Search

In recent years, deep learning has revolutionized natural language processing (NLP) by enabling the development of models that can learn complex representations of language data, leading to significant improvements in performance across a wide range of NLP tasks. Deep learning models for NLP typically use large amounts of data to train deep neural networks, allowing them to learn the patterns and relationships in language data. This is in contrast to traditional NLP approaches, which rely on hand-engineered features and rules to perform NLP tasks. The ability of deep neural networks to learn hierarchical representations of language data, handle variable-length input sequences, and perform well on large datasets makes them well-suited for NLP applications. Driven by the exponential growth of textual data and the increasing demand for condensed, coherent, and informative summaries, text summarization has been a critical research area in the field of NLP. Applying deep learning to text summarization refers to the use of deep neural networks to perform text summarization tasks. In this survey, we begin with a review of fashionable text summarization tasks in recent years, including extractive, abstractive, multi-document, and so on. Next, we discuss most deep learning-based models and their experimental results on these tasks. The paper also covers datasets and data representation for summarization tasks. Finally, we delve into the opportunities and challenges associated with summarization tasks and their corresponding methodologies, aiming to inspire future research efforts to advance the field further. A goal of our survey is to explain how these methods differ in their requirements as understanding them is essential for choosing a technique suited for a specific setting. This survey aims to provide a comprehensive review of existing techniques, evaluation methodologies, and practical applications of automatic text summarization. [ABSTRACT FROM AUTHOR]

Cervical cancer (CC) has become one of the serious and deadly diseases in women around the world. Predicting a CC is at risk because testing is not possible at the early stage. Doctors predict the types of cancer by collecting cervical cells and by intervening in person. This approach affects the level of prediction due to human negligence, high cost, and is time consuming. In this paper, we propose the automatic cancer classification using deep neural network to overcome this problem. The proposed work has four stages namely, pre-processing, outlier elimination, dimensionality reduction, and classification. Initially, the missing test data should be removed. Second, the inconsistent data are eliminated based on identical values. Third, principal component analysis (PCA) is used to overcome the limitations caused by high-volume data. Finally, enter the reduced size database in the proposed neural network (DNN) classifier and classify the input data as normal or abnormal. We implement the suggested method using Python and we inspect the performance in terms of different metrics. [ABSTRACT FROM AUTHOR]

A novel ensemble machine learning approach for predicting energy consumption in smart appliances is presented in this paper. The main objective is minimizing the number of necessary sensors and improving the prediction accuracy at the same time. The proposed method combines the Fuzzy C-Means method with a multi-stream deep neural network to achieve this goal. The method focuses on prediction accuracy and aims to extract the minimum number of essential features from the dataset corresponding to the required sensors. These selected features are then scatter-reduced and homogenized into subsets. Each subset is used to train a cluster-specific deep neural network designed exclusively for that subset. The final prediction is obtained by computing the fuzzy-weighted sum of these cluster-specific network outputs. Numerical results show that the proposed prediction method outperforms conventional methods in terms of root mean square error and mean absolute percentage error criteria, despite using fewer sensors. This improvement can be attributed to the reduced dataset scatter, which improves the learning speed and model performance. Furthermore, the fuzzy combination of the outputs improves the final prediction accuracy. Overall, the proposed approach provides a more cost-effective and accurate solution for predicting the energy consumed by smart appliances. [ABSTRACT FROM AUTHOR]

This paper plans to implement a novel detection model of maliciously encrypted internet protocol network flow using the deep structured concept. The major processing levels are (i) data collection, (ii) feature extraction, (iii) optimal feature selection, and (iv) detection. In the beginning, the standard dataset is taken from online databases. The deep convolutional neural network (DCNN) is introduced for the deep feature extraction process. The accurate features are chosen by the crossover decision-based krill herd algorithm (CD-KHA) which helps to minimize the training complexity of the deep structured architecture. These selected features are given to the hybridized deep learning with long short-term memory (LSTM) and deep neural network (DNN). Here, the structural design of the model is improved by the same CD-KHA. Through the comparison and analysis, the accuracy rate of the offered method shows higher performance than the other baseline approaches. [ABSTRACT FROM AUTHOR]

In this paper, we analyzed the deep neural network (DNN) model and proposed a DNN-based method to build the training model for professional farmers. This paper aims to construct the vocational farmer cultivation model and seek a better path for transforming farmers into new experienced farmers by analyzing each training body involved in the cultivation of vocational farmers and studying their respective problems and reasons. The conceptual and logical structures of the system database were designed, and MySQL was selected for database implementation to complete the information of professional farmers. The system network topology and logical architecture are created, and the functions of view, control, business logic and data access layers are divided. This paper combines the DNN with the vocational farmer training enhancement decision tree. The experimental results of this model are most intuitive and accurate. This paper reconstructs the neural network model using the global average pooling layer to better model the vocational farmer training model to replace the fully connected layer in the original convolutional neural network. At the same time, to make the network model produce a lower probability of overfitting, a dropout layer is added to the layer after the fully connected layer to improve the efficiency of the neural network further to enhance vocational farmer training. The experimental content of this paper provides a new research direction for the estimation of vocational farmer cultivation. The above modeling is used to improve the vocational farmer cultivation model and accelerate the process of vocational farmer cultivation. [ABSTRACT FROM AUTHOR]

The price of carbon emission rights in the market fluctuates greatly due to various factors from economy, finance, and climate. For an enterprise that needs to conduct carbon trading activities, it is extremely necessary to fully grasp the price of carbon trading in the future period. Thus in this paper, a deep neural network-based assistive decision model for financial risk prediction in carbon trading market is proposed for this purpose. Specifically, the dynamic risk spillover effects of domestic and international carbon trading markets are studied, and a frontier time-varying model is utilized to measure the risk spillover effects. Then, the deep neural network is used for quantitative research and to construct an intelligent decision scheme that outputs financial risk prediction results. Four perspectives, energy price, climate environment, carbon market price, and macroeconomics, are selected as the input to analyze the influence factors of carbon emission rights price. Finally, several linear regression models are adopted as the baseline methods for comparison, and experimental results show that the proposed method can achieve better prediction performance compared with baseline methods. [ABSTRACT FROM AUTHOR]

Malware developers often employ code obfuscation techniques to conceal their malicious functionality, making it challenging to detect and analyze such software. While various de-obfuscation techniques exist, the majority of them require prior knowledge of the obfuscation tools and techniques in use. Identifying the specific obfuscation tools or algorithms applied to the obfuscated code is thus of vital importance, which, however, typically demands in-depth expert knowledge and substantial efforts. Therefore, this paper presents DeObA, a deep learning (DL) driven approach for the precise and efficient detection of obfuscation algorithms on the fine-grained function-level code snippets. To comprehensively capture unique patterns or features of different obfuscation algorithms from code, DeObA works on multiple distinct code views, encompassing token sequences, abstract syntax trees (AST) and program dependency graphs (PDG), which will reflect the code's lexical morphology, syntactic and structural aspects. After individually collecting obfuscation-indicative features with well-matched DL encoder from each code view, a self-attention-based fusion strategy is performed on these features to produce an integrated, dense, yet feature-rich vector. This vector is then fed into a softmax classification layer for prediction. Due to the lack of a moderately sized dataset, a large obfuscation corpus is curated with 7 different obfuscation tools and a total of 12 obfuscation algorithms on 39,070 C/C + + functions. The experimental evaluations conducted on the dataset exhibit a distinguished detection performance of DeObA, which achieve accuracy rates of 99.90% and 99.19% on the obfuscation tool detection and obfuscation algorithm detection tasks, respectively. The ablation study also confirms the active role of considering multiple distinct code views and the effectiveness of the designed self-attention-based fusion strategy. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) have been successfully applied to investigations of numerical dynamics of finite-dimensional nonlinear systems such as ODEs instead of finding numerical solutions to ODEs via the traditional Runge–Kutta method and its variants. To show the advantages of DNNs, in this paper, we demonstrate that the DNNs are more efficient in finding topological horseshoes in chaotic dynamical systems. [ABSTRACT FROM AUTHOR]

To improve the recognition ability of clinical named entity recognition (CNER) in a limited number of Chinese electronic medical records, it provides meaningful support for clinical advanced knowledge extraction. In this paper, using CCKS2019 Chinese electronic medical record as an experimental data source, a fusion model enhanced by knowledge graph (KG) is proposed, and the model is applied to specific Chinese CNER tasks. This study consists of three main parts: single-mode model construction and comparison experiment, KG enhancement experiment, and model fusion experiment. The model has achieved good performance in CNER from the results. The accuracy rate, recall rate, and F1 value are 83.825%, 84.705%, and 84.263%, respectively, which is the global optimal, which proves the effectiveness of the model. This provides a good help for further research of medical information. [ABSTRACT FROM AUTHOR]

Catastrophic forgetting is a well-known characteristic of diverse parameterized supervised learning models. Artificial Neural Networks (ANN) face severe catastrophic forgetting or catastrophic interference in the sequential learning of information that is intolerable to both engineering applications and the human memory model. This problem can be solved through the machine learning community. The main intent of this paper is to implement a novel continuous learning model that could overcome the problem of catastrophic forgetting. The stream data from diverse benchmark sources are used for experimenting. The proposed model adopts the Deep Neural Network (DNN) with testing weight updates. When new data are given, the hybrid meta-heuristic algorithm helps to update the weight that manages to prevent the learning from catastrophic forgetting. The weight update strategy for solving the catastrophic forgetting is done by the hybridization of Shark Smell Optimization (SSO) and Jaya Algorithm (JA) that is named as Hybrid Shark Smell with Jaya Optimization (HSS-JO). A multi-objective function concerning the parameters associated with catastrophic forgetting like accuracy and remembering is used for framing the proposed continuous learning. The proof of the proposed model over conventional models on three publicly available datasets is given for final validation. From the analysis, in Table 3, the accuracy of the proposed HSS-JO-DNN is 38%, 0.5%, 0.55%, 0.14%, 0.98%, and 0.5% superior to DT, NB, KNN, SVM, NN, and RNN, respectively. For dataset 2, the FNR of the proposed HSS-JO-DNN is 90% superior to DT, 89% improved than NB, KNN, and NN, 94% improved than SVM, and 24% improved than RNN. Similarly, the proposed HSS-JO performance is higher in all the results. Thus, the proposed HSS-JO performs better than all the other traditional methods. [ABSTRACT FROM AUTHOR]

In the process of learning, learners will express their emotions through a variety of forms, facial expressions and voice are more obvious, which are most easily obtained through computers. In the previous methods, it is mainly based on a single modal, such as expression, speech, text and so on. Due to the diversity of information, the accuracy rate of multimodal recognition is higher than that of single modal recognition. Therefore, this paper proposed a DNN-based multimodal learning emotion analysis method which combines video and speech to detect students' learning emotion in real time. We use this method to automatically identify learning emotions in primary school English classroom. According to different learning emotions, the PAD emotion scale was used to correspond learning emotions with learning states. Teachers can judge students' learning state according to the change of students' learning emotions, so as to adjust teaching methods and strategies in time. [ABSTRACT FROM AUTHOR]

The optimization of the problems significantly improves the solution of the complex problems. The reduction in the feature dimensionality is enormously salient to reduce the redundant features and improve the system accuracy. In this paper, an amalgamation of different concepts is proposed to optimize the features and improve the system classification. The experiment is performed on the facial expression detection application by proposing the amalgamation of deep neural network models with the variants of the gravitational search algorithm. Facial expressions are the movement of the facial components such as lips, nose, eyes that are considered as the features to classify human emotions into different classes. The initial feature extraction is performed with the local binary pattern. The extracted feature set is optimized with the variants of gravitational search algorithm (GSA) as standard gravitational search algorithm (SGSA), binary gravitational search algorithm (BGSA) and fast discrete gravitational search algorithm (FDGSA). The deep neural network models of deep convolutional neural network (DCNN) and extended deep convolutional neural network (EDCNN) are employed for the classification of emotions from imagery datasets of JAFFE and KDEF. The fixed pose images of both the datasets are acquired and comparison based on average recognition accuracy is performed. The comparative analysis of the mentioned techniques and state-of-the-art techniques illustrates the superior recognition accuracy of the FDGSA with the EDCNN technique. [ABSTRACT FROM AUTHOR]

Visualization is primarily utilized as a training method to enhance athletic movement quality, increase concentration power, and minimize competition stress on the player while building firm confidence. Physical literacy (PL) provides a valuable lens for analyzing physical activity (PA) movement in more significant social and affective learning processes. This paper presents an Interactive Visualization positioning in physical education (IVPPE) to deal with the signal fluctuations and positioning techniques in visualizing Deep Neural Network (DNN). To ensure the success of their game, athletes are always looking for new ways to improve their health and performance. Using sensors to keep tabs on training and recovery has become more popular among athletes. Currently, sports teams are using sensors to track both the players' internal and external workloads. It illustrates the multilayer localizer (MLL) based on transfer learning to improve the positioning accuracy and physical literacy positioning model (PLPM) as a health determinant. A variety of data augmentation techniques are used to combat signal fluctuations. As a result, the combined effects of motivation-promoting physical activity-based visualization improve the accuracy ratio to 96.7%, prediction ratio to 96.2%, efficiency ratio to 96.8%, and reduce the error rate to 18.7%, stress level (52.8%) compared to other conventional models and have a positive impact on the localizer and positioning, making a difference in physical activity (PA) levels. [ABSTRACT FROM AUTHOR]

In this paper, a speech enhancement method using noise classification and Deep Neural Network (DNN) was proposed. Gaussian mixture model (GMM) was employed to determine the noise type in speech-absent frames. DNN was used to model the relationship between noisy observation and clean speech. Once the noise type was determined, the corresponding DNN model was applied to enhance the noisy speech. GMM was trained with mel-frequency cepstrum coefficients (MFCC) and the parameters were estimated with an iterative expectation-maximization (EM) algorithm. Noise type was updated by spectrum entropy-based voice activity detection (VAD). Experimental results demonstrate that the proposed method could achieve better objective speech quality and smaller distortion under stationary and non-stationary conditions. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) with ReLU activation function are proved to be able to express viscosity solutions of linear partial integrodifferential equations (PIDEs) on state spaces of possibly high dimension d. Admissible PIDEs comprise Kolmogorov equations for high-dimensional diffusion, advection, and for pure jump Lévy processes. We prove for such PIDEs arising from a class of jump-diffusions on ℝ d , that for any suitable measure μ d on ℝ d , there exist constants C , , > 0 such that for every ∈ (0 , 1 ] and for every d ∈ ℕ the DNN L 2 (μ d) -expression error of viscosity solutions of the PIDE is of size with DNN size bounded by C d − . In particular, the constant C > 0 is independent of d ∈ ℕ and of ∈ (0 , 1 ] and depends only on the coefficients in the PIDE and the measure used to quantify the error. This establishes that ReLU DNNs can break the curse of dimensionality (CoD for short) for viscosity solutions of linear, possibly degenerate PIDEs corresponding to suitable Markovian jump-diffusion processes. As a consequence of the employed techniques, we also obtain that expectations of a large class of path-dependent functionals of the underlying jump-diffusion processes can be expressed without the CoD. [ABSTRACT FROM AUTHOR]