Bi-LSTM Model Research Articles

Dynamic Integration and Innovative Application of Red Cultural Resources in Civic and Political Education in Colleges and Universities

Abstract With the deepening of the reform of civic education in colleges and universities, the traditional mode of civic education has gradually revealed its limitations. The integration of red cultural resources into the ideological education of colleges and universities has become a more common method of ideological education. According to the attributes of red cultural resources in civic education, the study combines the HMM model, BiLSTM model, and BiLSTM-CRF model to construct a red cultural resource base for civic education courses in colleges and universities so as to dynamically integrate red cultural resources in civic education in colleges and universities, analyze the textual features of the red cultural resources in the research methods in the college and university education resource base, and explore the teaching of civic education in colleges and universities. The top five high-frequency words in the mainstream research methods are “history” (540), “comparison” (538), “literature” (486), “system” (334), “discipline” (245), and the most frequent words in the empirical research method are “case” (67), “investigation “(26), “interview” (23), “culture” (15), and “qualitative research” (18). The degree of understanding of the content of Yan’an red cultural resources by students of colleges and universities in Shaanxi Province is Yan’an spirit (14.65%), celebrity heroes’ deeds (26.19%), red literary writings (3.59%), red attractions (35.95%), the course of the revolutionary struggle (25.16%), deeds of poverty alleviation (19.54%), and no understanding (8.57%).

Design of a financial reporting management generation system based on Bi-LSTM model and MultiWord-Embedding method

Design of a financial reporting management generation system based on Bi-LSTM model and MultiWord-Embedding method

Research status of abnormal lipid metabolism and tumorigenesis and development

Abstract There is a close relationship between abnormal lipid metabolism and tumor malignant behavior, and abnormal lipid metabolism plays a crucial role in developing malignant tumors. Based on BiLSTM model, combined with Transformer Encoder and CRF decoder, the article successfully constructed a joint extraction model of medical literature, and with the help of Neo4j technology, built the knowledge graph of lipid metabolism abnormality and tumor occurrence and development. The study used data sources from WOSCC, CNKI, Wanfang, VIP, and other databases as data sources. It used bibliometric analysis and tools like CiteSpace and VOS viewer to visualize and analyze related studies in-depth. The study results showed that Oral Oncology in the UK ranked first in abnormalities of lipid metabolism in the number of publications, with a total of 301 related papers and an impact factor of 5.118. The number of studies related to oncology increased from 11 in 2010 to 414 in 2023, with a growth of more than 36.64 times. By comprehensively analyzing the current situation of abnormal lipid metabolism and tumorigenesis and development, this paper provides new ideas and perspectives for the study of cancer prevention, diagnosis, treatment and mechanism. It helps to promote the in-depth research and development of related fields.

Construction of a Knowledge Graph Based on the Study of English Translation of Traditional Chinese Medicine Terminology

Abstract This study centers on the English translation of Chinese medicine terms and the construction of knowledge graph, to solve the problem of the accuracy of Chinese medicine terminology translation through scientific and technological means, and to improve the communication efficiency and accuracy of Chinese medicine in the international arena. First, we collected Chinese medicine-related data from websites such as “Seek Medical Help” and “Seek Medical Help” through crawler technology, then performed data cleaning and fusion processing to eliminate data redundancy and inconsistency. Then, we defined 17 types of concepts and 22 conceptual relationships related to TCM ancient books, as well as the corresponding attribute definitions, to ensure the accuracy and completeness of the knowledge graph. The Bi-LSTM model for text disambiguation and Labeling further improved data processing efficiency. Eventually, this study successfully constructed a knowledge graph of English translation of TCM terms containing 50051 nodes and 13521 relations. This knowledge graph improves the accuracy of TCM terminology translation and provides a powerful tool for international dissemination and academic research of TCM terminology.

SBiLM: Siamese Bi-LSTM model for handling imbalance in fake review detection

The growing significance of online reviews in e-commerce platforms has a profound impact on consumers' purchase decisions. Unfortunately, dishonest sellers exploit this system by engaging in deceptive practices and manipulating reviews. These fake reviews are very hard to be detected by humans. Hence, the issue of detecting fake online reviews has gained significant attention due to their prevalence. Typically, the datasets available have much higher number of real reviews as compared to fake reviews, which leads to data imbalance problem. Machine learning algorithms struggle to learn from these datasets and give biased results. However, existing studies on this topic have not adequately addressed the challenges posed by imbalanced data. They have mostly used under-sampling or over-sampling to handle imbalance in datasets, which leads to potential information loss or overfitting due to replication. Hence, to handle this class imbalance problem without using sampling techniques, this paper proposes a novel SBiLM model using Siamese Neural Network with Bidirectional LSTM and Manhattan Distance. SBiLM takes pair of reviews as inputs and computes similarity between them using distance metric. The outcomes indicate that the SBiLM model exhibits better performance in terms of both accuracy and loss, when compared with traditional deep learning models on a highly imbalanced restaurant review dataset. This presents a promising strategy for tackling the issues related to data imbalance in the domain of fake review detection.

Recongnition of Distracted Driving Behavior Based on Improved Bi-LSTM Model and Attention Mechanism

Recongnition of Distracted Driving Behavior Based on Improved Bi-LSTM Model and Attention Mechanism

Trajectory-Unaware Channel Gain Forecast in a Distributed Massive MIMO System Based on a Multivariate BiLSTM Model

Trajectory-Unaware Channel Gain Forecast in a Distributed Massive MIMO System Based on a Multivariate BiLSTM Model

Predicting the correlation between neurological abnormalities and thyroid dysfunction using artificial neural networks

<p>In this work, a deep learning model was developed to predict future neurological parameters for patients with hypothyroidism, enabling proactive health management. The model features a sequential architecture, comprising a long short-term memory (LSTM) layer, a bidirectional LSTM layer, and several fully connected layers. The study assessed the interplay between serum cortisol, dopamine, and GABA levels in hypothyroid individuals, aiming to illuminate how these hormonal fluctuations influence the condition's symptoms and progression, especially in relation to Parkinson's disease. Conducted at the Tabriz Sadra Institute of Medical Sciences in Iran, the observational study involved 80 hypothyroid patients and 80 age-matched healthy controls. The findings showed a correlation between cortisol levels and TSH and an inverse relationship with T3 and T4 levels among hypothyroid patients. Dopamine levels also correlated with TSH, T3, and T4, highlighting their potential impact on Parkinson's disease. Notably, hypothyroid patients aged 54–71 years old experiencing visual hallucinations had reduced occipital GABA levels correlating with hormone levels. The results indicated significant relationships among cortisol, dopamine, and GABA levels, providing insights into their roles in the pathophysiology of hypothyroidism and its association with neurological disorders. The BiLSTM model achieved the highest accuracy at 92.79% for predicting Parkinson's disease likelihood in adult hypothyroid patients, while the traditional LSTM model reached 84.48%. This research suggests promising avenues for future studies and has important implications for clinical management and treatment strategies.</p>

Optimised hybrid CNN bi-LSTM model for stock price forecasting

Optimised hybrid CNN bi-LSTM model for stock price forecasting

SENTIMENT ANALYSIS OF CODE-MIXED LANGUAGES

In the multilingual context of today, code-mixed language is frequently utilized. It happens when a sentence contains both foreign language vocabulary and grammar. Finding the sentence's polarity value is the aim of sentiment analysis of code-mixed language. It is mostly concerned with sentiment analysis of tweets that contain extra Hindi and English words and symbols. The collection is composed of 20,000 tweets, which produces word-level representations of the tweets for use as input in several models, including CNN, LSTM, and Bi-LSTM. When compared to other models, the Bi-LSTM model performs better. The precision of CNN, LSTM and Bi-LSTM is 65.00%, 58.59% and 54.24% respectively.

Metaphorical Interpretation of Early Works of Art Using Symbolization Methods

Abstract The unique style of early works of fine art depends on the infinite derivation of the image factor symbols metaphorically behind them, so the symbolic interpretation of early works of fine art is a search for the missing beauty of contemporary art. In this paper, we start from multi-scale association rules, use Gaussian pyramid and cubic convolution methods to extract image metaphor features in fine art works, and weight the features. Based on Putschke’s emotion classification, a multimodal metaphor dataset is constructed. The symbolization method is used to represent the symbolic emotions in the art works, and then the bidirectional Bi-LSTM model is used for recognition. On this basis, using the model constructed in this paper, the symbolic and imagery features of art works are analyzed, and the symbolic techniques of art works are interpreted from three perspectives: brushstroke, color, and spatial metaphor. Structural metaphors in fine art works contain 40% neutral emotions, followed by 36.4% positive emotions. Stroke A has a higher mean score at 3 and 4 line sample points, respectively, of -1.1646 and -1.1106, and the emotions triggered by these two line samples are more significant. Interpreting early art works can help enhance the aesthetics of contemporary art for modern audiences.

Aspect category learning and sentimental analysis using weakly supervised learning

The surge of e-commerce reviews has presented a challenge in manually annotating the vast volume of reviews to comprehend their underlying aspects and sentiments. This research focused on leveraging weakly supervised learning to tackle aspect category learning and the sentiment classification of reviews. Our approach involves the generation of labels for both aspects and sentiments, employing the Snorkel framework of WSL, which incorporates aspect terms, review sentiment scores, and review ratings as sources of weak signals. This innovative strategy significantly reduces the laborious labeling efforts required for processing such extensive datasets. In this study, we deployed hybrid models, namely BiLSTM, CNN-BiLSTM, and CNN-LSTM, which harness multiple inputs, including review text, aspect terms, and ratings. Our proposed model employs two distinct loss functions: Binary Cross Entropy with Sigmoid Activation for Multi-Label Classification, enabling us to learn aspect Labels such as Quality, Usability, Service, Size, and Price, and Categorical Cross Entropy with Softmax Activations for Multi-Class Classification. Subsequently, we meticulously evaluate the performance metrics of these three implemented models, including Macro F1 score and MacroPrecision. CNN & Bi-LSTM model attained 0.78 and 0.79 F1 scores on aspect and sentiment identification, respectively. The outcomes of this research are poised to make a substantial contribution to e-commerce platforms, offering an efficient and automated means to label and analyze vast troves of user reviews.

E-BabyNet: Enhanced Action Recognition of Infant Reaching in Unconstrained Environments.

Machine vision and artificial intelligence hold promise across healthcare applications. In this paper, we focus on the emerging research direction of infant action recognition, and we specifically consider the task of reaching which is an important developmental milestone. We develop E-babyNet, a lightweight yet effective neural-network-based framework for infant action recognition that leverages the spatial and temporal correlation of bounding boxes of infants' hands and objects to reach for to determine the onset and offset of the reaching action. E-babyNet consists of two main layers based on two LSTM and a Bidirectional LSTM (BiLSTM) model, respectively. The first layer provides a pre-evaluation of the reaching action for each hand by providing onset and offset keyframes. Then, the biLSTM model merges the previous outputs to deliver an outcome of the reaching actions detection for each frame including the reaching hand. We evaluated our approach against four other lightweight structures using a dataset comprising 5,865 annotated images resulting in 16,337 bounding boxes from 375 distinctive infant reaching actions performed while sitting by different subjects in unconstrained (home/clinic) environments. Results illustrate the effectiveness of our approach and ability to provide reliable reaching action detection and offer onset and offset keyframes with a precision of one frame. Moreover, the biLSTM layer can handle the transition between reaching actions and help reduce false detections.

Optimised hybrid CNN bi-LSTM model for stock price forecasting

Optimised hybrid CNN bi-LSTM model for stock price forecasting

A Benchmark Dataset for Cricket Sentiment Analysis in Bangla Social Media Text

This study introduces a novel benchmark dataset designed for Cricket Sentiment Analysis on Bangla social media posts, emphasizing a low-resource setting. The dataset was meticulously curated through manual collection across diverse social media platforms, ensuring comprehensive representation of user sentiments. Annotations validated dataset quality, achieving a remarkable Cohen Kappa score of 0.97. Experimentation with machine learning (ML) models revealed challenges, with traditional approaches yielding modest RNN accuracy of 0.5239. However, deep learning (DL) models showcased significant performance enhancements. The LSTM model achieved 0.897 accuracy, while the BiLSTM model surpassed expectations at 0.952. These findings highlight DL’s efficacy in capturing nuanced sentiments in Bangla cricket-related social media posts, contributing a high-quality benchmark dataset and insights into DL’s suitability for sentiment analysis in low-resource linguistic contexts.

Load Forecasting with Hybrid Deep Learning Model for Efficient Power System Management

Aim: Load forecasting with for efficient power system management Background:: Short-term energy load forecasting (STELF) is a valuable tool for utility companies and energy providers because it allows them to predict and plan for changes in energy. Method:: 1D CNN BI-LSTM model incorporating convolutional layers. Result:: The results provide the Root Mean Square Error of 0.952. The results shows that the proposed model outperforms the existing CNN based model with improved accuracy, hourly prediction, load forecasting. Conclusion:: The proposed model has several applications, including optimal energy allocation and demand-side management, which are essential for smart grid operation and control. The model’s ability to accurately management forecast electricity load will enable power utilities to optimize their generation.

Sentiment Analysis on IMDB Review Dataset

A computational method known as sentiment analysis is employed to ascertain the emotional undertone or attitude of a text document, such as a review, tweet, or news story. Using machine learning models, deep neural network models, and natural language processing, the method entails examining the text to determine whether it expresses positive or negative sentiment. In this study, models like Naive Bayes, Logistic Regression, LSTM, LSVM, Decision tree, and BiLSTM are utilized to conduct a sentiment analysis (SA) study on the IMDB dataset. The goal of the investigation is to evaluate how well these models perform in retrospect on movie reviews, categorizing them as positive or negative. The study investigates the effects of data pre-processing methods and hyperparameter tuning on the models’ accuracy. The final results demonstrate that the BiLSTM model outperforms the other models in terms of recall, precision, and accuracy, followed by the LSTM, Logistic Regression, LSVM, Decision Tree, and Naive Bayes models. The research emphasizes the potential of deep learning models—in particular, BiLSTM in sentiment analysis tasks, as well as the significance of hyper-parameter tuning and pre-processing methods in achieving high accuracy.

Optimization of the visual communication path of data news in the context of the Internet

Abstract Visual news belongs to a kind of data news, which uses emerging technology to bring users a new reading experience and improve the news dissemination effect. In this paper, we utilize the self-attention mechanism and BiLSTM model to extract the content of data news documents and select and classify the audio features of data news by the AdaBoost algorithm. ResNet50 is used as the backbone network, combined with multiple residual unit modules for news multi-scale image feature extraction, and the text, audio and image features of the data news are fused by constructing a multimodal feature adaptive fusion model to further optimize the visual display of the data news. This paper verifies the model’s effectiveness for the data news visualization technique through multiple perspectives, including training loss curve, performance comparison, and ablation experiment. The results show that the loss value of the model based on the Self-Attention-BiLSTM model for news text feature extraction is 0.211 after 150 iterations. The AdaBoost-based news audio feature classification method has an average classification accuracy of 97.56% for the positive diagonal when the noise is raised from 0dB to 30 dB. By adding the residual unit module to the ResNet50 backbone network, the accuracy of the multi-scale image feature extraction model has been improved by 2.77% compared to the single backbone network. The information age requires the full integration of technology and news and combining the corresponding Internet platform for the visual display of data news in order to promote the expansion of the visual communication path of data news.

Predicting Traffic Flow Parameters for Sustainable Highway Management: An Attention-Based EMD–BiLSTM Approach

The long-term prediction of highway traffic parameters is frequently undermined by cumulative errors from various influencing factors and unforeseen events, resulting in diminished predictive accuracy and applicability. In the pursuit of sustainable highway development and eco-friendly transportation strategies, forecasting these traffic flow parameters has emerged as an urgent concern. To mitigate issues associated with cumulative error and unexpected events in long-term forecasts, this study leverages the empirical mode decomposition (EMD) method to deconstruct time series data. This aims to minimize disturbances from data fluctuations, thereby enhancing data quality. We also incorporate the BiLSTM model, ensuring bidirectional learning from extended time series data for a thorough extraction of relevant insights. In a pioneering effort, this research integrates the attention mechanism with the EMD–BiLSTM model. This synergy deeply excavates the spatiotemporal characteristics of traffic volume data, allocating appropriate weights to significant information, which markedly boosts predictive precision and speed. Through comparisons with ARIMA, LSTM, and BiLSTM models, we demonstrate the distinct advantage of our approach in predicting traffic volume and speed. In summary, our study introduces a groundbreaking technique for the meticulous forecasting of highway traffic volume. This serves as a robust decision-making instrument for both sustainable highway development and transportation management, paving the way for more sustainable, efficient, and environmentally conscious highway transit.

Deep Learning Based Automatic Answer Scoring Through Bi-Directional LSTM

Due to population expansion and the increasing importance of education, it is becoming increasingly difficult for assessors to evaluate the correctness and relevance of the responses provided by students. The LSTM model was initially used to build the answer-scoring system. The Bi-LSTM model has been designed with callbacks to acquire the student answer scoring system due to the LSTM's limitations for optimal scoring. The proposed system has been implemented using the ASAP Short Answer Scoring dataset. The results show that the system developed using Bi-LSTM displays better performance than LSTM.