Clinical Efficacy and Safety of Buzhong Yiqi Decoction in Treating Epigastric Pain: A Systematic Review and Meta-Analysis

Jiajing Miao

pp.1-10 DOI: 10.62051/26wakj53

Abstract: Epigastric pain is the most common digestive tract symptom in clinical practice without good treatment to intervene at present. Buzhong Yiqi decoction (BYD) is a relatively common traditional Chinese medicine for the treatment of digestive tract diseases now, which can yiqi in the spleen and stomach. Hence, this study aims to explore the clinical efficacy and safety of BYD in the treatment of epigastric pain, so as to provide a reference for the clinical treatment of epigastric pain in the … Read More

Application and Optimization of Various Machine Learning Models in Social E-Commerce Marketing Strategies

Zhen Li

pp.11-21 DOI: 10.62051/bsm4y952

Abstract: In the context of rapid development in social e-commerce, the optimization of marketing strategies urgently requires new technological approaches. This study investigates the application of four artificial intelligence algorithms—supervised learning, deep learning, unsupervised learning, and reinforcement learning—in Douyin live shopping and Kuaishou platform shopping, proposing a series of innovative marketing strategies. Based on an analysis of 920,000 user behavior records, we evaluate the … Read More

Using Deep Learning to Predict Global Population Dynamics and Construction Risks

Kai Jin, Xingxin Yang, Yonghao Zhou, Yongzheng Wu

pp.22-29 DOI: 10.62051/3my9gm68

Abstract: In this study, a long short-term memory network (LSTM) model is used to predict the population size and risk level of each country in 2030 by combining global population data from 1950 to 2021 and country risk rating indices from 1954 to 2023.The core of the LSTM model is its three gating units: forgetting gates, input gates, and output gates, which enable the model to effectively deal with the long-term dependence problems and avoid the problems of gradient vanishing and gradient explosion in … Read More

Exploration and Application of Emotional Interactive Design in Game Design

Weihang Weng

pp.30-37 DOI: 10.62051/bxmrxs86

Abstract: This paper aims to explore the application of emotional interaction design in game design and analyze its influence on game experience. Emotional interactive design takes emotion and emotional experience as the core of design, and strives to create richer and deeper user experience through various technical means and design strategies. In the field of game design, the research and application of emotional interactive design are relatively few, and its potential and value need to be tapped. This … Read More

Analysis DevOps efficiency and digital transformation of digital economy, cross-border e-commerce, and brand building:

Jianzhong Li, Qiang Wan, Wenjuan Ma, Xiaoting Fang, Chuyi Yin, Jun Cui

pp.38-47 DOI: 10.62051/gc7xf329

Abstract: As IT-based DevOps Abilities and Automation testing theory, this study examines factors that encourage and discourage DevOps abilities and automation technology have become a major trend in the development of internet or IT enterprises, The main aim of this paper is to investigate how the use of DevOps has affected the quality of software. Another main aim is to explore and identify ways to continuously increase software quality. One way of finding information on this study is to conduct a … Read More

Research on influencing factors of pharmaceutical e-commerce sales based on web crawler and support vector machine

Shengbo Hu

pp.48-59 DOI: 10.62051/1609wx31

Abstract: Based on the current background of the rapid development of the pharmaceutical e-commerce industry, this paper provides an in-depth discussion of the factors affecting pharmaceutical e-commerce sales. With the help of Python crawler technology, the pharmaceutical e-commerce data of Alibaba Health platform is collected with GanMaoLingKeLi(999) as an example. Using support vector machine (SVM), according to the selected characteristic indicators, different schemes are set to predict the sales of … Read More

Comparative Analysis of Machine Learning Algorithms for Consumer Credit Risk Assessment

Tianyi Xu

pp.60-67 DOI: 10.62051/r1m3pg16

Abstract: In the rapidly evolving landscape of financial technology, machine learning algorithms are increasingly supplanting traditional methodologies for evaluating consumer credit risk. This study leverages a comprehensive dataset comprising 10,000 credit accounts to conduct a comparative analysis of four prevalent machine learning algorithms: Logistic Regression, Decision Tree, Random Forest, and Gradient Boosting Machine (GBM). The results distinctly favor GBM, which achieves an AUC of 0.87, closely … Read More

Research on Photovoltaic Power Generation Prediction Based on Ensemble Learning DBO-LSTM-EBRB

Boyi Fu, Jiayan Lin

pp.68-78 DOI: 10.62051/qvae5840

Abstract: Photovoltaic power generation represents a pivotal form of renewable energy. Accurate power prediction is therefore of paramount importance to the advancement of the energy revolution. This paper examines the Yumara Solar System PV plant in the central region of Australia as a case study. The research begins with the use of the k nearest neighbor algorithm (KNN) and extreme gradient boosting algorithm (XGBoost) to pre-process the PV power generation data from the PV plant. This is followed by … Read More

Acoustic method Temperature and velocity fields in the furnace Co-measurement method study

Yanqin Li

pp.79-85 DOI: 10.62051/z4rzrn36

Abstract: The combustion power field and velocity field of power station boiler chamber have a direct impact on the boiler operation economy and reliability, and the power field in the furnace must be measured collaboratively. However, the thermal conditions of the power field environment is harsh, the traditional method can not be effectively detected, non-contact acoustic wave method can be taken to measure, high precision, simple methods, real-time detection can be realized. Based on this, this paper … Read More

Collaborative Optimization of Game Enemy Design and Network Security Defense Based on Deep Reinforcement Learning

Jianshu Liu

pp.86-91 DOI: 10.62051/4xk79k26

Abstract: The purpose of this paper is to explore the cooperative optimization strategy of game enemy design based on Deep Reinforcement Learning (DRL) and Network Security Defense (NSD). By analyzing the correlation between game enemy design and NSD, this paper puts forward a method of integrating DRL technology to improve the game experience and protect the security of the game system. Firstly, the paper introduces the basic concepts and existing research progress of game enemy design and NSD. Then, the … Read More

Innovation and Challenges of Smart Metrology in the Industry 4.0 Era

Yubin Zhao

pp.92-96 DOI: 10.62051/wpd6hm42

Abstract: Smart Metrology refer to a way of measure thing by advance technology, those technology include IOT, AI and Deep Learning. It’s not only just a way of measure thing, but also provide manufacturing some way to manage themselves, especially within the framework of Industry 4.0/5.0. in this article, we will talk about some cutting-edge technology and typical case, from there, we will learn and get some basic metrology data. Finally, the challenges and trends will be discussed including some … Read More

Design and Implementation of a Microblog Public Opinion Visualization System Based on Flask and ECharts

Yun Liu, Dong Xiao

pp.97-104 DOI: 10.62051/nq8zkq20

Abstract: Conducting public opinion analysis on Weibo data is of significant importance to decision-making processes in government, enterprises, and personal contexts. This paper presents the design and implementation of a real-time microblog public opinion visualization system based on Flask and ECharts. The system aims at effectively monitoring Weibo data in real time, performing sentiment analysis, and trend prediction.The system adopts a B/S architecture, employing distributed web crawling techniques … Read More

Validity of data estimation methods in large-scale insurance datasets

Jinrong Zhao, Daibin Lan, Tengfei Meng, Wanting Kan

pp.105-111 DOI: 10.62051/vdknqp32

Abstract: In the insurance industry, accurately processing and analysing large-scale datasets is critical for risk assessment and decision-making. In this study, a comprehensive database was built by collecting and integrating weather-related data, insurance industry data, and attribute-specific data to support in-depth analyses of the impact of extreme weather events. In the data preprocessing stage, we adopted mean-filling and plurality-filling methods to deal with missing data, while applying the 3σ … Read More

Research on Mechanical Fault Diagnosis and Prediction Technology Based on Deep Learning

Jiahao Lv

pp.112-117 DOI: 10.62051/vbkk3b17

Abstract: This study introduces an innovative deep learning architecture, amalgamating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks, termed the CNN-LSTM model. Its efficacy in both identifying and anticipating mechanical failures is explored through an examination of vibration datasets sourced from actual industrial machinery. The assessment delves into the model's capabilities across various fault categories and severities. Findings indicate that the CNN-LSTM model … Read More

Research and Application of Random Forest Model Based on Genetic Algorithm Optimisation

Lixiang Yu, Wenkui Wu

pp.118-122 DOI: 10.62051/1w92yr11

Abstract: In this study, an in-depth analysis of the relationship between infant behavioural characteristics and mothers' physical and psychological indicators was conducted by integrating a random forest model optimised by a genetic algorithm. A mathematical model of treatment cost and health improvement rate was also established, which provides a scientific basis and technical support for infant behaviour analysis and individualized intervention strategies. Read More

A Survey of Studies on Discourse Structure and Relation

Nianyi Huang

pp.123-129 DOI: 10.62051/64dyv490

Abstract: Discourse Analysis aims at high-level semantic and structural analysis. Discourse structure analysis and relation recognition are two key tasks in discourse analysis research, while discourse analysis plays an important role in studying the structure and semantic content of texts. This paper firstly introduces the Rhetorical Structure Theory (RST) and the Penn Discourse TreeBank (PDTB) annotation standards and its corresponding resources establishment of each corpus. Then the mainstream models … Read More

Research on Recognition of Deck Cars Based on Big Data Technology

Jinsong Li

pp.130-135 DOI: 10.62051/cw566037

Abstract: With the increasing number of vehicles and the increasingly prominent traffic safety problems, deck cars have become a difficult problem that seriously affects social security and traffic order. Aiming at the problem of deck car recognition, this paper proposes a deck car recognition model based on big data technology. By collecting a large number of vehicle data, combining with deep learning and traditional machine learning methods, an effective recognition model of deck vehicles is designed … Read More

RAINBOW: Resilient Asymmetric Imaging Non-linear Bit-level Ordering with Hyperchaotic Operation for Color image Encryption

Wenhui Zhang

pp.136-148 DOI: 10.62051/x7y04r49

Abstract: Hyperchaotic encryption, known for its high level of unpredictability and complexity, is widely used in the field of image encryption. However, current hyperchaotic image encryption tech- niques have certain limitations, particularly in terms of their simplistic processing and lack of depth in layer interaction. These limitations ultimately hinder their effectiveness in ensuring security. In order to overcome these challenges, we propose RAINBOW, a method that integrates bit-level and … Read More

Optimization and User Behavior Analysis of Accounting Online Informatization Service Platform Using UTAUT

Chujie Sun

pp.149-155 DOI: 10.62051/scj3xy69

Abstract: In order to optimize the accounting online informatization service platform and gain in-depth insights into user behavior, this work first analyzes the user behavior of the accounting online informatization service platform based on the core variables of the Unified Theory of Acceptance and Use of Technology (UTAUT). Next, a correlation analysis model is constructed to validate the impact of four variables—age, gender, occupation, and years of service—on user behavior. The research results … Read More

Analysis on the application of strategic information system of ERKE

Yixuan Li

pp.156-161 DOI: 10.62051/by4yhz45

Abstract: ERKE as an early well-known domestic sports brand, its sales and management mode has its uniqueness, this paper analyzes the SIS characteristics, advantages and suggestions of ERKE brand by comparing it with the SIS of its main competitor brand Li-Ning. Read More

Research and development of plateau portable landslide detection equipment based on Jetson Nano

Jianyu Xu, Siwei Cheng, Libin Su, Yonggang Guo

pp.162-171 DOI: 10.62051/eqrtb452

Abstract: In response to the problems that landslides occur in remote locations, are difficult to monitor and landslide target detection is not easily deployed at the embedded end, a landslide detection device based on the Jetson nano edge device is developed. The technology detects information of landslide feature objects through YOLOV5m technology, and is able to output landslide area information as well as geographic location information while accurately detecting landslide targets. A dataset of 25,000 … Read More

A Fourier series model and parametric study for single person three-way continuous walking load

Ping Li

pp.172-180 DOI: 10.62051/a32pct74

Abstract: The characteristics and mathematical model of the walking load is the basis for studying   human-induced vibration in large-span flexible structures. In this paper, 2842 sets of effective walking load datum were collected by three-way force plate test. The correlation analysis shows that the correlations between the vertical component, the horizontal component and the longitudinal component of the walking load are weak, the Fourier series models of the three directional components of the walking … Read More