Constrained Clustering Algorithm Research Articles

Three-view cotton flower counting through multi-object tracking and RGB-D imagery

Monitoring the number of cotton flowers can provide important information for breeders to assess the flowering time and the productivity of genotypes because flowering marks the transition from vegetative growth to reproductive growth and impacts the final yield. Traditional manual counting methods are time-consuming and impractical for large-scale fields. To count cotton flowers efficiently and accurately, a multi-view multi-object tracking approach was proposed by using both RGB and depth images collected by three RGB-D cameras fixed on a ground robotic platform. The tracking-by-detection algorithm was employed to track flowers from three views simultaneously and remove duplicated counting from single views. Specifically, an object detection model (YOLOv8) was trained to detect flowers in RGB images and a deep learning-based optical flow model Recurrent All-pairs Field Transforms (RAFT) was used to estimate motion between two adjacent frames. The intersection over union and distance costs were employed to associate flowers in the tracking algorithm. Additionally, tracked flowers were segmented in RGB images and the depth of each flower was obtained from the corresponding depth image. Those flowers tracked with known depth from two side views were then projected onto the middle image coordinate using camera calibration parameters. Finally, a constrained hierarchy clustering algorithm clustered all flowers in the middle image coordinate to remove duplicated counting from three views. The results showed that the mean average precision of trained YOLOv8x was 96.4%. The counting results of the developed method were highly correlated with those counted manually with a coefficient of determination of 0.92. Besides, the mean absolute percentage error of all 25 testing videos was 6.22%. The predicted cumulative flower number of Pima cotton flowers is higher than that of Acala Maxxa, which is consistent with what breeders have observed. Furthermore, the developed method can also obtain the flower number distributions of different genotypes without laborious manual counting in the field. Overall, the three-view approach provides an efficient and effective approach to count cotton flowers from multiple views. By collecting the video data continuously, this method is beneficial for breeders to dissect genetic mechanisms of flowering time with unprecedented spatial and temporal resolution, also providing a means to discern genetic differences in fecundity, the number of flowers that result in harvestable bolls. The code and datasets used in this paper can be accessed on GitHub: https://github.com/UGA-BSAIL/Multi-view_flower_counting.

Retracted: Analysis of College Students’ Ability to Improve Innovation and Entrepreneurship Based on Constrained Clustering Algorithm

Retracted: Analysis of College Students’ Ability to Improve Innovation and Entrepreneurship Based on Constrained Clustering Algorithm

An adaptive constrained clustering approach for real-time fault detection of industrial systems

Thanks to the pervasive deployment of sensors in Industry 4.0, data-driven methods are recently playing an important role in the fault diagnosis and prognosis of industrial systems. In this paper, a novel Adaptive Constrained Clustering algorithm is defined to support real-time fault detection of an industrial machine, by clustering the incoming monitoring data into two clusters over time, representing the nominal and non-nominal work conditions, respectively. To this aim, the proposed algorithm relies on a two-stage procedure: micro-clustering and constrained macro-clustering. The former stage is responsible for grouping the batches of work-cycle data into micro-clusters, while the data stream continuously arrives from the data acquisition system. Then, after condensing the micro-clusters into vectors of cluster features, and leveraging on additional knowledge on the nominal and non-nominal working conditions (i.e., constraints on some samples), the second stage aims at offline grouping the micro-clusters features into macro-clusters. Experimental results on a real-world industrial case study show that the proposed real time framework achieves the same results of offline baseline methods (e.g., Constrained K-means) with a higher responsiveness and processing speed; in comparison to stream baseline methods (e.g., Stream K-means), the proposed approach obtains more accurate and easily interpretable results.

On the statistical evaluation of bubbly flows using Voronoi cells grouped in clusters with fixed cell count

The extraction of statistical information from bubbly flow experiments is crucial for numerical studies. Knowledge regarding probability distributions is particularly relevant in cases where a model relying solely on the use of mean values would lead to inaccurate results. As such, existing studies have focused on evaluating spatial distributions and local histograms for the void fraction, bubble density, and bubble size. However, the traditional box-counting method, employed by various studies, results in inconsistencies when deriving these quantities, especially when the respective two-phase flow features regions with low bubble densities or density gradients. This study demonstrates the application and benefits of combining Voronoi diagrams with a constrained K-Means clustering algorithm as a method for analyzing bubbly flows. We conduct three test cases: The first two cases use synthetic snapshots with prescribed characteristics to show the influence of evaluation settings and to critically quantify the errors, and the last test uses snapshot data of a plunging-jet experiment with air entrainment. We, then, compare the identified entrainment rate and the mean void-fraction distribution with empirical values from the literature. All three test cases show good agreement with the prescribed field characteristics (synthetic snapshots) and the data from the literature (experiment). Beyond demonstrating its applicability, we also show how this method can derive local histograms more consistently. The derivation is robust throughout the domain in comparison with traditional methods. For these reasons, we conclude that this method provides good estimates of spatial distributions.

Towards more efficient local search algorithms for constrained clustering

Constrained clustering extends clustering by integrating user constraints, and aims to determine an optimal assignment under the constraints. In this paper, we propose a local search algorithm called FastCCP to solve the constrained clustering problem. In the algorithm, instances connected by must-link constraints are first merged into nodes, and then, a local search method is performed to handle the cannot-link constraints while minimizing the Within-Cluster Sum of Squares (WCSS). Several strategies are proposed to enhance the solution diversity and achieve a trade-off between constraint satisfaction and WCSS minimization during the search. Furthermore, a node-filtering strategy is proposed to improve the efficiency of the algorithm. Experiments are performed on benchmark datasets to evaluate our algorithm. The comparative results indicate that our algorithm outperforms state-of-the-art algorithms in terms of both the solution quality and CPU runtime.

Construction of Automatic Matching Recommendation System for Web Page Image Packaging Design Based on Constrained Clustering Algorithm

With the rapid development of artificial intelligence technology, computer vision science has also gained new opportunities. As the foundation of computer vision and numerous artificial intelligence applications, image matching technology has received extensive attention from researchers and companies around the world. However, in web design, the research on the image matching system is not mature enough, which results in a series of problems such that the web design is not beautiful enough, and the figures do not conform to the design theme. Therefore, it is the current trend to deeply study the structure of the automatic matching recommendation system for web page image packaging design. The purpose of this paper is to use the constrained clustering algorithm to study how to construct an automatic matching recommendation system for web page image packaging design. This paper first gives a general introduction to the classification of constrained clustering algorithms. Then, the operation mechanism and model establishment of SURF feature description operator, SIFT feature description operator, and ORB feature description operator are described in detail. Then, through experiments, the matching accuracy of the web page image matching system based on the constrained clustering algorithm and the influence of parameter changes are compared with other algorithms. Finally, a comparative experiment is carried out on the image matching effects of the three feature description operators. The matching speed, noise sensitivity, and rotation type experiments are introduced respectively. By constructing the web page image packaging design of the constrained clustering algorithm to automatically match the algorithm model of the recommender system and experimenting with the model, the advantages of the constrained clustering algorithm in the model construction are proved. The experimental results show that the constrained clustering algorithm has higher image matching efficiency and matching accuracy, and the accuracy of image feature extraction is better than other algorithms. However, when the network structure division attribution threshold is ϕ = 0.4 , the clustering performance of the constrained clustering algorithm is better. Compared with the parameter 100, when the parameter is 500 and 1000, the accuracy of the constrained clustering algorithm can be improved, and the calculation accuracy is increased by 0.317.

Analysis of College Students’ Ability to Improve Innovation and Entrepreneurship Based on Constrained Clustering Algorithm

With the expansion of college enrollment, college graduates have continued to expand, and the employment situation has become more and more severe. As a new form of employment, innovation and entrepreneurship are becoming more and more important in college teaching. Entrepreneurial success is crucial. This paper proposes an entropy-based active learning method (ALPCS), which is divided into three stages: selection, exploration, and consolidation. The main contents are as follows: in the selection stage, the fuzzy c -means algorithm is used to obtain the membership of all samples, then calculate their Shannon entropy, and finally, select the sample with large Shannon entropy to generate an information subset (the larger the Shannon entropy, the greater the uncertainty, and the more information it contains). The distance-first strategy actively selects samples from the information subset to construct a cluster skeleton cluster. If it is equal to the real number of clusters, it enters the consolidation phase; otherwise, the active learning method stops. In the consolidation phase, sequentially from the information, the nonskeleton set points with the largest uncertainty are selected in the subset to form queries with the points in the skeleton set until the must-link constraint is formed. In this stage, the principle of minimum symmetric relative entropy first is used to reduce the number of queries. The ALPCS algorithm is compared and evaluated, and the final experimental results show that the ALPCS algorithm has a good performance when the number of queries is large.

Constrained clustering and multiple kernel learning without pairwise constraint relaxation

Clustering under pairwise constraints is an important knowledge discovery tool that enables the learning of appropriate kernels or distance metrics to improve clustering performance. These pairwise constraints, which come in the form of must-link and cannot-link pairs, arise naturally in many applications and are intuitive for users to provide. However, the common practice of relaxing discrete constraints to a continuous domain to ease optimization when learning kernels or metrics can harm generalization, as information which only encodes linkage is transformed to informing distances. We introduce a new constrained clustering algorithm that jointly clusters data and learns a kernel in accordance with the available pairwise constraints. To generalize well, our method is designed to maximize constraint satisfaction without relaxing pairwise constraints to a continuous domain where they inform distances. We show that the proposed method outperforms existing approaches on a large number of diverse publicly available datasets, and we discuss how our method can scale to handling large data.

The use of milk Fourier-transform mid-infrared spectroscopy to diagnose pregnancy and determine spectral regional associations with pregnancy in US dairy cows

Accurate early diagnosis of pregnancy is important for timely reproductive management of dairy farms. Fourier-transform mid-infrared (FT-MIR) milk spectral data are routinely used for determining milk components such as fat and protein, whereas milk composition is known to change with advancing stages of pregnancy. The objectives of this study were to compare partial least squares discriminant analysis (PLS-DA) and a Bayesian variable selection regression model (BayesC) for the diagnosis of pregnancy status (PS) from milk FT-MIR data and to infer any spectral regions that might be highly associated with PS at various stages of pregnancy. Conception dates on confirmed pregnant cows were obtained from Holstein cows within 123 herds in Michigan, Ohio, and Indiana during 2018 and 2019. Milk samples from these pregnant cows at 7 different stages of pregnancy were case-control matched to open contemporary herd mates to be within the same stage (±10 d for days in milk) of lactation for the same milk sample test date. The FT-MIR data were obtained for all of these milk samples. Ten-fold herd-independent cross-validation was used to compare PLS-DA versus BayesC using the area under the receiver operating characteristic curve (AUC). The BayesC model demonstrated higher mean AUC compared with PLS-DA at all stages exceeding 60 d of pregnancy. The mean BayesC AUC at stage 1 (1-30 d) was 0.58 ± 0.02, which was superior to a random guess (AUC = 0.50) yet too low to be of practical use. The mean BayesC AUC at stage 7 (≥180 d) was 0.13 greater compared with that of stage 1 (1-30 d) and 0.07 to 0.10 greater compared with stages 2, 3, 4, 5, and 6 (31-180 d in 30-d increments). The mean AUC of stages 2 to 6 were 0.03 to 0.06 greater compared with stage 1 yet again too low to be of practical use. Because of high multicollinearity between many adjacent wavenumbers, a spatially constrained clustering algorithm was used to adaptively partition wavenumbers into 68 windows before inferring associations of spectral regions with pregnancy. Pregnancy status was highly associated with wavenumber windows 1,063 to 1,134 cm-1, 1,201 to 1,257 cm-1, and 1,260 to 1,432 cm-1 based on an estimated BayesC posterior probability of association (PPA) approaching 100% for each of these windows at all pregnancy stages. Other windows ranging from 1,730 to 1,764 cm-1, 1,775 to 1,992 cm-1, 1,995 to 2,163 cm-1, and 2,167 to 2,316 cm-1 had varying medium to high PPA (30% to 100%) across stages. The estimated PPA in wavenumber regions from 1,477 to 1,507 cm-1, and 1,510 to 1,574 cm-1 was weaker in stages 1 and 2 compared with later stages, whereas for the regions 2,984 to 3,077 cm-1 and 3,081 to 3,133 cm-1 the effect of pregnancy was greater for stage 1 compared with other stages. Despite our conclusion that milk FT-MIR data poorly diagnose PS, our study provides new insights into spectral regions that are strongly associated with PS and warrant greater attention.

Transformation and Optimization of Rural Ecological Endowment Industry Chain Based on Constrained Clustering Algorithm

China is experiencing a serious aging crisis, with the number of elderly people rising at an unprecedented rate. First and foremost, the pension industry's service object is the pension. To build an old-age industry complex, make use of the unique natural resources in the countryside, provide the original ecological old-age care services, and transform, optimize, and make efficient use of the existing policies and technologies. The drawbacks of the traditional pension model are becoming increasingly apparent. We must investigate a new pension model in order to ensure the long-term development of China's pension system and reduce the increased pension burden on governments at all levels. The rural areas' unique natural resources should be utilized to provide unique ecological elderly care services, and transformation and optimization must be implemented (that is, making efficient use of existing policies and technology to construct an elderly care industry complex). As a new pension mode for the elderly to become more connected to the natural world and improve their physical and mental health, ecological pensions have emerged as a new economic growth point that can fill the gap in the pension industry's supply while also meeting the elderly's growing spiritual and cultural needs. A constrained clustering algorithm is proposed in this article. Unsupervised learning is used in the constrained clustering algorithm. The clustering algorithm must determine the data objects to be clustered because they are not labeled. Because the data objects have no prior knowledge, the clustering algorithm analyzes them using the same principles. The effectiveness of the clustering results is determined by the dataset's adherence to the previously stated principles. The constrained clustering algorithm has greatly improved the transformation and optimization of the rural ecological elderly care industrial chain.

Regional Variation in Forest Canopy Height and Implications for Koala (Phascolarctos cinereus) Habitat Mapping and Forest Management

Previous research has shown that the Koala (Phascolarctos cinereus) prefers larger trees, potentially making this a key factor influencing koala habitat quality. Generally, tree height is considered at regional scales which may overlook variation at patch or local scales. In this study, we aimed to derive a set of parameters to assist in classifying koala habitat in terms of tree height, which can then be used as an overlay for existing habitat maps. To determine canopy height variation within a specific forest community across a broad area in eastern Australia, we used freely available Airborne Laser Scanning (ALS) data and adopted a straightforward approach by extracting maximum-height ALS returns within a total of 288 30 m × 30 m “virtual” ALS plots. Our findings show that while maximum tree heights generally fall within published regional-scale parameters (mean height 33.2 m), they vary significantly between subregions (mean height 28.8–39.0 m), within subregions (e.g., mean height 21.3–29.4 m), and at local scales, the tree heights vary in response to previous land-use (mean height 28.0–34.2 m). A canopy height dataset useful for habitat management needs to recognise and incorporate these variations. To examine how this information might be synthesised into a usable map, we used a wall-to-wall canopy height map derived from ALS to investigate spatial and nonspatial clustering techniques that capture canopy height variability at both intra-subregional (100s of hectares) and local (60 hectare) scales. We found that nonspatial K-medians clustering with three or four height classes is suited to intra-subregional extents because it allows for simultaneous assessment and comparison of multiple forest community polygons. Spatially constrained clustering algorithms are suited to individual polygons, and we recommend the use of the Redcap algorithm because it delineates contiguous height classes recognisable on a map. For habitat management, an overlay combining these height classification approaches as separate attributes would provide the greatest utility at a range of scales. In addition to koala habitat management, canopy height maps could also assist in managing other fauna; identifying forest disturbance, regenerating forest, and old-growth forest; and identifying errors in existing forest maps.

Improving Text Clustering with Social Tagging

In this paper we study the use of social bookmarking to improve the quality of text clustering. Recently constrained clustering algorithms have been presented as a successful tool to introduce domain knowledge in the clustering process. This paper uses the tags saved by the users of Delicious to generate non artificial constraints for constrained clustering algorithms. The study demonstrates that it is possible to achieve a high percentage of good constraints with this simple approach and, more importantly, the evaluation shows that the use of these constraints produces a great improvement (up to 91.25%) of the clustering algorithms effectiveness.

The spatial agglomeration of the MICE industry

AbstractMICE is one of the most profitable sectors of the tourism industry, with an effective impact on local economies. However, the investigation of its spatial agglomeration has not been fully explored. In this study, we use information on the venues' characteristics and territorial distribution to identify convention firms' agglomeration in Emilia‐Romagna (Italy), through a constrained clustering algorithm. This approach enables the inclusion of both non‐geographical aspects, measured by the Krugman sectoral index, and geographical information. Findings show the existence of developed and developing convention agglomerations, with different MICE offers. Using convention demand data, we improve the cluster's profiles and propose some managerial strategies.

Improving evolutionary constrained clustering using Active Learning

The high cost of labeling data for analysis increased the interest in semi-supervised learning, especially constrained clustering, which usually involves reduced cost. At the same time, Active Learning (AL) aims to minimize the cost of creating labeled datasets by trying to identify which unlabeled data are more relevant for using during the learning process, considering which labels are already available. This paper proposes four AL strategies to an evolutionary constrained clustering algorithm (FIECE-EM) based on Gaussian Mixture Models (GMM), with corresponding theoretical asymptotic analyses. These strategies use information from many different sources, such as the partition, the population, and even specific aspects of the algorithm. We perform empirical evaluation on 14 well-known datasets, as a way to measure the impacts of each strategy both in relation to accuracy and labeling cost. The results were compared with baseline supervised algorithms as well as COBRAS, a state-of-the-art Active Learning algorithm for constrained clustering. Three of the proposed strategies obtained significantly better results than COBRAS in our empirical evaluation. Thus, the combination of FIECE-EM with these strategies can be considered viable alternatives for AL in a constrained clustering setting.

Repeated Record Ordering for Constrained Size Clustering

One of the main techniques used in data mining is data clustering, which has many applications in computer science, biology and social sciences. Constrained clustering is a type of clustering in which side information provided by the user is incorporated into current clustering algorithms. One of the well researched constrained clustering algorithms is called microaggregation. In a microaggregation technique, the algorithm divides the dataset into groups containing at least members, where is a user-defined parameter. The main application of microaggregation is in Statistical Disclosure Control (SDC) for privacy preserving data publishing. A microaggregation algorithm is qualified based on the sum of within-group squared error, . Unfortunately, it has been proven that the optimal microaggregation problem is NP-Hard in general, but the special univariate case can be solved optimally in polynomial time. Many heuristics exist for the general case of the problem that are founded on the univariate case. These techniques order multivariate records in a sequence. This paper proposes a novel method for record ordering. Starting from a conventional clustering algorithm, the proposed method repeatedly puts multivariate records into a sequence and then clusters them again. The process is repeated until no improvement is achieved. Extensive experiments have been conducted in this research to confirm the effectiveness of the proposed method for different parameters and datasets.

When Cluster Analysis Meets Geography: The Spatial Agglomeration of the MICE Industry

In this study, we investigate the spatial agglomeration of the Meetings, Incentives, Conferences, and Exhibitions (MICE) industry. We use detailed information on the convention venues characteristics and their spatial distribution to identify clusters by using the spatially constrained clustering algorithm. This approach enables the inclusion of geographical and non-geographical information in the clustering algorithm. In particular, the non-geographical aspects are measured by the Krugman sectoral dissimilarity index based on convention centers’ seat places; beside, a spatial contiguity matrix is used as geographical information. Our findings show the existence of developed and developing convention clusters, with different MICE offer. Using convention production's data for each cluster, we were able to conclude the cluster’s profile and propose managerial strategies.

Active Learning for Constrained Document Clustering with Uncertainty Region

Constrained clustering is intended to improve accuracy and personalization based on the constraints expressed by an Oracle. In this paper, a new constrained clustering algorithm is proposed and some of the informative data pairs are selected during an iterative process. Then, they are presented to the Oracle and their relation is answered with “Must-link (ML) or Cannot-link (CL).” In each iteration, first, the support vector machine (SVM) is utilized based on the label produced by the current clustering. According to the distance of each document from the hyperplane, the distance matrix is created. Also, based on cosine similarity of word2vector of each document, the similarity matrix is created. Two types of probability (similarity and degree of similarity) are calculated and they are smoothed for belonging to neighborhoods. Neighborhoods form the samples that are labeled by Oracle, to be in the same cluster. Finally, at the end of each iteration, the data with a greater level of uncertainty (in term of probability) is selected for questioning the oracle. In order to evaluate, the proposed method is compared with famous state-of-the-art methods based on two criteria and over a standard dataset. The result demonstrates an increased accuracy and stability of the obtained result with fewer questions.

A constrained agglomerative clustering approach for unipartite and bipartite networks with application to credit networks

Researchers and practitioners have been interested in solving real-world problems through clustering. The clustering of nodes in networks with unipartite or bipartite structure is important to explore real-world complex networks present in nature and society. Bipartite networks form an important class of complex networks because they reveal the heterogeneity of nodes in a network. However, most extant clustering methods focus only on unipartite networks. In this work, a novel constrained agglomerative clustering method applicable to unipartite and bipartite networks has been proposed. Initially, the topology of a network is modeled according to set-theoretic principles. Subsequently, the concepts related to rough set theory and relative linkage are used to cluster the set of nodes. The utility and effectiveness of the proposed approach are demonstrated through offline experiments on unipartite and bipartite networks. A comparison against ten state-of-the-art similarity measures over two different partitional clustering algorithms reveals the effectiveness of the proposed relative linkage measure. Moreover, a comparative analysis with state-of-the-art network clustering methods reveals the viability of the proposed rough set-based constrained agglomerative clustering algorithm. Finally, the proposed method has been applied for the detection of cohesive subgroups of banks in a real bipartite network formed by mapping credit relationships between Indian firms and banks.

Kernel-Based Robust Bias-Correction Fuzzy Weighted C-Ordered-Means Clustering Algorithm

The spatial constrained Fuzzy C-means clustering (FCM) is an effective algorithm for image segmentation. Its background information improves the insensitivity to noise to some extent. In addition, the membership degree of Euclidean distance is not suitable for revealing the non-Euclidean structure of input data, since it still lacks enough robustness to noise and outliers. In order to overcome the problem above, this paper proposes a new kernel-based algorithm based on the Kernel-induced Distance Measure, which we call it Kernel-based Robust Bias-correction Fuzzy Weighted C-ordered-means Clustering Algorithm (KBFWCM). In the construction of the objective function, KBFWCM algorithm comprehensively takes into account that the spatial constrained FCM clustering algorithm is insensitive to image noise and involves a highly intensive computation. Aiming at the insensitivity of spatial constrained FCM clustering algorithm to noise and its image detail processing, the KBFWCM algorithm proposes a comprehensive algorithm combining fuzzy local similarity measures (space and grayscale) and the typicality of data attributes. Aiming at the poor robustness of the original algorithm to noise and outliers and its highly intensive computation, a Kernel-based clustering method that includes a class of robust non-Euclidean distance measures is proposed in this paper. The experimental results show that the KBFWCM algorithm has a stronger denoising and robust effect on noise image.

Spatially Constrained Fuzzy c-Means Clustering Algorithm for Image Segmentation

The fuzzy c-means (FCM) clustering is an unsupervised clustering method, which has been widely used in image segmentation. In this paper, a spatially constrained fuzzy c-means clustering algorithm for image segmentation is proposed to overcome the sensitivity of the FCM clustering algorithm to noises and other imaging artifacts. Firstly, the local prior probabilities of pixel classification are defined according to the fuzzy membership function values of neighbouring pixels, and then those local prior probabilities are incorporated into the objective function of the standard FCM. Thus, the local spatial information embedded in the image is incorporated into the FCM algorithm. Experimental results on the synthetic and real images are given to demonstrate the robustness and validity of the proposed algorithm.