Means Clustering Algorithm Research Articles

A V2X-Integrated Positioning Methodology in Ultradense Networks

Intelligent transport systems demand the provision of a continuous high-accuracy positioning service. However, a vehicle positioning system typically has to operate in dense urban areas where conventional satellite-based positioning systems suffer severe performance degradation. 5G technology presents a new paradigm to provide ubiquitous connectivity, where the vehicle-to-everything (V2X) communication turns out to be highly conducive to enable both accurate positioning and the emerging Internet of Vehicles (IoV). Due to the high probability of Line-of-Sight (LoS) communication, as well as the diversity and number of reference stations, the application of ultradense networks (UDN) in the vehicle-to-infrastructure (V2I) subsystem is envisaged to complement the existing positioning technologies. Moreover, the cooperative determination of location information could be enhanced by the vehicle-to-vehicle (V2V) subsystem. In this article, we propose a V2X-integrated positioning methodology in UDN, in which the V2I, V2V, and inertial navigation systems (INSs) are unified for data fusion. This formulation is an iterative high-dimensional estimation problem, and an efficient multiple particle filter (MPF)-based method is proposed for solving it. In order to mitigate the non-LoS (NLoS) impact and provide a relatively accurate input to the MPF, we introduce an advanced anchor selection method using the geometry-based <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means clustering (GK) algorithm based on the characteristics of network densification. Numerical results demonstrate that utilizing the GK algorithm in the proposed integrated positioning system could achieve 18.7% performance gains in accuracy, as compared with a state-of-the-art approach.

An integrated optimization approach using a collaborative strategy for sustainable cities freight transportation: A Case study

• Logistics collaboration is studied in the planning of sustainable city freight transportation. • An integrated and collaborative approach is proposed for sustainable freight logistics networks. • Three sustainability dimensions are considered. • A case study is conducted to show the applicability of proposed approach and the effects of collaboration on the sustainable development of the society and the environment. In recent years, the increasing freight transportation activities has caused extensive economic, environmental and social impacts on society. Therefore, it becomes necessary for logistics companies to find high-performance strategies to enhance their sustainability. Collaboration between companies appears as one of the promising solution that improves the freight transport efficiency of modern cities. Existing studies on collaborative transport did not sufficiently account for sustainability aspects and they mainly discuss the independent planning of decision-making problems with economic objectives. However, collaboration an integrated decision-making process can significantly ameliorate the effectiveness of urban transportation systems. This study addresses the issue of sustainable freight transportation planning by formulating and solving a collaborative and integrated two-echelon inventory, location and routing problem (2E-CILRP). The 2E-CILRP is formulated as a multi-objective integer programming model that minimizes logistics costs, C O 2 emissions and accident rate. A hybrid heuristic based on machine learning is also introduced to solve the studied problem. The proposed approach combines k -means clustering and genetic algorithms. Comparison of the obtained results with those provided with exact method reveals that the developed approach is more efficient and more practical for designing integrated and collaborative networks with large-sized data. A case study of four agri-food SMEs in France is investigated in order to demonstrate the sustainable benefits of the developed optimization approach. The obtained results suggest that the developed approach can significantly reduce the level of C O 2 emissions, logistics costs and accident rate caused by transportation in cities.

Unsupervised Deep Learning for Road Crack Classification by Fusing Convolutional Neural Network and K_Means Clustering

Pavement crack detection, classification, and characterization are key components of automatic pavement monitoring systems. Most of the currently acceptable methods used for these purposes are less satisfactory, which resulted in the fact that manual condition surveys are still adopted by many departments, considering the overall cost of pavement assessment. Moreover, current advanced deep learning-based road crack classification approaches are primarily supervised methods, which reduced the efficiency and hindered the intelligent aspects of the methods. Considering these problems, this research conducted edge-cutting work in proposing unsupervised deep learning methods for pavement crack classification. The proposed method fused convolution neural network architecture with the K_means clustering algorithm to achieve unsupervised feature learning. Considering the simplicity aspect of the model, AlexNet is selected as the base CNN model to build the fused architecture. The constructed crack classification model was trained and tested on road crack images collected by both automatic vehicles and smartphones, which showed satisfactory performance. Meanwhile, comparative experiments of transverse, longitudinal, and alligator crack classification are conducted between the proposed method and traditional unsupervised method, which proved the superiority of the proposed method (average accuracies for transverse, longitudinal, and alligator are 0.806, 0.792, and 0.913, respectively).

Robust RSSI-Based Indoor Positioning System Using K-Means Clustering and Bayesian Estimation

This work proposes a new indoor positioning system, named KLIP, that uses the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${K}$ </tex-math></inline-formula> -means clustering algorithm to split the environment into different sets of log-distance propagation models in order to better characterize the indoor environment and further improve the position estimation using Bayesian inference. Our proposed method is validated in a large-scale, real-world scenario composed of Bluetooth Low Energy (BLE)-based devices. We demonstrate, throughout the paper, that the addition of location information of training points to the received signal strength indicator (RSSI) as an attribute for the clustering step improves the positioning accuracy. Moreover, the obtained results show that our solution outperforms the naive Bayesian estimation up to 12% – regarding the positioning accuracy – and the broadly deployed <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula> NN for reduced training dataset size – regarding both accuracy and online processing time. In this sense, KLIP proves to be an efficient and scalable alternative when both site-survey effort and energy consumption constraints must be taken into account.

Regression Analysis of Factors Based on Cluster Analysis of Acute Radiation Pneumonia due to Radiation Therapy for Lung Cancer.

We conducted in this paper a regression analysis of factors associated with acute radiation pneumonia due to radiation therapy for lung cancer utilizing cluster analysis to explore the predictive effects of clinical and dosimetry factors on grade ≥2 radiation pneumonia due to radiation therapy for lung cancer and to further refine the effect of the ratio of the volume of the primary foci to the volume of the lung lobes in which they are located on radiation pneumonia, to refine the factors that are clinically effective in predicting the occurrence of grade ≥2 radiation pneumonia. This will provide a basis for better guiding lung cancer radiation therapy, reducing the occurrence of grade ≥2 radiation pneumonia, and improving the safety of radiotherapy. Based on the characteristics of the selected surveillance data, the experimental simulation of the factors of acute radiation pneumonia due to lung cancer radiation therapy was performed based on three signal detection methods using fuzzy mean clustering algorithm with drug names as the target and adverse drug reactions as the characteristics, and the drugs were classified into three categories. The method was then designed and used to determine the classification correctness evaluation function as the best signal detection method. The factor classification and risk feature identification of acute radiation pneumonia due to radiation therapy for lung cancer based on ADR were achieved by using cluster analysis and feature extraction techniques, which provided a referenceable method for establishing the factor classification mechanism of acute radiation pneumonia due to radiation therapy for lung cancer and a new idea for reuse of ADR surveillance report data resources.

Apriori association rule and K-means clustering algorithms for interpretation of pre-event landslide areas and landslide inventory mapping

Abstract In this paper, an inventory of the landslide that occurred in Karahacılı at the end of 2019 was created and the pre-landslide conditions of the region were evaluated with traditional statistical and spatial data mining methods. The current orthophoto of the region was created by unmanned aerial vehicle (UAV). In this way, the landslide areas in the region were easily determined. According to this, it was determined that the areas affected by the landslides had an average slide of 26.56 m horizontally. The relationships among the topographic, hydrographic, and vegetative factors of the region were revealed using the Apriori algorithm. It was determined that the areas with low vegetation in the study area with 55% confidence were of a Strong Slope feature from the Apriori algorithm. In addition, the cluster distributions formed by these factors were determined by K-means. Among the five clusters created with K-means, it was determined that the study area was 38% in the southeast, had a Strong Slope, Low Vegetation, Non-Stream Line, and a slope less than 140 m. K-means results of the study were made with performance metrics. Average accuracy, recall, specificity, precision, and F-1 score were found as 0.77, 0.69, 0.84, and 0.73 respectively.

Assessment of impervious surface in border area using multi-index from landsat 8 and fuzzy c means

This paper describes the process to generate an impervious surface map from Landsat 8 multi-index, namely urban index (UI), normalized difference built-up index (NDBI), normalized difference vegetation index (NDVI), and land surface temperature (LST). These multi-index and LST were input into fuzzy c means (FCM) clustering algorithm to create four fuzzy raster maps, namely high UI, high NDBI, low NDVI, and high LST. The output from FCM served as input for the fuzzy overlay method (FOM) resulted in impervious surface and non-impervious surface classes in the form of a raster map with 30 m x 30 m spatial resolution. The western border between Bogor Municipality and Bogor Regency is chosen as a study area because of data imbalance in both municipal authorities to delineate urban regions in conventional methods. Therefore FCM and FOM were applied to tackle the uncertainty might come from data imbalance and serve as time-saver methods to map impervious surface. The final impervious surface map yielded from the aforementioned methods, shows 82% overall accuracy. Results show that the impervious surface area in Bogor Municipality western border side is around 11.33 km2 (66.45%), while the impervious surface area in Bogor Regency border side is around 14.35 km2 (62.2%).

ANALYSIS OF THE APPLICABILITY CRITERION FOR K MEANS CLUSTERING ALGORITHM RUN TEN NUMBER OF TIMES ON THE FIRST 25 NUMBERS OF THE FIBONACCI SERIES

In this research investigation Analysis Of The Applicability Criterion For K Means Clustering Algorithm Run Ten Number Of Times On The First 25 Numbers Of The Fibonacci Series is performed. For this analysis RCB Model Of Applicability Criterion For K Means Clustering Algorithm is used. K-means is one of the simplest unsupervised learning algorithms that solve the well-known clustering problem. K- Means clustering algorithm is a scheme for clustering continuous and numeric data. As K-Means algorithm consists of scheme of random initialization of centroids, every time it is run, it gives different or slightly different results because it may reach some local optima. Quantification of such aforementioned variation is of some importance as this sheds light on the nature of the Discrete K-Means Objective function with regards its maxima and minima. The K-Means Clustering algorithm aims at minimizing the aforementioned Objective function. The RCB Model Of Applicability Criterion for K-Means Clustering aims at telling us if we can use the K-Means Clustering Algorithm on a given set of data within acceptable variation limits of the results of the K-Means Clustering Algorithm when it is run several times. KEY WORDS: K-means clustering algorithm, RCB model and Cluster evaluation.

Clinical Study of Virtual Reality Augmented Technology Combined with Contrast-Enhanced Ultrasound in the Assessment of Thyroid Cancer.

Thyroid cancer has become the most common malignant tumor in the endocrine system, and its global incidence has been showing an upward trend. The diagnosis methods of thyroid cancer include ultrasound, fine-needle aspiration cytology, and neck CT, but the single ultrasound feature cannot simultaneously take into account the sensitivity and specificity of more than 85% when diagnosing thyroid cancer. The development of virtual technology can significantly improve the diagnosis of the thyroid gland. Based on this, this article proposes a clinical study of virtual reality technology combined with contrast-enhanced ultrasound in the assessment of thyroid cancer. This article uses a variety of methods, such as literature method, mathematical statistics, and experimental research, in-depth study of the theoretical cornerstones of virtual reality augmented technology, the application status of ultrasound contrast technology, and so on. And a fuzzy mean clustering algorithm was proposed to identify ultrasound images. Then, a clinical experiment of virtual reality augmented technology combined with contrast-enhanced ultrasound was designed to evaluate thyroid cancer, which included comparison of contrast-enhanced ultrasound signs, analysis of enhancement results, multifactor logistic analysis, and diagnostic efficacy analysis of ultrasound signs. The combined application of virtual reality augmented technology and contrast-enhanced ultrasound in the study of thyroid cancer has a sensitivity and specificity exceeding 85% as the diagnosis boundary changes, and the accuracy of the combined diagnosis is relatively high.

A colour-based image segmentation method for the measurement of masticatory performance in older adults

Masticatory efficiency in older adults is an important parameter for the assessment of their oral health and quality of life. This study presents a measurement method based on the automatic segmentation of two-coloured chewing gum based on a &lt;em&gt;K&lt;/em&gt;-means clustering algorithm. The solution proposed aims to quantify the mixed areas of colour in order to evaluate masticatory performance in different dental conditions. The samples were provided by ‘two-colour mixing’ tests, currently the most used technique for the evaluation of masticatory efficacy, because of its simplicity, low acquisition times and reduced cost. The image analysis results demonstrated a high discriminative power, providing results in an automatic manner and reducing errors caused by manual segmentation. This approach thus provides a feasible and robust solution for the segmentation of chewed samples. Validation was carried out by means of a reference software, demonstrating a good correlation (&lt;em&gt;R&lt;/em&gt;&lt;sup&gt;2 &lt;/sup&gt;= 0.64) and the higher sensitivity of the proposed method (+75 %). Tests on patients with different oral conditions demonstrated that the &lt;em&gt;K&lt;/em&gt;-means segmentation method enabled the automatic classification of patients with different masticatory conditions, providing results in a shorter time period (20 chewing cycles instead of 50).

An Edge Computing Node Deployment Method Based on Improved k-Means Clustering Algorithm for Smart Manufacturing

With the rapid development of the mobile Internet, Industrial Internet of Things, cyber-physical systems, and the emergence of edge computing has provided an opportunity to realize the high computing performance and low latency of intelligent devices in the smart manufacturing environment. In this paper, we propose and verify an edge computing node deployment method for smart manufacturing. First, the architecture of a smart manufacturing system used for implementing the edge computing node deployment methods is presented. Then, comprehensively balancing the network delay and computing resources deployment cost, and considering the influence of device spatial distribution, device function, and computing capacity of edge nodes on the above optimization objectives, the optimal deployment number of edge computing nodes is obtained by using an improved <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -means clustering algorithm. Finally, a prototype platform is developed to verify the proposed method experimentally, and compare the improved <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -means clustering deployment method, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i> -means clustering deployment method, and random deployment method. The proposed method is superior to the other two methods regarding both network delay and computing resources deployment cost. The experimental results show that the proposed edge computing node deployment method can be easily applied to the intelligent manufacturing system; also, the effectiveness and efficiency of this method are verified.

Fusion for Video Enhancement using Fuzzy-C means Clustering Algorithm

Fusion for Video Enhancement using Fuzzy-C means Clustering Algorithm

Automatic feature extraction and detection of plant leaf disease using GLCM features and convolutional neural networks

Agricultural productivity plays a key role in determining the economy of a country. Detection of plant leaf disease is a vital task as it greatly affects the agricultural productivity. If proper detection is not done, it may lead to serious damage in the quality and quantity of the agricultural yield. In this research we propose a novel scheme for the detection of plant leaf diseases using deep convolutional neural networks (DCNN). In the proposed framework, initially, the plant leaf images are preprocessed using filtering and enhancement techniques. In our work, image filtering is done using 2D Adaptive Anisotropic Diffusion Filter (2D AADF) for noise removal. Using these de-noised images, enhancement is done using Adaptive Mean Adjustment (AMA) technique. This step helps to intensify the region of interest in the image. Using the enhanced image, segmentation is performed by means of clustering and thresholding. Clustering is done using the Improved Fast Fuzzy C Means Clustering (IFFCMC) Algorithm and image thresholding is performed using the Adaptive Otsu (AO) thresholding algorithm. From the segmented images, features are extracted using grey level co-occurrence matrix (GLCM). Dimensionality reduction of features is performed using principle component analysis (PCA). Finally, classification is done using a novel DCNN architecture. The proposed architecture has four convolutional layers, two fully connected layers and one SoftMax layer. Experimental results show that the proposed framework is effective and achieves best classification results other classifiers.

Reproducibility of radiomic features using network analysis and its application in Wasserstein k-means clustering.

.Purpose: The goal of this study is to develop innovative methods for identifying radiomic features that are reproducible over varying image acquisition settings.Approach: We propose a regularized partial correlation network to identify reliable and reproducible radiomic features. This approach was tested on two radiomic feature sets generated using two different reconstruction methods on computed tomography (CT) scans from a cohort of 47 lung cancer patients. The largest common network component between the two networks was tested on phantom data consisting of five cancer samples. To further investigate whether radiomic features found can identify phenotypes, we propose a -means clustering algorithm coupled with the optimal mass transport theory. This approach following the regularized partial correlation network analysis was tested on CT scans from 77 head and neck squamous cell carcinoma (HNSCC) patients in the Cancer Imaging Archive (TCIA) and validated using an independent dataset.Results: A set of common radiomic features was found in relatively large network components between the resultant two partial correlation networks resulting from a cohort of lung cancer patients. The reliability and reproducibility of those radiomic features were further validated on phantom data using the Wasserstein distance. Further analysis using the network-based Wasserstein -means algorithm on the TCIA HNSCC data showed that the resulting clusters separate tumor subsites as well as HPV status, and this was validated on an independent dataset.Conclusion: We showed that a network-based analysis enables identifying reproducible radiomic features and use of the selected set of features can enhance clustering results.

Classification Of Gestational Diabetes Using Modified Fuzzy C Means Clustering And Machine Learning Technique

In the recent past, Gestational Diabetes (GD) has become oneof the major health issues in the domain of healthcare. GD is a slow and silent killer that slowly influences the physical body resistance mechanism and fundamental organs. The GD is a harmful threat of health that had occurred during pregnancy of women by affecting metabolism of glucose levelwhich leadsto health issues of pregnancy women and infant, so it is most important of effective and early prediction of GD. In this paper, intelligent diagnosis and prediction of GD is proposed based on processing of various attributes of patient. In the data mining analysis, the Linear Discriminative Analysis (LDA) technique is applied as data normalization process on patients attributes for dimension reduction. The Modified Fuzzy C Means Clustering (MFCM) algorithm is used for clustering data after preprocessing. The enhanced Naive Bayes classifier is applied for classifying various stages of GD of the patient. The experimental results prove that the proposed methodology is efficient and accurate in terms of graphical and numerical representations.

Recognition and Classification of Fetal Brain Abnormalities

In today’s world, not only adults, children, teenage suffer from different diseases but also the yet to be born babies suffer from various abnormalities. We hear many cases that the child was born with some disability and because of the delay in the discovery and operation of the disability, the disability becomes permanent. Out of one thousand, three women are pregnant with abnormal child. If somehow, we detect the abnormality in the child when it is in the fetal stage and operate and medicate according to that then the abnormality can be treated very effectively and efficiently. Our paper deals with the same concept of detecting and classifying the brain abnormalities in the fetus using various deep learning techniques and algorithms. There have been previous works on the same but the technique used by others included machine learning and it had some drawbacks which can be resolved using deep learning techniques. Deep learning has greater efficiency and advantage over machine learning. In our method of detection, we take the help of MRI (Magnetic Resonance Imaging) technique to first capture the brain image of the fetus. Then we perform various preprocessing steps to extract the ROI (Region of Interest). Then we use feature extraction and reduction techniques to obtain more developed and detailed image of the fetus. We compare the image with the normal fetal brain images to classify and detect abnormalities. We make the use of CNN (Convolutional Neural Network) classifier algorithm of the deep learning technique to achieve high level of accuracy. CNN algorithm is better than k means clustering and SVM classifier algorithm of machine learning techniques. Our work has shown higher accuracy than previous models and our future work will involve increasing of classification and data.

Improved Soft-k-Means Clustering Algorithm for Balancing Energy Consumption in Wireless Sensor Networks

Energy load balancing is an essential issue in designing wireless sensor networks (WSNs). Clustering techniques are utilized as energy-efficient methods to balance the network energy and prolong its lifetime. In this article, we propose an improved soft- $k$ -means (IS- $k$ -means) clustering algorithm to balance the energy consumption of nodes in WSNs. First, we use the idea of clustering by fast search and find of density peaks (CFSFDPs) and kernel density estimation (KDE) to improve the selection of the initial cluster centers of the soft $k$ -means clustering algorithm. Then, we utilize the flexibility of the soft- $k$ -means and reassign member nodes considering their membership probabilities at the boundary of clusters to balance the number of nodes per cluster. Furthermore, the concept of multicluster heads is employed to balance the energy consumption within clusters. Extensive simulation results under different network scenarios demonstrate that for small-scale WSNs with single-hop transmission, the proposed algorithm can postpone the first node death, the half of nodes death, and the last node death on average when compared to various clustering algorithms from the literature.

Classification of brain neoplasm from multi-modality MRI with the aid of ANFIS classifier

In medical Image processing, the chief objective is to detect Neoplasm effectively. Neoplasm is basically a sort of abnormal excessive cell growth but when it generates a mass, it is referred as tumors. Brain tumor (BT) is a deadly disease and also it is regarded as a common sort of cancer on adults and even on children. Therefore, early recognition of the correct sort of BT is significant for devising a proper treatment chart and envisioning patients' response to the adopted treatment. Human understanding of countless medical images (Abnormal or Normal) may bring misclassification and thereby there is a requisite of the automated recognition system for classifying the BT types. This paper offers an effective framework for classifying the BT from the multi-modality Magnetic Resonance Images (MRI) by employing ANFIS (Adaptive Neuro-Fuzzy Inference System) classifier. Primarily, the input data-set undertakes the process of skull stripping. Subsequently, the resultant skull striped image undergoes preprocessing utilizing AHE (Adaptive Histogram Equalization). Subsequently, the clustering process is done by employing the Modified-Fuzzy C Means (MFCM) clustering algorithm. From the benign and malignant classes, features are extorted, and then the optimized features are attained utilizing the Adaptive Elephant Herd Optimization (AEHO) algorithm. Finally, the different sorts of BT are effectively classified by implementing the ANFIS classifier. The outcomes are examined and contrasted to the other conventional techniques to corroborate that the proposed work classifies the BT in great efficiency.

Machine learning approach for categorical document mining

The word text mining or document mining means automatic classification of text documents to different categories depending on their content. At present days this area of research is attracting many researchers due to increasing use of electronic documents in everyday life. In this paper authors have proposed a document mining method using Bisecting K-means algorithm, KNN classifier and Decision tree. There are many machine learning classification algorithms used for information retrieval. But most of them have very high computational complexity. So a method Bisecting K – Means clustering algorithm instead of normal K-means algorithm is used here and this approach trivially reduces the number of comparisons compared to others. The researchers also used decision tree at last to obtain the sub categories more accurately. After analysis it is found that the combination of Bisecting K Means and KNN classifier enhance the accuracy of the categorization. Accuracy of this proposed system is shown for each category at Result and discussion section.

A strong reinforcement parallel implementation of k-means algorithm using message passing interface

In Data analysis process clustering is one of the standard methods, which is used in many area such as pattern recognition and image segmentation and statistics, bioinformatics etc. Clustering have several algorithms in that most well know simplest algorithm is K-means, because of its simplicity, empirical success and efficiency. This present reality applications produce tremendous volumes of data, subsequently, how to productively deal with these data in a significant mining task has been a difficult and huge issue. Likewise Message passing Interface (MPI) as a Programming model for increases the scalability, performance and execution speed. Enthused by this, MPI with strong reinforcement parallel K- means clustering algorithm is implemented in this paper. The efficiency of the strong reinforcement K means clustering algorithm is improved in parallel environment by implementing in MPI methodology. In this paper performance of the clustering the data using K- means is compared between sequentially run of K- means algorithm and parallel run of K-means algorithm in Message passing interface architecture in terms of overhead cost and execution.