Due to industrialization and the rising demand for energy, global energy consumption has been rapidly increasing. Recent studies show that the biggest portion of energy is consumed in residential buildings, i.e., in E...
详细信息
Due to industrialization and the rising demand for energy, global energy consumption has been rapidly increasing. Recent studies show that the biggest portion of energy is consumed in residential buildings, i.e., in European Union countries up to 40% of the total energy is consumed by households. Most residential buildings and industrial zones are equipped with smart sensors such as metering electric sensors, that are inadequately utilized for better energy management. In this paper, we develop a hybrid convolutional neural network (CNN) with an long short-term memory autoencoder (LSTM-AE) model for future energy prediction in residential and commercial buildings. The central focus of this research work is to utilize the smart meters' data for energy forecasting in order to enable appropriate energy management in buildings. We performed extensive research using several deep learning-based forecasting models and proposed an optimal hybrid CNN with the LSTM-AE model. To the best of our knowledge, we are the first to incorporate the aforementioned models under the umbrella of a unified framework with some utility preprocessing. Initially, the CNN model extracts features from the input data, which are then fed to the LSTM-encoder to generate encoded sequences. The encoded sequences are decoded by another following LSTM-decoder to advance it to the final dense layer for energy prediction. The experimental results using different evaluation metrics show that the proposed hybrid model works well. Also, it records the smallest value for mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE) and mean absolute percentage error (MAPE) when compared to other state-of-the-art forecasting methods over the UCI residential building dataset. Furthermore, we conducted experiments on Korean commercial building data and the results indicate that our proposed hybrid model is a worthy contribution to energy forecasting.
Wrong-Way Driving (WWD) crashes are relatively rare but more likely to produce fatalities and severe injuries than other crashes. WWD crash segment prediction task is challenging due to its rare nature, and very few r...
详细信息
Wrong-Way Driving (WWD) crashes are relatively rare but more likely to produce fatalities and severe injuries than other crashes. WWD crash segment prediction task is challenging due to its rare nature, and very few roadway segments experience WWD events. WWD crashes involve complex interactions among roadway geometry, vehicle, environment, and drivers, and the effect of these complex interactions is not always observable and measurable. This study applied two advanced Machine Learning (ML) models to overcome the imbalanced dataset problem and identified local and global factors contributing to WWD crash segments. Five years (2015-2019) of WWD crash data from Florida state were used in this study for WWD model development. The first modeling approach applied four different hybrid data augmentation techniques to the training dataset before applying the XGBoost classification algorithm. In the second model, a rare event modeling approach using the autoencoder-based anomaly detection method was applied to the original data to identify WWD roadway segments. A third model was applied based on the statistical method to compare the performance of ML models in predicting the WWD segments. The performance comparison of the adopted models showed that the XGBoost model with the Adaptive Synthetic Sampling (ADASYN) method performed best in terms of precision and recall values compared to the autoencoder-based anomaly detection method. The best-performing model was used for the feature analysis with an interpretable machine-learning technique. The SHapley Additive exPlanations (SHAP) values showed that high-intensity developed land use, length of roadway, log of Annual Average Daily traffic (AADT), and lane width were positively associated with WWD roadway segments. The results of this study can be used to deploy WWD countermeasures effectively.
Flexibility is often a key determinant of protein function. To elucidate the link between their molecular structure and role in an organism, computational techniques such as molecular dynamics can be leveraged to char...
详细信息
Flexibility is often a key determinant of protein function. To elucidate the link between their molecular structure and role in an organism, computational techniques such as molecular dynamics can be leveraged to characterize their conformational space. Extensive sampling is, however, required to obtain reliable results, useful to rationalize experimental data or predict outcomes before experiments are carried out. We demonstrate that a generative neural network trained on protein structures produced by molecular simulation can be used to obtain new, plausible conformations complementing preexisting ones. To demonstrate this, we show that a trained neural network can be exploited in a protein-protein docking scenario to account for broad hinge motions taking place upon binding. Overall, this work shows that neural networks can be used as an exploratory tool for the study of molecular conformational space.
Community detection has long been a fascinating topic in complex networks since the community structure usually unveils valuable information of interest. The prevalence and evolution of deep learning and neural networ...
详细信息
Community detection has long been a fascinating topic in complex networks since the community structure usually unveils valuable information of interest. The prevalence and evolution of deep learning and neural networks have been pushing forward the advancement in various research fields and also provide us numerous useful and off the shelf techniques. In this paper, we put the cascaded stacked autoencoders and the unsupervised extreme learning machine (ELM) together in a two-level embedding process and propose a novel community detection algorithm. Extensive comparison experiments in circumstances of both synthetic and real-world networks manifest the advantages of the proposed algorithm. On one hand, it outperforms the k-means clustering in terms of the accuracy and stability thus benefiting from the determinate dimensions of the ELM block and the integration of sparsity restrictions. On the other hand, it endures smaller complexity than the spectral clustering method on account of the shrinkage in time spent on the eigenvalue decomposition procedure.
Faults in a power electronic component (inverter, converter, modules, etc.) can severely affect the reliability, efficiency, as well as the security of the entire power conversion system if not detected by early warni...
详细信息
Faults in a power electronic component (inverter, converter, modules, etc.) can severely affect the reliability, efficiency, as well as the security of the entire power conversion system if not detected by early warning. The inverters that are the most common power converters in the industry are widely used in power supplies, energy management systems, motor control, etc. Nevertheless, due to the diverse operating conditions and complexity of the drive system, the power converters employed in drive systems are more prone to faults. Moreover, collecting a large amount of labeled data in the nonlinear industrial environment is not practical, and this imposes challenges to the prior approaches as they claim a bulk amount of labeled data to be generalized. Taking this as a research challenge, this letter proposes a sparse-autoencoder-based unsupervised power converter fault detection and classification scheme that learns the fault-oriented features from the unlabeled dataset. In addition, the precision and sensitivity study are conducted in this letter to justify whether the proposed scheme delivers a reliable performance or not.
A hospital operating status evaluation data analysis system was established based on the autoencoder's network. The Gibbs sampling method is used to obtain the approximate distribution of RBM. In addition, the Aut...
详细信息
A hospital operating status evaluation data analysis system was established based on the autoencoder's network. The Gibbs sampling method is used to obtain the approximate distribution of RBM. In addition, the autoencoder neural network can also select feature dimensions that can better characterize the characteristics of financial operation data from a large amount of financial operation data. Deep learning methods are used to study the redundant information elimination method and the generation mechanism of multi -source heterogeneity in multi -source heterogeneous networks. The principle of intrinsic compression is used to reduce the dimensionality of the redundancy in the network and obtain the compression redundancy objective function. This article sets thresholds for information classification on the Internet. The approach was tested using financial data from a medical institution. Use smart encoders to extract 17 financial indicators from financial data that can be used for modeling. The evaluation results are used as the output vector of the model. Comparative experiments show that the AUC value and accuracy of the method proposed in this article can be improved by 0.84 and 83.33% compared with the AUC value of shallow logistic regression and BP neural network. This algorithm has apparent improvements.
The AI community has been paying attention to submodular functions due to their various applications (e.g., target search and 3D mapping). Learning submodular functions is a challenge since the number of a function...
详细信息
The AI community has been paying attention to submodular functions due to their various applications (e.g., target search and 3D mapping). Learning submodular functions is a challenge since the number of a function's outcomes of N sets is 2N. The state-of-the-art approach is based on compressed sensing techniques, which are to learn submodular functions in the Fourier domain and then recover the submodular functions in the spatial domain. However, the number of Fourier bases is relevant to the number of sets' sensing overlapping. To overcome this issue, this research proposed a submodular deep compressed sensing (SDCS) approach to learning submodular functions. The algorithm consists of learning autoencoder networks and Fourier coefficients. The learned networks can be applied to predict 2N values of submodular functions. Experiments conducted with this approach demonstrate that the algorithm is more efficient than the benchmark approach.
Autism spectrum disorder is one of the most common neurodevelopmental conditions associated with sensory and social communication impairments. Previous neuroimaging studies reported that atypical nodal- or network-lev...
详细信息
Autism spectrum disorder is one of the most common neurodevelopmental conditions associated with sensory and social communication impairments. Previous neuroimaging studies reported that atypical nodal- or network-level functional brain organization in individuals with autism was associated with autistic behaviors. Although dimensionality reduction techniques have the potential to uncover new biomarkers, the analysis of whole-brain structural connectome abnormalities in a low-dimensional latent space is underinvestigated. In this study, we utilized autoencoder-based feature representation learning for diffusion magnetic resonance imaging-based structural connectivity in 80 individuals with autism and 61 neurotypical controls that passed strict quality controls. We generated low-dimensional latent features using the autoencoder model for each group and adopted an integrated gradient approach to assess the contribution of the input data for predicting latent features during the encoding process. Subsequently, we compared the integrated gradient values between individuals with autism and neurotypical controls and observed differences within the transmodal regions and between the sensory and limbic systems. Finally, we identified significant associations between integrated gradient values and communication abilities in individuals with autism. Our findings provide insights into the whole-brain structural connectome in autism and may help identify potential biomarkers for autistic connectopathy.
Internet of things (IoT) and cloud computing are used in many real-time smart applications such as smart healthcare, smart traffic, smart city, and smart industries. Fog computing has been introduced as an intermediat...
详细信息
Internet of things (IoT) and cloud computing are used in many real-time smart applications such as smart healthcare, smart traffic, smart city, and smart industries. Fog computing has been introduced as an intermediate layer to reduce communication delay between cloud and IoT devices. To improve the performance of these smart applications, a predictive maintenance system needs to adopt an anomaly detection and root cause analysis model that helps to resolve anomalies and avoid such anomalies in the future. The state-of-the-art work on data-driven root cause analysis suffers from scalability, accuracy, and interpretability. In this paper, a multi-agent-based improved data-driven root cause analysis technique is introduced to identify anomalies and their root causes. The deep learning model LSTM autoencoder is used to find the anomalies, and a game theory approach called SHAP algorithm is used to find the root cause of the anomaly. The evaluation result shows the improvement in accuracy and interpretability as compared to state-of-the-art works.
Hyperspectral image (HSI) consists of hundreds of narrow spectral band components with rich spectral and spatial information. Extreme Learning Machine (ELM) has been widely used for HSI analysis. However, the classica...
详细信息
Hyperspectral image (HSI) consists of hundreds of narrow spectral band components with rich spectral and spatial information. Extreme Learning Machine (ELM) has been widely used for HSI analysis. However, the classical ELM is difficult to use for sparse feature leaning due to its randomly generated hidden layer. In this paper, we propose a novel unsupervised sparse feature learning approach, called Evolutionary Multiobjective-based ELM (EMO-ELM), and apply it to HSI feature extraction. Specifically, we represent the task of constructing the ELM autoencoder (ELM-AE) as a multiobjective optimization problem that takes the sparsity of hidden layer outputs and the reconstruction error as two conflicting objectives. Then, we adopt an Evolutionary Multiobjective Optimization (EMO) method to solve the two objectives, simultaneously. To find the best solution from the Pareto solution set and construct the best trade-off feature extractor, a curvature-based method is proposed to focus on the knee area of the Pareto solutions. Benefited from the EMO, the proposed EMO-ELM is less prone to fall into a local minimum and has fewer trainable parameters than gradient-based AEs. Experiments on two real HSIs demonstrate that the features learned by EMO-ELM not only preserve better sparsity but also achieve superior separability than many existing feature learning methods.
暂无评论