Search results

To predict the price of battery-grade lithium carbonate accurately and provide proper guidance to investors, a method called MFTBGAM is proposed in this study. This method integrates textual and numerical information using TCN-BiGRU–Attention.

The Word2Vec model is initially employed to process the gathered textual data concerning battery-grade lithium carbonate. Subsequently, a dual-channel text-numerical extraction model, integrating TCN and BiGRU, is constructed to extract textual and numerical features separately. Following this, the attention mechanism is applied to extract fusion features from the textual and numerical data. Finally, the market price prediction results for battery-grade lithium carbonate are calculated and outputted using the fully connected layer.

Experiments in this study are carried out using datasets consisting of news and investor commentary. The findings reveal that the MFTBGAM model exhibits superior performance compared to alternative models, showing its efficacy in precisely forecasting the future market price of battery-grade lithium carbonate.

The dataset analyzed in this study spans from 2020 to 2023, and thus, the forecast results are specifically relevant to this timeframe. Altering the sample data would necessitate repetition of the experimental process, resulting in different outcomes. Furthermore, recognizing that raw data might include noise and irrelevant information, future endeavors will explore efficient data preprocessing techniques to mitigate such issues, thereby enhancing the model’s predictive capabilities in long-term forecasting tasks.

The price prediction model serves as a valuable tool for investors in the battery-grade lithium carbonate industry, facilitating informed investment decisions. By using the results of price prediction, investors can discern opportune moments for investment. Moreover, this study utilizes two distinct types of text information – news and investor comments – as independent sources of textual data input. This approach provides investors with a more precise and comprehensive understanding of market dynamics.

We propose a novel price prediction method based on TCN-BiGRU Attention for “text-numerical” information fusion. We separately use two types of textual information, news and investor comments, for prediction to enhance the model's effectiveness and generalization ability. Additionally, we utilize news datasets including both titles and content to improve the accuracy of battery-grade lithium carbonate market price predictions.

A new Chatbot system is implemented to provide both voice-based and textual-based communication to address student queries without any delay. Initially, the input texts are gathered from the chat and then the gathered text is fed to pre-processing techniques like tokenization, stemming of words and removal of stop words. Then, the pre-processed data are given to the Natural Learning Process (NLP) for extracting the features, where the XLnet and Bidirectional Encoder Representations from Transformers (BERT) are utilized to extract the features. From these extracted features, the target-based fused feature pools are obtained. Then, the intent detection is carried out to extract the answers related to the user queries via Enhanced 1D-Convolutional Neural Networks with Long Short Term Memory (E1DCNN-LSTM) where the parameters are optimized using Position Averaging of Binary Emperor Penguin Optimizer with Colony Predation Algorithm (PA-BEPOCPA). Finally, the answers are extracted based on the intent of a particular student’s teaching materials like video, image or text. The implementation results are analyzed through different recently developed Chatbot detection models to validate the effectiveness of the newly developed model.

A smart model for the NLP is developed to help education-related institutions for an easy way of interaction between students and teachers with high prediction of accurate data for the given query. This research work aims to design a new educational Chatbot to assist the teaching-learning process with the NLP. The input data are gathered from the user through chats and given to the pre-processing stage, where tokenization, steaming of words and removal of stop words are used. The output data from the pre-processing stage is given to the feature extraction phase where XLnet and BERT are used. In this feature extraction, the optimal features are extracted using hybrid PA-BEPOCPA to maximize the correlation coefficient. The features from XLnet and features from BERT were given to target-based features fused pool to produce optimal features. Here, the best features are optimally selected using developed PA-BEPOCPA for maximizing the correlation among coefficients. The output of selected features is given to E1DCNN-LSTM for implementation of educational Chatbot with high accuracy and precision.

The investigation result shows that the implemented model achieves maximum accuracy of 57% more than Bidirectional long short-term memory (BiLSTM), 58% more than One Dimansional Convolutional Neural Network (1DCNN), 59% more than LSTM and 62% more than Ensemble for the given dataset.

The prediction accuracy was high in this proposed deep learning-based educational Chatbot system when compared with various baseline works.

The overload of user-generated content in online mental health community makes the focus and resonance tendencies of the participating groups less clear. Thus, the purpose of this paper is to build an early identification mechanism for users' high attention content to promote early intervention and effective dissemination of professional medical guidance.

We decouple the identification mechanism from two processes: early feature combing and algorithmic model construction. Firstly, based on the differentiated needs and concerns of the participant groups, the multiple features of “information content + source users” are refined. Secondly, a multi-level fusion model is constructed for features processing. Specifically, Bidirectional Encoder Representation from Transformers (BERT)-Bi-directional Long-Short Term Memory (BiLSTM)-Linear are used to refine the semantic features, while Graph Attention Networks (GAT) is used to capture the entity attributes and relation features. Finally, the Convolutional Neural Network (CNN) is used to optimize the multi-level fusion features.

The results show that the ACC of the multi-level fusion model is 84.42%, F1 is 79.43% and R is 76.71%. Compared with other baseline models and single feature elements, the ACC and F1 values are improved to different degrees.

The originality of this paper lies in analyzing multiple features based on early stages and constructing a new multi-level fusion model for processing. Further, the study is valuable for the orientation of psychological patients' needs and early guidance of professional medical care.

Harmonic drives are used widely in aviation, robotics and instrumentation due to their benefits including high transmission ratio, compact structure and zero backlash. One of the common faults of a harmonic drive is the axial movement of the input shaft. In such a case, its input shaft moves in the axial direction relative to the body of the harmonic drive. The purpose of this study is to propose two fault diagnosis methods based on the current signal of the driving servomotor for the axial movement failure in terms of input shafts of harmonic drives.

In the two proposed fault diagnosis methods, the wavelet threshold algorithm is firstly used for filtering noises of the motor current signal. Then, the feature of the denoised current signal is extracted by the empirical mode decomposition (EMD) method and the wavelet packet energy-entropy (WPEE) theory, respectively, obtaining two kinds of feature sets. After a deep learning model based on the deep belief network (DBN) is constructed and trained by using these feature sets, we finally identify the normal harmonic drives and the ones with the axial movement fault.

In contrast to the traditional back propagation (BP) neural network model and support vector machine (SVM) model, the fault diagnosis methods based on the combination of the EMD (as well as the WPEE) and the DBN model can obtain higher accuracy rates of fault diagnosis for axial movement of harmonic drives, which can be greater than or equal to 97% based on the data of the performed experiment.

The authors propose two fault diagnosis methods based on the current signal of the driving servomotor for the axial movement failure in terms of input shafts of harmonic drives, which are verified by the experiment. The presented study may be beneficial for the development of self-diagnosis and self-repair systems of different robots and precision machines using harmonic drives.

Incorporating dynamic spatial effects exhibits considerable potential in improving the accuracy of forecasting tourism demands. This study aims to propose an innovative deep learning model for capturing dynamic spatial effects.

A novel deep learning model founded on the transformer architecture, called the spatiotemporal transformer network, is presented. This model has three components: the temporal transformer, spatial transformer and spatiotemporal fusion modules. The dynamic temporal dependencies of each attraction are extracted efficiently by the temporal transformer module. The dynamic spatial correlations between attractions are extracted efficiently by the spatial transformer module. The extracted dynamic temporal and spatial features are fused in a learnable manner in the spatiotemporal fusion module. Convolutional operations are implemented to generate the final forecasts.

The results indicate that the proposed model performs better in forecasting accuracy than some popular benchmark models, demonstrating its significant forecasting performance. Incorporating dynamic spatiotemporal features is an effective strategy for improving forecasting. It can provide an important reference to related studies.

The proposed model leverages high-frequency data to achieve accurate predictions at the micro level by incorporating dynamic spatial effects. Destination managers should fully consider the dynamic spatial effects of attractions when planning and marketing to promote tourism resources.

This study incorporates dynamic spatial effects into tourism demand forecasting models by using a transformer neural network. It advances the development of methodologies in related fields.

纳入动态空间效应在提高旅游需求预测的准确性方面具有相当大的潜力。本研究提出了一种捕捉动态空间效应的创新型深度学习模型。

本研究提出了一种基于变压器架构的新型深度学习模型, 称为时空变压器网络。该模型由三个部分组成：时空转换器、空间转换器和时空融合模块。时空转换器模块可有效提取每个景点的动态时间依赖关系。空间转换器模块可有效提取景点之间的动态空间相关性。提取的动态时间和空间特征在时空融合模块中以可学习的方式进行融合。通过卷积运算生成最终预测结果。

结果表明, 与一些流行的基准模型相比, 所提出的模型在预测准确性方面表现更好, 证明了其显著的预测性能。纳入动态时空特征是改进预测的有效策略。它可为相关研究提供重要参考。

所提出的模型利用高频数据, 通过纳入动态空间效应, 在微观层面上实现了准确预测。旅游目的地管理者在规划和营销推广旅游资源时, 应充分考虑景点的动态空间效应。

本研究通过使用变压器神经网络, 将动态空间效应纳入旅游需求预测模型。它推动了相关领域方法论的发展。

La incorporación de efectos espaciales dinámicos ofrece un considerable potencial para mejorar la precisión de la previsión de la demanda turística. Este estudio propone un modelo innovador de aprendizaje profundo para capturar los efectos espaciales dinámicos.

Se presenta un novedoso modelo de aprendizaje profundo basado en la arquitectura transformadora, denominado red de transformador espaciotemporal. Este modelo tiene tres componentes: el transformador temporal, el transformador espacial y los módulos de fusión espaciotemporal. El módulo transformador temporal extrae de manera eficiente las dependencias temporales dinámicas de cada atracción. El módulo transformador espacial extrae eficientemente las correlaciones espaciales dinámicas entre las atracciones. Las características dinámicas temporales y espaciales extraídas se fusionan de manera que se puede aprender en el módulo de fusión espaciotemporal. Se aplican operaciones convolucionales para generar las previsiones finales.

Los resultados indican que el modelo propuesto obtiene mejores resultados en la precisión de las previsiones que algunos modelos de referencia conocidos, lo que demuestra su importante capacidad de previsión. La incorporación de características espaciotemporales dinámicas supone una estrategia eficaz para mejorar las previsiones. Esto puede proporcionar una referencia importante para estudios afines.

El modelo propuesto aprovecha los datos de alta frecuencia para lograr predicciones precisas a nivel micro incorporando efectos espaciales dinámicos. Los gestores de destinos deberían tener plenamente en cuenta los efectos espaciales dinámicos de las atracciones en la planificación y marketing para la promoción de los recursos turísticos.

Este estudio incorpora efectos espaciales dinámicos a los modelos de previsión de la demanda turística mediante el empleo de una red neuronal transformadora. Supone un avance en el desarrollo de metodologías en campos afines.

The objective is to develop a more effective model that simplifies and accelerates the news classification process using advanced text mining and deep learning (DL) techniques. A distributed framework utilizing Bidirectional Encoder Representations from Transformers (BERT) was developed to classify news headlines. This approach leverages various text mining and DL techniques on a distributed infrastructure, aiming to offer an alternative to traditional news classification methods.

This study focuses on the classification of distinct types of news by analyzing tweets from various news channels. It addresses the limitations of using benchmark datasets for news classification, which often result in models that are impractical for real-world applications.

The framework’s effectiveness was evaluated on a newly proposed dataset and two additional benchmark datasets from the Kaggle repository, assessing the performance of each text mining and classification method across these datasets. The results of this study demonstrate that the proposed strategy significantly outperforms other approaches in terms of accuracy and execution time. This indicates that the distributed framework, coupled with the use of BERT for text analysis, provides a robust solution for analyzing large volumes of data efficiently. The findings also highlight the value of the newly released corpus for further research in news classification and emotion classification, suggesting its potential to facilitate advancements in these areas.

This research introduces an innovative distributed framework for news classification that addresses the shortcomings of models trained on benchmark datasets. By utilizing cutting-edge techniques and a novel dataset, the study offers significant improvements in accuracy and processing speed. The release of the corpus represents a valuable contribution to the field, enabling further exploration into news and emotion classification. This work sets a new standard for the analysis of news data, offering practical implications for the development of more effective and efficient news classification systems.

Community question answering (CQA) platforms play a significant role in knowledge dissemination and information retrieval. Expert recommendation can assist users by helping them find valuable answers efficiently. Existing works mainly use content and user behavioural features for expert recommendation, and fail to effectively leverage the correlation across multi-dimensional features.

To address the above issue, this work proposes a multi-dimensional feature fusion-based method for expert recommendation, aiming to integrate features of question–answerer pairs from three dimensions, including network features, content features and user behaviour features. Specifically, network features are extracted by first learning user and tag representations using network representation learning methods and then calculating questioner–answerer similarities and answerer–tag similarities. Secondly, content features are extracted from textual contents of questions and answerer generated contents using text representation models. Thirdly, user behaviour features are extracted from user actions observed in CQA platforms, such as following and likes. Finally, given a question–answerer pair, the three dimensional features are fused and used to predict the probability of the candidate expert answering the given question.

The proposed method is evaluated on a data set collected from a publicly available CQA platform. Results show that the proposed method is effective compared with baseline methods. Ablation study shows that network features is the most important dimensional features among all three dimensional features.

This work identifies three dimensional features for expert recommendation in CQA platforms and conducts a comprehensive investigation into the importance of features for the performance of expert recommendation. The results suggest that network features are the most important features among three-dimensional features, which indicates that the performance of expert recommendation in CQA platforms is likely to get improved by further mining network features using advanced techniques, such as graph neural networks. One broader implication is that it is always important to include multi-dimensional features for expert recommendation and conduct systematic investigation to identify the most important features for finding directions for improvement.

This work proposes three-dimensional features given that existing works mostly focus on one or two-dimensional features and demonstrate the effectiveness of the newly proposed features.

The internet has completely merged into contemporary life. People are addicted to using internet services for everyday activities. Consequently, an abundance of information about people and organizations is available online, which encourages the proliferation of cybercrimes. Cybercriminals often use malicious links for large-scale cyberattacks, which are disseminated via email, SMS and social media. Recognizing malicious links online can be exceedingly challenging. The purpose of this paper is to present a strong security system that can detect malicious links in the cyberspace using natural language processing technique.

The researcher recommends a variety of approaches, including blacklisting and rules-based machine/deep learning, for automatically recognizing malicious links. But the approaches generally necessitate the generation of a set of features to generalize the detection process. Most of the features are generated by processing URLs and content of the web page, as well as some external features such as the ranking of the web page and domain name system information. This process of feature extraction and selection typically takes more time and demands a high level of expertise in the domain. Sometimes the generated features may not leverage the full potentials of the data set. In addition, the majority of the currently deployed systems make use of a single classifier for the classification of malicious links. However, prediction accuracy may vary widely depending on the data set and the classifier used.

To address the issue of generating feature sets, the proposed method uses natural language processing techniques (term frequency and inverse document frequency) that vectorize URLs. To build a robust system for the classification of malicious links, the proposed system implements weighted soft voting classifier, an ensemble classifier that combines predictions of base classifiers. The ability or skill of each classifier serves as the base for the weight that is assigned to it.

The proposed method performs better when the optimal weights are assigned. The performance of the proposed method was assessed by using two different data sets (D1 and D2) and compared performance against base machine learning classifiers and previous research results. The outcome accuracy shows that the proposed method is superior to the existing methods, offering 91.4% and 98.8% accuracy for data sets D1 and D2, respectively.

The new customer churn prediction (CCP) utilizing deep learning is developed in this work. Initially, the data are collected from the WSDM-KKBox’s churn prediction challenge dataset. Here, the time-varying data and the static data are aggregated, and then the statistic features and deep features with the aid of statistical measures and “Visual Geometry Group 16 (VGG16)”, accordingly, and the features are considered as feature 1 and feature 2. Further, both features are forwarded to the weighted feature fusion phase, where the modified exploration of driving training-based optimization (ME-DTBO) is used for attaining the fused features. It is then given to the optimized and ensemble-based dilated deep learning (OEDDL) model, which is “Temporal Context Networks (DTCN), Recurrent Neural Networks (RNN), and Long-Short Term Memory (LSTM)”, where the optimization is performed with the aid of ME-DTBO model. Finally, the predicted outcomes are attained and assimilated over other classical models.

The features are forwarded to the weighted feature fusion phase, where the ME-DTBO is used for attaining the fused features. It is then given to the OEDDL model, which is “DTCN, RNN, and LSTM”, where the optimization is performed with the aid of the ME-DTBO model.

The accuracy of the implemented CCP system was raised by 54.5% of RNN, 56.3% of deep neural network (DNN), 58.1% of LSTM and 60% of RNN + DTCN + LSTM correspondingly when the learning percentage is 55.

The proposed CCP framework using the proposed ME-DTBO and OEDDL is accurate and enhances the prediction performance.

Traditional visual simultaneous localization and mapping (SLAM) systems are primarily based on the assumption that the environment is static, which makes them struggle with the interference caused by dynamic objects in complex industrial production environments. This paper aims to improve the stability of visual SLAM in complex dynamic environments through semantic segmentation and its optimization.

This paper proposes a real-time visual SLAM system for complex dynamic environments based on YOLOv5s semantic segmentation, named YLS-SLAM. The system combines semantic segmentation results and the boundary semantic enhancement algorithm. By recognizing and completing the semantic masks of dynamic objects from coarse to fine, it effectively eliminates the interference of dynamic feature points on the pose estimation and enhances the retention and extraction of prominent features in the background, thereby achieving stable operation of the system in complex dynamic environments.

Experiments on the Technische Universität München and Bonn data sets show that, under monocular and Red, Green, Blue - Depth modes, the localization accuracy of YLS-SLAM is significantly better than existing advanced dynamic SLAM methods, effectively improving the robustness of visual SLAM. Additionally, the authors also conducted tests using a monocular camera in a real industrial production environment, successfully validating its effectiveness and application potential in complex dynamic environment.

This paper combines semantic segmentation algorithms with boundary semantic enhancement algorithms to effectively achieve precise removal of dynamic objects and their edges, while ensuring the system's real-time performance, offering significant application value.