Fuzzy Clustering Algorithm Research Articles

Integrating Low-Level Visual Cues for Enhanced Unsupervised Semantic Segmentation

Unsupervised semantic segmentation algorithms aim to identify meaningful semantic groups without annotations. Recent approaches leveraging self-supervised transformers as pre-training backbones have successfully obtained high-level dense features that effectively express semantic coherence. However, these methods often overlook local semantic coherence and low-level features such as color and texture. We propose integrating low-level visual cues to complement high-level visual cues derived from self-supervised pre-training branches. Our findings indicate that low-level visual cues provide a more coherent recognition of color-texture aspects, ensuring the continuity of spatial structures within classes. This insight led us to develop IL2Vseg, an unsupervised semantic segmentation method that leverages the complementation of low-level visual cues. The core of IL2Vseg is a spatially-constrained fuzzy clustering algorithm based on color affinities, which preserves the intra-class affinity of spatially-adjacent and similarly-colored pixels in low-level visual cues. Additionally, to effectively couple low-level and high-level visual cues, we introduce a feature similarity loss function to optimize the feature representation of fused visual cues. To further enhance consistent feature learning, we incorporate contrast loss functions based on color invariance and luminosity invariance, which improve the learning of features from different semantic categories. Extensive experiments on multiple datasets, including COCO-Stuff-27, Cityscapes, Potsdam, and MaSTr1325, demonstrate that IL2Vseg achieves state-of-the-art results.

A novel competitive cuckoo search algorithm for node placement in wireless sensor networks

Wireless sensor networks (WSNs) are essential for many different types of applications, including industrial, commercial, and agricultural. Inadequate node location, dynamic nodes, network longevity, increased packet drop rates, scaling problems, limited adaptability, and changing climatic conditions pose challenges to the WSN's efficacy. Numerous bio-inspired algorithms have been previously introduced for node placement, demonstrating a significant improvement in data aggregation performance. However, because of the low variability in the solution, weak convergence, and poor balance between exploitation and exploration, the results of WSNs are challenging to interpret. With a unique competitive Cuckoo search algorithm (CCSA), this research presents a connectivity-aware, energy- efficient, and node placement method. Using the elite population to increase the variety of the answer, the suggested competitive strategy aims to enhance convergence. It additionally employs the fuzzy C-mean clustering algorithm. The clustering optimization based on cluster head energy, density, location, Gini coefficients, and other comparable factors uses an artificial bee colony optimization (ABC) algorithm to enhance the clustering and cluster head position. A comparison between the recommended scheme and the traditional state-of-the-art reveals that the suggested system performs better regarding network throughput, residual energy, and network lifetime.

Analysis of Structural Changes and Employment Dynamics in the Labor Market of Kazakhstan

Understanding structural dynamics and workforce segmentation has become essential for sustainable economic policy and employment regulation in the context of global economic transformation, technological change, and labour market volatility. The goal of the current study is to identify key worker groups with varying levels of employment stability, staff turnover, and personnel cost distribution. The fuzzy clustering algorithm (Fuzzy C-Means) is used as the primary method, which makes it possible to assign objects to several clusters with varying degrees of affiliation. The analysis was based on official statistics of the labor market in the Republic of Kazakhstan for the period 2013-2023. The analysis revealed three stable clusters: stable workforce flow cluster with low staff turnover (0.172) and balanced replacement (0.152); adaptive cluster with moderate instability, turnover of 0.355 and demand for labor up to 30 020 people; unbalanced cluster with high-cost variability (up to 19 billion tenge), compensation (coefficient of variation of 0.386) and maximum admission of graduates (up to 86,227 people). Kazakhstan's labor market is characterized by stability in traditional sectors, moderate adaptation in cyclical industries, and high volatility in technologically advanced and competitive segments. These results suggest the need for a differentiated employment policy that considers industry-specific characteristics and the digital transformation of the economy. Future research should investigate sector-specific models of human resource transformation and explore how employment dynamics can be integrated into strategies for sustainable and innovation-driven development.

SEGMENTATION OF GRAYSCALE LOW-CONTRAST IMAGES USING FUZZY TRANSFORMS OF TYPE-2

Segmentation of low-contrast grayscale images is a rather complex task due to the lack of a priori information about the location and characteristics of objects of interest that can be compared with noise. To solve this problem, various fuzzy algorithms based on the processing of membership functions to fuzzy sets describing the analyzed properties are currently often used. The paper proposes the algorithm for segmenting halftone images based on the iterative application of type-1 and type-2 fuzzy transformations. The presented algorithm provides sufficient image segmentation for visual analysis, without allowing excessive detailing, and has a small number of control parameters that do not require lengthy tuning. Unlike the fuzzy clustering algorithms, it does not use the fuzzy cluster center matrix, which reduces the computational load. Experimental results are presented on the example of real grayscale medical images segmentation.

Structure information preserving domain adaptation network for fault diagnosis of Sucker Rod Pumping systems.

Structure information preserving domain adaptation network for fault diagnosis of Sucker Rod Pumping systems.

Application of computer wireless network database technology in information management

Abstract This article discusses the application of computer wireless network database technology in information management, aiming to solve the problem of low efficiency in information management by improving query efficiency and upload rate. Through standardized database technical operations, such as unified addition, deletion, query, and introduction, orderly adjustment and modification of internal big data are carried out to ensure that information transmission can be accurately reflected in the network structure to improve the quality of the system operation. This article uses a fuzzy clustering algorithm to evaluate the information management system comprehensively. It deeply analyzes the significant effects of database technology in improving user experience and enhancing system adaptability through experiments. The experimental results show that the new system is superior to the traditional information management system in data collection, upload efficiency, task management, query statistics, data monitoring, buffering effect, data encryption, access control, resource utilization, bandwidth utilization, data storage efficiency, scalability, reliability, and disaster recovery capability, user experience, and system adaptability. Specifically, the average response time of the new system is less than 2.5 s, the data upload rate reaches 146 Mbps, the user login success rate and the authentication accuracy rate are close to 100%, the resource utilization and network bandwidth utilization reach high levels in different periods, and the data storage efficiency is improved by 0.21. The system’s scalability is improved by 0.29 with the support of database technology. These data show that computer wireless network database technology can significantly improve the efficiency and security of information management and effectively support the needs of high data volume and high-speed industries, such as finance, medical care, and e-commerce.

Food detection and volume estimation for nutritional analysis

A healthy lifestyle and the prevention of chronic illnesses like diabetes and obesity depend on the precise calculation of dietary nutrition values, including calories, proteins, and carbs. Automated food recognition and volume estimate from photos is a viable solution to the problems with traditional nutritional assessment approaches, which rely on self-reporting and are prone to mistakes. Real-time nutrition estimate smartphone apps have been made possible by recent developments in machine learning (ML) and deep learning (DL). Techniques for food categorization, segmentation, and volume estimation that are used in automated dietary assessment systems are examined in this paper. Traditional machine learning (ML) techniques like support vector machines and k-nearest neighbors were used in early research, but convolutional neural networks (CNNs) and optimization techniques like fuzzy clustering and evolutionary algorithms are used in more recent studies. Additionally, the research emphasizes the difficulties in food segmentation, the use of picture datasets like Food-101, and the incorporation of depth estimate methods for volume measurement. Automated nutritional assessment systems provide increased accuracy and user engagement with the growing usage of AI-driven models, opening the door to better public health nutrition programs. For thorough nutrition estimate, future studies should concentrate on enhancing segmentation methods, diversifying datasets, and combining multi-modal data sources. Keywords: Food Detection, Nutritional Analysis, Food Volume Estimation, Machine Learning (ML), Deep Learning (DL), Convolutional Neural Networks (CNNs)

A novel distributed semi-supervised fuzzy clustering method applied on dental X-ray images

Semi-supervised clustering methods are applied in various fields. However, these methods have the limitations when the size of data is large. Thus, distributed clustering models are proposed. By separating data set into some parts, distributed models overcome the challenges of big size dataset. In this paper, a novel model, based on semi-supervised fuzzy clustering and distributed mechanism, is proposed. In our research, the method to define distributed additional information is introduced. This additional information is used to implement distributed semi-supervised fuzzy clustering model on three datasets. The main contribution in this paper is the proposal of distributed semi-supervised fuzzy clustering algorithm (denoted as DSSFCM) that performs on Master – Slave model on homogeneous datasets.

Behavioral Correlation-Based Residential Space Modularization Using Design Structure Matrix and Fuzzy C-Means Clustering Algorithm

This study introduces an automated method for constructing residential functional modules from the perspective of user behavior. By integrating the design structure matrix (DSM) and Fuzzy C-Means Clustering Algorithm (FCM), this approach systematically explores architectural functional modules. The DSM is employed to statistically analyze the correlations between residential behaviors. These correlations are then processed using FCM to generate various module segmentation schemes. The optimal scheme is selected based on modularity calculations. The results demonstrate improved modularity compared to traditional room-based designs, offering a greater variety of combinations and hierarchical organization. This methodology provides architects with a novel approach to address space integration challenges.

Unconstrained Fuzzy C-Means Algorithm.

Fuzzy C-Means algorithm (FCM) is one of the most commonly used fuzzy clustering algorithm, which uses the alternating optimization algorithm to update the membership matrix and the cluster center matrix. FCM achieves effective results in clustering tasks. However, due to many constraints, the objective function is inconvenient to optimize directly and is prone to converges to a suboptimal local minimum, which affects the clustering performance. In this paper, we propose a minimization problem equivalent to FCM. Firstly, we use the optimal solution when fixing the cluster center matrix to replace the membership matrix, transforming the original constrained optimization problem into an unconstrained optimization problem, thus reducing the number of variables. We then use gradient descent instead of alternating optimization to solve the model, so we call this model UC-FCM. Extensive experimental results show that UC-FCM can obtain better local minimum and achieve superior clustering performance compared to FCM under the same initialization. Moreover, UC-FCM is also competitive compared with other advanced clustering algorithms.

Genotyping Identification of Maize Based on Three-Dimensional Structural Phenotyping and Gaussian Fuzzy Clustering

The maize tassel represents one of the most pivotal organs dictating maize yield and quality. Investigating its phenotypic information constitutes an exceedingly crucial task within the realm of breeding work, given that an optimal tassel structure is fundamental for attaining high maize yields. High-throughput phenotyping technologies furnish significant tools to augment the efficiency of analyzing maize tassel phenotypic information. Towards this end, we engineered a fully automated multi-angle digital imaging apparatus dedicated to maize tassels. This device was employed to capture images of tassels from 1227 inbred maize lines falling under three genotype classifications (NSS, TST, and SS). By leveraging the 3D reconstruction algorithm SFM (Structure from Motion), we promptly obtained point clouds of the maize tassels. Subsequently, we harnessed the TreeQSM algorithm, which is custom-designed for extracting tree topological structures, to extract 11 archetypal structural phenotypic parameters of the maize tassels. These encompassed main spike diameter, crown height, main spike length, stem length, stem diameter, the number of branches, total branch length, average crown diameter, maximum crown diameter, convex hull volume, and crown area. Finally, we compared the GFC (Gaussian Fuzzy Clustering algorithm) used in this study with commonly used algorithms, such as RF (Random Forest), SVM (Support Vector Machine), and BPNN (BP Neural Network), as well as k-Means, HCM (Hierarchical), and FCM (Fuzzy C-Means). We then conducted a correlation analysis between the extracted phenotypic parameters of the maize tassel structure and the genotypes of the maize materials. The research results showed that the Gaussian Fuzzy Clustering algorithm was the optimal choice for clustering maize genotypes. Specifically, its classification accuracies for the Non-Stiff Stalk (NSS) genotype and the Tropical and Subtropical (TST) genotype reached 67.7% and 78.5%, respectively. Moreover, among the materials with different maize genotypes, the number of branches, the total branch length, and the main spike length were the three indicators with the highest variability, while the crown volume, the average crown diameter, and the crown area were the three indicators with the lowest variability. This not only provided an important reference for the in-depth exploration of the variability of the phenotypic parameters of maize tassels but also opened up a new approach for screening breeding materials.

Exploration of Computer Vision Technology and Legal Consideration of Online False Propaganda Behavior in the Perspective of Civil and Commercial Law

Abstract False propaganda behavior seriously misleads consumers, and the general people are deeply hurt by this, so the monitoring of online propaganda behavior has become an urgent issue. This paper introduces a method for monitoring false propaganda behavior based on computer vision technology. A video capture card is used to capture network signals for subsequent image recognition. For the characteristics of video content recognition, the “first and last key extraction method” is used to extract key frames. Then the selected key frames are preprocessed for binarization. In the binarization module of the system, the fuzzy C-mean clustering algorithm is designed and applied for image binarization in this paper. Finally, the template-based matching method is used for image recognition, and it has been appropriately improved in this module to enhance its efficiency and accuracy in recognizing false propaganda behaviors on the Internet. On the basis of the above work, this topic in the civil and commercial law vision is from three aspects about the network false behavior propaganda considerations, in order to make this aspect of the law and regulations more perfect. In this paper, the method was used to carry out image testing experiments on false network propaganda behavior. The experimental results show that the recognition accuracy of the method for different types of false propaganda behavior is 90% and above, and the recognition accuracy of the false propaganda behavior of the user evaluation category is as high as 99%. This indicates that the method holds practical significance in addressing online false propaganda behavior.

Research on the Innovation Path of Civic Education for College Students under the New Media Environment

Abstract By virtue of its ability to adapt to the psychological characteristics of college students, new media has now become a key carrier for the development of Civic and Political Education in colleges and universities. This paper explains the algorithmic recommendation mechanism of new media from multiple perspectives, the opportunities and challenges for college students’ civic education, and proposes a personalized recommendation algorithm for college students’ civic education based on LDA model. On the basis of similarity calculation, a user behavior feature extraction model is established. And combined with the fuzzy C-mean clustering algorithm, the joint information entropy of new media user behavior is calculated, and the joint information entropy results are optimized for the new media recommendation algorithm. Finally, the effectiveness and problems of the new media environment in the ideological and political education of college students are empirically analyzed. The results show that for the new media communication of college students’ Civic and Political Education, 22.04 percent of the students gave a satisfactory answer of 5 points in the content dimension. It shows that in the new media environment, the content of the Civic and Political Education still needs to be constantly innovated, and actively explore the content that is compatible with the physical and mental development and characteristics of college students.

The construction of a multi-platform system for teaching journalism and communication based on big data technology

Abstract Building experimental teaching platforms and analyzing student learning data to help improve instructional design are trends in the context of the big data era. This paper combines the innovative multi-type practical teaching theory to build an all-media experimental platform with three departments, namely, gathering department, editorial department and production department, and makes it available to journalism learners. The fuzzy C-mean clustering algorithm based on DTW is designed and applied to analyze the data of the all-media experimental platform. Combine the platform data to analyze the types of learners and the characteristics of learning behaviors of each category, and provide teaching improvement methods for teachers based on the relevant analysis results. By analyzing the data of the all-media experimental platform, it can be seen that there is an overall correlation between the students’ learning performance and the number of days of using the platform, the number of interactions, as well as the number of chapters studied, the number of forum speeches, and the number of horizontal playbacks. Students were further categorized into a total of six categories such as focused learners, continuous learners, etc. In which continuous learners accounted for the largest proportion of 38%, while abandoned learners accounted for the smallest proportion of only 2%, and other categories of learners accounted for between 4% and 25%. Improving teaching planning based on the results of platform data analysis will effectively improve the skill level of news communication learners and lay the foundation for their subsequent path to the news communication profession.

Novel Multiple Criteria Group Decision-Making Method Based on Hesitant Fuzzy Clustering Algorithm

Novel Multiple Criteria Group Decision-Making Method Based on Hesitant Fuzzy Clustering Algorithm

Integrated energy-efficient routing and secure data management for location-aware wireless sensor networks with PFO leveraged improved fuzzy unequal clustering algorithm (IFUC)

Combining energy-efficient routing with secure data management for LAWSNs represents a challenging research domain and an emerging scientific paradigm. This approach includes various elements, for example, data collection, asymmetrical clustering and hybrid optimization as well as a model of the combined encryption Wireless Sensor Networks (WSNs). In the process of data collection, sensor nodes will sense environmental information (temperature, humidity, etc.), sample regularly and fuse to detect redundancy information for power saving. Geospatial clustering with IFUC is important in location-aware routing. This approach overcomes the hot spot problem and provides energy-efficient management of traffic within and between clusters by optimizing cluster sizes based on their access to the base station. Here, a hybrid encryption model is presented to combine asymmetric RSA with symmetric data encryption standard (3DES) encryption in order to carry out absolute encrypted data transmission, minimizing the probability of unauthorized accessible information. All the keys are systematically managed, periodically renewed, and handpicked through the phoenix fusion optimiser (PFO). The data transfer process is about the encryption of data by hardcoded keys and how this encrypted information is sent on the best route possible. The cluster heads (CHs) fuse data in clusters to minimize the redundant transmission of data. This data is then shared along the inter-cluster pathways to become a base station. A holistic energy-efficient, secure and optimized data handling solution tailored for location-aware wireless sensor networks (WSN) is thus proposed, extending the lifespan and enhancing the efficiency of the network using an integrated strategy.

Comparison of Fuzzy Clustering Algorithms on UI GreenMetric University Rankings

That universities will supply remarkable assistance on the pathway to sustainability by providing intellectual leadership in attaining a sustainable society is an acceptable and emphasized issue. Herewith, in this work, we aimed to divide the campuses into homogeneous groups using fuzzy clustering techniques by employing the UI GreenMetric World University Rankings data having ranked the world's prestigious universities every year since 2010. In the results obtained, these universities are separated into four groups. Generalized possibilistic fuzzy clustering algorithm formed the most homogeneous clusters. Also, this algorithm clustered universities in a shortest time. While the "education and research" and "waste" categories are the strength aspect of the top green campuses, "water" is determined as the improvement aspect of the less sustainable campuses.

Classification and Recognition of Music Curriculum Resources Based on Improved Fuzzy C-Means Clustering Algorithm

Classification and Recognition of Music Curriculum Resources Based on Improved Fuzzy C-Means Clustering Algorithm

Module Configuration of Rail Freight Transportation with Both Customer Segmentation and Product Family Genealogy in China

The Chinese government is actively restructuring transportation to shift towards more sustainable rail freight transportation (RFT); however, there is still a lack of more systematic optimization in the whole production chain. This study develops a dual-focus modular configuration approach to explore the integration of customer demand and the production chain to achieve more sustainable operations in RFT. Customers have yielded eleven distinct groups, and operational processes have been segmented into sixteen modules by using the Ant Colony Optimization-based Fuzzy C-Means Clustering (ACOFCM) algorithm. Consequently, a Product Family Genealogy (PFG) model is conducted to identify three tailored product families (i.e., cross-border, multi-modal and general freight product). The developed dual-focus modular configuration approach has been proven to be feasible by utilizing a backtracking algorithm through a case study in an RFT logistics enterprise in China, which provides a standardization and optimization for RFT modular configurations.

An Unsupervised Remote Sensing Image Change Detection Method Based on RVMamba and Posterior Probability Space Change Vector

Change vector analysis in posterior probability space (CVAPS) is an effective change detection (CD) framework that does not require sound radiometric correction and is robust against accumulated classification errors. Based on training samples within target images, CVAPS can generate a uniformly scaled change-magnitude map that is suitable for a global threshold. However, vigorous user intervention is required to achieve optimal performance. Therefore, to eliminate user intervention and retain the merit of CVAPS, an unsupervised CVAPS (UCVAPS) CD method, RFCC, which does not require rigorous user training, is proposed in this study. In the RFCC, we propose an unsupervised remote sensing image segmentation algorithm based on the Mamba model, i.e., RVMamba differentiable feature clustering, which introduces two loss functions as constraints to ensure that RVMamba achieves accurate segmentation results and to supply the CSBN module with high-quality training samples. In the CD module, the fuzzy C-means clustering (FCM) algorithm decomposes mixed pixels into multiple signal classes, thereby alleviating cumulative clustering errors. Then, a context-sensitive Bayesian network (CSBN) model is introduced to incorporate spatial information at the pixel level to estimate the corresponding posterior probability vector. Thus, it is suitable for high-resolution remote sensing (HRRS) imagery. Finally, the UCVAPS framework can generate a uniformly scaled change-magnitude map that is suitable for the global threshold and can produce accurate CD results. The experimental results on seven change detection datasets confirmed that the proposed method outperforms five state-of-the-art competitive CD methods.