Showing papers on "Hybrid neural network published in 2020"

Teaching learning optimization and neural network for the effective prediction of heat transfer rates in tube heat exchangers

Abstract: Heat exchangers are widely used in many field for the purpose of heat from one medium to another. In heat exchanger one or more fluids are used, and which are various types based on its flow and construction. Design of heat exchanger is one of the important field, in the research due to its application. In recent decade the simulation is used in most of the engineering application. A proper simulation technique can effectively analysis the functionality and behavior of any machine before its construction or production. In this sense the machine learning techniques are used in some simulation analysis to model the machine or engine. In this work we used a hybrid neural network for the modeling of shell and tube type heat exchanger and its heat transfer rate is predicted effectively. The computational performance of the proposed technique is compared with the conventional technique and it is proved the effectiveness of the hybrid machine learning technique.

Hybrid Deep Neural Networks for Detection of Non-Technical Losses in Electricity Smart Meters

Abstract: Non-technical losses (NTL) in electricity utilities are responsible for major revenue losses. In this paper, we propose a novel end-to-end solution to self-learn the features for detecting anomalies and frauds in smart meters using a hybrid deep neural network. The network is fed with simple raw data, removing the need of handcrafted feature engineering. The proposed architecture consists of a long short-term memory network and a multi-layer perceptrons network. The first network analyses the raw daily energy consumption history whilst the second one integrates non-sequential data such as its contracted power or geographical information. The results show that the hybrid neural network significantly outperforms state-of-the-art classifiers as well as previous deep learning models used in NTL detection. The model has been trained and tested with real smart meter data of Endesa, the largest electricity utility in Spain.

A novel deep learning framework for state of health estimation of lithium-ion battery

Abstract: The state-of-health (SOH) estimation is a challenging task for lithium-ion battery, which contribute significantly to maximize the performance of battery-powered systems and guide the battery replacement. The complexity of degeneration mechanism enables data-driven methods to replace mechanism modeling methods to estimate SOH. The insight that motivates this study is that the charging curve of constant current-constant voltage charging mode could reflect the magnitude of SOH from the perspective of capacity. The proposed approach is based on a hybrid neural network called gate recurrent unit-convolutional neural network (GRU-CNN), which can learn the shared information and time dependencies of the charging curve with deep learning technology. Then the SOH could be estimated with the new observed charging curves such as voltage, current and temperature. The approach is demonstrated on the public NASA Randomized Battery Usage dataset and Oxford Battery Degradation dataset, and the maximum estimation error is limited to within 4.3%, thus proving its effectiveness.

A Short-Term Load Forecasting Method Based on GRU-CNN Hybrid Neural Network Model

Abstract: Short-term load forecasting (STLF) plays a very important role in improving the economy and stability of the power system operation. With the smart meters and smart sensors widely deployed in the power system, a large amount of data was generated but not fully utilized, these data are complex and diverse, and most of the STLF methods cannot well handle such a huge, complex, and diverse data. For better accuracy of STLF, a GRU-CNN hybrid neural network model which combines the gated recurrent unit (GRU) and convolutional neural networks (CNN) was proposed; the feature vector of time sequence data is extracted by the GRU module, and the feature vector of other high-dimensional data is extracted by the CNN module. The proposed model was tested in a real-world experiment, and the mean absolute percentage error (MAPE) and the root mean square error (RMSE) of the GRU-CNN model are the lowest among BPNN, GRU, and CNN forecasting methods; the proposed GRU-CNN model can more fully use data and achieve more accurate short-term load forecasting.

Tianjic: A Unified and Scalable Chip Bridging Spike-Based and Continuous Neural Computation

Abstract: Toward the long-standing dream of artificial intelligence, two successful solution paths have been paved: 1) neuromorphic computing and 2) deep learning. Recently, they tend to interact for simultaneously achieving biological plausibility and powerful accuracy. However, models from these two domains have to run on distinct substrates, i.e., neuromorphic platforms and deep learning accelerators, respectively. This architectural incompatibility greatly compromises the modeling flexibility and hinders promising interdisciplinary research. To address this issue, we build a unified model description framework and a unified processing architecture (Tianjic), which covers the full stack from software to hardware. By implementing a set of integration and transformation operations, Tianjic is able to support spiking neural networks, biological dynamic neural networks, multilayered perceptron, convolutional neural networks, recurrent neural networks, and so on. A compatible routing infrastructure enables homogeneous and heterogeneous scalability on a decentralized many-core network. Several optimization methods are incorporated, such as resource and data sharing, near-memory processing, compute/access skipping, and intra-/inter-core pipeline, to improve performance and efficiency. We further design streaming mapping schemes for efficient network deployment with a flexible tradeoff between execution throughput and resource overhead. A 28-nm prototype chip is fabricated with >610-GB/s internal memory bandwidth. A variety of benchmarks are evaluated and compared with GPUs and several existing specialized platforms. In summary, the fully unfolded mapping can achieve significantly higher throughput and power efficiency; the semi-folded mapping can save 30x resources while still presenting comparable performance on average. Finally, two hybrid-paradigm examples, a multimodal unmanned bicycle and a hybrid neural network, are demonstrated to show the potential of our unified architecture. This article paves a new way to explore neural computing.

City-Wide Traffic Congestion Prediction Based on CNN, LSTM and Transpose CNN

Abstract: Traffic congestion is a significant problem faced by large and growing cities that hurt the economy, commuters, and the environment. Forecasting the congestion level of a road network timely can prevent its formation and increase the efficiency and capacity of the road network. However, despite its importance, traffic congestion prediction is not a hot topic among the researcher and traffic engineers. It is due to the lack of high-quality city-wide traffic data and computationally efficient algorithms for traffic prediction. In this paper, we propose (i) an efficient and inexpensive city-wide data acquisition scheme by taking a snapshot of traffic congestion map from an open-source online web service; Seoul Transportation Operation and Information Service (TOPIS), and (ii) a hybrid neural network architecture formed by combing Convolutional Neural Network, Long Short-Term Memory, and Transpose Convolutional Neural Network to extract the spatial and temporal information from the input image to predict the network-wide congestion level. Our experiment shows that the proposed model can efficiently and effectively learn both spatial and temporal relationships for traffic congestion prediction. Our model outperforms two other deep neural networks (Auto-encoder and ConvLSTM) in terms of computational efficiency and prediction performance.

Automatic Fish Population Counting by Machine Vision and a Hybrid Deep Neural Network Model.

Abstract: In intensive aquaculture, the number of fish in a shoal can provide valuable input for the development of intelligent production management systems. However, the traditional artificial sampling method is not only time consuming and laborious, but also may put pressure on the fish. To solve the above problems, this paper proposes an automatic fish counting method based on a hybrid neural network model to realize the real-time, accurate, objective, and lossless counting of fish population in far offshore salmon mariculture. A multi-column convolution neural network (MCNN) is used as the front end to capture the feature information of different receptive fields. Convolution kernels of different sizes are used to adapt to the changes in angle, shape, and size caused by the motion of fish. Simultaneously, a wider and deeper dilated convolution neural network (DCNN) is used as the back end to reduce the loss of spatial structure information during network transmission. Finally, a hybrid neural network model is constructed. The experimental results show that the counting accuracy of the proposed hybrid neural network model is up to 95.06%, and the Pearson correlation coefficient between the estimation and the ground truth is 0.99. Compared with CNN- and MCNN-based methods, the accuracy and other evaluation indices are also improved. Therefore, the proposed method can provide an essential reference for feeding and other breeding operations.

Neural network modeling for groundwater-level forecasting in coastal aquifers

Abstract: Advances in the artificial intelligence-based models can act as robust tools for modeling hydrological processes. Neural network architectures coupled with learning algorithms are considered as useful modeling tools for groundwater-level fluctuations. Emotional artificial neural network coupled with genetic algorithm (EANN-GA) is one such novel hybrid neural network which has been used in the present study for the forecasting of groundwater levels at three sites (Site H3, Site H4.5, and Site H9) in a coastal aquifer system. This study was conceived to address and investigate the efficiency of the ensemble model (EANN-GA) for forecasting one-month ahead groundwater level and to compare its performance with emotional artificial neural network (EANN), generalized regression neural network (GRNN), and the conventional feedforward neural network (FFNN). Variations in the rainfall, tidal levels, and groundwater levels are selected as inputs for the development of EANN-GA, EANN, GRNN, and FFNN models. Suitable goodness-of-fit criteria such as Nash–Sutcliffe efficiency (NSE), bias, root mean squared error (RMSE), and graphical indicators are used for assessing the efficiency of the developed models. The improvement in the performance of the EANN-GA model over the developed EANN, GRNN, and FFNN models in terms of NSE is 0.81, 6.02, and 9.56% at Site H3; 4.35, 5.50, and 22.68% at Site H4.5; and 1.05, 7.18, and 21.75% at Site H9. Thus, it can be inferred that the EANN-GA model outperforms the developed EANN model, GRNN model, and FFNN model. Further, this paper examines the predictive capability of extreme events by the EANN-GA, EANN, GRNN, and FFNN models. The RMSE values of the EANN-GA model at all peak points are found as 0.27, 0.23, and 0.10 m at sites H3, H4.5, and H9, respectively, and the results indicate superior performance of EANN-GA model. To check the generalization ability of the developed EANN-GA models, they are validated with the data of another site (Site I2) located in the same coastal aquifer. Superior prediction capability and generalization ability make the EANN-GA model a better alternative for predicting groundwater levels. Overall, this study demonstrates the effectiveness of EANN-GA in modeling spatio-temporal fluctuations of groundwater levels. It is also concluded that the EANN-GA model yields remarkably better predictions of extreme events, and hence, it could be a promising technique for developing alarm systems for real-world water problems.

Remaining useful life prediction based on denoising technique and deep neural network for lithium-ion capacitors

Abstract: Lithium-ion capacitor is a hybrid electrochemical energy storage device which combines the merits of lithium-ion battery and electric double-layer capacitor. It is of great importance to monitor the real capacity to evaluate failures of lithium-ion capacitors. Remaining Useful Life (RUL), which is referred to remaining cycle number before reaching its End of Life (EOL) threshold, is a key part in the prognostics and health management and an important indicator of the depletion capacity of lithium-ion capacitor. In this paper, we propose a hybrid neural network which combine with the convolutional neural network and Bidirectional Long Short-Term Memory Network (Bi-LSTM), the data will be used to train this model. Finally, the verifications among different prediction horizons and other methods are discussed. According to the experimental and analysis results, the proposed approach has high reliability and prediction accuracy, which can be applied to battery monitoring and prognostics, as well as generalized to other prognostic applications.

Data Augmentation for Motor Imagery Signal Classification Based on a Hybrid Neural Network.

Abstract: As an important paradigm of spontaneous brain-computer interfaces (BCIs), motor imagery (MI) has been widely used in the fields of neurological rehabilitation and robot control. Recently, researchers have proposed various methods for feature extraction and classification based on MI signals. The decoding model based on deep neural networks (DNNs) has attracted significant attention in the field of MI signal processing. Due to the strict requirements for subjects and experimental environments, it is difficult to collect large-scale and high-quality electroencephalogram (EEG) data. However, the performance of a deep learning model depends directly on the size of the datasets. Therefore, the decoding of MI-EEG signals based on a DNN has proven highly challenging in practice. Based on this, we investigated the performance of different data augmentation (DA) methods for the classification of MI data using a DNN. First, we transformed the time series signals into spectrogram images using a short-time Fourier transform (STFT). Then, we evaluated and compared the performance of different DA methods for this spectrogram data. Next, we developed a convolutional neural network (CNN) to classify the MI signals and compared the classification performance of after DA. The Frechet inception distance (FID) was used to evaluate the quality of the generated data (GD) and the classification accuracy, and mean kappa values were used to explore the best CNN-DA method. In addition, analysis of variance (ANOVA) and paired t-tests were used to assess the significance of the results. The results showed that the deep convolutional generative adversarial network (DCGAN) provided better augmentation performance than traditional DA methods: geometric transformation (GT), autoencoder (AE), and variational autoencoder (VAE) (p < 0.01). Public datasets of the BCI competition IV (datasets 1 and 2b) were used to verify the classification performance. Improvements in the classification accuracies of 17% and 21% (p < 0.01) were observed after DA for the two datasets. In addition, the hybrid network CNN-DCGAN outperformed the other classification methods, with average kappa values of 0.564 and 0.677 for the two datasets.

Predicting the Trend of Stock Market Index Using the Hybrid Neural Network Based on Multiple Time Scale Feature Learning

Abstract: In the stock market, predicting the trend of price series is one of the most widely investigated and challenging problems for investors and researchers. There are multiple time scale features in financial time series due to different durations of impact factors and traders’ trading behaviors. In this paper, we propose a novel end-to-end hybrid neural network, a model based on multiple time scale feature learning to predict the price trend of the stock market index. Firstly, the hybrid neural network extracts two types of features on different time scales through the first and second layers of the convolutional neural network (CNN), together with the raw daily price series, reflect relatively short-, medium- and long-term features in the price sequence. Secondly, considering time dependencies existing in the three kinds of features, the proposed hybrid neural network leverages three long short-term memory (LSTM) recurrent neural networks to capture such dependencies, respectively. Finally, fully connected layers are used to learn joint representations for predicting the price trend. The proposed hybrid neural network demonstrates its effectiveness by outperforming benchmark models on the real dataset.

Medical Image Classification Using a Light-Weighted Hybrid Neural Network Based on PCANet and DenseNet

Abstract: Medical image classification plays an important role in disease diagnosis since it can provide important reference information for doctors. The supervised convolutional neural networks (CNNs) such as DenseNet provide the versatile and effective method for medical image classification tasks, but they require large amounts of data with labels and involve complex and time-consuming training process. The unsupervised CNNs such as principal component analysis network (PCANet) need no labels for training but cannot provide desirable classification accuracy. To realize the accurate medical image classification in the case of a small training dataset, we have proposed a light-weighted hybrid neural network which consists of a modified PCANet cascaded with a simplified DenseNet. The modified PCANet has two stages, in which the network produces the effective feature maps at each stage by convoluting inputs with various learned kernels. The following simplified DenseNet with a small number of weights will take all feature maps produced by the PCANet as inputs and employ the dense shortcut connections to realize accurate medical image classification. To appreciate the performance of the proposed method, some experiments have been done on mammography and osteosarcoma histology images. Experimental results show that the proposed hybrid neural network is easy to train and it outperforms such popular CNN models as PCANet, ResNet and DenseNet in terms of classification accuracy, sensitivity and specificity.

Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Abstract: Event-based cameras display great potential for a variety of tasks such as high-speed motion detection and navigation in low-light environments where conventional frame-based cameras suffer critically. This is attributed to their high temporal resolution, high dynamic range, and low-power consumption. However, conventional computer vision methods as well as deep Analog Neural Networks (ANNs) are not suited to work well with the asynchronous and discrete nature of event camera outputs. Spiking Neural Networks (SNNs) serve as ideal paradigms to handle event camera outputs, but deep SNNs suffer in terms of performance due to the spike vanishing phenomenon. To overcome these issues, we present Spike-FlowNet, a deep hybrid neural network architecture integrating SNNs and ANNs for efficiently estimating optical flow from sparse event camera outputs without sacrificing the performance. The network is end-to-end trained with self-supervised learning on Multi-Vehicle Stereo Event Camera (MVSEC) dataset. Spike-FlowNet outperforms its corresponding ANN-based method in terms of the optical flow prediction capability while providing significant computational efficiency.

Spike-FlowNet: Event-Based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks

Abstract: Event-based cameras display great potential for a variety of tasks such as high-speed motion detection and navigation in low-light environments where conventional frame-based cameras suffer critically. This is attributed to their high temporal resolution, high dynamic range, and low-power consumption. However, conventional computer vision methods as well as deep Analog Neural Networks (ANNs) are not suited to work well with the asynchronous and discrete nature of event camera outputs. Spiking Neural Networks (SNNs) serve as ideal paradigms to handle event camera outputs, but deep SNNs suffer in terms of performance due to the spike vanishing phenomenon. To overcome these issues, we present Spike-FlowNet, a deep hybrid neural network architecture integrating SNNs and ANNs for efficiently estimating optical flow from sparse event camera outputs without sacrificing the performance. The network is end-to-end trained with self-supervised learning on Multi-Vehicle Stereo Event Camera (MVSEC) dataset. Spike-FlowNet outperforms its corresponding ANN-based method in terms of the optical flow prediction capability while providing significant computational efficiency.

A novel approach to generate a large scale of supervised data for short text sentiment analysis

Abstract: As for the complexity of language structure, the semantic structure, and the relative scarcity of labeled data and context information, sentiment analysis has been regarded as a challenging task in Natural Language Processing especially in the field of short-text processing. Deep learning model need a large scale of training data to overcome data sparseness and the over-fitting problem, we propose multi-granularity text-oriented data augmentation technologies to generate large-scale artificial data for training model, which is compared with Generative adversarial network(GAN). In this paper, a novel hybrid neural network model architecture(LSCNN) was proposed with our data augmentation technology, which is can outperforms many single neural network models. The proposed data augmentation method enhances the generalization ability of the proposed model. Experiment results show that the proposed data augmentation method in combination with the neural networks model can achieve astonishing performance without any handcrafted features on sentiment analysis or short text classification. It was validated on a Chinese on-line comment dataset and Chinese news headline corpus, and outperforms many state-of-the-art models. Evidence shows that the proposed data argumentation technology can obtain more accurate distribution representation from data for deep learning, which improves the generalization characteristics of the extracted features. The combination of the data argumentation technology and LSCNN fusion model is well suited to short text sentiment analysis, especially on small scale corpus.

PV Power Prediction, Using CNN-LSTM Hybrid Neural Network Model. Case of Study: Temixco-Morelos, México

Abstract: Due to the intermittent nature of solar energy, accurate photovoltaic power predictions are very important for energy integration into existing energy systems. The evolution of deep learning has also opened the possibility to apply neural network models to predict time series, achieving excellent results. In this paper, a five layer CNN-LSTM model is proposed for photovoltaic power predictions using real data from a location in Temixco, Morelos in Mexico. In the proposed hybrid model, the convolutional layer acts like a filter, extracting local features of the data; then the temporal features are extracted by the long short-term memory network. Finally, the performance of the hybrid model with five layers is compared with a single model (a single LSTM), a CNN-LSTM hybrid model with two layers and two well known popular benchmarks. The results also shows that the hybrid neural network model has better prediction effect than the two layer hybrid model, the single prediction model, the Lasso regression or the Ridge regression.

A new method of emotional analysis based on CNN–BiLSTM hybrid neural network

Abstract: The hybrid neural network model proposed in this paper consists of two main parts: extracting local features of text vectors by convolutional neural network, extracting global features related to text context by BiLSTM, and fusing the features extracted by the two complementary models. In this paper, the pre-processed sentences are put into the hybrid neural network for training. The trained hybrid neural network can automatically classify the sentences. When testing the algorithm proposed in this paper, the training corpus is Word2vec. The test results show that the accuracy rate of text categorization reaches 94.2%, and the number of iterations is 10. The results show that the proposed algorithm has high accuracy and good robustness when the sample size is seriously unbalanced.

Hybrid Neural Network for Sina Weibo Sentiment Analysis

Abstract: Sina Weibo sentiment analysis technology provides the methods to survey public emotion about the related events or products in China. Most of the current works in sentiment analysis are to apply neural networks, such as convolution neural network (CNN), long short-term memory (LSTM), or C-LSTM. In this article, a novel structure of a hybrid neural network model is proposed to deal with the polysemy phenomena of words and topic confusion with Sina Weibo. First, the embeddings from language models (ELMo) and some statistical methods based on the corpus and sentiment lexicon are employed to extract the features. This method uses latent semantic relationships in different linguistic contexts and cooccurrence statistical features between words in Weibo. Second, for the classification model, unlike traditional C-LSTM which feeds CNN’s output into LSTM, we employ several filters with variable window sizes to extract a sequence of high-level word representation in different granularity distributions of text data in multichannel CNN. At the same time, obtain the sentence representation in Bi-LSTM. Then, concatenate the outputs of multichannel CNN and Bi-LSTM. In conclusion, the results indicate that the proposed model performs better on the precision, recall, and F1-score for Weibo sentiment analysis.

Bitcoin price forecasting method based on CNN-LSTM hybrid neural network model

Abstract: In this study, aiming at the problem that the price of Bitcoin varies greatly and is difficult to predict, a hybrid neural network model based on convolutional neural network (CNN) and long short-term memory (LSTM) neural network is proposed. The transaction data of Bitcoin itself, as well as external information, such as macroeconomic variables and investor attention, are taken as input. Firstly, CNN is used for feature extraction. Then the feature vectors are input into LSTM for training and forecasting the short-term price of Bitcoin. The result shows that the CNN-LSTM hybrid neural network can effectively improve the accuracy of value prediction and direction prediction compared with the single structure neural network. The finding has important implications for researchers and investors in the digital currencies market.

Surrogate Modeling of Electrical Machine Torque Using Artificial Neural Networks

Abstract: Machine learning and artificial neural networks have shown to be applicable in modeling and simulation of complex physical phenomena as well as creating surrogate models trained with physics-based simulation data for numerous applications that require good computational performance. In this article, we review widely the surrogate modeling concept and its applications in the electrical machine context. We present comprehensively a workflow for developing data-driven surrogate models including data generation with physics-based simulation and design of experiments, preprocessing of training data, and training and testing of the surrogates. We compare neural networks and gradient boosting decision trees in modeling and simulation of torque behavior of a permanent magnet synchronous machine together with selected design of experiments approaches with respect to surrogate accuracy and computational efficiency. In addition, an approach to utilizing domain knowledge to create a hybrid surrogate model in order to improve the surrogate accuracy is shown. The accuracy of the selected hybrid neural network was better than with the gradient boosting approach and was close to the finite element simulation, whereas its run-time efficiency was significantly better compared to the finite element simulation with a speed-up factor of over 2,000. In addition, combining the sampling methods provided better results than the selected methods alone.

Toward Smart Lockdown: A Novel Approach for COVID-19 Hotspots Prediction Using a Deep Hybrid Neural Network

Abstract: COVID-19 caused the largest economic recession in the history by placing more than one third of world’s population in lockdown. The prolonged restrictions on economic and business activities caused huge economic turmoil that significantly affected the financial markets. To ease the growing pressure on the economy, scientists proposed intermittent lockdowns commonly known as “smart lockdowns”. Under smart lockdown, areas that contain infected clusters of population, namely hotspots, are placed on lockdown, while economic activities are allowed to operate in un-infected areas. In this study, we proposed a novel deep learning prediction framework for the accurate prediction of hotpots. We exploit the benefits of two deep learning models, i.e., Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) and propose a hybrid framework that has the ability to extract multi time-scale features from convolutional layers of CNN. The multi time-scale features are then concatenated and provide as input to 2-layers LSTM model. The LSTM model identifies short, medium and long-term dependencies by learning the representation of time-series data. We perform a series of experiments and compare the proposed framework with other state-of-the-art statistical and machine learning based prediction models. From the experimental results, we demonstrate that the proposed framework beats other existing methods with a clear margin.

Critical Temperature Prediction of Superconductors Based on Atomic Vectors and Deep Learning

Abstract: In this paper, a hybrid neural network (HNN) that combines a convolutional neural network (CNN) and long short-term memory neural network (LSTM) is proposed to extract the high-level characteristics of materials for critical temperature (Tc) prediction of superconductors. Firstly, by obtaining 73,452 inorganic compounds from the Materials Project (MP) database and building an atomic environment matrix, we obtained a vector representation (atomic vector) of 87 atoms by singular value decomposition (SVD) of the atomic environment matrix. Then, the obtained atom vector was used to implement the coded representation of the superconductors in the order of the atoms in the chemical formula of the superconductor. The experimental results of the HNN model trained with 12,413 superconductors were compared with three benchmark neural network algorithms and multiple machine learning algorithms using two commonly used material characterization methods. The experimental results show that the HNN method proposed in this paper can effectively extract the characteristic relationships between the atoms of superconductors, and it has high accuracy in predicting the Tc.

App-Net: A Hybrid Neural Network for Encrypted Mobile Traffic Classification

Abstract: With the exponential growth of mobile traffic data, mobile traffic classification is in a great need. It is an essential step to improve the performance of network services such as QoS and security monitoring. However, the widespread use of encrypted protocols, especially the TLS protocol, has posed great challenges to traditional traffic classification techniques. As the rule-based deep packet inspection approaches are ineffective for encrypted traffic classification, various machine learning methods have been studied and used. Recently, deep learning solutions which enable automatic feature extraction are also proposed to classify encrypted traffic. In this paper we propose App-Net, an end-to-end hybrid neural network, to learn effective features from raw TLS flows for mobile app identification. App-Net is designed by combining RNN and CNN in a parallel way. So that it can learn a joint flow-app embedding to characterize both flow sequence patterns and unique app signatures. We evaluate App-Net on a real-world dataset that covering 80 apps. The results show that our method can achieve an excellent performance and outperform the state-of-the-art methods.

Enhanced ELITE-Load: A Novel CMPSOATT Methodology Constructing Short-Term Load Forecasting Model for Industrial Applications

Abstract: This article presents a two-layer hybrid neural network framework, termed enhanced ELITE (E-ELITE), for short-term load forecasting (STLF) with high-performance forecasting capability and accuracy. The design of the E-ELITE is based on a novel three-stage methodology that is composed of Stage I: optimal structure, Stage II: highly accurate and diverse members of neural network, and Stage III: a neural network-based ensemble. We explore the capability of our proposed consensus-based mixed-integer particle swarm optimization-assisted TRUST-TECH (CMPSOATT) method in each of the three-stage methodology to achieve the following advantages: first high-quality local optimal solutions or even the global optimal solution and second computational speed; consequently, the forecasting accuracy and generalization ability of the E-ELITE is enhanced by CMPSOATT via a training procedure to design a diverse set of optimal ANN forecasting engines in the bottom layer and another training procedure to achieve higher performance results than any engines in the top layer. The resulting E-ELITE is shown to obtain a more accurate, scalable, and better generalization STLF forecasting performance with less computational effort than other powerful forecasting methods through a utility-scale dataset.