Forward Information Research Articles

Traffic signal current prediction algorithm based on CNN and LSTM

Abstract Traffic signal failures can lead to severe accidents and citywide traffic disruptions, making their reliable operation essential. This study collected real-world data from intersection traffic signals and constructed a dataset. Based on the current data from traffic signals, the Formatted pass-Dot product attention-LSTM (FD-LSTM )model was proposed. The model utilizes one-dimensional convolution and max pooling
for feature extraction, employs dual LSTM units to process forward and backward information, incorporates Dropout to prevent overfitting, and uses the dot-product attention mechanism to enhance the importance of key features. The model is trained using the Adam optimization algorithm. Comparative experiments demonstrate that the FD-LSTM model outperforms other models.

A Method for Filling Missing Values in Multivariate Sequence Bidirectional Recurrent Neural Networks Based on Feature Correlations

Multivariate real-life time series data often contain missing values. These missing values often affect subsequent prediction tasks. Traditional imputation methods generally consider only some of the characteristics of multivariate time series data. This can easily lead to inaccurate filling results. In this paper, a feature correlation-based bidirectional recurrent network (BRNN-FR) is proposed to solve the problem of missing values in multivariate sequence data. First, this method involves the design of a bidirectional prediction network based on time intervals and the use of forward and reverse time series information between data points to obtain the characteristics of data changes with time to the greatest extent. Second, considering the correlation between features, a combined feature selection strategy based on the Pearson correlation coefficient and mutual information was proposed. A multiple regression model was established to predict between features. Finally, a bidirectional network ensemble filling algorithm based on the relationships between features is established to predict missing values. Comprehensive experiments on four public datasets show that the mean absolute error (MAE), root mean square error (RMSE) and maximum R2 value (R2_score) of the BRNN-FR algorithm in the direct imputation test are better than those of the other comparison methods in most cases. BRNN-FR also achieved a better area under the curve (AUC) in the indirect comparison experiment of two classifications of in-hospital death after filling the medical dataset. Using the AIR air quality dataset and the power transformer temperature dataset from the ETTH1 interpolation regression to predict the next 3hours and 6hours of average numerical results, most of the optimal regression results are obtained.

Intelligent prediction of rail corrugation evolution trend based on self-attention bidirectional TCN and GRU

Analyzing the evolution trend of rail corrugation using signal processing and deep learning is critical for railway safety, as current traditional methods struggle to capture the complex evolution of corrugation. This present study addresses the challenge of accurately capturing this trend, which relies significantly on expert judgment, by proposing an intelligent prediction method based on self-attention (SA), a bidirectional temporal convolutional network (TCN), and a bidirectional gated recurrent unit (GRU). First, multidomain feature extraction and adaptive feature screening were used to obtain the optimal feature set. These features were then combined with principal component analysis (PCA) and the Mahalanobis distance (MD) method to construct a comprehensive health indicator (CHI) that reflects the evolution of rail corrugation. A bidirectional fusion model architecture was employed to capture the temporal correlations between forward and backward information during corrugation evolution, with SA embedded in the model to enhance the focus on key information. The outcome was a rail corrugation trend prediction network that combined a bidirectional TCN, bidirectional GRU, and SA. Subsequently, a multi-strategy improved crested porcupine optimizer (CPO) algorithm was constructed to automatically obtain the optimal network hyperparameters. The proposed method was validated with on-site rail corrugation data, demonstrating superior predictive performance compared to other advanced methods. In summary, the proposed method can accurately predict the evolution trend of rail corrugation, offering a valuable tool for on-site railway maintenance.

A mental health monitoring system based on intelligent algorithms and biosensors: Algorithm behaviour analysis and intervention strategies

Introduction: Mental health monitoring encompasses the systematic observation and assessment of an individual’s psychological well-being, aiming to detect, understand and manage mental health conditions. It involves various techniques and interventions tailored to support individuals in achieving and maintaining optimal mental wellness. Recent advancements include the use of biosensors and biomechanics to analyze physiological signals that correlate with mental states, providing a more comprehensive understanding of psychological well-being. Aim: The aim of this research is to construct an innovative mental health monitoring system established on intelligent algorithms and biomechanical data through behaviour analysis and intervention strategies. Methodology: We propose a novel Snow Ablation-driven Bi-directional Fine-tuned Recurrent Neural Network (SA-BFRNN) to identify the state of mental health. In addition to behavioural data, biosensors are employed to collect real-time physiological signals such as heart rate variability, skin conductance, and muscle tension, offering objective markers of mental stress and anxiety. These biomechanical inputs are integrated into the system for multi-modal analysis. We employ the SA algorithm, iteratively removing less influential connections and nodes based on their impact on model performance. This process enhances network efficiency and generalization capabilities, refining the BFRNN for mental health state identification. Utilizing a questionnaire with 25 questions, administered to a selected group of 756 individuals, we validate our proposed model. Biosensor data is synchronized with questionnaire responses to improve the precision of mental state identification. Clustering-derived labels are validated with mean opinion score. These labels inform classifiers for individual mental health prediction, aligning with our objective of robust mental health assessment through data-driven approaches. SA-BFRNN integrates both forward and backward temporal information, enhancing its ability to discern subtle patterns in behaviour. Through iterative fine-tuning, our network learns to adapt to diverse datasets, enabling precise identification of mental health states. Research findings: In the result evaluation phase, we thoroughly examine how well our proposed SA-BFRNN model recognizes various states of mental health across different parameters. Our findings also highlight the significance of incorporating biomechanics, where biosensor data showed a strong correlation with mental health indicators, thereby augmenting the accuracy of the system. Our findings emphasize the efficacy of the SA-BFRNN technique, as demonstrated by its overall performance in terms of recall (92.56%), accuracy (90.13%), F1-score (88.16%) and precision (89.23%). Our experimental results unequivocally demonstrate that our proposed model performed better than other traditional approaches in classifying contents from multimodal data, showing notable enhancements in accuracy and robustness, particularly under dynamic conditions.

Degradation prediction for mechanical components based on transfer learning and a multistage statistical model

Rolling bearings serve as vital elements in mechanical components; their degradation significantly influences equipment reliability and safety. Previous studies primarily focus on single-stage degradation methods, limiting their applicability for predicting degradation trends across varying conditions and hindering generalization. To address this challenge, we propose a multistage statistical model and a multistage transfer learning based on bidirectional gated recurrent unit with an attention mechanism (MSTL-BGRUA) to predict the multistage degradation trend of bearings under cross-working conditions. Given the nonlinear properties of bearing degradation, we present an online multistage division method to identify degradation characteristics. The degradation features of bearing’s vibration signal are extracted and classified into multiple degradation stages based on a mutation identification policy via the statistical model. Subsequently, a BGRUA model is proposed to balance forward and backward information and assign different weights, achieving accurate prediction for each identified degradation stage. Based on the presented BGRUA, we incorporate an MSTL method for degradation prediction to maintian accuracy under crossing working conditions. Finally, a prognosis framework using both the statistical model and the MSTL-BRGUA model is presented to predict bearing status under different degradation stages. A validation of the presented method is conducted using a vibration dataset, demonstrating its superior predictive performance compared to other advanced degradation prediction methods.

Revealing the sentiment propagation under the conscious emotional contagion mechanism in the social media ecosystem: For public opinion management

In public opinion events, the breeding of negative sentiment has a serious negative impact on the network environment and even offline lives. Hence, establishing an emotion-based propagation dynamic model to catch the sentiment development patterns is essential for helping public opinion management. We propose an E-SLFI (Emotion-driven Susceptible-Latent-Forwarding-Immune) model, which describes the dynamics of the sentiment propagation of ternary polarities under the promoting effect of the conscious emotional contagion mechanism. An empirical case composed of 16,354 pieces of forwarding information and two phases verifies the effectiveness of the proposed sentiment propagation dynamic model, due to the fitting optimization indicator MAPE equals 0.0942 % and 0.0066 % respectively. Further, we simulate the model and implement sensitivity analysis of the important parameters of the model. Combining the results of experiments, we find that enhancing the emotional consensus of recipients and inducers can decide the main sentiment in the system, and anti-emotional consensus can improve the existence of weak sentiments. Our work here is conducive to designing online public sentiment guidance strategies to manage public opinion and calming the network atmosphere to a certain extent.

Recurrent feature supplementation network for video super-resolution

ABSTRACT Efficient aggregation of temporal information is the basis for achieving video super-resolution. Most researchers have employed alignment or propagation to exploit the temporal information of consecutive frames. However, they frequently overlook the centrality of the reference frame in the model reconstruction when using temporal features. Thus, in this paper, we design a novel recurrent feature supplementation network. We divide the temporal information into three parts: surrounding, back propagation and forward propagation, and extract and fuse them separately. A new grouping approach is proposed for extracting features from the reference frame and its surroundings. The backward temporal fusion module and the forward temporal fusion module are designed to aggregate the backward and forward temporal information at a distance. The temporal fusion module is designed to aggregate temporal information from different parts. Moreover, we propose a feature supplementation mechanism to improve the stability of the model. The feature supplement module is devised to improve the utilization of input features and the stability of the model. Experiments demonstrate that our model achieves the state-of-the-art performance.

Learning automata based routing and content delivery for vehicular named data networking

In Vehicular Named Data Networking (VNDN), vehicle mobility leads to frequent reverse-path interruptions and stale forwarding information, which further results in content delivery failures and disenables aggregation. Taking into account these limitations, we propose a learning automata based routing and content delivery solution for VNDN. The novelties of the solution are threefold: (1) Learning automata is leveraged to make forwarding decisions and deliver vehicular contents; (2) Various metrics including connection durations, unsatisfied requests and data response delays are utilized to compute the selection probability of each vehicle in order to select the best vehicle for content delivery; and (3) Aggregation and in-network caching are achieved through stable reverse paths. The typical application of the proposal is that vehicles rapidly access nearby road conditions to maneuver safe driving. The proposal is evaluated quantitatively. Compared with the existing solutions, the proposal reduces the content delivery latency and overheads by nearly 32.54% and 38.3%, respectively.

Stratified yield prediction in fractured wells based on a multitasking bidirectional recurrent network

Prediction of fluid production from hydraulically fractured wells is often difficult due to the incomplete understanding of the production mechanism and the limited availability of data. In this paper, we propose a prediction model (MTL-Bi-LSTM-CNN) to predict production in all layers of fractured wells based on convolutional neural network (CNN), bidirectional long and short-term memory network (Bi-LSTM) and multi-task learning (MTL). The model integrates the fracturing parameters with data from various layers of each well. It harnesses both forward and backward bi-directional information from multiple layered fractured wells to capture the intrinsic dependencies of data features, enhancing the accuracy of fluid production prediction. The results demonstrate that the prediction of stratified data using the network model proposed in this paper has higher accuracy and smaller error than single-well unstratified prediction. Consequently, this approach significantly improves the accuracy, robustness, and versatility of predicting fluid production and moisture content in fractured wells.

74‐1: Display Reflectance Measurements Finally Made Simple, Comprehensive and Affordable

Analysis of the point‐spread function (PSF) yields the directional variations of scattered light with high resolution in the vicinity of the specular direction and now, finally, at reduced but sufficient resolution, also at off‐specular directions, thus providing a basis for the determination of a set of complete in‐plane BRD/BTD functions. This approach is applied to both identification and separation of mirror, haze and Lambertian reflection components which then can be classified into such components that are forwarding visual information to the observer (i. e. visual signal) and disturbing reflections (i.e. visual noise).

STBGRN: A Traffic Prediction Model Based on Spatiotemporal Bidirectional Gated Recurrent Units and Graph Convolutional Residual Networks

With the development of society and the advancement of urbanization, the development of intelligent transportation system has attracted much attention. Efficient and accurate traffic flow prediction is one of the core tasks in the research of intelligent transportation system. Most of the existing spatiotemporal traffic flow prediction models do not make full use of various periodic spatiotemporal dynamic characteristics of traffic flow, and it is difficult to effectively capture the complex spatiotemporal changes of traffic flow. To accurately predict the traffic flow of complex urban network, this paper proposes a traffic prediction model (STBGRN) based on spatiotemporal bidirectional gated cycle unit (ST-BiGRU) and graph convolution residual network (GCN-ResNet). The spatiotemporal information in traffic data is learned using the spatiotemporal bidirectional GRU coupled with the forward and backward information of the current time step, and the topology structure of the traffic network is captured by the graph convolution residual network, which is combined to complete the prediction task of the urban traffic network. In this paper, STBGRN was tested on two real data sets, SZ-taxi and Los-loop, and compared with other baseline methods, the RMSE index reached 3.857 and 5.461, and the MAE index reached 2.702 and 3.781, respectively. Accuracy index is 72.66% and 91.35%, R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}^{2}$$\\end{document} index is 0.858 and 0.845, var index is 0.858 and 0.849. The experimental results show that STBGRN model can obtain spatiotemporal dependence from complex traffic data, and can be used in spatiotemporal traffic data processing.

A Lightweight_PAEKS-based energy scheduling model considering priority in MicroGrid

Priority-based energy scheduling is proposed, whereby the data utility of measured user information in smart meters, including the priority and power demand of power consumers and the maximum power supply of power suppliers, is leveraged to ensure that in the case of limited power resources within islanded microgrids, energy is allocated to power consumers in the order of high to low priority. Nonetheless, in terms of data utility, most existing strategies only consider high-priority power consumers, neglecting the priority of power suppliers and low-priority power consumers, thus damaging the fairness of low-priority consumers and the interests of power suppliers, to the detriment of these groups. Moreover, smart meters are vulnerable to data integrity attacks, which may result in the manipulation of measured user information during the forwarding process, thereby disrupting normal priority-based energy scheduling. Therefore, focusing on data utility without considering data security is insufficient. Researchers have extensively investigated how to secure smart meters within advanced metering infrastructure (AMI), primarily employing cryptography-based methods to encrypt user information in measured meters and decrypt it at the microgrid central controller (MGCC), thereby protecting the data confidentiality of user information during the forwarding process and preventing data tampering. However, the prevailing cryptographic methods used to secure smart meters are extremely complex, and make smart meters and local controllers on the forwarding path unable to obtain any user information in which embedded consumers’ priority and cannot leverage the data utility of priority to forward information accordingly. In other words, existing models cannot simultaneously achieve data confidentiality and data utility during the forwarding process. To solve these issues, this study investigates a Lightweight_PAEKS-based energy scheduling model considering priority in microgrid (LPESCP). As a lightweight solution, the LPESCP comprehensively considers data confidentiality and data utility, as well as the priority and fairness of all users, to ensure the security of smart meters and optimize energy scheduling. In particular, the data utility problem is solved by using an optimization model that aims to maximize the global satisfaction degree of all users in terms of priority and fairness. The Lightweight_PAEKS and Paillier encryption scheme are used so that nodes on the forwarding path can successfully match priority-related keyword and forward information in order of the keyword corresponding emergency coefficient indicating the urgency levels of information, ensuring data utility, while do not know the specific keyword, emergency coefficient and other information, ensuring data confidentiality. To verify the effectiveness of the LPESCP, experiments are conducted for three cases generated based on random numbers. The results show that the LPESCP model can effectively ensure energy supply to consumers, comprehensively considering data confidentiality and utility as well as priority and fairness of all users. In addition, the global satisfaction degree and time overhead are introduced as metrics to verify that the LPESCP strategy is more effective in providing greater global satisfaction degree and lower time overhead than existing priority-based energy scheduling models.

Similarity indicator and CG-CGAN prediction model for remaining useful life of rolling bearings

To tackle the challenges of performing early fault warning and improving the prediction accuracy for the remaining useful life (RUL) of rolling bearings, this paper proposes a similarity health indicator and a predictive model of CG-conditional generative adversarial network (CGAN), which relies on a CGAN that combines one-dimensional convolutional neural network (CNN) with a bidirectional gate recurrent unit (Bi-GRU). This framework provides a comprehensive theoretical foundation for RUL prediction of rolling bearings. The similarity health indicator allows for early fault warning of rolling bearings without expert knowledge. Within the CGAN framework, the inclusion of constraints guides the generation of samples in a more targeted manner. Additionally, the proposed CG-CGAN model incorporates Bi-GRU to consider both forward and backward information, thus improving the precision of RUL forecasting. Firstly, the similarity indicator between the vibration signals of the rolling bearing over its full life span and the standard vibration signals (healthy status) is calculated. This indicator helps to determine the early deterioration points of the rolling bearings. Secondly, the feature matrix composed of traditional health indicators and similarity health indicator, is utilized to train and test the proposed CG-CGAN model for RUL prediction. Finally, to corroborate the efficacy of the proposed method, two sets of real experiment data of rolling bearing accelerated life from the Intelligent Maintenance Systems (IMS) are utilized. Experimental findings substantiate that the proposed similarity health indicator offers early fault alerts and precisely delineates the performance diminution of the rolling bearing. Furthermore, the put-forward CG-CGAN model achieves high-precision RUL prediction of rolling bearing.

Experimental Study on Combustion Characteristics of Solvent and Fire Behavior During a Solvent Fire at Nuclear Fuel Cycling Facility

A fire accident is one typical postulated accident in a nuclear fuel cycling facility. Safety-related data on a combustible fire are necessary to evaluate the safety of nuclear fuel cycling facilities under fire accident conditions quantitatively. Accurate and reliable data should be obtained by performing some demonstration tests. This study deals with the ignition and combustion characteristics of solvent involved at a nuclear fuel cycling facility and the fire behavior during a solvent fire. Small-scale and large-scale tests were conducted at the China Institute for Radiation Protection. The minimum ignition energy of the solvent under different temperatures was obtained. The test data were used to judge the possibility that the organic solvent ignited by a spark. Parameters such as combustion rate, smoke gas, aerosol release of solvent combustion, temperature distribution, and pressure change in the solvent fire cell were also obtained. The test results can be used as conservative estimates of the amount of aerosol release during a solvent fire. The experimental data also can be used to develop preventive and mitigation measures for solvent fire accidents. This paper puts forward information based on the experimental data and the recent international study.

TITAN: Combining a bidirectional forwarding graph and GCN to detect saturation attack targeted at SDN.

The decoupling of control and forwarding layers brings Software-Defined Networking (SDN) the network programmability and global control capability, but it also poses SDN security risks. The adversaries can use the forwarding and control decoupling character of SDN to forge legitimate traffic, launching saturation attacks targeted at SDN switches. These attacks can cause the overflow of switch flow tables, thus making the switch cannot forward benign network traffic. How to effectively detect saturation attack is a research hotspot. There are only a few graph-based saturation attack detection methods. Meanwhile, the current graph generation methods may take useless or misleading information to the attack detection, thus decreasing the attack detection accuracy. To solve the above problems, this paper proposes TITAN, a bidirecTional forwardIng graph-based saturaTion Attack detectioN method. TITAN defines flow forwarding rules and topology information, and designs flow statistical features. Based on these definitions, TITAN generates nodes of the bi-forwarding graph based on the flow statistics features and edges of the bi-forwarding graph based on the network traffic routing paths. In this way, each traffic flow in the network is transformed into a bi-directional forwarding graph. Then TITAN feeds the above bidirectional forwarding graph into a Graph Convolutional Network (GCN) to detect whether the flow is a saturation attack flow. The experimental results show that TITAN can effectively detect saturation attacks in SDNs with a detection accuracy of more than 97%.

Fault Diagnosis of Hydraulic Components Based on Multi-Sensor Information Fusion Using Improved TSO-CNN-BiLSTM.

In order to realize the accurate and reliable fault diagnosis of hydraulic systems, a diagnostic model based on improved tuna swarm optimization (ITSO), optimized convolutional neural networks (CNNs), and bi-directional long short-term memory (BiLSTM) networks is proposed. Firstly, sensor selection is implemented using the random forest algorithm to select useful signals from six kinds of physical or virtual sensors including pressure, temperature, flow rate, vibration, motor power, and motor efficiency coefficient. After that, fused features are extracted by CNN, and then, BiLSTM is applied to learn the forward and backward information contained in the data. The ITSO algorithm is adopted to adaptively optimize the learning rate, regularization coefficient, and node number to obtain the optimal CNN-BiLSTM network. Improved Chebyshev chaotic mapping and the nonlinear reduction strategy are adopted to improve population initialization and individual position updating, further promoting the optimization effect of TSO. The experimental results show that the proposed method can automatically extract fusion features and effectively utilize multi-sensor information. The diagnostic accuracies of the plunger pump, cooler, throttle valve, and accumulator are 99.07%, 99.4%, 98.81%, and 98.51%, respectively. The diagnostic results of noisy data with 0 dB, 5 dB, and 10 dB signal-to-noise ratios (SNRs) show that the ITSO-CNN-BiLSTM model has good robustness to noise interference.

Secrecy Enhancement of relay cooperative NOMA network based on user behavior

From the perspective of information security, relays exhibit varying levels of trustworthiness when forwarding information. For screening and eliminating the malicious users of cooperative NOMA relay networks, a reputation-based algorithm is proposed, in which the user relays (URs) are categorized into three types based on their behaviors—malicious users, speculative users, and honest users. Meanwhile, in order to minimize information leakage at the relay, cooperative interference signals are transmitted by far user (FU) and near user (NU) via the uplink while the base station (BS) is also transmitting signals to the relay. This approach increases inter-user interference (IUI) to confuse the eavesdropping capability of the relay. To verify the superiority of the proposed scheme, an asymptotic lower bound expression for the ergodic secrecy rate (ESR) of the downlink is derived to characterize the secrecy performance of the proposed scheme. Furthermore, in the case of limited system power, a joint power allocation algorithm based on the golden section method is also proposed to further enhance the security performances of the system. The simulation results validate the accuracy of the derived analysis results and demonstrate that the proposed scheme has a significant improvement in the ESR compared with the traditional scheme.

A polarisation coding scheme based on an integrated sensing and communication system

Integrated sensing and communication (ISAC) technology enhances the spectrum utilization of the system by interchanging the spectrum between communication and sensing, which has gained popularity in scenarios such as vehicle-to-everything (V2X). With the aim of providing more dependable services for vehicles in high-speed mobile scenarios, we propose a scheme based on sense-assisted polarisation coding. Specifically, the base station acquires the vehicle's positional information and channel strength parameters through the forward time slot echo information. This information informs the creation of the coding architecture for the following time slot. This approach not only optimizes resource consumption but also enhances system dependability. Our simulation results confirm that the introduced scheme displays a notable improvement in the bit error rate (BER) when compared to traditional communication frameworks, maintaining this advantage across both unimpeded and compromised channel conditions.

Forward Looking Disclosure and Its Determinants: Empirical Evidence from the Listed Banks of Bangladesh

Forward looking information is an emerging issue in academic and corporate arena. Today’s dynamic and competitive business world, the disclosure of forward looking information gives competitive advantages. The main objective of the study is to empirically find out the extent of forward looking disclosure and it’s determinants in the banking sector of Bangladesh. To conduct the study total 120 firm years are considered as sample from 30 listed banks from DSE as sample during the period 2017 to 2021. The average mean value of forward looking information is 38% which indicates poor quality of forward looking information in the most regulated sectors of Bangladesh. The results using multivariate regression analysis shows that board independence, audit firm size and firm’s profitability have positive and significant relationship with forward looking disclosure index (FLDI). This study also finds that foreign ownership, board size and audit independence have significant negative relationship with FLDI. But this study didn’t find any significant association of forward looking information with firm size, female board members, sponsor /directors in the banking sector of Bangladesh. To the best of our knowledge, there is scarcity of research that has been examined the disclosure of forward looking information and it’s determinants in banking sector of Bangladesh as well as very limited work is done in other sectors. The study will contribute to the existing scarce literature and may influence the policymakers and regulators to incorporate regulations to increase the quality and extent of forward looking disclosure.

GastroBot: a Chinese gastrointestinal disease chatbot based on the retrieval-augmented generation.

Large Language Models (LLMs) play a crucial role in clinical information processing, showcasing robust generalization across diverse language tasks. However, existing LLMs, despite their significance, lack optimization for clinical applications, presenting challenges in terms of illusions and interpretability. The Retrieval-Augmented Generation (RAG) model addresses these issues by providing sources for answer generation, thereby reducing errors. This study explores the application of RAG technology in clinical gastroenterology to enhance knowledge generation on gastrointestinal diseases. We fine-tuned the embedding model using a corpus consisting of 25 guidelines on gastrointestinal diseases. The fine-tuned model exhibited an 18% improvement in hit rate compared to its base model, gte-base-zh. Moreover, it outperformed OpenAI's Embedding model by 20%. Employing the RAG framework with the llama-index, we developed a Chinese gastroenterology chatbot named "GastroBot," which significantly improves answer accuracy and contextual relevance, minimizing errors and the risk of disseminating misleading information. When evaluating GastroBot using the RAGAS framework, we observed a context recall rate of 95%. The faithfulness to the source, stands at 93.73%. The relevance of answers exhibits a strong correlation, reaching 92.28%. These findings highlight the effectiveness of GastroBot in providing accurate and contextually relevant information about gastrointestinal diseases. During manual assessment of GastroBot, in comparison with other models, our GastroBot model delivers a substantial amount of valuable knowledge while ensuring the completeness and consistency of the results. Research findings suggest that incorporating the RAG method into clinical gastroenterology can enhance the accuracy and reliability of large language models. Serving as a practical implementation of this method, GastroBot has demonstrated significant enhancements in contextual comprehension and response quality. Continued exploration and refinement of the model are poised to drive forward clinical information processing and decision support in the gastroenterology field.