Dianchi College

Heterogeneous information networks (HINs) comprise vertices and edges with different types, representing different objects and links, so as to abstract and model the real world more completely and naturally. Rich structural and semantic information contained in HINs provides new opportunities and challenges to discover hidden patterns in HINs. Community Search (CS) over HINs, aiming to find a subgraph that satisfies the given conditions, provides important support for various applications such as team formation, personalized recommendation, fraud detection, group identification, and so on, and many CS approaches have been proposed recently. This study introduces types of HINs, CS constraints, search strategies, proposes a novel taxonomy of CS over HINs, and reviews the CS models as well as solutions over different HINs. It then analyzes and compares the characteristics of different models and solutions, and summarizes evaluation metrics generally used in literature. This survey aims to provide valuable insights on the latest progress of CS over HINs, facilitating researchers conduct in-depth research in this field.

Financial stress index (FSI), as a financial risk measure, can timely reflect the risk of China’s financial market with early warning function and forecasting ability. First of all, referring to the IMF index system, this paper constructs the pressure indicators of China’s financial market, and then establishes the impulse response function of VAR (2,2) model with the main macroeconomic variables to analyze the impact of the FSI index on China’s macroeconomic. The research conclusion shows that the financial stress index constructed in this paper has a lasting negative impact on China’s major macroeconomic variables. At the same time, FSI can objectively and timely reflect the crisis warning of financial risk, and can also well correspond to the real economic and financial events that have happened already.

Traditional classification methods often depend on manual annotations and expert judgments, which are time-consuming, labor-intensive, and inefficient for large-scale data. This paper introduces a music genre classification algorithm based on machine learning to enhance efficiency and accuracy. The study begins by preprocessing audio data through format conversion and wavelet threshold denoising. Features are then extracted using short-time Fourier transform (STFT) to obtain MFCC (Mel-Frequency Cepstral Coefficients), along with chroma and rhythm features. For model construction, a deep learning model combining convolutional neural network (CNN) and recurrent neural network (RNN) is employed to capture spatiotemporal dependencies in the audio data. Experiments were conducted using two large-scale datasets with a total scale of 500,000 audio tracks, and the results show that the proposed model achieved high classification accuracy on both datasets, with a test set accuracy of 89.3% on the online music platform dataset. In addition, compared with traditional machine learning models, the algorithm proposed in this study performed better in terms of classification accuracy and overall recall rate. This study not only improves the accuracy of music genre classification but also provides technical support for fields such as music recommendation and copyright management.

In order to prevent supply chain financial risks (SCFR), commercial banks should establish a risk assessment index system and introduce the BPNN (Back Propagation Neural Network) model into SCFR assessment to achieve prediction of SCFR. This article constructs a BPNN model, builds a SCFR evaluation index system, and uses genetic algorithm (Genetic Algorithm, GA) to optimize the weights and thresholds of the BPNN, then applies the BPNN model optimized by genetic algorithm to the SCFR assessment of commercial banks. The article finally verifies the effectiveness of the GA-BPNN model. The results show that the GA-BPNN model can increase the accuracy of risk assessment to a maximum of 95.7%, which will be of great help to future risk assessment research.

This article designs and implements a comprehensive system. The system integrates many functional modules such as data collection, processing, feature extraction, trend prediction and individualized recommendation. In terms of methods, this article adopts a prediction model combining time series analysis and ML (Machine Learning) algorithm to capture the dynamic changes of music popularity, and designs a mixed recommendation strategy to meet the individualized needs of users. In the experimental verification stage, an experimental data set containing real user behavior data and music feature information is constructed, and the prediction accuracy and recommendation effect of the system are comprehensively evaluated. The results show that the prediction accuracy of the fashion trend prediction model on the test set is over <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 0. 5 \%}$</tex>, and the recommendation algorithm is excellent in improving user satisfaction, click-through rate and playing time. These results fully prove the effectiveness and feasibility of the system and method proposed in this study. It not only provides new ideas and methods for music trend prediction and individualized recommendation, but also provides strong technical support for the operation and development of music platform.

As the material living standards of residents rapidly improve, the demand for fruits and vegetables continues to rise. Agricultural greenhouses, as a critical means of increasing fruit and vegetable yields, require effective control of temperature, humidity, and light intensity to ensure rapid crop growth. Traditional manual monitoring and control methods are inefficient and labor-intensive. Against the backdrop of rapid developments in electronic technology, this paper innovatively designs a greenhouse IoT intelligent control system based on a microcontroller, achieving real-time monitoring and automated control of greenhouse environment parameters. The innovations of this system are evident in several aspects: Firstly, it employs an STM32 microcontroller as the main control chip, integrating YL-69 soil moisture sensors, GL5506 photodiodes, and DS18B20 temperature sensors to achieve high-precision detection of soil moisture, light intensity, and temperature. Secondly, an LCD1602 display is used to timely showcase real-time environmental parameters, and alarm thresholds can be set via buttons. If these thresholds are exceeded, a buzzer sounds an alarm. Concurrently, the system utilizes water pumps and supplementary LED lights to intelligently adjust humidity and light intensity within the greenhouse. Most importantly, by incorporating the ESP8266 module, the system achieves remote data transmission, allowing users to view real-time environmental parameters via a mobile app and set thresholds and control operations. This greenhouse IoT intelligent control system not only features alarm functions for exceeded environmental parameters but also enables automatic adjustment through intelligent devices and supports remote control, greatly enhancing operational convenience and system practicality. Overall, this system innovatively integrates various sensing technologies and IoT communication, providing an efficient and intelligent solution for the modern management of agricultural greenhouses. It exhibits broad market prospects and holds significant importance for advancing agricultural modernization.

The code length of a source can be reduced effectively by using conditional probability distributions in a context model. However, the larger the size of the context model, the more difficult the estimation of the conditional probability distributions in the model by using the counting statistics from the source symbols. In order to deal with this problem, a hierarchical clustering based context quantization algorithm is used to combine the conditional probability distributions in the context model to minimize the description length. The simulation results show that it is a good method for quantizing the context model. Meanwhile, the initial cluster centers and the number of classes do not need to be determined in advance any more. Thus, it can greatly simplify the quantizer design for the context quantization problem.

Cultural amalgamation is not only a striking phenomenon in discrete literary works, but also a literary reality in the creation of non-native language literary works in the multicultural context. Through the text analysis of the latest English novel "Snow Lily" by Li Yan, a Chinese Canadian writer, this paper discusses the application of the combination of Chinese and Western cultures in literary works in the multicultural context. At this time, Utopia plays a negative role in reality, alerting people to reset their hopes in time, in order to connect with the future; Although it is an exotic life from the bottom of the society, the protagonist Lily never gives up her efforts. She is pursuing a kind of universal values about the growth of the soul and human beings. Utopia has realized the budding role of the future ideology here.

With the continuous acceleration of urbanization, a large number of people have flooded into cities, and improving the level of urban services is urgent. Relying on mobile Internet technology, smart cities have realized the functions of rapid transmission, accurate query, intelligent management and so on of data and information through data collection, sorting, storage, analysis, viewing, etc., so that enterprises, residents and governments can enjoy intelligent production processes, perfect public services, and information-based management, which not only helps to improve the level of urban services, but also can effectively solve the problems of traffic congestion, housing shortage, medical and health insufficiency and other problems caused by population agglomeration, and improve the efficiency of resource use. Starting from the role of mobile Internet in smart cities, this paper discusses the use of mobile Internet in smart cities in order to improve the development level of smart cities.

to save material circle and hexagon are often used shapes for web opening in praxis; horizontal plates are often welded on web for stiffening large web opening. These common used shape of opening and stiffening way for large opening are proved as inefficient by finite element analyze. There are new shape of opening and new type of stiffener for large opening, which proved to have the best load bearing behavior respectively. More details will be introduced in following.

Due to the heterogeneity of data distribution in real life and the spatial autocorrelation among spatial instances, traditional spatial co-location pattern mining methods tend to ignore valuable information specific to local regions. To address the limitation, regional co-location pattern mining has been proposed to find patterns that may be hidden within local regions. In this paper, a fuzzy regional co-location pattern mining framework based on efficient density peak clustering and maximal fuzzy grid cliques is presented. By incorporating a grid-splitting method and fuzzy theory, an efficient density peak clustering algorithm is proposed to divide the global area into distinct local regions. Furthermore, we propose a method to materialize the neighbor relationships between instances based on the maximal fuzzy grid cliques and parallelize the clustering process to improve the algorithm efficiency. Experimental results show that the proposed algorithm can not only reduce the time consumption by about 40% but also mine meaningful patterns with tighter instance distributions. Received: 24 November 2023 | Revised: 25 January 2024 | Accepted: 7 February 2024 Conflicts of Interest Lizhen Wang is an Editorial Board Member for Journal of Data Science and Intelligent Systems and was not involved in the editorial review or the decision to publish this article. The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in GitHub at https://github.com/Vansank/DataSet.git. Author Contribution Statement Tao Zhou: Conceptualization, Methodology, Software, Formal analysis, Investigation, Data curation, Writing - original draft, Visualization. Lizhen Wang: Conceptualization, Methodology, Validation, Formal analysis, Resources, Writing - review &amp; editing, Supervision, Project administration, Funding acquisition. Dongsheng Wang: Investigation, Visualization. Vanha Tran: Validation, Data curation, Writing - review &amp; editing.

Current research on measuring currency internationalization has important implications for effectively examining the scope of currency internationalization among emerging economies. We examined the effects of countries’ financial development on their currency internationalization from a multidimensional globalization perspective. Using imbalanced panel data from 167 countries spanning from 1970 to 2021, we constructed a comprehensive indicator for measuring the currency internationalization process. Our findings highlight the significant role of financial development in promoting currency internationalization, particularly under high levels of globalization. The results reveal considerable differences in the impact of financial development between emerging markets and developed economies. Further, globalization of trade and finance were found to be important factors restricting currency internationalization. Thus, this study explains the phased development of currency internationalization from a globalization perspective.

After the 2008 financial crisis, the whole world financial markets became more fluctuates, the same to China also. It is necessary to pay great attention to high volatility problem in Chinese market, and also the uncertainty problem, risk accumulation and spillover effect come along with it. This paper calculates stock market return and builds financial stress index to explore the risk spillover effect. Empirical results show that the Chinese financial market have higher volatility than other countries. The Chinese stock market had higher dynamic market co-movement with international financial markets after 2008 financial crisis. What’s more, this article also finds the financial risk spreads between China and US. When the US financial stress index increases, China's financial stress index experiences a larger increase. However, after the change in China's financial stress index, the US financial stress index has no obvious trend of change. So we should pay more attention to periods of Chinese financial market risk and its spillover.

In recent years, with the development of the service industry, the queuing problem of improving the effectiveness of resource allocation to reduce the waiting time of customers has become more prominent. Existing researches mainly focus on the fixed matching rate model, and lack the in-depth exploration of the variable matching rate in real service scenarios. This paper constructs an M/M/c model of variable matching rate, considering the impact of various factors on the customer arrival rate and service rate in practical service contexts. Innovatively, we propose a variable matching rate formula applicable when the number of customers exceeds the number of service stations, addressing the gaps in the current research. By constructing a two-dimensional Markov quasi-birth-and-death process and generator matrix, it establishes an infinite-dimensional steady-state probability equation to calculate system performance metrics. Finally, a reasonable range of matching rates is determined by simulation, and system metrics are compared between fixed and variable matching rate M/M/c models.

The development of digital inclusive finance (DIF) helps solve problems such as information asymmetry and adverse selection in traditional inclusive finance, and improves the coverage, availability, and satisfaction of financial services, but DIF itself also faces many risks. The DIF risk evaluation and decision-making system based on big data and artificial intelligence (AI) technology can help solve the information asymmetry problem in DIF and reduce the problems of adverse selection and moral hazard in DIF, thereby improving the efficiency and quality of DIF services. This article discusses the DIF risk assessment and decision-making system based on big data and AI technology from the aspects of data quality, algorithm model, data sharing and business management, with a view to providing reference for the development of DIF business. The results show that the service efficiency of the DIF risk assessment and decision-making system based on big data and AI technology can reach up to $90 \%$.

As we hasten into the digital age, facial recognition technology has emerged as a pivotal innovation across various domains such as security authentication, surveillance, and identity verification. This research delves into and enhances the Convolutional Neural Network (CNN) framework within the MATLAB environment, substantially augmenting the efficacy of facial recognition algorithms. The manuscript begins by tracing the evolution and current achievements within the facial recognition field, followed by an exploration into the theoretical foundation and key technologies of facial recognition. The aim of this study is to develop an advanced facial recognition algorithm based on CNN, employing efficient image preprocessing techniques such as grayscale conversion, noise reduction, and feature extraction, thereby significantly improving recognition accuracy and processing speed. Experiments conducted within MATLAB showcase the dual advancements in efficiency and speed offered by the optimized algorithm compared to traditional methods. Moreover, the paper discusses the adaptability of this algorithm in complex scenarios and the challenges and strategies likely to be encountered during pragmatic application. The outcomes of this research not only validate the practicality of the proposed algorithm but also illuminate directions and methodologies for the future exploration of facial recognition technology.

The primary purpose is to measure competency gaps between industry expectations and the capabilities of newly graduated quantity surveyors in China. A new measure with high-dimensional measurement error model was used for assessing the competency gaps. We adopted the purposive sampling to gather data through a questionnaire survey of recently graduated quantity surveying professionals who had worked in China for no more than 3 years. The results reveal a competency gap in job matching. Specifically, there is a moderate competency gap in personality and minor gaps in professional knowledge, professional skills, and professional ethics. And the top three competency gap indicators are business administration, personal image, and innovative insight. The findings emphasize the need for educational programs to integrate management and personality development, fostering multidisciplinary capabilities in students.

Kinship addressing terms are the basic part of the lexicon system with the features of long history,high frequency and stability.Influenced by Chinese kinship terms in Yi-Chinese contacts,there have been some variation and diversion in Yi Kinship terms.The interaction shows the influences and blending between different languages and cultures.

NOTICE OF RETRACTION: While investigating potential publication-related misconduct in connection with the ICIMTech 2021 Conference Proceedings, serious concerns were raised that cast doubt on the integrity of the peer-review process and all papers published in the Proceedings of this Conference. The integrity of the entire Conference has been called into question. As a result, of its investigation, ACM has decided to retract the Entire Conference Proceedings and all related papers from the ACM Digital Library.

Uncertain knowledge graphs store the relations between entities in the real world in the form of weighted triples, where the weights indicate the confidence scores of the triples to be true. However, there is limited research on the inference of uncertain knowledge graphs, especially in the integration of symbolic and numerical methods. Rules are explicit knowledge. Encoding the rules directly can provide more knowledge graph semantic information and can make full use of the interpretability and accuracy of logical rules. Unfortunately, none of the existing methods directly encode rules for uncertain knowledge graphs, but only use rules to calculate the confidence of unseen triples in training data. In this paper, we propose a new reasoning model CRLUKG for uncertain knowledge graphs, that combines the advantages of symbolic and numerical reasoning. We directly encode rules mined from the knowledge graph as one of the inputs of the CRLUKG model. Compositional representation learning with triple and rule embedding is implemented for optimizing objective function for triples and relations pairs. Experimental results demonstrate that our proposed method enhances the accuracy of reasoning, and furthermore, CRLUKG exhibits superior performance in comparison to baseline models when handling multi-task scenarios.