Transferring Multi-Channel Convolutional Neural Network Model for Cross-Domain Sentiment Analysis

The influencing factors of community risk are complex. For the low accuracy of traditional prediction model, a multichannel convolutional neural network community risk prediction model is proposed by improving convolutional neural network of deep learning. First of all, in the community risk prediction model, the structure of multichannel input convolutional neural network is selected. Then, add it into the full connection layer. Subsequently, the DenseNet layer is added to establish connections between different network layers. Finally, the receptive field is improved, and the gradient disappearance is solved. Thus, the prediction accuracy of model is improved. Compared with the traditional model, the proposed multichannel convolutional neural network model has better prediction accuracy. In addition, it performs better on the three indicators, namely, correlation coefficient R , coefficient of determination R 2 , and mean square root error RMSE. Compared with the commonly used LSTM model and logic regression model, the proposed model also has certain advantages, which is more suitable for community risk prediction.

As the number of social media comments available online grows, the spread of hate speech has grown gradually. When someone uses hate speech as a weapon to injure, degrade, and humiliate others, their freedom, dignity, and personhood can be jeopardized. Deep neural network-based hate speech detection models, such as the conventional single channel convolutional neural network (SC-CNN), have recently demonstrated promising results. The success of the models, however, is dependent on the type of language they are trained on and the training data size. Even with a small amount of training data, the model's performance can be improved by using a multichannel convolutional neural network (MC-CNN) model. The study assesses and compares the performance of a multichannel convolutional neural network model to single channel convolutional neural network models using a support vector machine (SVM) as a baseline. The models' F1 score values are computed, and promising results are obtained. The MC-CNN model outperforms the SC-CNN models in all three hate speech datasets. The study's findings indicate that the proposed MC-CNN model could be used as a deep learning-based alternative for hate speech detection.

Production forecasting is vital in the oil and gas sector, empowering engineers with insights for effective reservoir management. This paper introduces the concept of Transfer Learning as a powerful tool in the domain of machine-learning-assisted production forecasting that accounts of 3D spatial distributions of three geological properties, namely porosity, permeability, and saturation, two completion parameters, namely hydraulic fracture height and length, and production constraint. Transfer learning efficiently leverages knowledge from one problem to improve generalization on another, especially when data is scarce and computational resources are limited. To demonstrate the utility of transfer learning, we evaluate two scenarios of transfer learning. The first transfer learning scenario demonstrates the generalization of the forecasting to cases with variable hydraulic fracture spacing using limited training data. The second transfer learning scenario demonstrates the generalization of the forecasting to cases with variable natural fracture spacing and natural fracture permeability using limited training data. Source dataset contained 2000 realizations, while the target dataset contained 20, 40, 60, 80, 100, 250, 500, or 1000 realizations to represent the scenarios of limited training-data availability. The study confirms the benefits of transfer learning when the training dataset size is small (generally less than 100 training realizations); however, under large training dataset size (around 500 or more training realizations), transfer learning is not needed. For the first scenario involving variable hydraulic fracture spacing, the use of transfer learning ensured that the source model can be trained on target dataset with 80 realizations for gas rate forecasting at an accuracy of 25% in terms of MAPE, and with 500 realizations for condensate rate forecasting at an accuracy of 12% in terms of MAPE. Similarly, for the second scenario involving variable natural fracture spacing and natural fracture permeability, the use of transfer learning ensured that the source model can be trained on target dataset with 250 realizations for gas rate forecasting at an accuracy of 24% in terms of MAPE, and with 500 realizations for condensate rate forecasting at an accuracy of 23% in terms of MAPE. This illustrates the potential of transfer learning in improving forecasting models with limited data using a well pre-trained model and enhanced hyperparameter tuning of the transfer learning model. For cases with 500 or more training realizations, transfer learning severely underperforms as compared to training a conventional machine-learning model from scratch. The paper explores two cases of transfer learning.

A transfer learning-based approach to fatigue life prediction of corroded bimetallic steel bars using small samples

Source datasets are selected with high similarity to target datasets to improve the effect of transfer learning. The low similarity between the source and target datasets may lead to negative transfer. This paper proposes a similarity-based time series source dataset selection method for transfer learning. First, to reduce the complexity of the operation, we use Dynamic time-warped barycentric averaging to obtain the prototype signals of each dataset and convert the dataset similarity calculation into the similarity calculation between the prototype signals. The dynamic time warping (DTW) algorithm, commonly used to calculate time-series signal similarity, does not consider the effect of signal complexity and the amount of data the dataset contains on the signal similarity calculation. This article makes improvements to the above issues. Experiments are carried out on 20-time series datasets archived by the University of California Riverside. Experimental results show that the average transfer effect of source datasets selected by the proposed method is better than the commonly used dataset similarity measurement method based on DTW.

Aiming at the problem that normal vector representation method cannot fully represent the emotional semantic information contained in the text when dealing with Chinese text sentiment analysis task, a multi-granularity convolutional capsule neural network model is constructed. The input of sentiment analysis model is vector representation of the texts trained through the language model. As there exists the problem that a single language model is not enough to abstract text features, a multi-granularity text vector representation method based on BERT is proposed. The text vector representations with different granularities are input into the improved multi-channel convolutional capsule neural network. The capsule layer can associate the low-level and high-level text features, and it will extract information selectively through the dynamic routing algorithm to construct emotional and semantic features of the whole text. Multiple comparative experiments confirm that the method proposed in this paper will efficiently improve the accuracy of Chinese sentiment analysis.

There are two problems in facial expression recognition: one is that single-channel network can only extract a single feature, the other is that the multi-channel network can extract a variety of features, but it increases the amount of computation. This paper proposes an expression recognition method based on image fusion and transfer learning. It combines the knowledge and experience of traditional methods with the computing power of deep learning methods. The method firstly locates and segments the face according to human experience of knowing things. The segmented area is the face, eyes and mouth which affect expression most. Then the features of the three perspectives are fused to form a three-channel picture containing the face, eye and mouth area. Finally, it is sent to the network which has preliminary experience in understanding things for transfer learning. Experimental results show that this method has achieved good results on CK + and JAFFE datasets with the average accuracy 100% and 98.55%. Compared with single-channel and multi-channel convolutional neural networks, the presented method can effectively improve the accuracy of facial expression recognition.

Sentiment analysis has emerged as a powerful tool in financial markets, offering the ability to harness market participants' collective wisdom and emotions to make more informed investment decisions. This research paper presents a comprehensive literature review on sentiment analysis models in predicting stock prices, focusing on the Bank Nifty Index, a critical benchmark in the Indian financial sector. The review begins by elucidating the significance of sentiment analysis in stock price prediction, highlighting its pivotal role in capturing market sentiment, investor emotions, and their impact on asset valuations. A detailed overview of sentiment sources, encompassing financial news, social media, reports, and other relevant data streams, provides insight into the rich tapestry of information that sentiment analysis can leverage. The paper delves into various sentiment analysis approaches, from traditional lexicon-based and rule-based methods to cutting-edge machine learning and deep learning techniques. It elucidates the intricate process of integrating sentiment analysis with stock price prediction models, exploring feature concatenation, time series integration, and weighted data to incorporate sentiment insights effectively. Evaluation metrics crucial for assessing the performance of both sentiment analysis models and stock price prediction models are thoroughly discussed. It concludes by highlighting the substantial potential of sentiment analysis in augmenting stock price prediction, offering investors and traders valuable tools to navigate the complexities of financial markets.

Rapid and accurate estimation of the state of health of lithium-ion batteries is of great significance. This paper aims to address two issues faced when applying deep learning methods to estimate the health status of lithium-ion batteries: high data quality requirements and poor model generalizability. This paper proposes a comparison-transfer learning approach with cyclic synchronization to estimate the state of health of lithium-ion batteries. First, a cyclic synchronization method based on the Bezier curve fitting algorithm is introduced to synchronize the data obtained at different charge–discharge cycles of the lithium-ion battery, facilitating input to the model. Second, a comparison-transfer network using the Pearson correlation coefficient is proposed to transfer knowledge from the source dataset to predict the target dataset under different environmental temperatures. By training a pre-trained model on the source dataset and utilizing the correlation coefficient to analyze the similarity between the source and target datasets, the accumulated knowledge in the source dataset can be effectively utilized to enhance prediction performance on the target dataset. In the experiments, the proposed method is validated using the lithium-ion battery aging public datasets. The experimental results demonstrate that the proposed approach achieves superior prediction performance in the case of small-sample sizes, exhibiting higher accuracy and stability compared to traditional deep learning methods.

Understanding and comprehending humans' views, beliefs, attitudes, or opinions toward a particular entity is sentiment analysis (SA). Advancements in e‐commerce platforms has led to an abundance of the real‐time and free forms of opinions floating on social media platforms. This real‐world data are imprecise and vague hence fuzzy logic is required to deal with such subjective data. Since opinions can be fuzzy in nature and definitions of opinion words can be elucidated differently; fuzzy logic has witnessed itself as an effective method to capture the expression of opinions. The study presents an elaborate review of the around 170 published research works for SA using fuzzy logic. The primary emphasis is focused on text‐based SA, audio‐based SA, and fusion of text‐audio features‐based SA. This article discusses the various novel ways of classifying fuzzy logic‐based SA research articles, which have not been accomplished by any other review article till date. The article puts forward the importance of SA tasks and identifies how fuzzy logic adds to this importance. Finally, the article outlines a taxonomy for sentiment classification based on the technique‐supervised and unsupervised in the SA models and comprehensively reviews the SA approaches specific to their task. Prominently, this study highlights the suitability of fuzzy‐based SA approaches into five different classes vis‐a‐vis (a) Sentiment Cognition from Words using fuzzy logic, (b) Sentiment Cognition from Phrases using fuzzy logic, (c) Fuzzy‐rule based SA, (d) Neuro‐fuzzy network‐based SA, and (e) Fuzzy Emotion Recognition.This article is categorized under:Algorithmic Development > Text MiningFundamental Concepts of Data and Knowledge > Motivation and Emergence of Data Mining

We present the technologies and host components developed to power a speech-based dialogue manager with affective capabilities. The overall goal is that the system adapts its response to the sentiment and arousal level of the user inferred by analysing the linguistic and paralinguistic information embedded in his or her interaction. A linguistic-based, dedicated sentiment analysis component determines the body of the system response. A paralinguistic-based, dedicated arousal recognition component adjusts the energy level to convey in the affective system response. The sentiment analysis model is trained using the CMU-MOSEI dataset and implements a hierarchical contextual attention fusion network, which scores an Unweighted Average Recall (UAR) of 79.04 % on the test set when tackling the task as a binary classification problem. The arousal recognition model is trained using the MSP-Podcast corpus. This model extracts the Mel-spectrogram representations of the speech signals, which are exploited with a Convolutional Neural Network (CNN) trained from scratch, and scores a UAR of 61.11 % on the test set when tackling the task as a three-class classification problem. Furthermore, we highlight two sample dialogues implemented at the system back-end to detail how the sentiment and arousal inferences are coupled to determine the affective system response. These are also showcased in a proof of concept demonstrator. We publicly release the trained models to provide the research community with off-the-shelf sentiment analysis and arousal recognition tools.

Aspect extraction is a subtask of sentiment analysis that deals with identifying opinion targets in an opinionated text .Existing approaches to aspect extraction typically rely on using handcrafted features, linear and integrated network architectures.Although these methods can achieve good performances, however, they are time-consuming and often very complicated.In real-life systems, a simple model with competitive results is generally more effective and preferable over complicated models.In this paper, we present a multichannel convolutional neural network for aspect extraction.The model consists of deep CNN (Convolutional Neural Network) with two input channels: Word embedding channel which aims to encode semantic information of the words and POS (part of speech) tag embedding channel, to facilitate the sequential tagging process.To get the vector representation of words, we initialized the word embedding channel and POS channel using pre-trained word2vec and one-hot-vector of POS tags respectively.Both the word embedding and POS embedding vectors were fed into the convolutional layer and concatenated to a one-dimensional vector which is finally pooled and processed using a softmax function for sequence labeling.We finally conducted a series of experiments using four different datasets.The results indicated better performance compared to the baseline models.

Given its demonstrated ability in analyzing and revealing patterns underlying data, Deep Learning (DL) has been increasingly investigated to complement physics-based models in various aspects of smart manufacturing, such as machine condition monitoring and fault diagnosis, complex manufacturing process modeling, and quality inspection. However, successful implementation of DL techniques relies greatly on the amount, variety, and veracity of data for robust network training. Also, the distributions of data used for network training and application should be identical to avoid the internal covariance shift problem that reduces the network performance applicability. As a promising solution to address these challenges, Transfer Learning (TL) enables DL networks trained on a source domain and task to be applied to a separate target domain and task. This paper presents a domain adversarial TL approach, based upon the concepts of generative adversarial networks. In this method, the optimizer seeks to minimize the loss (i.e., regression or classification accuracy) across the labeled training examples from the source domain while maximizing the loss of the domain classifier across the source and target data sets (i.e., maximizing the similarity of source and target features). The developed domain adversarial TL method has been implemented on a 1-D CNN backbone network and evaluated for prediction of tool wear propagation, using NASA's milling dataset. Performance has been compared to other TL techniques, and the results indicate that domain adversarial TL can successfully allow DL models trained on certain scenarios to be applied to new target tasks.

Sentiment analysis refers to the automated process of identifying the underlying emotional tone conveyed in a text. This task has become increasingly crucial today due to the exponential growth of opinion-oriented text generation on various online platforms including social media and e-commerce websites. The process of sentiment analysis has evolved through different phases like the use of handcrafted rules, sentiment-oriented dictionaries, machine learning, deep learning, transformer models, and large language models. These different phases have enriched the field of sentiment analysis and enabled it to get better insights into text for sentiment analysis. One of the most impactful developments in sentiment analysis was the creation of embedding’s for words or sentences, which are useful for representing unstructured data as structured data. These embedding are representing words or sentences as numerical vectors in a high-dimensional space and have proven effective in capturing the semantic relationships between words. By leveraging the power of embedding’s, sentiment analysis models can understand the complexities of human language and provide more precise insights into people's emotions and opinions. However, word embedding’s not inherently generated for sentiment analysis, which means that they are not inherently sentiment-oriented. Therefore, many researchers have focused on developing sentiment-oriented word embedding’s for sentiment words, but they have overlooked the importance of intensity words such as “little”, “high”, and “extremely”. These intensity words determine the level of sentiment expressed in text, which is particularly useful for fine-level sentiment analysis. To address this issue, a review proposes an intensity-aware word embedding development model and sentiment analysis with ML.

Photoplethysmography (PPG) changes according to arterial blood pressure (ABP). The change in the physiological signal reflects the change in the functional state of the heart and vascular system. To prevent cardiovascular disease due to hypertension, the PPG signal has been widely used for non-invasive continuous estimation of blood pressure. In recent years, artificial neural network-based algorithms have found the relationship between ABP and related physiological signals. Compared with traditional cuff measurement methods, it is more intuitive to understand the overall blood pressure trend and avoid invasive pressure Measured bleeding risk. Most artificial neural networks use an electrocardiogram (ECG) and PPG at the same time, and the ECG acquisition device needs electrodes and wires to the chest cavity, which indirectly affects the convenience of physiological signal acquisition. Using three feature extraction techniques with different detailed attributes for a single PPG measurement and substituting short-time Fourier transform (STFT), continuous wavelet transform (CWT), and Hilbert-Huang transform (HHT) into the "compound multi-channel convolutional neural network(CMCNN)" model, we evaluate the overall blood pressure value. Considering that the distorted data caused by motion artifacts causes the training results to fail to converge, we select Physionet's MIMIC-III database and use data purification-based processing steps. We screen out the artifact labels for PPG and ABP at first and then use the artifact labels to perform seven-level data segmentation. Finally, using STFT, CWT, and HHT, we obtain spectrogram, scalogram, and Hilber spectrum. The original waveform of PPG and the spectrum, the scalogram, and the Hilbert spectrum are used as input data for learning and analysis. Compare with the traditional machine learning method, the blood pressure estimation results is closer to the actual situation.