Initial Cluster Research Articles

Supramolecular Host–Guest Assemblies of [M6Cl14]2–, M = Mo, W, Clusters with γ-Cyclodextrin for the Development of CLUSPOMs

Host–guest assemblies open up opportunities for developing novel functional CLUSPOM multicomponent systems based on transition metal clusters (CLUS), polyoxometalates (POMs) and macrocyclic organic ligands. In water–ethanol solution γ-cyclodextrin (γ-CD) interacts with halide metal clusters [M6Cl14]2– (M = Mo, W) to form sandwich-type structures. The supramolecular association between the clusters and CDs, however, remains weak in solution, and the interactions are not strong enough to prevent the hydrolysis of the inorganic guest. Although analysis of the resulting crystal structures reveals inclusion complexation, 1H NMR experiments in solution show no specific affinity between the two components. The luminescent properties of the host–guest compounds in comparison with the initial cluster complexes are also studied to evaluate the influence of CD.

Evolution of Clinical Phenotypes of COVID-19 Patients During Intensive Care Treatment: An Unsupervised Machine Learning Analysis.

Identification of clinical phenotypes in critically ill COVID-19 patients could improve understanding of the disease heterogeneity and enable prognostic and predictive enrichment. However, previous attempts did not take into account temporal dynamics with high granularity. By including the dimension of time, we aim to gain further insights into the heterogeneity of COVID-19. We used granular data from 3202 adult COVID patients in the Dutch Data Warehouse that were admitted to one of 25 Dutch ICUs between February 2020 and March 2021. Parameters including demographics, clinical observations, medications, laboratory values, vital signs, and data from life support devices were selected. Twenty-one datasets were created that each covered 24 h of ICU data for each day of ICU treatment. Clinical phenotypes in each dataset were identified by performing cluster analyses. Both evolution of the clinical phenotypes over time and patient allocation to these clusters over time were tracked. The final patient cohort consisted of 2438 COVID-19 patients with a ICU mortality outcome. Forty-one parameters were chosen for cluster analysis. On admission, both a mild and a severe clinical phenotype were found. After day 4, the severe phenotype split into an intermediate and a severe phenotype for 11 consecutive days. Heterogeneity between phenotypes appears to be driven by inflammation and dead space ventilation. During the 21-day period, only 8.2% and 4.6% of patients in the initial mild and severe clusters remained assigned to the same phenotype respectively. The clinical phenotype half-life was between 5 and 6 days for the mild and severe phenotypes, and about 3 days for the medium severe phenotype. Patients typically do not remain in the same cluster throughout intensive care treatment. This may have important implications for prognostic or predictive enrichment. Prominent dissimilarities between clinical phenotypes are predominantly driven by inflammation and dead space ventilation.

Canopy-MMD Text Clustering Algorithm Based on Simulated Annealing and Canopy Optimization

<p>Aiming at the problems that traditional K-means text clustering cannot automatically determine the number of clusters and is sensitive to initial cluster centers, this paper proposes a Canopy-MMD text clustering algorithm based on simulated annealing and silhouette coefficient optimization. The algorithm uses the simulated annealing algorithm combined with the silhouette coefficient to optimize the Canopy algorithm to find the optimal number of clusters, and uses the optimal number of clusters to determine the scale coefficient in the MMD algorithm, and finally achieves a better text clustering effect. The Sohu News dataset of Sogou Lab is experimentally analyzed and compared with the clustering results obtained by traditional K-means and algorithms in the literature. The experimental results show that the clustering performance of the algorithm is better than the traditional K-means algorithm and the algorithm in the literature, and the accuracy, precision, recall and F value are improved by 8.02%, 8.91%, 8.02%, 9.51% compared with the traditional K-means algorithm, which can be widely used in fields such as text mining, knowledge graph and natural language processing.</p> <p> </p>

Consensus fuzzy clustering by sequential quadratic programming approach

Existing fuzzy clustering ensemble approaches do not consider dependability. This causes those methods to be fragile in dealing with unsuitable basic partitions. While many ensemble clustering approaches are recently introduced for improvement of the quality of the partitioning, but lack of a median partition based consensus function that considers more participate reliable clusters, remains unsolved problem. Dealing with the mentioned problem, an innovative weighting fuzzy cluster ensemble framework is proposed according to cluster dependability approximation. For combining the fuzzy clusters, a fuzzy co-association matrix is extracted in a weighted manner out of initial fuzzy clusters according to their dependabilities. The suggested objective function is a constrained nonlinear objective function and we solve it by sparse sequential quadratic programming (SSQP). Experimentations indicate our method can outperform modern clustering ensemble approaches.

Possibilistic c-means clustering based on the nearest-neighbour isolation similarity

Clustering is widely used in data mining and machine learning. The possibilistic c-means clustering (PCM) method loosens the constraint of the fuzzy c-means clustering (FCM) method to solve the problem of noise sensitivity of FCM. But there is also a new problem: overlapping cluster centers are not suitable for clustering non-cluster distribution data. We propose a novel possibilistic c-means clustering method based on the nearest-neighbour isolation similarity in this paper. All samples are taken as the initial cluster centers in the proposed approach to obtain k sub-clusters iteratively. Then the first b samples farthest from the center of each sub-cluster are chosen to represent the sub-cluster. Afterward, sub-clusters are mapped to the distinguishable space by using these selected samples to calculate the nearest-neighbour isolation similarity of the sub-clusters. Then, adjacent sub-clusters can be merged according to the presented connecting strategy, and finally, C clusters are obtained. Our method proposed in this paper has been tested on 15 UCI benchmark datasets and a synthetic dataset. Experimental results show that our proposed method is suitable for clustering non-cluster distribution data, and the clustering results are better than those of the comparison methods with solid robustness.

A Novel Dynamic Transmission Power of Cluster Heads Based Clustering Scheme

Clustering methods are promising tools for ensuring the network scalability and maintainability of large-scale flying ad hoc networks (FANETs). However, due to the high mobility and limited energy resources of unmanned aerial vehicles (UAVs), it is difficult to maintain the network reliability and extend the network life of FANETs. In this paper, a new K-means algorithm is developed, and a dynamic transmission power of the cluster heads based clustering (DTPCH-C) scheme is proposed. The goal of this scheme is presented for FANETs to improve the reliability and lifetime of FANETs. Firstly, the optimal number of clusters is calculated and the initial UAV clusters are set up by a K-means algorithm. Then, using a weighted clustering algorithm, the adaptive node degree, the node energy and the distance from the cluster head are weighted and summed for the cluster head election. In the process of inter-cluster communication, the cluster head adjusts its transmit power in real-time through meshing and mobile prediction, thus saving the energy consumption and improving the network lifetime. The proposed DTPCH-C simultaneously optimizes the cluster number, the cluster head energy consumption, the selected cluster head, and the cluster maintenance process. The simulation results show that compared with traditional clustering methods, the proposed DTPCH-C has obvious advantages in terms of the network reliability, network life, and energy consumption.

Using Transport Activity-Based Model to Simulate the Pandemic

We use an activity-based transport model to simulate the progression of a virus at the regional scale. We analyse several scenarios corresponding to distinct situations and describing how small initial clusters of infected agents expand and reach a pandemic level. We evaluate the effectiveness of some public restrictions and compare the number of infections with respect to the base-case scenario, where no restrictions are in place. We consider the wearing of masks in public transport and/or in some activities (work, leisure and shopping) and the implementation of a lockdown. Our analysis shows that education, including the primary level, is one of the major activities where infections occur. We find that the wearing of masks in transportation only does not yield important impacts. The lockdown is efficient in containing the spread of the virus but, at the same time, significantly increases the length of the wave (factor of two). This is because the number of agents who are susceptible to be infected remains high. Our analysis uses the murdasp tool specifically designed to process the output of transport models and performs the simulation of the pandemic.

The transformation education concept in the digital ecosystem of a territorial production cluster

A new approach to the formation of distributed digital educational ecosystems in territorial production clusters is proposed. This can not only eliminate the shortcomings of the traditional education system, but also create a promising platform for a new modern educational technology. The basis for building such an ecosystem are modern achievements in the field of control systems, digitalization and artificial intelligence. Currently, the education market is seriously influenced by scientific results in the field of artificial intelligence and the rapid development of digital technologies. As practice has shown, it is necessary to take into account quite unpredictable natural disasters and pandemics, as well as the complex geopolitical and economic situation in the world. In these conditions, one of the few serious opportunities for universities to maintain and strengthen their positions in the education market, which will change rapidly in the near future, is the transformation of processes within the framework of new technological trends based on digital platforms of industrial cluster ecosystems. The digital twin can be used both for real-time decision-making and for forecasting and planning the process for the entire training period. The university and the enterprises of the territorial cluster that provide part of the educational services under this approach are integrated into a single mechanism for solving the tasks of flexible individual training in accordance with the needs of the cluster in highly qualified personnel. Within the framework of the proposed approach, it is possible to build a hybrid educational university environment integrated with the real objects of the territory’s economy, which in this case becomes the most important component of the digital educational ecosystem. The proposed concept makes it possible to predict and plan the training of the right specialists, since the entire scheme of the educational process in this case is closely connected with the enterprises of the real sector for the entire period of training. This becomes possible due to the fact that training takes place according to flexible, updated programs that reflect the constantly changing requirements of enterprises to the competencies of employees.

Photometric and structural parameters of newly discovered nuclear star clusters in Local Volume galaxies

ABSTRACTWe use high-resolution Hubble Space Telescope imaging data of dwarf galaxies in the Local Volume ($\lesssim {11}\, \mathrm{Mpc}$) to parameterize 19 newly discovered nuclear star clusters (NSCs). Most of the clusters have stellar masses of $M_{\star }^{\mathrm{nsc}} \lesssim 10^{6}{\, {\rm M}_{\odot }}$ and compare to Galactic globular clusters in terms of ellipticity, effective radius, stellar mass, and surface density. The clusters are modelled with a Sérsic profile and their surface brightness evaluated at the effective radius reveals a tight positive correlation to the host galaxy stellar mass. Our data also indicate an increase in slope of the density profiles with increasing mass, perhaps indicating an increasing role for in situ star formation in more massive hosts. We evaluate the scaling relation between the clusters and their host galaxy stellar mass to find an environmental dependence: for NSCs in field galaxies, the slope of the relation is $\alpha = 0.82^{+0.08}_{-0.08}$ whereas $\alpha = 0.55^{+0.06}_{-0.05}$ for dwarfs in the core of the Virgo cluster. Restricting the fit for the cluster to $M_{\star }^{\mathrm{gal}} \ge 10^{6.5}{\, {\rm M}_{\odot }}$ yields $\alpha = 0.70^{+0.08}_{-0.07}$, in agreement with the field environment within the 1σ interval. The environmental dependence is due to the lowest-mass nucleated galaxies and we speculate that this is either due to an increased number of progenitor globular clusters merging to become an NSC, or due to the formation of more massive globular clusters in dense environments, depending on the initial globular cluster mass function. Our results clearly corroborate recent results in that there exists a tight connection between NSCs and globular clusters in dwarf galaxies.

Research on the Siting of Rural Public Cultural Space Based on the Path-Clustering Algorithm: A Case Study of Yumin Township, Yushu City, Jilin Province, China

Cultural revitalization is the foundation of rural revitalization. Rural public cultural spaces are important places for rural residents to participate in cultural activities and important carriers for the occurrence, inheritance and development of rural culture. In this study, we propose a siting analysis method for public cultural spaces based on a path-clustering algorithm. Then, Yumin Township in Jilin Province is used as a case study to test the method. Within the township area, public cultural spaces are divided into three types based on the difference in service scope: “single-village decentralized”, “single-village concentration” and “multi-village concentration”. This paper focuses on the analysis of the siting of the “multi-village concentration” type of public cultural spaces using a path-clustering algorithm. First, the path-clustering algorithm is written, and then its parameters, initial clustering centers and number of clusters are analyzed for their effect on the clustering results. Two parameters, within-cluster sum of path distance (WCSPD) and maximum value of the path distance within-cluster (MPDWC), are proposed to evaluate the results of the algorithm. Then, taking Yumin Township of Jilin Province as an example, the villages in the township are clustered with travel distance as the main influencing factor. It is ensured that the shortest path distance from the central village in each cluster to other villages is no greater than the set travel distance. Finally, the public cultural space is constructed in the central village to serve all villages in the cluster. This siting analysis method can output a variety of results that can be used as a reference for decision making in rural public cultural space planning.

Machine learning discovery of new phases in programmable quantum simulator snapshots

Machine learning has recently emerged as a promising approach for studying complex phenomena characterized by rich datasets. In particular, data-centric approaches lead to the possibility of automatically discovering structures in experimental datasets that manual inspection may miss. Here, we introduce an interpretable unsupervised-supervised hybrid machine learning approach, the hybrid-correlation convolutional neural network (hybrid-CCNN), and apply it to experimental data generated using a programmable quantum simulator based on Rydberg atom arrays. Specifically, we apply hybrid-CCNN to discover and identify new quantum phases on square lattices with programmable interactions. The initial unsupervised dimensionality reduction and clustering stage first reveals five distinct quantum phase regions. In a second supervised stage, we refine these phase boundaries and seek insights into the phases by training multiple CCNN classifiers. A learned spatial weighting, introduced to the CCNNs in this work, enables discovery of spatial structure at scales beyond the filter size. The characteristic spatial weightings and snippets of correlations specifically recognized in each phase capture quantum fluctuations in the striated phase and identify a previously undetected boundary-ordered phase as well as motifs of more exotic ordered phases. These observations demonstrate that a combination of programmable quantum simulators with machine learning can be used as a powerful tool for detailed exploration of correlated quantum states of matter.

Equivalent modeling and multi-parameter coupling optimization for DFIG-based wind farms considering SSO mode

As a low-carbon and environmentally friendly renewable energy source, wind power has been globally recognized as the best solution to achieve energy saving and emission reduction and promote low-carbon economic growth. With the increase of wind power penetration, wind power has a great impact on sub-synchronous state stability and dynamic characteristics of the grid-connected system. Aiming at the fact that the correlation between clustering indexes and sub-synchronous oscillation (SSO) mode and the difference of the contribution to the clustering results are seldom considered in the current equivalent modeling of doubly-fed induction generator (DFIG)-based wind farm, this paper proposes a clustering method based on the index dimension reduction and weighted fuzzy C-means (WFCM) clustering algorithm. Besides, for the SSO study of the grid-connected system without sufficiently considering the coupling effects between controller parameters, a multi-parameter coupling optimization design strategy combining orthogonal experiment method (OEM) and response surface method is proposed. Firstly, the dominant variables of SSO mode of the DFIG-based wind farm connected to weak grid by series compensation system are taken as the initial clustering indexes. After dimension reduction by principal component analysis, the WFCM algorithm is utilized to cluster the wind farm. Then, the proportional and integral coefficients of the grid-side controller, rotor-side controller and phase-locked loop are optimized to achieve the simultaneous optimization of the SSO characteristics and dynamic characteristics of the system. Finally, the interaction between control parameters and the influence degree and trend on the system performance are quantitatively evaluated, and the optimal parameter combination is obtained. The proposed strategy can mitigate SSO more effectively while improving anti-interference than the particle swarm optimization based on OEM.

Implementation of K-Means Algorithm with Clustering Method to Data Management of Covid-19 Case in West Bandung Using Orange Application

Covid-19 cases in Indonesia have not disappeared to the until now. Coronavirus has spread to almost all provinces in Indonesia, one of the province is West Java. There are 27 regencies/cities in West Java that have become the spread of the Covid-19 case, one of which is West Bandung Regency. To make it easier for the regional government of West Bandung Regency to take action in an effort to prevent the spread of Covid-19, research is needed to determine the level of distribution of Covid-19 cases which are divided into 3 clusters, namely high, medium and low clusters. Researchers analyzed using the data mining method with the K-Means Clustering algorithm through the Orange Application. Data processing is started from determining amount of the data to be clustered into 3 high, medium and low, then determining the initial centroid cluster center point (iteration 1) that has been determined randomly, then calculating the distance of each data to the center of the cluster between objects to closest centroid. The distribution of cluster 1, cluster 2, and cluster 3 as many as 16 data in the K-Means Clustering process using the Orange Application. The research results show that there are 8 sub-districts for high clusters, 2 sub-districts for medium clusters and 6 sub-districts for low clusters in West Bandung Regency.

The Fast Detection of Crop Disease Leaves Based on Single-Channel Gravitational Kernel Density Clustering

Plant diseases and pests may seriously affect the yield of crops and even threaten the survival of human beings. The characteristics of plant diseases and insect pests are mainly reflected in the occurrence of lesions on crop leaves. Machine vision disease detection is of great significance for the early detection and prevention of plant diseases and insect pests. A fast detection method for lesions based on a single-channel gravitational kernel density clustering algorithm was designed to examine the complexity and ambiguity of diseased leaf images. Firstly, a polynomial was used to fit the R-channel feature histogram curve of a diseased leaf image in the RGB color space, and then the peak point and peak area of the fitted feature histogram curve were determined according to the derivative attribute. Secondly, the cluster numbers and the initial cluster center of the diseased leaf images were determined according to the peak area and peak point. Thirdly, according to the clustering center of the preliminarily determined diseased leaf images, the single-channel gravity kernel density clustering algorithm in this paper was used to achieve the rapid segmentation of the diseased leaf lesions. Finally, the experimental results showed that our method could segment the lesions quickly and accurately.

Optimization of Linear Quantization for General and Effective Low Bit-Width Network Compression

Current edge devices for neural networks such as FPGA, CPLD, and ASIC can support low bit-width computing to improve the execution latency and energy efficiency, but traditional linear quantization can only maintain the inference accuracy of neural networks at a bit-width above 6 bits. Different from previous studies that address this problem by clipping the outliers, this paper proposes a two-stage quantization method. Before converting the weights into fixed-point numbers, this paper first prunes the network by unstructured pruning and then uses the K-means algorithm to cluster the weights in advance to protect the distribution of the weights. To solve the instability problem of the K-means results, the PSO (particle swarm optimization) algorithm is exploited to obtain the initial cluster centroids. The experimental results on baseline deep networks such as ResNet-50, Inception-v3, and DenseNet-121 show the proposed optimized quantization method can generate a 5-bit network with an accuracy loss of less than 5% and a 4-bit network with only 10% accuracy loss as compared to 8-bit quantization. By quantization and pruning, this method reduces the model bit-width from 32 to 4 and the number of neurons by 80%. Additionally, it can be easily integrated into frameworks such as TensorRt and TensorFlow-Lite for low bit-width network quantization.

KCFS-YOLOv5: A High-Precision Detection Method for Object Detection in Aerial Remote Sensing Images

Aerial remote sensing image object detection, based on deep learning, is of great significance in geological resource exploration, urban traffic management, and military strategic information. To improve intractable problems in aerial remote sensing image, we propose a high-precision object detection method based on YOLOv5 for aerial remote sensing image. The object detection method is called KCFS-YOLOv5. To obtain the appropriate anchor box, we used the K-means++ algorithm to optimize the initial clustering points. To further enhance the feature extraction and fusion ability of the backbone network, we embedded the Coordinate Attention (CA) in the backbone network of YOLOv5 and introduced the Bidirectional Feature Pyramid Network (BiFPN) in the neck network of conventional YOLOv5. To improve the detection precision of tiny objects, we added a new tiny object detection head based on the conventional YOLOv5. To reduce the deviation between the predicted box and the ground truth box, we used the SIoU Loss function. Finally, we fused and adjusted the above improvement points and obtained high-precision detection method: KCFS-YOLOv5. This detection method was evaluated on three datasets (NWPU VHR-10, RSOD, and UCAS-AOD-CAR). The comparative experiment results demonstrate that our KCFS-YOLOv5 has the highest accuracy for the object detection in aerial remote sensing image.

Concept lattice simplification with fuzzy linguistic information based on three-way clustering

Numerous linguistically valued facts from the actual world have been modeled using the fuzzy linguistic approach. Concept lattice theory has the potential to be used in information processing in imprecise language environments as a methodology for data analysis and knowledge representation. The concept lattice with linguistic values can manage fuzzy linguistic data which are either comparable or incomparable. However, the acquired conceptual knowledge is difficult to understand due to the substantial amount of linguistic concept knowledge in the concept lattice with imprecise linguistic information. This work proposes a linguistic-valued layered concept lattice simplification method based on three-way clustering to reduce the scale of the linguistic-valued layered concept lattice. In order to create the linguistically valued layered concept lattice, a reconstruction function is first used to produce an attribute selection model in fuzzy linguistic formal contexts. Second, the intent similarity and extent similarity are employed to achieve the concept similarity measure in linguistic-valued layered concept lattices, taking into account the relationship among various layers of fuzzy linguistic values. To get the initial concept hard clustering results, the linguistic-valued layered concepts are then clustered using k-modes clustering. In addition, we explore the classification of boundary linguistic-valued layered concepts and achieve the three-way clustering findings of linguistic-valued layered concepts to deal with the ambiguity of linguistic expressions. Finally, experimental findings on real-world datasets show how effective the proposed method is for simplifying linguistic-valued layered concept lattices.

Snowmelt detection on the Antarctic ice sheet surface based on XPGR with improved ant colony algorithm

ABSTRACT This study presents an XPGR coupled with an improved ant colony algorithm to automatically detect the Antarctic ice sheet surface snowmelt and acquire high-precision snowmelt information. This approach first enlarges the difference between dry snow and wet snow using the XPGR algorithm and then utilizes an enhanced ant colony algorithm to adaptively find the best threshold for segmenting dry snow and wet snow. The dissimilarity matrix, which determines the initial clustering centre and utilizes Levy flight to modify the clustering radius dynamically, is a major advancement to the ant colony algorithm. The method proposed in this study was compared to the standard XPGR algorithm from October 2017 to February 2018 and from October 2019 to February 2020 to evaluate the practicality and rationale of the proposed method. The further verification of six automatic weather stations (AWS) shows that the method proposed in this study has higher accuracy.

A colour transfer method of interior design based on machine learning

In order to overcome the problems of large colour range, low structure similarity and poor objective evaluation index in the process of interior design colour transfer, this paper proposes a new method of interior design colour transfer based on machine learning. In this method, K-means algorithm is introduced to eliminate the uneven brightness area of the target image. The target image is processed by initial clustering, and the iterative threshold segmentation method is used to obtain the final clustering accurate target image. Combined with machine learning, the corresponding samples are selected on the two images to finish colouring, and the colour transfer of interior design is realised by referring to the coloured sample block. The experimental results show that the colour degree of the proposed method is maintained between 33 and 45, the structural similarity is always above 95%, and the comprehensive objective evaluation index value is close to 100%.

Improved Hybrid Swarm Intelligence for Optimizing the Energy in WSN

In this current century, most industries are moving towards automation, where human intervention is dramatically reduced. This revolution leads to industrial revolution 4.0, which uses the Internet of Things (IoT) and wireless sensor networks (WSN). With its associated applications, this IoT device is used to compute the received WSN data from devices and transfer it to remote locations for assistance. In general, WSNs, the gateways are a long distance from the base station (BS) and are communicated through the gateways nearer to the BS. At the gateway, which is closer to the BS, energy drains faster because of the heavy load, which leads to energy issues around the BS. Since the sensors are battery-operated, either replacement or recharging of those sensor node batteries is not possible after it is deployed to their corresponding areas. In that situation, energy plays a vital role in sensor survival. Concerning reducing the network energy consumption and increasing the network lifetime, this paper proposed an efficient cluster head selection using Improved Social spider Optimization with a Rough Set (ISSRS) and routing path selection to reduce the network load using the Improved Grey wolf optimization (IGWO) approach. (i) Using ISSRS, the initial clusters are formed with the local nodes, and the cluster head is chosen. (ii) Load balancing through routing path selection using IGWO. The simulation results prove that the proposed optimization-based approaches efficiently reduce the energy through load balancing compared to existing systems in terms of energy efficiency, packet delivery ratio, network throughput, and packet loss percentage.