Computer Science › Information Systems

Advanced Decision-Making Techniques

Works Count: 50804

Wikipedia

Description

This cluster of papers focuses on the application of spatial data mining techniques, cloud models, and advanced technologies such as process neural networks, fuzzy neural networks, virtual reality simulation, and 3D laser scanning in various domains. It also encompasses research on information security risk assessment, network security evaluation, and GIS data mining using quantitative and qualitative research methods.

Keywords

Spatial Data Mining; Cloud Model; Information Security Risk Assessment; Process Neural Networks; Fuzzy Neural Network; Virtual Reality Simulation; Network Security Evaluation; 3D Laser Scanning; GIS Data Mining; Quantitative and Qualitative Research

An Algorithm for Distributed Reinforcement Learning in Cooperative Multi-Agent Systems

2000-06-29

Martin Lauer , Martin Riedmiller

Aggregation operators on intuitionistic trapezoidal fuzzy number and its application to multi-criteria decision making problems

2009-04-01

Jian‐qiang Wang , Zhang Zhong

Intuitionistic trapezoidal fuzzy numbers and their operational laws are defined. Based on these operational laws, some aggregation operators, including intuitionistic trapezoidal fuzzy weighted arithmetic averaging operator and weighted geometric averaging … Intuitionistic trapezoidal fuzzy numbers and their operational laws are defined. Based on these operational laws, some aggregation operators, including intuitionistic trapezoidal fuzzy weighted arithmetic averaging operator and weighted geometric averaging operator are proposed. Expected values, score function, and accuracy function of intuitionitsic trapezoidal fuzzy numbers are defined. Based on these, a kind of intuitionistic trapezoidal fuzzy multi-criteria decision making method is proposed. By using these aggregation operators, criteria values are aggregated and integrated intuitionistic trapezoidal fuzzy numbers of alternatives are attained. By comparing score function and accuracy function values of integrated fuzzy numbers, a ranking of the whole alternative set can be attained. An example is given to show the feasibility and availability of the method.

Quantitative Hierarchical Threat Evaluation Model for Network Security

2006-01-01

Xiuzhen Chen

Evaluating security threat status is very important in network security management and analysis. A quantitative hierarchical threat evaluation model is developed in this paper to evaluate security threat status of … Evaluating security threat status is very important in network security management and analysis. A quantitative hierarchical threat evaluation model is developed in this paper to evaluate security threat status of a computer network system and the computational method is developed based on the structure of the network and the importance of services and hosts. The evaluation policy from bottom to top and from local to global is adopted in this model. The threat indexes of services, hosts and local networks are calculated by weighting the importance of services and hosts based on attack frequency, severity and network bandwidth consumption, and the security threat status is then evaluated. The experiment results show that this model can provide the intuitive security threat status in three hierarchies: services, hosts and local networks so that system administrators are freed from tedious analysis tasks based on the alarm datasets to have overall security status of the entire system. It is also possible for them to find the security behaviors of the system, to adjust the security strategies and to enhance the performance on system security. This model is valuable for guiding the security engineering practice and developing the tool of security risk evaluation.

An Investigation of Methods for Reducing Sampling Error in Certain IRT Procedures

1984-07-01

Marilyn S. Wingersky , Frederic M. Lord

The sampling errors of maximum likelihood esti mates of item response theory parameters are studied in the case when both people and item parameters are estimated simultaneously. A check on … The sampling errors of maximum likelihood esti mates of item response theory parameters are studied in the case when both people and item parameters are estimated simultaneously. A check on the validity of the standard error formulas is carried out. The effect of varying sample size, test length, and the shape of the ability distribution is investigated. Finally, the ef fect of anchor-test length on the standard error of item parameters is studied numerically for the situation, common in equating studies, when two groups of ex aminees each take a different test form together with the same anchor test. The results encourage the use of rectangular or bimodal ability distributions, and also the use of very short anchor tests.

View PDF Chat

Normal ogive model on the continuous response level in the multidimensional latent space

1974-03-01

Fumiko Samejima

Integration of ART-Kohonen neural network and case-based reasoning for intelligent fault diagnosis

2003-10-16

Bo‐Suk Yang , Tian Han , Yongsu Kim

Fault diagnosis of machines based on D–S evidence theory. Part 1: D–S evidence theory and its improvement

2005-10-14

Xianfeng Fan , Ming J. Zuo

A discussion on Extent Analysis Method and applications of fuzzy AHP

1999-07-01

Kejun Zhu , Jing Yu , Da-Yong Chang

Method of multi-criteria group decision-making based on cloud aggregation operators with linguistic information

2014-03-06

Jian‐qiang Wang , Peng Lu , Hong‐yu Zhang +1 more

The average spearman rank correlation coefficient

1952-12-01

Samuel B. Lyerly

Reduction of Tomato Leaflet Photosynthesis Rates by Mining Activity of Liriomyza sativae (Diptera: Agromyzidae)

1983-10-01

Marshall W. Johnson , Stephen C. Welter , Nick C. Toscano +2 more

Effects of mining activities of Liriomyza sativae Blanchard on leaf conductance and photosynthesis rates of tomato leaflets were examined in the field. Photosynthesis rates in mined tissues were reduced 62% … Effects of mining activities of Liriomyza sativae Blanchard on leaf conductance and photosynthesis rates of tomato leaflets were examined in the field. Photosynthesis rates in mined tissues were reduced 62% compared with rates in unmined leaflets. A negative linear correlation was found between the percentage of mining in a leaflet and photosynthesis and stomatal conductance rates in the unmined tissues. Effects of L. sativae mining upon leaflet photosynthesis were not isolated to mined areas alone, and low levels of mining activity greatly reduced leaflet photosynthesis.

Generic normal cloud model

2014-05-09

Guoyin Wang , Changlin Xu , Deyi Li

An Uncertain Linguistic Multi-criteria Group Decision-Making Method Based on a Cloud Model

2014-03-27

Jian‐qiang Wang , Juan‐juan Peng , Hong‐yu Zhang +2 more

An Efficient Method for Reliability Evaluation of a General Network

1978-08-01

Suresh Rai , K.K. Aggarwal

This paper presents a method for finding the terminal-pair reliability expression of a general network. First, the system success function S is found, beginning from the connection matrix for the … This paper presents a method for finding the terminal-pair reliability expression of a general network. First, the system success function S is found, beginning from the connection matrix for the logic diagram of the network. Second, using the concept of Exclusive operator, S is changed to its equivalent S (disjoint) form, and the reliability expression has been derived. The method has the advantage of not requiring step by step testing for disjointness. Examples illustrate the method.

Developing a cloud model based risk assessment methodology for tunnel-induced damage to existing pipelines

2014-04-12

Limao Zhang , Xianguo Wu , Queqing Chen +2 more

A Simple, Positive Semi-Definite, Heteroskedasticity and Autocorrelation Consistent Covariance Matrix

1987-05-01

Whitney K. Newey , Kenneth D. West

This paper describes a simple method of calculating a heteroskedasticity and autocorrelation consistent covariance matrix that is positive semi-definite by construction. It also establishes consistency of the estimated covariance matrix … This paper describes a simple method of calculating a heteroskedasticity and autocorrelation consistent covariance matrix that is positive semi-definite by construction. It also establishes consistency of the estimated covariance matrix under fairly general conditions.

View PDF Chat

Averaging model applied to the size-weight illusion

1970-01-01

Norman H. Anderson

View PDF Chat

An Information Fusion Fault Diagnosis Method Based on Dimensionless Indicators With Static Discounting Factor and KNN

2015-11-03

Jianbin Xiong , Qinghua Zhang , Guoxi Sun +3 more

For petrochemical rotating machinery and equipment, the reliability of the diagnostic evidence is affected by uncertain factors, causing conflicts between evidence provided by the various information sources, and thus affecting … For petrochemical rotating machinery and equipment, the reliability of the diagnostic evidence is affected by uncertain factors, causing conflicts between evidence provided by the various information sources, and thus affecting the validity of the fault diagnosis. This paper presents an information fusion fault diagnosis method that is based on a static discounting factor and combines K-nearest neighbors (KNNs) with dimensionless indicators. The method uses evidence reasoning to process the uncertainty and accuracy of the information through the KNN algorithm and dimensionless indicators to turn petrochemical machinery sensor input signals into the reliability of structure framework, according to the static discount factor, after correction evidence and evidence theory formula was used to fusion and, based on the fusion result, the fault type diagnosis decision-making. Experimental results show that the method can effectively reduce the influence of unreliable factors on the fusion results, thus allowing more accurate decision making.

Variable Fuzzy Sets and its Application in Comprehensive Risk Evaluation for Flood-control Engineering System

2006-04-01

Shouyu Chen , Yu Guo

Uncertainty in Artificial Intelligence

1990-01-01

Overview on fuzzy multi-criteria decision-making approach

2008-01-01

Jian‐qiang Wang

As one of the advanced research direction in decision-making fields, fuzzy multi-criteria decision-making is of wide applications in real decision-making. The current research on the multi-criteria linguistic decision-making methods and … As one of the advanced research direction in decision-making fields, fuzzy multi-criteria decision-making is of wide applications in real decision-making. The current research on the multi-criteria linguistic decision-making methods and fuzzy multi-criteria decision-making methods based on fuzzy number, intuitionistic fuzzy set and Vague set are reviewed. The definition of intuitionistic trapezoidal fuzzy number and interval intuitionistic trapezoidal fuzzy number are given, and the fuzzy number and intuitionistic fuzzy set are extended. Some problems and future research directions on fuzzy multi-criteria decision-making are also proposed.

On Water-saving Irrigation

2002-01-01

Luo Jia

Water-saving irrigation is an effective method to mitigate water resources lackage.It's a kind of scientific irrigation techniques,and a technological support of production increasing.The writer puts forword 3 aspects in water-saving … Water-saving irrigation is an effective method to mitigate water resources lackage.It's a kind of scientific irrigation techniques,and a technological support of production increasing.The writer puts forword 3 aspects in water-saving irrigation,such as engineering measures,irrigation program and irrigation management.

A Summary of Traffic Flow Forecasting Methods

2004-01-01

Wei Guan

Real-time traffic flow forecasting is one of important issues of ITS research.Some forecasting models including history average,time-series,Kalman filtering,non-parametric regression,neural networks and synthetic model,etc,have been established.Review of these existing forecasting models,and … Real-time traffic flow forecasting is one of important issues of ITS research.Some forecasting models including history average,time-series,Kalman filtering,non-parametric regression,neural networks and synthetic model,etc,have been established.Review of these existing forecasting models,and probable frequency of traffic flow forecasting research field is presented..

Multi-criteria decision-making method based on aggregation operators for intuitionistic linguistic fuzzy numbers

2010-01-01

Hanbo Li

Intuitionistic linguistic fuzzy numbers,as well as their operational laws,expected values,score function and accuracy function are defined.Some intuitionistic linguistic fuzzy aggregation operators are proposed,including weighted arithmetic averaging operator and weighted geometric … Intuitionistic linguistic fuzzy numbers,as well as their operational laws,expected values,score function and accuracy function are defined.Some intuitionistic linguistic fuzzy aggregation operators are proposed,including weighted arithmetic averaging operator and weighted geometric averaging operator.For fuzzy multi-criteria decision making problems,in which the criteria values are intuitionistic linguistic fuzzy numbers,an approach based on intuitionistic linguistic fuzzy aggregation operators is proposed.By using these aggregation operators,criteria values are aggregated and integrated intuitionistic linguistic fuzzy numbers of alternatives are attained.By comparing score function and accuracy function values of integrated fuzzy numbers,a ranking of the whole alternative set can be attained.Analysis of an example shows the feasibility and effectiveness of the method.

Fuzzy Multi-Criteria Decision Making

2008-01-01

Cengiz Kahraman

Prediction of rock burst classification using cloud model with entropy weight

2016-07-01

Keping Zhou , Yun Lin , Hongwei Deng +2 more

Perceiving safety risk of buildings adjacent to tunneling excavation: An information fusion approach

2016-10-01

Limao Zhang , Xianguo Wu , Hongping Zhu +1 more

A new safety assessment model for complex system based on the conditional generalized minimum variance and the belief rule base

2016-12-01

Gailing Li , Zhijie Zhou , Changhua Hu +3 more

A Linguistic Large Group Decision Making Method Based on the Cloud Model

2018-04-02

Pei Wang , Xuanhua Xu , Shuai Huang +1 more

Serving as an effective tool for describing both randomness and fuzziness of qualitative concepts, the cloud model has become a common topic of research. By realizing the uncertain transformation between … Serving as an effective tool for describing both randomness and fuzziness of qualitative concepts, the cloud model has become a common topic of research. By realizing the uncertain transformation between qualitative concepts and quantitative data, the cloud model provides a new way to deal with group decision making problems in the linguistic environment. However, classical methods based on the cloud model mainly focus on addressing problems with a small number of decision makers. In this paper, we apply the cloud model to the decision making problems that involve a large group of decision makers. Specifically, we first define a new measure of fuzzy distance for clouds based on the $\boldsymbol { \alpha -cuts}$. On the basis of the proposed fuzzy distance measure, we then present a new similarity measure between clouds. Next, we construct an improved clustering approach based on the traditional hierarchical clustering algorithm. Furthermore, we develop a hybrid weight scheme to obtain the cluster weight vector, which takes both the subgroup size and the variance into consideration. Moreover, we present a consensus-based method based on the cloud model for large group decision making with linguistic information. Finally, in order to confirm the validity and effectiveness of the proposed method, we give an application in the context of the Belt and Road Initiative of China, and perform some detailed comparisons to show the advantages of the proposed method.

Synthetic well logs generation via Recurrent Neural Networks

2018-07-17

Dongxiao Zhang , Yuntian Chen , Meng Jin

To supplement missing logging information without increasing economic cost, a machine learning method to generate synthetic well logs from the existing log data was presented, and the experimental verification and … To supplement missing logging information without increasing economic cost, a machine learning method to generate synthetic well logs from the existing log data was presented, and the experimental verification and application effect analysis were carried out. Since the traditional Fully Connected Neural Network (FCNN) is incapable of preserving spatial dependency, the Long Short-Term Memory (LSTM) network, which is a kind of Recurrent Neural Network (RNN), was utilized to establish a method for log reconstruction. By this method, synthetic logs can be generated from series of input log data with consideration of variation trend and context information with depth. Besides, a cascaded LSTM was proposed by combining the standard LSTM with a cascade system. Testing through real well log data shows that: the results from the LSTM are of higher accuracy than the traditional FCNN; the cascaded LSTM is more suitable for the problem with multiple series data; the machine learning method proposed provides an accurate and cost effective way for synthetic well log generation.

Fault diagnosis for photovoltaic array based on convolutional neural network and electrical time series graph

2019-06-28

Xiaoyang Lu , Peijie Lin , Shuying Cheng +4 more

A new quantitative method for risk assessment of water inrush in karst tunnels based on variable weight function and improved cloud model

2019-10-23

Chunjin Lin , Meng Zhang , Zongqing Zhou +4 more

Establishment and application of intelligent city building information model based on BP neural network model

2020-02-05

Yanwen Li , Ke Cao

Urban rail transit operation safety evaluation based on an improved CRITIC method and cloud model

2020-06-20

Hua-Wen Wu , Zhen Jin , Jing Zhang

Risk assessment and management of excavation system based on fuzzy set theory and machine learning methods

2020-12-28

Song-Shun Lin , Shui‐Long Shen , Annan Zhou +1 more

How to achieve new progress in ecological civilization construction? – Based on cloud model and coupling coordination degree model

2021-05-17

Zhili Zuo , Haixiang Guo , Jinhua Cheng +1 more

Ecological civilization construction (ECC) has become an essential strategy for achieving sustainable development and resolving China's severe resource and environmental issues. Therefore, to understand the current status and spatio-temporal characteristics … Ecological civilization construction (ECC) has become an essential strategy for achieving sustainable development and resolving China's severe resource and environmental issues. Therefore, to understand the current status and spatio-temporal characteristics of China's ECC, this study constructed an indicator system with 23 indicators to investigate China's ECC trends from 2000 to 2019. A cloud model was adopted to obtain the ECC evaluation results. A standard deviational ellipse model was employed to reveal the spatial ECC dynamic evolution process. A coupling coordination degree model was applied to measure the relationship between the ECC and the economy, society, and nature. It was found that: (i) China has not yet fully entered the ecological civilization stage. China's ECC is slightly higher than the "normal" level, with East China having the highest ECC level; (ii) There is a "gradual" process in the ECC in the six regions, the ECC in 30 Chinese provinces had a generally positive trend from 2000 to 2019; however, the ECC development speed in Northeast China was relatively backward; (iii) The coupling and coordination degree of economy, society, and nature shows significant regional differentiation, with the coast being better than the inland and the south being better than the north. Finally, we put forward policy recommendations to improve the level of China's ECC from four aspects: narrowing regional differences, strengthening regional cooperation, using scientific and technological means, and increasing ecological culture cultivation.

Geomatics and Information Science of Wuhan University

2006-05-05

Shiyuan Hu , LI Deren , Yaolin Liu +1 more

The veracity of land evaluation is tightly related to the reasonable weights of land estimate factors.By mapping qualitative linguistic words into a fine-changeable cloud drops and translating the uncertain factor … The veracity of land evaluation is tightly related to the reasonable weights of land estimate factors.By mapping qualitative linguistic words into a fine-changeable cloud drops and translating the uncertain factor conditions into quantitative values with the uncertain illation based on the cloud model,and then,integrating correlation analysis,a new way of figuring out the weight of land estimate factors is proposed.It may solve the limitations of the conventional ways.

An Improved Bearing Fault Diagnosis Method using One-Dimensional CNN and LSTM

2018-06-14

Honghu Pan , Fan Hong-hu , Pan He +2 more

As one of the most critical components in rotating machinery, bearing fault diagnosis has attracted many researchers' attention.The traditional methods for bearing fault diagnosis normally requires three steps, including data … As one of the most critical components in rotating machinery, bearing fault diagnosis has attracted many researchers' attention.The traditional methods for bearing fault diagnosis normally requires three steps, including data pre-processing, feature extraction and pattern classification, which require much expertise and experience.This paper takes advantage of deep learning algorithms and proposes an improved bearing fault diagnosis method based on a convolutional neural network (CNN) and a long-short-term memory (LSTM) recurrent neural network whose input is the raw sampling signal without any pre-processing or traditional feature extraction.The CNN is frequently used in image classification as it could extract features automatically from high-dimensional data, while LSTM is most applied in speech recognition as it considers time coherence.This paper combined one-dimensional CNN and LSTM into one unified structure by using the CNN's output as input to the LSTM to identify the bearing fault types.First, a part of raw bearing signal data is used as the training dataset in the model, and the simulation ends when the number of iterations reaches a specific value.Second, the rest of the signal data was input in the trained model as the testing dataset to verify the effectiveness of the proposed method.The results show that the average accuracy rate in the testing dataset of this proposed method reaches more than 99 %, which outperforms other algorithms for bearing fault diagnosis.

View PDF Chat

Methods of Information Geometry

2007-04-13

Shun-ichi Amari , Hiroshi Nagaoka

A Regression Method for Real Estate Price Index Construction

1963-12-01

Martin J. Bailey , Richard F. Muth , Hugh O. Nourse

Abstract Quality differences make estimation of price indexes for real properties difficult, but these can be largely avoided by basing an index on sales prices of the same property at … Abstract Quality differences make estimation of price indexes for real properties difficult, but these can be largely avoided by basing an index on sales prices of the same property at different times. The problem of combining price relatives of repeat sales of properties to obtain a price index can be converted into a regression problem, and standard techniques of regression analysis can be used to estimate the index. This method of estimation is more efficient than others for combining price relatives in that it utilizes information about the price index for earlier periods contained in sales prices in later periods. Standard errors of the estimated index numbers can be readily computed using the regression method, and it permits certain effects on the value of real properties to be eliminated from the index.

Fuzzy Set Theory — and Its Applications

1985-01-01

H.‐J. Zimmermann

Reliability based design

2010-11-29

S. S. Rao

Design of mechanical components and systems Monte Carlo simulation reliability-based optimum design strength-based reliability and interface theory reliability testing time dependent reliability of components and systems failure modes, event tree … Design of mechanical components and systems Monte Carlo simulation reliability-based optimum design strength-based reliability and interface theory reliability testing time dependent reliability of components and systems failure modes, event tree and fault tree analysis quality control and reliability modeling of geometry, material strength and loads structural reliability weakest link and fail safe systems maintainability and availability extremal distributions random variables and probability distributions functions of random variables basic probability theory.

Study on the Universality of the Normal Cloud Model

2005-01-01

LiDeyi , LiuChangyu , LiuLuying

The distribution function is an important tool in the study of the stochastic variances. The normal distribution is very popular in the nature and our society. The idea of membership … The distribution function is an important tool in the study of the stochastic variances. The normal distribution is very popular in the nature and our society. The idea of membership functions is the foundation of the fuzzy sets theory. While the fuzzy theory is widely used, the completely certain membership function that has no any fuzziness at all has been the bottleneck of the applications of this theory.Cloud models are the effective tools in transforming between qualitative concepts and their quantitative expressions. It can represent the fuzziness and randomness and their relations of uncertain concepts. Also cloud models can show the concept granularity in multi-scale spaces by the digital characteristic Entropy (En). The normal cloud model not only broadens the form conditions of the normal distribution but also makes the normal membership function be the expectation of the random membership degree. In this paper, the universality of the normal cloud model is proved, which is more superior and easier, and can fit the fuzziness and gentleness of human cognitive processing.It would be more applicable and universal in the representation of uncertain notions.

Research on Transformer Fault Diagnosis and Maintenance Strategy Generation Based on TransQwen Model

2025-06-23

Zichun Xue , Bo Wang , Hengrui Ma +3 more | Processes

Currently, transformer fault diagnosis primarily relies on the subjective judgment of maintenance personnel, which entails significant human effort and expertise. Moreover, unstructured text data—such as historical defect logs and maintenance … Currently, transformer fault diagnosis primarily relies on the subjective judgment of maintenance personnel, which entails significant human effort and expertise. Moreover, unstructured text data—such as historical defect logs and maintenance records—are not effectively leveraged for the intelligent generation of maintenance strategies, hindering accurate status evaluation and proactive risk management. This paper proposes TransQwen, a domain-adapted LLM tailored for transformer fault diagnosis and maintenance strategy generation. Built upon the Qwen-7B-Chat architecture, TransQwen is fine-tuned on a domain-specific corpus encompassing transformer fault cases aligned with technical standards and operational procedures. It integrates DoRA for efficient parameter adaptation and RoPE to enhance positional encoding during training. The model is evaluated in three core tasks: fault type classification, fault severity grading, and strategy generation. The results show significant improvements—over 10 percentage point gains in standard conditions and up to 30 percentage points in F1 score under extreme low-sample settings (e.g., 100 samples), demonstrating robust generalization. In the maintenance strategy generation experiment, all the evaluation results of the TransQwen model reached the optimal. Through a knowledge-driven approach, the model can perform question-and-answer tasks involving professional knowledge in the power vertical field, and customize and generate accurate maintenance strategies for specific fault scenarios.

Feature Selection and Model Application of Machine Learning in Educational Quality Assessment

2025-06-20

Xiaolan Li | International journal of education and social development.

In today's society, education, as a key force driving personal growth and social progress, is highly valued for its quality. Educational quality assessment is an important means to ensure and … In today's society, education, as a key force driving personal growth and social progress, is highly valued for its quality. Educational quality assessment is an important means to ensure and improve the quality of education. It not only helps educational institutions understand their own teaching effectiveness and identify problems in the teaching process, but also provides scientific basis for educational decision-making, promotes the rational allocation of educational resources, and ultimately achieves the goals of educational equity and quality improvement.

Evaluation method of operation and maintenance effectiveness level based on DPSIR model

2025-06-19

Yuhong Zhang , Zhiyao Zhao , Wenshi Ren +3 more | International Journal of Systems Assurance Engineering and Management

Research on Substation Electrical Proximity Early-Warning Technology Based on the “Electric Field + Distance” Double Criterion

2025-06-16

Jing Zhao , S. Li , Qianhao She +6 more | Sensors

With the continuous improvement of China's power grid, safety issues in substation operation and maintenance have become increasingly prominent. However, the existing electrical proximity early-warning devices are inadequate for the … With the continuous improvement of China's power grid, safety issues in substation operation and maintenance have become increasingly prominent. However, the existing electrical proximity early-warning devices are inadequate for the complex environments of substations, highlighting the urgent need to develop new electrical proximity early-warning technologies. Based on the safety needs of substation operators, this paper proposes an electrical proximity early-warning method that integrates 'electric field + distance'. It combines MEMS electric field test technology with ultrasonic ranging technology and designs a double-criterion electrical proximity early-warning device. Based on the COMSOL 6.0 finite-element electric field simulation and the construction safety specification for substation equipment, a multistage electric-field early-warning threshold has been reasonably formulated. A field test conducted at a 220 kV substation demonstrates that this device can issue alerts for various electrical proximity threat levels of the circuit breaker within 0.1 s, which is faster and more accurate than existing commercial electrical proximity early-warning devices. The double-criterion early-warning system minimizes the risk of missed alarms during multi-distance measurements. Additionally, its flexible warning threshold accommodates the increasingly complex operational requirements of substations.

Research on the correction method for detecting the roughness of rural highway

2025-06-16

Kuang Zhang , Yapeng Yang , Yufan Wu | International Conference on Frontiers of Traffic and Transportation Engineering (FTTE 2022)

LLM-based Sensitive Data Recognition with Stepwise Chain-of-thought Reasoning

2025-06-13

Honggang Wang , Shenglong Liu , Yi-Wen Jiang +2 more | International Journal of Pattern Recognition and Artificial Intelligence

Marine monitoring information security risk assessment method based on expert scoring and interval evidential reasoning

2025-06-13

Ting Hu , Yuanhui Guan , Chao Chen +2 more | International Journal of Information Technology & Decision Making

Credit Risk Management Based on Decision Tree Model

2025-06-13

Yutian Gan , Han Luo , Wei Wei | Advances in Economics Management and Political Sciences

Against the backdrop of rapid advancements in fintech and the continuous expansion of credit markets, traditional credit risk assessment methods have revealed significant limitations. Machine learning methods offer new opportunities … Against the backdrop of rapid advancements in fintech and the continuous expansion of credit markets, traditional credit risk assessment methods have revealed significant limitations. Machine learning methods offer new opportunities for credit risk management. This study focuses on applying machine learning methods to credit risk management. We utilize a credit risk dataset from Kaggle (Default of Credit Card Clients Dataset) to analyze and compare the performance of logistic regression, decision tree, and random forest models across multiple dimensions, including accuracy, recall rate, and interpretability. The results demonstrate that the decision tree model exhibits comprehensive performance in credit default prediction. Future research could incorporate diverse data types, develop visualization tools, establish real-time monitoring and dynamic updating systems, and extend applications across industries to enhance the accuracy and foresight of credit risk assessment, thereby promoting the widespread adoption of machine learning in financial risk management. The research holds theoretical significance and offers practical technical solutions for real-world lending operations.

A cloud model-based quantitative assessment system for surface deterioration of Taihu rockery in Jiangnan gardens: Yunwu rockery in Humble Administrator’s Garden

2025-06-12

Zhouzhou Chen , Jie Pan , Qianli Dong +1 more | Research Square (Research Square)

<title>Abstract</title> The Jiangnan Garden Rockery heritage site holds the largest number and highest aesthetic value of rockery among China’s classical gardens. However, its surface has significantly deteriorated. To support conservation … <title>Abstract</title> The Jiangnan Garden Rockery heritage site holds the largest number and highest aesthetic value of rockery among China’s classical gardens. However, its surface has significantly deteriorated. To support conservation planning, this study developed a quantitative evaluation system using a cloud model to enhance reliability and accuracy.. The system classifies deterioration into five levels and was validated through on-site surveys. Digital modelling of artificial rockery provided the ratio of deteriorated to total surface area, indicating Level 3 deterioration. Comparative experiments used ultrasonic velocity and Leeb hardness as degradation indicators. Based on existing standards and prior research, classification criteria for stone cultural relic deterioration were established. Measurements taken from degraded surfaces matched Grade III deterioration. Consistent results over three sets of experiments verified the evaluation system’s scientific validity.

Research on bearing fault diagnosis based on secondary decomposition and stochastic configuration network

2025-06-08

Jiansheng Hu , Chuanzhi Zang | 2022 IEEE Congress on Evolutionary Computation (CEC)

Settlement early warning method for high speed railway subgrades based on TD Transformer

2025-06-05

Wen Kebing , Liang Qinghuai | Scientific Reports

During high speed railway construction, shield-tunnel undercrossing frequently induces subgrade settlement, which threatens project safety and progress. Existing settlement monitoring methods struggle to provide timely early warnings due to unclear … During high speed railway construction, shield-tunnel undercrossing frequently induces subgrade settlement, which threatens project safety and progress. Existing settlement monitoring methods struggle to provide timely early warnings due to unclear data features and inadequate long-term dependency modeling.To address this, we propose a settlement early warning method for high-speed railway subgrades based on TD Transformer. Firstly, we utilize temporal-spatial enhanced attention (TSEA) for feature extraction from high-speed railway settlement data, effectively resolving the problem of vague features post-extraction. Secondly, dynamic global temporal attention (DGTA) is employed to dynamically capture and represent the long-term dependencies of settlement data. Experimental results demonstrate that TD Transformer achieves Accuracy, Precision, Recall, and F1-Score of 93.39%, 93.10%, 93.40%, and 93.24%, respectively, outperforming other advanced settlement early warning methods for high-speed railway subgrade with relative improvements of 1.24%, 1.3%, 1.3%, and 1.27%.This method effectively forecasts subgrade settlement and exhibits significant superiority in the task of multi-factor settlement early warning for high-speed railway subgrades.

Research on the Design of Enclosed Protective Discharge Gap for Transformer Neutral Point Based on Energy Aggregation Characteristics

2025-06-01

Xiaohui Li , Jun Kang , Jianwu Li +7 more | Journal of Physics Conference Series

Abstract Power transformers are very important components of the power system, playing a crucial role in controlling the voltage of electrical energy and driving the transmission of electrical energy. However, … Abstract Power transformers are very important components of the power system, playing a crucial role in controlling the voltage of electrical energy and driving the transmission of electrical energy. However, in transformers above 110kV, the breakdown voltage of the protection gap is highly dispersed. Due to the influence of altitude and other factors, the protection effect of the neutral point, especially in Northwest China, is poor, prone to protection mal-operation, which seriously affects the lives of residents and social production. Based on this the development of neutral point protection equipment is of great significance. This article focuses on the energy concentration characteristics of discharge gaps in enclosed spaces. By calculating the arc energy value and the number and duration of energy super-positions within the protective equipment’s enclosed casing, the enclosed shell structure and design pressure boundary are determined. An enclosed shell that meets the usage requirements is designed, and the accuracy and rationality of the design are verified through various performance tests.

Application of K-means Clustering Data Mining in Grouping Data of People with Disabilities

2025-06-01

Moh. Bahauddin , Zaehol Fatah | JEECS (Journal of Electrical Engineering and Computer Sciences)

Data mining is critical in enabling organizations to derive reliable insights from data. Social welfare remains a significant challenge in Indonesia, particularly for people with disabilities, emphasizing the need for … Data mining is critical in enabling organizations to derive reliable insights from data. Social welfare remains a significant challenge in Indonesia, particularly for people with disabilities, emphasizing the need for targeted strategies. However, developing research has not used natural characteristics according to disability problems. This study utilizes the K-Means Clustering algorithm to analyze and categorize the population of people with disabilities in East Java. The attributes include the type of disability, population size, and regional distribution. We employs a dataset from the East Java Central Bureau of Statistics, comprising 342 data points across eight attributes, including region, disability type, and year. The analysis involves data preprocessing, transformation, clustering, and evaluation using the Davies-Bouldin Index (DBI). The results identify two optimal clusters, achieving the lowest DBI score of 0.097, indicating high cluster quality. Cluster 0 represents regions with fewer people with disabilities, while Cluster 1 highlights areas with higher populations. These findings provide a foundation for developing more focused and inclusive welfare programs tailored to regional needs, enhancing the quality of life for people with disabilities.

Research on dam health diagnosis methodology based on a cloud model and enhanced Dempster-Shafer evidence theory

2025-06-01

Yong Xiong , Kui Wang , Cheng Yang +2 more | Insight - Non-Destructive Testing and Condition Monitoring

As the water conservancy sector progresses, ensuring the safety of reservoir dams has become a paramount concern. As currently employed in dam health diagnosis, Dempster-Shafer (D-S) evidence theory encounters challenges … As the water conservancy sector progresses, ensuring the safety of reservoir dams has become a paramount concern. As currently employed in dam health diagnosis, Dempster-Shafer (D-S) evidence theory encounters challenges due to its synthesis rules, which may lead to issues such as an inability to apply certain rules or contradiction with human intuition. Consequently , this paper proposes an enhancement to D-S evidence theory by incorporating evidence credibility (Crd(m i )) obtained from evidence similarity coefficients and integrating indicator weights to form indicator fusion coefficients. Building upon this enhancement, a methodology for reservoir dam health diagnosis based on a cloud model and improved D-S evidence theory is introduced. A method combining subjective and objective weighting is employed to assign weights to dam diagnostic indicators using an analytic hierarchy process-entropy weight methodlargest difference method (AHP-EWM-LDM). Finally, dam health diagnosis is conducted on reservoir dams based on cloud modelling and enhanced D-S evidence theory. The feasibility of this method is verified.

A Hybrid Method of Corporate Financial Performance Prediction Based on Common Model and Convolutional Neural Network

2025-05-31

Xiaochuan Tian | International Journal of High Speed Electronics and Systems

Performance data are affected by market environment, business demand, policy changes, and other factors, resulting in an obvious nonlinear relationship between the influencing factors across the period. The convolutional neural … Performance data are affected by market environment, business demand, policy changes, and other factors, resulting in an obvious nonlinear relationship between the influencing factors across the period. The convolutional neural network (CNN) method cannot deal with such nonlinear relationship data directly, and the oscillation caused by stochastic gradient descent leads to local optimization, resulting in poor prediction results. Therefore, the interperiod impact prediction method of corporate financial performance based on the Public model is proposed. Based on the enterprise’s financial data, the method involves several steps. First, it extracts the principal component data pertinent to the enterprise’s intellectual capital through principal component analysis. Subsequently, the public model is employed to measure the intellectual capital of the enterprise, utilizing the extracted principal component data related to intellectual capital, such as coefficients and the coefficient of intellectual capital efficiency, among other indicators. Last, the intellectual capital indicators of various enterprises are combined with those of the current enterprise, taking into account the coefficients of the current enterprise’s value-added intellectual capital. Using different enterprise intellectual capital indicators and current enterprise financial performance data as input, the method incorporates machine learning algorithms within a CNN model for iterative feature extraction operations. Additionally, the Adam optimization algorithm is introduced to adaptively adjust the learning rate of the CNN model, thereby enhancing its anti-interference ability. The output of this process is the prediction results detailing the interperiod impact on the enterprise’s financial performance. Experimental results demonstrate that this method can effectively extract the principal components from the enterprise’s financial data and accurately measure the current enterprise’s intellectual capital. Furthermore, it predicts the interperiod impact of the enterprise’s financial performance over the next 12 months, based on factors such as capital utilization efficiency and return on net assets, related to the enterprise’s intellectual capital. The application of this method yields superior results.

The Principle and Application of Diamond Quantum Sensor

2025-05-31

Yuji Hatano , Akimichi Nakazono , Mutsuko Hatano | The Journal of the Institute of Electrical Engineers of Japan

Exponential Similarity Measure Based Selection of Cloud Service Provisioning in Cloud

2025-05-31

Vishal Meshram , Suvarna S. Pawar , Vidula Meshram +7 more | Mathematical Modelling and Engineering Problems

Risk evaluation of metro tunnel shield construction based on game variable weight extension cloud theory

2025-05-30

Xiuxia Sun , Lirong Wu , Dun Wu | Scientific Reports

Research on architectural engineering Cost Prediction and Analysis Based on Generative Adversarial Network and Reinforcement Learning

2025-05-30

Shan Xie , Xiao Li | International Journal of Reliability Quality and Safety Engineering

Transformer Fault Diagnosis Based on Feature Parameter Preference and ICOA Optimization CNN

2025-05-30

Yong Jiang , Shuming Hu , Lina Yao +3 more | Engineering Research Express

Abstract To improve the accuracy of fault diagnosis for power transformers, an RFRFE-ICOA-CNN intelligent fault diagnosis method for power transformers based on Dissolved Gas Analysis (DGA) in oil is proposed. … Abstract To improve the accuracy of fault diagnosis for power transformers, an RFRFE-ICOA-CNN intelligent fault diagnosis method for power transformers based on Dissolved Gas Analysis (DGA) in oil is proposed. First, to address the issue that manually selecting fault feature parameters may lead to the omission of some key features, and that multi-dimensional raw fault data can increase the difficulty of transformer fault diagnosis, a method combining the Recursive Feature Elimination (RFRFE) algorithm with Random Forest is proposed for optimal selection of fault feature parameters. Next, the Improved Coati Optimization Algorithm (ICOA) is introduced to optimize the hyperparameters of the Convolutional Neural Network (CNN), such as learning rate, kernel size and number, and the number of neurons in the fully connected layer, in order to improve the accuracy of the model's diagnostic results. Finally, through case studies, the performance of the established RFRFE-ICOA-CNN method is evaluated, and the effectiveness of the proposed method for transformer fault diagnosis is validated.

Research on Airport Traffic Situation Based on Multi-Source Data

2025-05-29

Jie Ren , Weijia Hao | Frontiers in Computing and Intelligent Systems

With the rapid development of the aviation industry, the complexity and uncertainty of airport traffic situations have increased significantly. Existing prediction methods for airport operations often rely on single data … With the rapid development of the aviation industry, the complexity and uncertainty of airport traffic situations have increased significantly. Existing prediction methods for airport operations often rely on single data sources, which fail to comprehensively and accurately reflect dynamic changes in airport operations. This study proposes a multi-source data fusion framework for airport traffic situations and establishes an intelligent prediction model based on the fused data to achieve precise forecasting. Furthermore, optimization strategies for airport operations, including resource allocation and flight scheduling, are proposed based on prediction results. The effectiveness of these strategies is validated through simulation experiments. The results demonstrate that the intelligent prediction method based on multi-source data fusion significantly improves the accuracy and reliability of airport operation forecasting, providing a scientific basis for airport management and enhancing operational efficiency and service quality. The innovation of this research lies in proposing a hierarchical fusion architecture that combines deep learning with attention mechanisms to address spatiotemporal alignment challenges of heterogeneous data, as well as employing multi-objective optimization algorithms to balance resource utilization and passenger satisfaction metrics.

Gearbox fault diagnosis based on multi-channel orthogonal attention network

2025-05-28

Xiang Wu , Yu Fu , Qi Wu +3 more | Signal Image and Video Processing

A cross-domain intelligent fault diagnosis method based on three-branch meta metric learning network for few-shot fault diagnosis

2025-05-27

Bo Wang , Wenlong Yang

Abstract Despite the advancements made by deep learning methods in rolling bearing fault diagnosis, their reliance on large labeled datasets restricts their practical applicability in real-world scenarios where such data … Abstract Despite the advancements made by deep learning methods in rolling bearing fault diagnosis, their reliance on large labeled datasets restricts their practical applicability in real-world scenarios where such data is often limited. This raises the challenge of building models that can function effectively with minimal data and perform well under varying operational conditions. To address this issue, we propose the Three-Branch Prototype Network (TBPN), which adopts a meta-learning strategy, forming tasks by randomly sampling original signals from different operating conditions. At first, we enhance the original signals corresponding to known operating con-ditions using a denoising strategy based on the Gram matrix in the time and frequency domains. These enhanced time-domain and frequency-domain signals, along with the original signals, are fed into the TBPN model as three branches to extract and fuse fault features. Next, a metric learner is applied to derive prototype representations for each type of fault and calculate the distances between these prototypes and the query fault features, which are then used in a softmax function for multi-class fault classification. The TBPN model demonstrates superior performance in providing rapid and accurate fault classification for rolling bearings, even under un-known operating conditions, by updating its parameters using minimal sample data. To fully assess the performance of our proposed method, we conducted extensive experiments across various industrial settings using the Case Western Reserve University Rolling Bearing Dataset and the Laboratory Rolling Bearing Dataset. The results underscore the effectiveness of TBPN in addressing the challenge of few-shot fault classification in complex environments.

Road damage prediction and intelligent maintenance methods based on stacking ensemble learning

2025-05-27

Jianxi Ou , Jianqin Zhang , Haoyu Li +1 more

Xây dựng và phát triển thuật toán cho bài toán bắn mục tiêu trên thiết bị ngầm

2025-05-26

Thanh Vi Xuan , Thìn Nguyễn Văn , Chiến Phan Văn +1 more | Journal of Military Science and Technology

Các hệ thống bắn mục tiêu trên phương tiện ngầm trước đây là các hệ máy tính điện cơ có kết cấu cơ khí vô cùng phức tạp, các bài … Các hệ thống bắn mục tiêu trên phương tiện ngầm trước đây là các hệ máy tính điện cơ có kết cấu cơ khí vô cùng phức tạp, các bài toán được lý tưởng hóa với các thông số được thiết lập trước. Hiện nay, với xu hướng số hóa, các loại máy tính số với khả năng xử lý tính toán cao đã thay thế các máy tính điện cơ trước đây và đã được lắp đặt, sử dụng trên các phương tiện ngầm. Trên cơ sở nghiên cứu lý thuyết từ hệ thống thông tin - điều khiển tự động hóa AIUS trên tàu của lực lượng Hải quân, bài báo sẽ trình bày nghiên cứu về xây dựng thuật toán và phát triển phần mềm bắn mục tiêu trên cơ sở lý thuyết đã có. Sau đó, tiến hành cài đặt và thử nghiệm trên máy tính số để kiểm tra. Kết quả nghiên cứu cho thấy thuật toán thử nghiệm trên máy tính số có kết quả tương đương máy tính điện cơ, tốc độ xử lý nhanh và đáp ứng được các thay đổi liên tục của mục tiêu.

Accurate prediction of college students' information anxiety based on optimized random forest and category boosting fusion model

2025-05-26

Bin Wang , Shao Li

Research into the Design of Tunnel Photovoltaic Sunshades Based on Visual Efficacy Experiments

2025-05-24

Hongjun Cui , Beilu Zhang , Minqing Zhu

Aiming at the problem of “black hole effect” at tunnel entrances, this study proposes a widely applicable design method for photovoltaic sunshade, which not only verifies the theoretical effect of … Aiming at the problem of “black hole effect” at tunnel entrances, this study proposes a widely applicable design method for photovoltaic sunshade, which not only verifies the theoretical effect of the design scheme through a combination of simulation and experiment, but also provides sufficient theoretical basis for the design selection of sunshades. This study is divided into the following key stages. First, analyzing the shortcomings of existing studies and clarifying the importance of driver reaction time as a safety indicator. Second, constructing an evaluation framework integrating economy, safety, and visual comfort to ensure the comprehensiveness and scientificity of the evaluation of design options. Then, proposing a series of pre-selected sunshade design options and simulating the illumination changes of each viewpoint in different scenarios by means of the visual efficacy experiments. Subsequently, two-factor ANOVA and simple effect analysis are used to study in depth the mechanism of the influence of the combination of sunshade length and light transmission rate on drivers’ reaction times, and to reveal the role of the key design parameters. Finally, the combined weight and technique for order of preference by similarity to ideal solution (TOPSIS) method is used for comprehensive evaluation and to determine the optimal design scheme. Taking Rongwu Expressway Yingerling Tunnel in China as an example, according to the research and analysis, the recommended design scheme of photovoltaic sunshade is as follows: the total length is 80 m, the combination of light transmittance is 0.8-0.6-0.4-0.2-0.1, and the length of each section is 16 m.

Partial Functioal Linear Model Based on RKHS and Ensemble Learning

2025-05-23

Mengyao Bian , Yaqi Pan , Zhangru Yin

A new partial functional linear model is proposed for functional and vector-valued covariates with a scalar response. The proposed model assumes a linear relationship between the functional predictors and the … A new partial functional linear model is proposed for functional and vector-valued covariates with a scalar response. The proposed model assumes a linear relationship between the functional predictors and the scalar response, which is approximately estimated using a functional principal component basis expansion. For the vector-valued covariates, the flexibility of the model is enhanced by assuming that the connection function with the scalar response resides in a Reproducing Kernel Hilbert Space (RKHS), enabling its representation through a kernel function expansion. Furthermore, instead of relying on model selection, a ensemble learning approach is employed. By constructing partial functional linear models with different truncation numbers and performing a weighted average, the issue of truncation number selection is effectively addressed. Simulation studies and real data analysis demonstrate that the proposed method exhibits superior performance and competitiveness compared to the benchmark models.

Wind Power Forecasting Based on Bidirectional LSTM Integrated with Chaos Enhancement Theory

2025-05-22

Yunhao Song

Wind energy prediction is crucial for efficient management and dispatch of power systems, and accurate prediction can optimize the integration of renewable energy sources and can be a good solution … Wind energy prediction is crucial for efficient management and dispatch of power systems, and accurate prediction can optimize the integration of renewable energy sources and can be a good solution for energy security. This study proposes a chaos-enhanced bi-directional LSTM model for wind power forecasting that incorporates chaotic signals from Lorentz attractors to enhance the feature representation of time series data and combines the powerful contextual information capturing capability of bi-directional LSTM. The goal of this research is to develop a model that outperforms traditional as well as current mainstream machine learning aspects of prediction methods. The method splices the generated slices of chaotic signals with the input sequences in the feature dimension and captures the forward and backward time dependencies using bi-directional LSTM, and finally feeds its output into the fully connected layer for final prediction. The experimental results show that the proposed model outperforms several current mainstream machine prediction models with a MAPE of only 0.5979% and an RMSE of 4.2, which demonstrates the effectiveness and superiority of the model in wind power prediction.

Application of AI technology in safety monitoring and warning at secondary schools

2025-05-22

Tran Huu Duat , Tran Ngoc Diem Trinh , Tran Thi Hoai Thuong

The research "application of ai technology in safety monitoring and warning at secondary schools" aims to develop a system for monitoring and ensuring railing safety in secondary schools by integrating … The research "application of ai technology in safety monitoring and warning at secondary schools" aims to develop a system for monitoring and ensuring railing safety in secondary schools by integrating Artificial Intelligence (AI) with IoT sensors. The system is designed to detect potential risks of students falling from railings and provide timely alerts to minimize accidents. The research methodology involves utilizing an AI camera for image recognition, a motion sensor to detect movement, and a distance sensor to measure the gap between individuals and the railing. Additionally, the system integrates a warning speaker and sends alert messages to mobile phones in hazardous situations. Data is collected and processed using an image recognition algorithm with an accuracy of over 80%, combined with sensor signals to determine safe or unsafe conditions. The motion sensor operates with an accuracy of 92%, while the distance sensor has an error margin of less than 5%. Experimental results indicate that the system achieves an image recognition accuracy of 85% in good lighting conditions and 78% in low-light environments. The findings demonstrate that the system effectively detects risks and issues timely warnings, paving the way for further research and applications in public spaces to enhance user safety.

Electromagnetic Relay Contact Resistance Prediction Based on TimeGAN with CNN-LSTM-Attention

2025-05-22

Dicheng Ma , Zhaobin Wang , T. He

Electromagnetic relays are critical in aerospace and military systems, affecting the safety and stability of applications like aircraft control, satellite communication, and missile launchers. However, the scarcity of degradation data … Electromagnetic relays are critical in aerospace and military systems, affecting the safety and stability of applications like aircraft control, satellite communication, and missile launchers. However, the scarcity of degradation data and complex variations in contact resistance pose challenges. Traditional methods often struggle with small samples. To address these issues, we propose a novel framework integrating TimeGAN with a CNN-LSTM-Attention model. TimeGAN generates synthetic degradation data that aligns with the statistical distribution of the original dataset, mitigating data scarcity. Data quality is evaluated using PCA and KDE. The CNN-LSTM model captures multi-scale temporal features, while the attention mechanism highlights critical features to improve contact resistance prediction accuracy. Experimental results show that the proposed framework outperforms traditional methods, demonstrating robust performance even without data augmentation. These findings offer a valuable foundation for health monitoring and fault prediction in high-reliability systems.

Tunnel Leakage Detection based on Infrared Imaging and Machine Learning in Complex Illumination

2025-05-22

Xiangchen Yao , Shuqi Ma , xu yuanzhen +1 more

Abstract Accurate and effective water leakage detection in tunnel linings under complex illumination conditions is crucial for ensuring operational safety. This paper proposed a method for detecting water leakage based … Abstract Accurate and effective water leakage detection in tunnel linings under complex illumination conditions is crucial for ensuring operational safety. This paper proposed a method for detecting water leakage based on infrared vision and an enhanced U-shaped network architecture. Initially, the lightweight Azure Kinect sensor was employed to capture both infrared and RGB images of tunnel linings under different illumination conditions. Three datasets: the RGB image under normal illumination (NRGB), the Infrared image under normal illumination (NIR), and the infrared image under low illumination (LIR) were created. Subsequently, an enhanced U-shaped network architecture (UKAN) was introduced for water leakage segmentation in tunnel linings. Moreover, Score-weighted and Layer-wise Class Activation Mapping were adopted to analyze the model's decision-making process. Experimental results revealed that the average detection accuracy for the NIR exceeded that of the NRGB by 2.4%, while the LIR was higher by 1.43%. The proposed UKAN architecture achieved optimal mean intersection over union scores of 84.1%, 86.5%, and 85.7% on NRGB, NIR, and LIR. Additionally, visual interpretability analysis showed that the UKAN's learning process was smooth, gradually shifting its focus from low-level features to target regions. This methodology facilitates efficient and accurate water leakage detection in tunnel linings under varying illumination conditions.&#xD;&#xD;

Bearing fault diagnosis method based on multi-level information fusion

2025-05-21

Daichao Wang , Yan Song , Jinhao Xing +3 more