Search

In modern networks, a Network Intrusion Detection System (NIDS) is a critical security device for detecting unauthorized activity. The categorization effectiveness for minority classes is limited by the imbalanced class issues connected with the dataset. We propose an Imbalanced Generative Adversarial Network (IGAN) to address the problem of class imbalance by increasing the detection rate of minority classes while maintaining efficiency. To limit the effect of the minimum or maximum value on the overall features, the original data was normalized and one-hot encoded using data preprocessing. To address the issue of the low detection rate of minority attacks caused by the imbalance in the training data, we enrich the minority samples with IGAN. The ensemble of Lenet 5 and Long Short Term Memory (LSTM) is used to classify occurrences that are considered abnormal into various attack categories. The investigational findings demonstrate that the proposed approach outperforms the other deep learning approaches, achieving the best accuracy, precision, recall, TPR, FPR, and F1-score. The findings indicate that IGAN oversampling can enhance the detection rate of minority samples, hence improving overall accuracy. According to the data, the recommended technique valued performance measures far more than alternative approaches. The proposed method is found to achieve above 98% accuracy and classifies various attacks significantly well as compared to other classifiers. [ABSTRACT FROM AUTHOR]

As the foundation of Posture Analysis, recognizing human activity accurately in real time assists in using machines to intellectualize living condition and monitor health status. In this paper, we focus on recognition based on raw time series data, which are continuously sampled by wearable sensors, and a fine-grained evidence reasoning approach has been proposed to produce a timely and reliable result. First, the basic time unit of input data is selected by finding a tradeoff between accuracy and time cost. Then, the approach uses Long Short Term Memory to extract features and project raw multidimensional data into probability assignments, followed by trainable evidence combination and inference network that reduce uncertainly to improve the classification accuracy. Experiments validate the effectiveness of fine granularity and evidence reasoning while the final results indicate that the recognition accuracy of this approach can reach 96.4% with no additional complexity in training. [ABSTRACT FROM AUTHOR]

Gesture recognition that is based on high-resolution radar has progressively developed in human-computer interaction field. In a radar recognition-based system, it is challenging to recognize various gesture types because of the lacking of gesture transversal feature. In this paper, we propose an integrated gesture recognition system that is based on frequency modulated continuous wave MIMO radar combined with deep learning network for gesture recognition. First, a pre-processing algorithm, which consists of the windowed fast Fourier transform and the intermediate-frequency signal band-pass-filter (IF-BPF), is applied to obtain improved Range Doppler Map. A range FFT based MUSIC (RFBM) two-dimensional (2D) joint super-resolution estimation algorithm is proposed to obtain a Range Azimuth Map to obtain gesture transversal feature. Range Doppler Map and Range Azimuth Map then respectively form a Range Doppler Map Time Sequence (RDMTS) and a Range Azimuth Map Time Sequence (RAMTS) in gesture recording duration. Finally, a Dual stream three-dimensional (3D) Convolution Neural Network combined with Long Short Term Memory (DS-3DCNN-LSTM) network is designed to extract and fuse features from both RDMTS and RAMTS, and then classify gestures with radial and transversal change. The experimental results show that the proposed system could distinguish 10 types of gestures containing transversal and radial motions with an average accuracy of 97.66%. [ABSTRACT FROM AUTHOR]

The ability to identify and accurately predict abnormal behavior is important for health monitoring systems in smart environments. Specifically, for elderly persons wishing to maintain their independence and comfort in their living spaces, abnormal behaviors observed during activities of daily living are a good indicator that the person is more likely to have health and behavioral problems that need intervention and assistance. In this paper, we investigate a variety of deep learning models such as Long Short Term Memory (LSTM), Convolutional Neural Network (CNN), CNN-LSTM and Autoencoder-CNN-LSTM for identifying and accurately predicting the abnormal behaviors of elderly people. The temporal information and spatial sequences collected over time are used to generate models, which can be fitted to the training data and the fitted model can be used to make a prediction. We present an experimental evaluation of these models performance in identifying and predicting elderly persons abnormal behaviors in smart homes, via extensive testing on two public data sets, taking into account different models architectures and tuning the hyperparameters for each model. The performance evaluation is focused on accuracy measure. [ABSTRACT FROM AUTHOR]

In this paper, a comparative study of the effectiveness of deep neural networks (DNNs) in the classification of pure and impure purees is conducted. Three different types of deep neural networks (DNNs)—the Gated Recurrent Unit (GRU), the Long Short Term Memory (LSTM), and the temporal convolutional network (TCN)—are employed for the detection of adulteration of strawberry purees. The Strawberry dataset, a time series spectroscopy dataset from the UCR time series classification repository, is utilized to evaluate the performance of different DNNs. Experimental results demonstrate that the TCN is able to obtain a higher classification accuracy than the GRU and LSTM. Moreover, the TCN achieves a new state-of-the-art classification accuracy on the Strawberry dataset. These results indicates the great potential of using the TCN for the detection of adulteration of fruit purees in the future. [ABSTRACT FROM AUTHOR]

Timely calls for help can really make a difference for elders who suffer from falls, particularly in private locations. Considering privacy protection and convenience for the users, in this paper, we approach the problem by using impulse–radio ultra-wideband (IR-UWB) monostatic radar and propose a learning model that combines convolutional layers and convolutional long short term memory (ConvLSTM) to extract robust spatiotemporal features for fall detection. The performance of the proposed scheme was evaluated in terms of accuracy, sensitivity, and specificity. The results show that the proposed method outperforms convolutional neural network (CNN)-based methods. Of the six activities we investigated, the proposed method can achieve a sensitivity of 95% and a specificity of 92.6% at a range of 8 meters. Further tests in a heavily furnished lounge environment showed that the model can detect falls with more than 90% sensitivity, even without re-training effort. The proposed method can detect falls without exposing the identity of the users. Thus, the proposed method is ideal for room-level fall detection in privacy-prioritized scenarios. [ABSTRACT FROM AUTHOR]

Sentiment analysis is a rapidly growing field of research due to the explosive growth in digital information. In the modern world of artificial intelligence, sentiment analysis is one of the essential tools to extract emotion information from massive data. Sentiment analysis is applied to a variety of user data from customer reviews to social network posts. To the best of our knowledge, there is less work on sentiment analysis based on the categorization of users by demographics. Demographics play an important role in deciding the marketing strategies for different products. In this study, we explore the impact of age and gender in sentiment analysis, as this can help e-commerce retailers to market their products based on specific demographics. The dataset is created by collecting reviews on books from Facebook users by asking them to answer a questionnaire containing questions about their preferences in books, along with their age groups and gender information. Next, the paper analyzes the segmented data for sentiments based on each age group and gender. Finally, sentiment analysis is done using different Machine Learning (ML) approaches including maximum entropy, support vector machine, convolutional neural network, and long short term memory to study the impact of age and gender on user reviews. Experiments have been conducted to identify new insights into the effect of age and gender for sentiment analysis. [ABSTRACT FROM AUTHOR]

Runoff modeling is one of the key challenges in the field of hydrology. Various approaches exist, ranging from physically based over conceptual to fully data driven models. In this paper, we propose a data driven approach using the state-of-the-art Long-Short-Term-Memory (LSTM) network. The proposed model was applied in the Poyang Lake Basin (PYLB) and its performance was compared with an Artificial Neural Network (ANN) and the Soil & Water Assessment Tool (SWAT). We first tested the impacts of the number of previous time step (window size) in simulation accuracy. Results showed that a window in improper large size will dramatically deteriorate the model performance. In terms of PYLB, a window size of 15 days might be appropriate for both accuracy and computational efficiency. We then trained the model with 2 different input datasets, namely, dataset with precipitation only and dataset with all available meteorological variables. Results demonstrate that although LSTM with precipitation data as the only input can achieve desirable results (where the NSE ranged from 0.60 to 0.92 for the test period), the performance can be improved simply by feeding the model with more meteorological variables (where NSE ranged from 0.74 to 0.94 for the test period). Moreover, the comparison results with the ANN and the SWAT showed that the ANN can get comparable performance with the SWAT in most cases whereas the performance of LSTM is much better. The results of this study underline the potential of the LSTM for runoff modeling especially for areas where detailed topographical data are not available. [ABSTRACT FROM AUTHOR]

Short term memory that records the current population has been an inherent component of Evolutionary Algorithms (EAs). As hardware technologies advance currently, inexpensive memory with massive capacities could become a performance boost to EAs. This paper introduces a Long Term Memory Assistance (LTMA) that records the entire search history of an evolutionary process. With LTMA, individuals already visited (i.e., duplicate solutions) do not need to be re-evaluated, and thus, resources originally designated to fitness evaluations could be reallocated to continue search space exploration or exploitation. Three sets of experiments were conducted to prove the superiority of LTMA. In the first experiment, it was shown that LTMA recorded at least 50 % more duplicate individuals than a short term memory. In the second experiment, ABC and jDElscop were applied to the CEC-2015 benchmark functions. By avoiding fitness re-evaluation, LTMA improved execution time of the most time consuming problems F 03 and F 05 between 7% and 28% and 7% and 16%, respectively. In the third experiment, a hard real-world problem for determining soil models' parameters, LTMA improved execution time between 26% and 69%. Finally, LTMA was implemented under a generalized and extendable open source system, called EARS. Any EA researcher could apply LTMA to a variety of optimization problems and evolutionary algorithms, either existing or new ones, in a uniform way. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have been shown to be effective for single sound source localization in shallow water environments. However, multiple source localization is a more challenging task because of the interactions among multiple acoustic signals. This paper proposes a framework for multiple source localization on underwater horizontal arrays using deep neural networks. The two-stage DNNs are adopted to determine both the directions and ranges of multiple sources successively. A feed-forward neural network is trained for direction finding, while the long short term memory recurrent neural network is used for source ranging. Particularly, in the source ranging stage, we perform subarray beamforming to extract features of sources that are detected by the direction finding stage, because subarray beamforming can enhance the mixed signal to the desired direction while preserving the horizontal-longitudinal correlations of the acoustic field. In this way, a universal model trained in the single-source scenario can be applied to multi-source scenarios with arbitrary numbers of sources. Both simulations and experiments in a range-independent shallow water environment of SWellEx-96 Event S5 are given to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Condition monitoring can improve the reliability of wind turbines, which can effectively reduce operation and maintenance costs. The temperature prediction model of wind turbine gearbox components is of great significance for monitoring the operation status of the gearbox. However, the complex operating conditions of wind turbines pose grand challenges to predict the temperature of gearbox components. In this study, an online hybrid model based on a long short term memory (LSTM) neural network and adaptive error correction (LSTM-AEC) using simple-variable data is proposed. In the proposed model, a more suitable deep learning approach for time series, LSTM algorithm, is applied to realize the preliminary prediction of temperature, which has a stronger ability to capture the non-stationary and non-linear characteristics of gearbox components temperature series. In order to enhance the performance of the LSTM prediction model, the adaptive error correction model based on the variational mode decomposition (VMD) algorithm is developed, where the VMD algorithm can effectively solve the prediction difficulty issue caused by the non-stationary, high-frequency and chaotic characteristics of error series. To apply the hybrid model to the online prediction process, a real-time rolling data decomposition process based on VMD algorithm is proposed. With aims to validate the effectiveness of the hybrid model proposed in this paper, several traditional models are introduced for comparative analysis. The experimental results show that the hybrid model has better prediction performance than other comparative models. [ABSTRACT FROM AUTHOR]

ITO/WOx/TaN and ITO/WOx/AlOx/TaN memory cells were fabricated as a neuromorphic device that is compatible with CMOS. They are suitable for the information age, which requires a large amount of data as next-generation memory. The device with a thin AlOx layer deposited by atomic layer deposition (ALD) has different electrical characteristics from the device without an AlOx layer. The low current is achieved by inserting an ultra-thin AlOx layer between the switching layer and the bottom electrode due to the tunneling barrier effect. Moreover, the short-term memory characteristics in bilayer devices are enhanced. The WOx/AlOx device returns to the HRS without a separate reset process or energy consumption. The amount of gradual current reduction could be controlled by interval time. In addition, it is possible to maintain LRS for a longer time by forming it to implement long-term memory. [ABSTRACT FROM AUTHOR]

Conventional classification of hand motions and continuous joint angle estimation based on sEMG have been widely studied in recent years. The classification task focuses on discrete motion recognition and shows poor real-time performance, while continuous joint angle estimation evaluates the real-time joint angles by the continuity of the limb. Few researchers have investigated continuous hand action prediction based on hand motion continuity. In our study, we propose the key state transition as a condition for continuous hand action prediction and simulate the prediction process using a sliding window with long-term memory. Firstly, the key state modeled by GMM-HMMs is set as the condition. Then, the sliding window is used to dynamically look for the key state transition. The prediction results are given while finding the key state transition. To extend continuous multigesture action prediction, we use model pruning to improve reusability. Eight subjects participated in the experiment, and the results show that the average accuracy of continuous two-hand actions is 97% with a 70 ms time delay, which is better than LSTM (94.15%, 308 ms) and GRU (93.83%, 300 ms). In supplementary experiments with continuous four-hand actions, over 85% prediction accuracy is achieved with an average time delay of 90 ms. [ABSTRACT FROM AUTHOR]

Declarative fact knowledge is a key component of crystallized intelligence. It is typically measured with multiple-choice (MC) items. Other response formats, such as open-ended formats are less frequently used, although these formats might be superior for measuring crystallized intelligence. Whereas MC formats presumably only require recognizing the correct response to a question, open-ended formats supposedly require cognitive processes such as searching for, retrieving, and actively deciding on a response from long-term memory. If the methods of inquiry alter the cognitive processes involved, mean-changes between methods for assessing declarative knowledge should come along with changes in the covariance structure. We tested these assumptions in two online studies administering declarative knowledge items in different response formats (MC, open-ended, and open-ended with cues). Item difficulty clearly increases in the open-ended methods although effects in logistic regression models vary slightly across items. Importantly, latent variable analyses suggest that the method of inquiry does not affect what is measured with different response formats. These findings clearly endorse the position that crystallized intelligence does not change as a function of the response format. [ABSTRACT FROM AUTHOR]

Diabetic Retinopathy affects one-third of all diabetic patients and may cause vision impairment. It has four stages of progression, i.e., mild non-proliferative, moderate non-proliferative, severe non-proliferative and proliferative Diabetic Retinopathy. The disease has no noticeable symptoms at early stages and may lead to chronic destruction, thus causing permanent blindness if not detected at an early stage. The proposed research provides deep learning frameworks for autonomous detection of Diabetic Retinopathy at an early stage using fundus images. The first framework consists of cascaded neural networks, spanned in three layers where each layer classifies data into two classes, one is the desired stage and the other output is passed to another classifier until the input image is classified as one of the stages. The second framework takes normalized, HSV and RGB fundus images as input to three Convolutional Neural Networks, and the resultant probabilistic vectors are averaged together to obtain the final output of the input image. Third framework used the Long Short Term Memory Module in CNN to emphasize the network in remembering information over a long time span. Proposed frameworks were tested and compared on the large-scale Kaggle fundus image dataset EYEPAC. The evaluations have shown that the second framework outperformed others and achieved an accuracy of 78.06% and 83.78% without and with augmentation, respectively. [ABSTRACT FROM AUTHOR]

Investment projects are not the only ones where significant complications in their implementation may occur. The fundamental question, how to specify threats hidden in time series, is one of the most important types of knowledge arising from the basic schedules' documentation. Feasibility studies, project proposals, organizational and production procedures, research projects, and others are major resources of information. The reason why to specify threats hidden in time series is the high cost of not revealing hidden threats. An illustrative clarification of the cost is given on the current data of nuclear power plants. Wherever one works with schedules and resources, the above-mentioned issue may appear. Undeniably, valid data is discoverable ex post in accounting, documentation, or even in the documentation of the preparation and implementation, and in the analyzes of the mechanisms for non-compliance with deadlines and cost increases. For implementation (i.e., ex ante use), the majority of projects are created by expert intuitive decision-making. In terms of content, these are sources of errors from the past, lacking analytical quantitative support (suffering from the so-called evidence shortage). Production schedule time series comprise: (a) cumulative volume, (b) speeds, and (c) accelerations. More recent, in addition to statistical analysis, is the focus on the long-term memory of time series and to the application of the Hurst exponent as indicators of predictability (ex-ante). This article offers a procedure for how to reveal hidden chaotic states in the time series of a project's output information. If it is possible to find chaotic behavior in the output information, these states must be searched for and removed in the original source model—the implementation project. Exceeding contractual terms and implementation costs leads to a threat to the economic basis—the collapse of the initial idea of the project's economy. As an example, nuclear power plant projects are shown. The article broadens the perspective of ex ante decision-making. [ABSTRACT FROM AUTHOR]

The rapid development in manufacturing industries due to the introduction of IIoT devices has led to the emergence of Industry 4.0 which results in an industry with intelligence, increased efficiency and reduction in the cost of manufacturing. However, the introduction of IIoT devices opens up the door for a variety of cyber threats in smart industries. The detection of cyber threats against such extensive, complex, and heterogeneous smart manufacturing industries is very challenging due to the lack of sufficient attack traces. Therefore, in this work, a Federated Learning enabled Deep Intrusion Detection framework is proposed to detect cyber threats in smart manufacturing industries. The proposed FLDID framework allows multiple smart manufacturing industries to build a collaborative model to detect threats and overcome the limited attack example problem with individual industries. Moreover, to ensure the privacy of model gradients, Paillier-based encryption is used in communication between edge devices (representative of smart industries) and the server. The deep learning-based hybrid model, which consists of a Convolutional Neural Network, Long Short Term Memory, and Multi-Layer Perceptron is used in the intrusion detection model. An exhaustive set of experiments on the publically available dataset proves the effectiveness of the proposed framework for detecting cyber threats in smart industries over the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In remote sensing images, change detection (CD) is required in many applications, such as: resource management, urban expansion research, land management, and disaster assessment. Various deep learning-based methods were applied to satellite image analysis for change detection, yet many of them have limitations, including the overfitting problem. This research proposes the Feature Weighted Attention (FWA) in Bidirectional Long Short-Term Memory (BiLSTM) method to reduce the overfitting problem and increase the performance of classification in change detection applications. Additionally, data usage and accuracy in remote sensing activities, particularly CD, can be significantly improved by a large number of training models based on BiLSTM. Normalization techniques are applied to input images in order to enhance the quality and reduce the difference in pixel value. The AlexNet and VGG16 models were used to extract useful features from the normalized images. The extracted features were then applied to the FWA-BiLSTM model, to give more weight to the unique features and increase the efficiency of classification. The attention layer selects the unique features that help to distinguish the changes in the remote sensing images. From the experimental results, it was clearly shown that the proposed FWA-BiLSTM model achieved better performance in terms of precision (93.43%), recall (93.16%), and overall accuracy (99.26%), when compared with the existing Difference-enhancement Dense-attention Convolutional Neural Network (DDCNN) model. [ABSTRACT FROM AUTHOR]

In an aging global society, a few complex problems have been occurring due to falls among the increasing elderly population. Therefore, falls are detected using a pendant-type sensor that can be worn comfortably for fall detection. The sensed data are processed by the embedded environment and classified by a long-term memory (LSTM). A fall detection system that combines a simple threshold method (STM) and LSTM, the STM-LSTM-based fall detection system, is introduced. In terms of training data accuracy, the proposed STM-LSTM-based fall detection system is compared with the previously reported STM-hidden Markov model (HMM)-based fall detection system. The training accuracy of the STM-LSTM fall detection system is 100%, while the highest training accuracy by the STM-HMM-based one is 99.5%, which is 0.5% less than the best of the STM-LSTM-based system. In addition, in the optimized LSTM fall detection system, this may be overfitted because all data are trained without separating any validation data. In order to resolve the possible overfitting issue, training and validation data are evaluated separately in 4:1, and then in terms of validation data accuracy of the STM-LSTM-based fall detection system, optimal values of the parameters in LSTM and normalization method are found as follows: best accuracy of 98.21% at no-normalization, no-sampling, 128hidden layer nodes, and regularization rate of 0.015. It is also observed that as the number of hidden layer nodes or sampling interval increases, the regularization rate at the highest value of accuracy increases. This means that overfitting can be suppressed by increasing the regularization, and thus an appropriate number of hidden layer nodes and a regularization rate must be selected to improve the fall detection efficiency. [ABSTRACT FROM AUTHOR]

In recent years, the use of renewable energy has grown significantly in electricity generation. However, the output of such facilities can be uncertain, affecting their reliability. The forecast of renewable energy production is necessary to guarantee the system's stability. Several authors have already developed deep learning techniques and hybrid systems to make predictions as accurate as possible. However, the accurate forecasting of renewable energy still is a challenging task. This work proposes a new hybrid system for renewable energy forecasting that combines the traditional linear model (Seasonal Autoregressive Integrated Moving Average—SARIMA) with a state-of-the-art Machine Learning (ML) model, Transformer neural network, using exogenous data. The proposal, named H-Transformer, is compared with other hybrid systems and single ML models, such as Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Recurrent Neural Networks (RNN), using five data sets of wind speed and solar energy. The proposed H-Transformer attained the best result compared to all single models in all datasets and evaluation metrics. Finally, the hybrid H-Transformer obtained the best result in most cases when compared to other hybrid approaches, showing that the proposal can be a useful tool in renewable energy forecasting. [ABSTRACT FROM AUTHOR]

Rapid advancements in the internet and communication domains have led to a massive rise in the network size and the equivalent data. Consequently, several new attacks have been created and pose several challenging issues for network security. In addition, the intrusions can launch several attacks and can be handled by the use of intrusion detection system (IDS). Though several IDS models are available in the literature, there is still a need to improve the detection rate and decrease the false alarm rate. The recent developments of machine learning (ML) and deep learning (DL)-based IDS systems are being deployed as possible solutions for effective intrusion detection. In this work, we propose an arithmetic optimization-enabled density-based clustering with deep learning (AOEDBC-DL) model for intelligent intrusion detection. The presented AOEDBC-DL technique follows a data clustering process to handle the massive quantity of network data traffic. To accomplish this, the AOEDBC-DL technique applied a density-based clustering technique and the initial set of clusters are initialized using the arithmetic optimization algorithm (AOA). In order to recognize and classify intrusions, a bidirectional long short term memory (BiLSTM) mechanism was exploited in this study. Eventually, the AOA was applied as a hyperparameter tuning procedure of the BiLSTM model. The experimental result analysis of the AOEDBC-DL algorithm was tested using benchmark IDS datasets. Extensive comparison studies highlighted the enhancements of the AOEDBC-DL technique over other existing approaches. [ABSTRACT FROM AUTHOR]

As scalar neurons of traditional neural networks promote dimension reduction caused by pooling, it is a difficult task to extract the high-dimensional spatial features and long-term correlation of pure signals from the noisy vibration signal. To address the above issues, a vibration signal denoising method based on the combination of a dilated self-attention capsule network and bidirectional long short memory network (DACapsNet–BiLSTM) is proposed to extract high-dimensional spatial features and learn long-term correlations between two adjacent time steps. An improved self-attention module with spatial feature extraction ability was constructed based on the random distribution of noise, which is embedded into the capsule network for the extracted spatial features and denoising. The dilated convolution is integrated into the improved capsule network to expand the receptive field to obtain the spatial features of the vibration signal. The output of the capsule network was used as the input of the bidirectional long-term and short-term memory network to obtain the timing characteristics of the vibration signal. Numerical experiments demonstrated that DACapsNet–BiLSTM performs better than other signal denoising methods, in terms of signal-to-noise ratio, mean square error, and mean absolute error metrics. [ABSTRACT FROM AUTHOR]

Drift is an important issue that impairs the reliability of sensors, especially in gas sensors. The conventional method usually adopts the reference gas to compensate for the drift. However, its classification accuracy is not high. We propose a supervised learning algorithm that is based on multi-classifier integration for drift compensation in this paper, which incorporates drift compensation into the classification process, motivated by the fact that the goal of drift compensation is to improve the classification performance. In our method, with the obtained characteristics of sensors and the advantage of Support Vector Machine (SVM) in few-shot classification, the improved Long Shot Term Memory (LSTM) is integrated to build the multi-class classifier model. We tested the proposed approach on the publicly available time series dataset that was collected over three years by the metal-oxide gas sensors. The results clearly indicate the superiority of multiple classifier approach, which achieves higher classification accuracy as compared with different approaches during testing period with an ensemble of classifiers in the presence of sensor drift over time. [ABSTRACT FROM AUTHOR]

Recently, the prediction of photovoltaic (PV) power has become of paramount importance to improve the expected revenue of PV operators and the effective operations of PV facility systems. Additionally, the precise PV power output prediction in an hourly manner enables more sophisticated strategies for PV operators and markets as the electricity price in a renewable energy market is continuously changing. However, the hourly prediction of PV power outputs is considered as a challenging problem due to the dynamic natures of meteorological information not only in a day but also across days. Therefore, in this paper, we suggest three PV power output prediction methods such as artificial neural network (ANN)-, deep neural network (DNN)-, and long and short term memory (LSTM)-based models that are capable to understand the hidden relationships between meteorological information and actual PV power outputs. In particular, the proposed LSTM based model is designed to capture both hourly patterns in a day and seasonal patterns across days. We conducted the experiments by using a real-world dataset. The experimental results show that the proposed ANN based model fails to yield satisfactory results, and the proposed LSTM based model successfully better performs more than 50% compared to the conventional statistical models in terms of mean absolute error. [ABSTRACT FROM AUTHOR]

Essay scoring is a critical task in education. Implementing automated essay scoring (AES) helps reduce manual workload and speed up learning feedback. Recently, neural network models have been applied to the task of AES and demonstrates tremendous potential. However, the existing work only considered the essay itself without considering the rating criteria behind the essay. One of the reasons is that the various kinds of rating criteria are very hard to represent. In this paper, we represent rating criteria by some sample essays that were provided by domain experts and defined a new input pair consisting of an essay and a sample essay. Corresponding to this new input pair, we proposed a symmetrical neural network AES model that can accept the input pair. The model termed Siamese Bidirectional Long Short-Term Memory Architecture (SBLSTMA) can capture not only the semantic features in the essay but also the rating criteria information behind the essays. We use the SBLSTMA model for the task of AES and take the Automated Student Assessment Prize (ASAP) dataset as evaluation. Experimental results show that our approach is better than the previous neural network methods. [ABSTRACT FROM AUTHOR]

Wireless Local Area Network (WLAN) positioning is a challenging task indoors due to environmental constraints and the unpredictable behavior of signal propagation, even at a fixed location. The aim of this work is to develop deep learning-based approaches for indoor localization and tracking by utilizing Received Signal Strength (RSS). The study proposes Multi-Layer Perceptron (MLP), One and Two Dimensional Convolutional Neural Networks (1D CNN and 2D CNN), and Long Short Term Memory (LSTM) deep networks architectures for WLAN indoor positioning based on the data obtained by actual RSS measurements from an existing WLAN infrastructure in a mobile user scenario. The results, using different types of deep architectures including MLP, CNNs, and LSTMs with existing WLAN algorithms, are presented. The Root Mean Square Error (RMSE) is used as the assessment criterion. The proposed LSTM Model 2 achieved a dynamic positioning RMSE error of 1.73 m , which outperforms probabilistic WLAN algorithms such as Memoryless Positioning (RMSE: 10.35 m ) and Nonparametric Information (NI) filter with variable acceleration (RMSE: 5.2 m ) under the same experiment environment. [ABSTRACT FROM AUTHOR]

The current work presents an effective fault detection and diagnosis (FDD) technique in wind energy converter (WEC) systems. The proposed FDD framework merges the benefits of kernel principal component analysis (KPCA) model and the bidirectional long short-term memory (BiLSTM) classifier. In the developed FDD approach, the KPCA model is applied to extract and select the most effective features, while the BiLSTM is utilized for classification purposes. The developed KPCA-based BiLSTM approach involves two main steps: feature extraction and selection, and fault classification. The KPCA model is developed in order to select and extract the most efficient features and the final features are fed to the BiLSTM to distinguish between different working modes. Different simulation scenarios are considered in this study in order to show the robustness and performance of the developed technique when compared to the conventional FDD methods. To evaluate the effectiveness of the proposed KPCA-based BiLSTM approach, we utilize data obtained from a healthy WTC, which are then injected with several fault scenarios: simple fault generator-side, simple fault grid-side, multiple fault generator-side, multiple fault grid-side, and mixed fault on both sides. The diagnosis performance is analyzed in terms of accuracy, recall, precision, and computation time. Furthermore, the efficiency of fault diagnosis is shown by the classification accuracy parameter. The experimental results show the efficiency of the developed KPCA-based BiLSTM technique compared to the classical FDD techniques (an accuracy of 97.30%). [ABSTRACT FROM AUTHOR]

The vertebrates' scaffold proteins of the Dlg-MAGUK family are involved in the recruitment, clustering, and anchoring of glutamate receptors to the postsynaptic density, particularly the NMDA subtype glutamate-receptors (NRs), necessary for long-term memory and LTP. In Drosophila, the only gene of the subfamily generates two main products, dlgA, broadly expressed, and dlgS97, restricted to the nervous system. In the Drosophila brain, NRs are expressed in the adult brain and are involved in memory, however, the role of Dlg in these processes and its relationship with NRs has been scarcely explored. Here, we show that the dlg mutants display defects in short-term memory in the olfactory associative-learning paradigm. These defects are dependent on the presence of DlgS97 in the Mushroom Body (MB) synapses. Moreover, Dlg is immunoprecipitated with NRs in the adult brain. Dlg is also expressed in the larval neuromuscular junction (NMJ) pre and post-synaptically and is important for development and synaptic function, however, NR is absent in this synapse. Despite that, we found changes in the short-term plasticity paradigms in dlg mutant larval NMJ. Together our results show that larval NMJ and the adult brain relies on Dlg for short-term memory/plasticity, but the mechanisms differ in the two types of synapses. [ABSTRACT FROM AUTHOR]

Many rumors spread quickly and widely on social media, affecting social stability. The rumors of most current detection methods only use textual information or introduce external auxiliary information (such as user information and propagation information) to enhance the detection effect, and the inherent statistical features of the corpus have not been fully used and compared with the external auxiliary features; in addition, statistical features are more certain and can only be obtained from textual information. Therefore, we adopted a method based on the adaptive fusion of word frequency distribution features and textual features to detect rumors. Statistical features were extracted by encoding statistical information through a variational autoencoder. We extracted semantic features and sequence features as textual features through a parallel network comprising a convolutional neural network and a bidirectional long-term memory network. In addition, we also designed an adaptive valve to only fuse useful statistical features with textual features according to the credibility of textual features, which can solve the over-fitting problem caused by the excessive use of statistical features. The accuracy of the model in three public datasets (Twitter15, Twitter16, and Weibo) reached 87.5%, 88.6%, and 95.8%, respectively, and the F1 value reached 87.4%, 88.5%, and 95.8%, respectively, showing that the model can effectively improve the performance of rumor detection. [ABSTRACT FROM AUTHOR]

An accurate mathematical model is a basis for controlling and estimating the state of an Autonomous underwater vehicle (AUV) system, so how to improve its accuracy is a fundamental problem in the field of automatic control. However, AUV systems are complex, uncertain, and highly non-linear, and it is not easy to obtain through traditional modeling methods. We fit an accurate dynamic AUV model in this study using the long short-term memory (LSTM) neural network approach. As hyper-parameter values have a significant impact on LSTM performance, it is important to select the optimal combination of hyper-parameters. The present research uses the improved Q-learning reinforcement learning algorithm to achieve this aim by improving its recognition accuracy on the verification dataset. To improve the efficiency of action exploration, we improve the Q-learning algorithm and choose the optimal initial state according to the Q table in each round of learning. It can effectively avoid the ineffective exploration of the reinforcement learning agent between the poor-performing hyperparameter combinations. Finally, the experiments based on simulated or actual trial data demonstrate that the proposed model identification method can effectively predict kinematic motion data, and more importantly, the modified Q-Learning approach can optimize the network hyperparameters in the LSTM. [ABSTRACT FROM AUTHOR]

The proliferation of spam in China has a negative impact on internet users' experiences online. Existing methods for detecting spam are primarily based on machine learning. However, it has been discovered that these methods are susceptible to adversarial textual spam that has frequently been imperceptibly modified by spammers. Spammers continually modify their strategies to circumvent spam detection systems. Text with Chinese homophonic substitution may be easily understood by users according to its context. Currently, spammers widely use homophonic substitution to break down spam identification systems on the internet. To address these issues, we propose a Bidirectional Gated Recurrent Unit (BiGRU)–Text Convolutional Neural Network (TextCNN) hybrid model with joint embedding for detecting Chinese spam. Our model effectively uses phonetic information and combines the advantages of parameter sharing from TextCNN with long-term memory from BiGRU. The experimental results on real-world datasets show that our model resists homophone noise to some extent and outperforms mainstream deep learning models. We also demonstrate the generality of joint textual and phonetic embedding, which is applicable to other deep learning networks in Chinese spam detection tasks. [ABSTRACT FROM AUTHOR]

Real-time, continuous and accurate blast furnace burden level information is of great significance for controlling the charging process, ensuring a smooth operation of a blast furnace, reducing energy consumption and emissions and improving blast furnace output. However, the burden level information measured by conventional mechanical stock rods and radar probes exhibit problems of weak anti-interference ability, large fluctuations in accuracy, poor stability and discontinuity. Therefore, a space-time fusion prediction and detection method of burden level based on a long-term focus memory network (LFMN) and an efficient structure self-tuning RBF neural network (ESST-RBFNN) is proposed. First, the space dimensional features are extracted by the space regression model based on radar data. Then, the LFMN is designed to predict the burden level and extract the time dimensional features. Finally, the ESST-RBFNN based on a proposed fast eigenvector space clustering algorithm (ESC) is constructed to obtain reliable and continuous burden level information with high accuracy. Both the simulation results and industrial verification indicate that the proposed method can provide real-time and continuous burden level information in real-time, which has great practical value for industrial production. [ABSTRACT FROM AUTHOR]

Smartphones have enabled the widespread use of mobile applications. However, there are unrecognized defects of mobile applications that can affect businesses due to a negative user experience. To avoid this, the defects of applications should be detected and removed before release. This study aims to develop a defect prediction model for mobile applications. We performed cross-project and within-project experiments and also used deep learning algorithms, such as convolutional neural networks (CNN) and long short term memory (LSTM) to develop a defect prediction model for Android-based applications. Based on our within-project experimental results, the CNN-based model provides the best performance for mobile application defect prediction with a 0.933 average area under ROC curve (AUC) value. For cross-project mobile application defect prediction, there is still room for improvement when deep learning algorithms are preferred. [ABSTRACT FROM AUTHOR]

Water is a fundamental resource for human survival but the consumption of water that is unfit for drinking leads to serious diseases. Access to high–resolution satellite imagery provides an opportunity for innovation in the techniques used for water quality monitoring. With remote sensing, water quality parameter concentrations can be estimated based on the band combinations of the satellite images. In this study, a hybrid remote sensing and deep learning approach for forecasting multi–step parameter concentrations was investigated for the advancement of the traditionally employed water quality assessment techniques. Deep learning models, including a convolutional neural network (CNN), fully connected network (FCN), recurrent neural network (RNN), multi–layer perceptron (MLP), and long short term memory (LSTM), were evaluated for multi–step estimations of an optically active parameter, i.e., electric conductivity (EC), and an inactive parameter, i.e., dissolved oxygen (DO). The estimation of EC and DO concentrations can aid in the analysis of the levels of impurities and oxygen in water. The proposed solution will provide information on the necessary changes needed in water management techniques for the betterment of society. EC and DO parameters were taken as independent variables with dependent parameters, i.e., pH, turbidity, total dissolved solids, chlorophyll– α , Secchi disk depth, and land surface temperature, which were extracted from Landsat–8 data from the years 2014–2021 for the Rawal stream network. The bi–directional LSTM obtained better results with a root mean square error (RMSE) of 0.2 (mg/L) for DO and an RMSE of 281.741 (μ S/cm) for EC, respectively. The results suggest that a hybrid approach provides efficient and accurate results in feature extraction and evaluation of multi–step forecast of both optically active and inactive water quality parameters. [ABSTRACT FROM AUTHOR]

The gasotransmitter hydrogen sulfide (H2S) produced by the transsulfuration pathway (TSP) is an important biological mediator, involved in many physiological and pathological processes in multiple higher organisms, including humans. Cystathionine-β-synthase (CBS) and cystathionine-γ-lyase (CSE) enzymes play a central role in H2S production and metabolism. Here, we investigated the role of H2S in learning and memory processes by exploring several Drosophila melanogaster strains with single and double deletions of CBS and CSE developed by the CRISPR/Cas9 technique. We monitored the learning and memory parameters of these strains using the mating rejection courtship paradigm and demonstrated that the deletion of the CBS gene, which is expressed predominantly in the central nervous system, and double deletions completely block short- and long-term memory formation in fruit flies. On the other hand, the flies with CSE deletion preserve short- and long-term memory but fail to exhibit long-term memory retention. Transcriptome profiling of the heads of the males from the strains with deletions in Gene Ontology terms revealed a strong down-regulation of many genes involved in learning and memory, reproductive behavior, cognition, and the oxidation–reduction process in all strains with CBS deletion, indicating an important role of the hydrogen sulfide production in these vital processes. [ABSTRACT FROM AUTHOR]

Simple Summary: Major histocompatibility complex molecules are of significant biological and clinical importance due to their utility in immunotherapy. The prediction of potential MHC binding peptides can estimate a T-cell immune response. The variable length of existing MHC binding peptides creates difficulty for MHC binding prediction algorithms. Thus, we utilized a bilateral and variable long-short term memory neural network to address this specific problem and developed a novel MHC binding prediction tool. As an important part of immune surveillance, major histocompatibility complex (MHC) is a set of proteins that recognize foreign molecules. Computational prediction methods for MHC binding peptides have been developed. However, existing methods share the limitation of fixed peptide sequence length, which necessitates the training of models by peptide length or prediction with a length reduction technique. Using a bidirectional long short-term memory neural network, we constructed BVMHC, an MHC class I and II binding prediction tool that is independent of peptide length. The performance of BVMHC was compared to seven MHC class I prediction tools and three MHC class II prediction tools using eight performance criteria independently. BVMHC attained the best performance in three of the eight criteria for MHC class I, and the best performance in four of the eight criteria for MHC class II, including accuracy and AUC. Furthermore, models for non-human species were also trained using the same strategy and made available for applications in mice, chimpanzees, macaques, and rats. BVMHC is composed of a series of peptide length independent MHC class I and II binding predictors. Models from this study have been implemented in an online web portal for easy access and use. [ABSTRACT FROM AUTHOR]

In immunology, the discovery of regulatory T (Treg) cells was a major breakthrough. Treg cells play a key role in pregnancy maintenance, in the prevention of autoimmune responses, and in the control of all immune responses, including responses to self cells, cancer, infection, and a transplant. It is currently unclear whether Treg cells are capable of long-term memory of an encounter with an antigen. Although the term "immunological memory" usually means an enhanced ability to protect the body from reinfection, the memory of the suppressive activity of Treg cells helps to avoid the state of generalized immunosuppression that may result from the second activation of the immune system. In this review, we would like to discuss the concept of regulatory memory and in which tissues memory Treg cells can perform their functions. [ABSTRACT FROM AUTHOR]

Detecting intrusions from the supervisory control and data acquisition (SCADA) systems is one of the most essential and challenging processes in recent times. Most of the conventional works aim to develop an efficient intrusion detection system (IDS) framework for increasing the security of SCADA against networking attacks. Nonetheless, it faces the problems of complexity in classification, requiring more time for training and testing, as well as increased misprediction results and error outputs. Hence, this research work intends to develop a novel IDS framework by implementing a combination of methodologies, such as clustering, optimization, and classification. The most popular and extensively utilized SCADA attacking datasets are taken for this system's proposed IDS framework implementation and validation. The main contribution of this work is to accurately detect the intrusions from the given SCADA datasets with minimized computational operations and increased accuracy of classification. Additionally the proposed work aims to develop a simple and efficient classification technique for improving the security of SCADA systems. Initially, the dataset preprocessing and clustering processes were performed using the multifacet data clustering model (MDCM) in order to simplify the classification process. Then, the hybrid gradient descent spider monkey optimization (GDSMO) mechanism is implemented for selecting the optimal parameters from the clustered datasets, based on the global best solution. The main purpose of using the optimization methodology is to train the classifier with the optimized features to increase accuracy and reduce processing time. Moreover, the deep sequential long short term memory (DS-LSTM) is employed to identify the intrusions from the clustered datasets with efficient data model training. Finally, the proposed optimization-based classification methodology's performance and results are validated and compared using various evaluation metrics. [ABSTRACT FROM AUTHOR]

Time series forecasting of passenger demand is crucial for optimal planning of limited resources. For smart cities, passenger transport in urban areas is an increasingly important problem, because the construction of infrastructure is not the solution and the use of public transport should be encouraged. One of the most sophisticated techniques for time series forecasting is Long Short Term Memory (LSTM) neural networks. These deep learning models are very powerful for time series forecasting but are not interpretable by humans (black-box models). Our goal was to develop a predictive and linguistically interpretable model, useful for decision making using large volumes of data from different sources. Our case study was one of the most demanded bus lines of Madrid. We obtained an interpretable model from the LSTM neural network using a surrogate model and the 2-tuple fuzzy linguistic model, which improves the linguistic interpretability of the generated Explainable Artificial Intelligent (XAI) model without losing precision. [ABSTRACT FROM AUTHOR]

Maintaining bridges that support road infrastructure is critical to the economy and human life. Structural health monitoring of bridges using vibration includes direct monitoring and drive-by monitoring. Drive-by monitoring uses a vehicle equipped with accelerometers to drive over bridges and estimates the bridge's health from the vehicle vibration obtained. In this study, we attempt to identify the driving segments on bridges in the vehicle vibration data for the practical application of drive-by monitoring. We developed an in-vehicle sensor system that can measure three-dimensional behavior, and we propose a new problem of identifying the driving segment of vehicle vibration on a bridge from data measured in a field experiment. The "on a bridge" label was assigned based on the peaks in the vehicle vibration when running at joints. A supervised binary classification model using C-LSTM (Convolution—Long-Term Short Memory) networks was constructed and applied to data measured, and the model was successfully constructed with high accuracy. The challenge is to build a model that can be applied to bridges where joints do not exist. Therefore, future work is needed to propose a running label on bridges based on bridge vibration and extend the model to a multi-class model. [ABSTRACT FROM AUTHOR]

The proliferation of sensing technologies such as sensors has resulted in vast amounts of time-series data being produced by machines in industrial plants and factories. There is much information available that can be used to predict machine breakdown and degradation in a given factory. The downtime of industrial equipment accounts for heavy losses in revenue that can be reduced by making accurate failure predictions using the sensor data. Internet of Things (IoT) technologies have made it possible to collect sensor data in real time. We found that hybrid modelling can result in efficient predictions as they are capable of capturing the abstract features which facilitate better predictions. In addition, developing effective optimization strategy is difficult because of the complex nature of different sensor data in real time scenarios. This work proposes a method for multivariate time-series forecasting for predictive maintenance (PdM) based on a combination of convolutional neural networks and long short term memory with skip connection (CNN-LSTM). We experiment with CNN, LSTM, and CNN-LSTM forecasting models one by one for the prediction of machine failures. The data used in this experiment are from Microsoft's case study. The dataset provides information about the failure history, maintenance history, error conditions, and machine features and telemetry, which consists of information such as voltage, pressure, vibration, and rotation sensor values recorded between 2015 and 2016. The proposed hybrid CNN-LSTM framework is a two-stage end-to-end model in which the LSTM is leveraged to analyze the relationships among different time-series data variables through its memory function, and 1-D CNNs are responsible for effective extraction of high-level features from the data. Our method learns the long-term patterns of the time series by extracting the short-term dependency patterns of different time-series variables. In our evaluation, CNN-LSTM provided the most reliable and highest prediction accuracy. [ABSTRACT FROM AUTHOR]

The use of renewable energies, such as Photovoltaic (PV) solar power, is necessary to meet the growing energy consumption. PV solar power generation has intrinsic characteristics related to the climatic variables that cause intermittence during the generation process, promoting instabilities and insecurity in the electrical system. One of the solutions for this problem uses methods for the Prediction of Solar Photovoltaic Power Generation (PSPPG). In this context, the aim of this study is to develop and compare the prediction accuracy of solar irradiance between Artificial Neural Network (ANN) and Long-Term Short Memory (LSTM) network models, from a comprehensive analysis that simultaneously considers two distinct sets of exogenous meteorological input variables and three short-term prediction horizons (1, 15 and 60 min), in a controlled experimental environment. The results indicate that there is a significant difference (p < 0.001) in the prediction accuracy between the ANN and LSTM models, with better overall prediction accuracy skill for the LSTM models (MAPE = 19.5%), except for the 60 min prediction horizon. Furthermore, the accuracy difference between the ANN and LSTM models decreased as the prediction horizon increased, and no significant influence was observed on the accuracy of the prediction with both sets of evaluated meteorological input variables. [ABSTRACT FROM AUTHOR]

The activation of cyclic adenosine monophosphate (cAMP) response element-binding protein (CREB) via phosphorylation in the hippocampus is an important signaling mechanism for enhancing memory processing. Although melatonin is known to increase CREB expression in various animal models, the signaling mechanism between melatonin and CREB has been unknown in vitro. Thus, we confirmed the signaling pathway between the melatonin receptor 1 (MT1) and CREB using melatonin in HT-22 cells. Melatonin increased MT1 and gradually induced signals associated with long-term memory processing through phosphorylation of Raf, ERK, p90RSK, CREB, and BDNF expression. We also confirmed that the calcium, JNK, and AKT pathways were not involved in this signaling pathway by melatonin in HT-22 cells. Furthermore, we investigated whether melatonin regulated the expressions of CREB-BDNF associated with long-term memory processing in aged HT-22 cells. In conclusion, melatonin mediated the MT1-ERK-p90RSK-CREB-BDNF signaling pathway in the in vitro long-term memory processing model and increased the levels of p-CREB and BDNF expression in melatonin-treated cells compared to untreated HT-22 cells in the cellular aged state. Therefore, this paper suggests that melatonin induces CREB signaling pathways associated with long-term memory processing in vitro. [ABSTRACT FROM AUTHOR]

Definition: Limbic encephalitis (LE) is an inflammatory disease of the brain, in which lesion is anatomically limited in structures of the limbic system. In some cases, LE can start with symptoms of limbic dysfunction with further involvement of other regions of the brain. Classic LE syndrome includes such symptoms as the development of personality disorders, depression, sleep disorders, epileptic seizures, hallucinations and cognitive disorders (short-term and long-term memory impairment). The information of clinical examination, electroencephalogram (EEG), magnetic resonance imaging (MRI) and cerebrospinal fluid studies (CSF) suggest the diagnosis of LE in most patients with Coronavirus Disease 2019 (COVID-19). [ABSTRACT FROM AUTHOR]

Statistical methods were traditionally primarily used for time series forecasting. However, new hybrid methods demonstrate competitive accuracy, leading to increased machine-learning-based methodologies in the financial sector. However, very little development has been seen in explainable AI (XAI) for financial time series prediction, with a growing mandate for explainable systems. This study aims to determine if the existing XAI methodology is transferable to the context of financial time series prediction. Four popular methods, namely, ablation, permutation, added noise, and integrated gradients, were applied to a recurrent neural network (RNN), long short-term memory (LSTM), and a gated recurrent unit (GRU) network trained on S&P 500 stocks data to determine the importance of features, individual data points, and specific cells in each architecture. The explainability analysis revealed that GRU displayed the most significant ability to retain long-term information, while the LSTM disregarded most of the given input and instead showed the most notable granularity to the considered inputs. Lastly, the RNN displayed features indicative of no long-term memory retention. The applied XAI methods produced complementary results, reinforcing paradigms on significant differences in how different architectures predict. The results show that these methods are transferable in the financial forecasting sector, but a more sophisticated hybrid prediction system requires further confirmation. [ABSTRACT FROM AUTHOR]

Background and motivation: Every year, millions of Muslims worldwide come to Mecca to perform the Hajj. In order to maintain the security of the pilgrims, the Saudi government has installed about 5000 closed circuit television (CCTV) cameras to monitor crowd activity efficiently. Problem: As a result, these cameras generate an enormous amount of visual data through manual or offline monitoring, requiring numerous human resources for efficient tracking. Therefore, there is an urgent need to develop an intelligent and automatic system in order to efficiently monitor crowds and identify abnormal activity. Method: The existing method is incapable of extracting discriminative features from surveillance videos as pre-trained weights of different architectures were used. This paper develops a lightweight approach for accurately identifying violent activity in surveillance environments. As the first step of the proposed framework, a lightweight CNN model is trained on our own pilgrim's dataset to detect pilgrims from the surveillance cameras. These preprocessed salient frames are passed to a lightweight CNN model for spatial features extraction in the second step. In the third step, a Long Short Term Memory network (LSTM) is developed to extract temporal features. Finally, in the last step, in the case of violent activity or accidents, the proposed system will generate an alarm in real time to inform law enforcement agencies to take appropriate action, thus helping to avoid accidents and stampedes. Results: We have conducted multiple experiments on two publicly available violent activity datasets, such as Surveillance Fight and Hockey Fight datasets; our proposed model achieved accuracies of 81.05 and 98.00, respectively. [ABSTRACT FROM AUTHOR]

Articulatory features are proved to be efficient in the area of speech recognition and speech synthesis. However, acquiring articulatory features has always been a difficult research hotspot. A lightweight and accurate articulatory model is of significant meaning. In this study, we propose a novel temporal convolution network-based acoustic-to-articulatory inversion system. The acoustic feature is converted into a high-dimensional hidden space feature map through temporal convolution with frame-level feature correlations taken into account. Meanwhile, we construct a two-part target function combining prediction's Root Mean Square Error (RMSE) and the sequences' Pearson Correlation Coefficient (PCC) to jointly optimize the performance of the specific inversion model from both aspects. We also further conducted an analysis on the impact of the weight between the two parts on the final performance of the inversion model. Extensive experiments have shown that our, temporal convolution networks (TCN) model outperformed the Bi-derectional Long Short Term Memory model by 1.18 mm in RMSE and 0.845 in PCC with 1 4 model parameters when optimizing evenly with RMSE and PCC aspects. [ABSTRACT FROM AUTHOR]

Accurate forecasts of ocean waves energy can not only reduce costs for investment, but it is also essential for the management and operation of electrical power. This paper presents an innovative approach based on long short-term memory (LSTM) to predict the power generation of an economical wave energy converter named "Searaser". The data for analysis is provided by collecting the experimental data from another study and the exerted data from a numerical simulation of Searaser. The simulation is performed with Flow-3D software, which has high capability in analyzing fluid–solid interactions. The lack of relation between wind speed and output power in previous studies needs to be investigated in this field. Therefore, in this study, wind speed and output power are related with an LSTM method. Moreover, it can be inferred that the LSTM network is able to predict power in terms of height more accurately and faster than the numerical solution in a field of predicting. The network output figures show a great agreement, and the root mean square is 0.49 in the mean value related to the accuracy of the LSTM method. Furthermore, the mathematical relation between the generated power and wave height was introduced by curve fitting of the power function to the result of the LSTM method. [ABSTRACT FROM AUTHOR]

To meet the challenge of video target tracking, based on a self-organization mapping network (SOM) and correlation filter, a long-term visual tracking algorithm is proposed. Objects in different videos or images often have completely different appearance, therefore, the self-organization mapping neural network with the characteristics of signal processing mechanism of human brain neurons is used to perform adaptive and unsupervised features learning. A reliable method of robust target tracking is proposed, based on multiple adaptive correlation filters with a memory function of target appearance at the same time. Filters in our method have different updating strategies and can carry out long-term tracking cooperatively. The first is the displacement filter, a kernelized correlation filter that combines contextual characteristics to precisely locate and track targets. Secondly, the scale filters are used to predict the changing scale of a target. Finally, the memory filter is used to maintain the appearance of the target in long-term memory and judge whether the target has failed to track. If the tracking fails, the incremental learning detector is used to recover the target tracking in the way of sliding window. Several experiments show that our method can effectively solve the tracking problems such as severe occlusion, target loss and scale change, and is superior to the state-of-the-art methods in the aspects of efficiency, accuracy and robustness. [ABSTRACT FROM AUTHOR]

Traffic safety has been thought of as a basic feature of transportation, recent developments in civil aviation have emphasized the need for risk identification and safety prediction. This study aims to increase en-route flight safety through the development of prediction models for flight conflicts. Firstly, flight conflicts time series and traffic parameters are extracted from historical ADS-B data. In the second step, a Long Short-Term Memory (LSTM) model is trained to make a one-step-ahead prediction on the flight conflict time series. The results show that the LSTM model has the greatest prediction effect (MAE 0.3901) with comparison to other models. Based on that, we add traffic parameters (volume, density, velocity) into the LSTM model as new input variables and issue a comprehensive analysis of the relative predictive power of traffic parameters. The accuracy of prediction model is validated with a mean error of less than 3%. Based on the improvements of model performance brought by traffic parameters, LSTM models with a single traffic parameter are proposed for further discussion. The results illustrate that volume is the most important factor in promoting prediction accuracy and density has an advantage of improvement in the aspect of model stability. [ABSTRACT FROM AUTHOR]