase spectra in parallel. The proposed MP-SENet adopts a codec architecture in which the encoder and decoder are bridged by convolution-augmented transformers. The encoder aims to encode time-frequency representations from the input noisy magnitude and phase spectra. The decoder is composed of parallel magnitude mask decoder and phase decoder, directly recovering clean magnitude spectra and clean-wrapped phase spectra by incorporating learnable sigmoid activation and parallel phase estimation architecture, respectively. Multi-level losses defined on magnitude spectra, phase spectra, short-time complex spectra, and time-domain waveforms are used to train the MP-SENet model jointly. Experimental results show that our proposed MP-SENet achieves a PESQ of 3.50 on the public VoiceBank+DEMAND dataset and outperforms existing advanced speech enhancement methods.
Due to the absorption and scattering effects of light in water bodies and the non-uniformity and insufficiency of artificial illumination, underwater images often present various degradation problems, impacting their ...
详细信息
Due to the absorption and scattering effects of light in water bodies and the non-uniformity and insufficiency of artificial illumination, underwater images often present various degradation problems, impacting their utility in underwater applications. In this paper, we propose a model-based underwater image simulation and learning-based underwater image enhancement method for coping with various degradation problems in underwater images. We first derive a simplified model for describing various degradation problems in underwater images, then propose a model-based image simulation method that can generate images with a wide range of parameter values. The proposed image simulation method also comes with an image-selection part, which helps to prune the simulation dataset so that it can serve as a training set for learning to enhance the targeted underwater images. Afterwards, we propose a convolutional neural network based on the encoder-decoder backbone to learn to enhance various underwater images from the simulated images. Experiments on simulated and real underwater images with different degradation problems demonstrate the effectiveness of the proposed underwater image simulation and enhancement method, and reveal the advantages of the proposed method in comparison with many state-of-the-art methods.
Representing the network loading in an appropriate manner to obtain a reliable forecast has been a challenging task for researchers. This study aims to determine the most effective data resampling strategy for enhanci...
详细信息
ISBN:
(纸本)9798350390438;9798350390421
Representing the network loading in an appropriate manner to obtain a reliable forecast has been a challenging task for researchers. This study aims to determine the most effective data resampling strategy for enhancing the accuracy of long-term electrical load forecasting using Long-Short Term Memory (LSTM) neural networks, focusing on a dataset with half-hourly measurements from a real UK grid supply point. Given the excessive granularity for long-term forecasting, it was explored to resample the data to a daily scale, evaluating four methods for aggregating active and reactive power, namely maximum active load and maximum absolute reactive load, maximum load with coincident reactive load, mean load with coincident reactive load, and modal (most probable) load with coincident reactive load. These methods were tested under three scenarios: a standard LSTM with varying architectures, a smoothed dataset using a novel uncertainty boundary approach, and a sequence-to-sequence encoder-decoder model. Performance was assessed using mean absolute percentage error ( MAPE). Results indicate that smoothing techniques coupled with maximum daily active power and hour-matched reactive power resampling significantly enhance forecast accuracy by reducing the influence of noise and outliers.
Since Hyperspectral images (HSIs) contain a large amount of spectral information, they can provide detailed spectral information and enable accurate CD. However, the spectral heterogeneity of HSIs may lead to false al...
详细信息
ISBN:
(纸本)9781510661196;9781510661202
Since Hyperspectral images (HSIs) contain a large amount of spectral information, they can provide detailed spectral information and enable accurate CD. However, the spectral heterogeneity of HSIs may lead to false alarms which will reduce detection accuracy. Additionally, it is difficult to collect and annotate pixel-level labels for CD in HSIs. Therefore, we propose an unsupervised symmetric tensor network (USTN) for HSIs CD. We design a novel multidimensional symmetric tensor framework to solve the problem of high-dimensional data processing. Furthermore, the framework integrates a spatial edge loss to preserve detailed spectral-spatial information. Finally, we use feature fusion to suppress the invariant components (i.e., the background) and highlight the variant components (i.e., temporal changes). Experiments on two sets of multitemporal HSIs, Hermiston and Bay Area, demonstrate the effectiveness of USTN for binary change detection.
Plant organ phenotyping represents a powerful tool to investigate the effects of biotic and abiotic factors on plant growth and development. Phenotyping typically involves the initial capture of high-resolution images...
详细信息
ISBN:
(纸本)9798350397871
Plant organ phenotyping represents a powerful tool to investigate the effects of biotic and abiotic factors on plant growth and development. Phenotyping typically involves the initial capture of high-resolution images of the plant of interest and the subsequent measurement of different morphometric parameters of specific plant organs. This second step is typically very time consuming and difficult to automate. To deal with this bottleneck, we developed a multi-class segmentation model based on U-shape network to identify hypocotyls and roots of young seedlings of the reference plant Arabidopsis thaliana. We applied a balanced cross entropy loss function to learn an alternative optimal network structure for this multi-class segmentation task. We evaluated our segmentation machine using 66 images of the wild-type Arabidopsis strain Col-0, as well as 34 images of the highly agravitropic and morphologically distinct mutant strain, aux1-7. Our model achieved a mean BFscore of 0.81 for Col-0 seedlings and 0.75 for aux1-7 mutant seedlings on the test dataset. Our model was also able to maintain accuracy in these two morphologically different genotypes suggesting that our segmentation procedure could be successfully applied to Arabidopsis seedlings showing broad morphological differences due to their genotype or treatment conditions. Appropriate segmentation is the first step in identifying phenotypic changes under hormone-mediated stress response. The identified growth parameters will be useful to identify the response associated with both abiotic and biotic stresses, which include but not limited to drought stress, heat stress, and the presence of pests or pathogens. The quantification of these parameters will aid assessment of genetic factors that contribute to the stress response.
Accurate service demand forecasting is crucial towards achieving effective resource allocation and service orchestration. However, existing solutions require separate prediction models for each service, which consumes...
详细信息
ISBN:
(纸本)9798350322392
Accurate service demand forecasting is crucial towards achieving effective resource allocation and service orchestration. However, existing solutions require separate prediction models for each service, which consumes significant computation resources. In this paper, we propose a novel approach that introduces a global prediction model capable of generating accurate multi-step predictions involving multiple services and that can potentially leveraged for facilitating proactive strategies for orchestrating multiple services. The proposed model is based on an encoder-decoder architecture that utilizes Graph Neural Networks (GNNs) to capture interdependencies among input variables and their trends. By iteratively updating graph node representations, our model effectively incorporates historical trends and potential dependencies. Furthermore, the incorporation of GNNs into the encoder-decoder architecture enables the proposed approach to leverage the correlations among input variables, thus making it suitable for multivariate forecasting. Experimental results demonstrate the superiority of the proposed approach in terms of accurately conducting multi-step multiservice demand predictions, when compared against numerous contemporary deep learning models.
Network traffic prediction plays a significant role in network management. Previous network traffic prediction methods mainly focus on the temporal relationship between network traffic, and used time series models to ...
详细信息
ISBN:
(纸本)9781665476409
Network traffic prediction plays a significant role in network management. Previous network traffic prediction methods mainly focus on the temporal relationship between network traffic, and used time series models to predict network traffic, ignoring the spatial information contained in traffic data. Therefore, the prediction accuracy is limited, especially in long-term prediction. To improve the prediction accuracy of the dynamic network traffic in the long term, we propose an Attention-based Spatial-Temporal Graph Network (ASTGN) model for network traffic prediction to better capture both the temporal and spatial relations between the network traffic. Specifically, in ASTGN, we exploit an encoder-decoder architecture, where the encoder encodes the input network traffic and the decoder outputs the predicted network traffic sequences, integrating the temporal and spatial information of the network traffic data through the Spatio-Temporal Embedding module. The experimental results demonstrate the superiority of our proposed method ASTGN in long-term prediction.
This study proposes a generic approach which performs a series of systematic analyses by first introducing a data volume decomposition method to generate useful data features for performing semantic segmentation analy...
详细信息
This study proposes a generic approach which performs a series of systematic analyses by first introducing a data volume decomposition method to generate useful data features for performing semantic segmentation analysis involving 3D point-cloud data. Pipeline parallelism protocol is then implemented to accelerate the deep learning model's training phase. Our proposed approach is verified by decomposing around 2.0 billion point-cloud data points, as extracted from an open-source Semantic3D dataset, into many 3D regular structures with defined numbers of voxels. Each derived 3D structure has imposed normality in their data distribution of the respective label classes. Using the optimal hyperparameters for model training, the resulting trained model achieves average overall accuracy (mOA) and average intersection over union (mIOU) values of 0.984 and 0.752, respectively, on a testing dataset having close to 800 million point-cloud data points. The results are comparable with that of other state-of-the-art models in the literature.
In this paper, we proposed an innovative encoder-decoder structure with a convolution long short-term memory (ED-ConvLSTM) network to forecast global total electron content (TEC) based on the International GNSS Servic...
详细信息
In this paper, we proposed an innovative encoder-decoder structure with a convolution long short-term memory (ED-ConvLSTM) network to forecast global total electron content (TEC) based on the International GNSS Service (IGS) TEC maps from 2005 to 2018 with 1-hr time cadence. The ED-ConvLSTM model is used to forecast TEC maps 1-7 days in advance through iterations. To investigate the model's performance, we compared the model with International Reference Ionosphere (IRI2016) model in 2014 and 2018, and compared the model with 1-day Beijing University of Aeronautics and Astronautics (BUAA) model in 2018. The results show that our 7-day ED-ConvLSTM model (ED-ConvLSTM model that forecasts 7 days in advance) outperforms IRI2016 in 2014 and 2018, and our 5-day ED-ConvLSTM model (ED-ConvLSTM model that forecasts 5 days in advance) outperforms 1-day BUAA model. Furthermore, the root mean square error (RMSE) from the 1-day ED-ConvLSTM model with respect to the IGS TEC maps decreases by 51.5% and 43%, respectively, in 2014 and 2018 compared with that from IRI2016 model. The RMSE from the 1-day ED-ConvLSTM model is 20.3% lower than that from the 1-day BUAA model in 2018. In addition, our model has the highest RMSE in the Equatorial Ionospheric Anomaly (EIA) region, but can roughly predict the features and locations of EIA. However, the model fails to forecast localized TEC enhancement and the sudden ionospheric response to the geomagnetic storms. Overall, the model shows competitive performance in medium-term global TEC maps prediction during geomagnetic quiet periods.
暂无评论