Sparse Fuzzy C-means Research Articles

Optimized Deep LSTM-Based Multi-Object Tracking with Occlusion Handling Mechanism

The multi-object tracking is a basic computer vision process having a huge class of real-life tools that range from monitoring of medical video to surveillance. The goal of tracking numerous items is to place numerous objects in a scene, handle their identities throughout time, and construct trajectories for analysis. However, this is a complex task, because of certain issues like occlusions, complicated object dynamics, and variations in the appearance of objects. In this research, a new technique named TPRO-based Deep LSTM is developed for tracking multi-object with occlusion handling. Here, the videos are considered as input wherein the extraction of frames is done from each video. Each frame undergoes pre-processing with filtering to eliminate noise from frames. By using a sparse Fuzzy c-Means (FCM) and Local Optimal-Oriented Pattern (LOOP) features, the localization of objects is done. Moreover, the visual and spatial trackings are considered for hybrid tracking. The second derivative model and neighborhood search model are used to perform visual tracking. Then the occlusion handling is performed. Concurrently, with the use of Deep Long Short-Term Memory (Deep LSTM) the spatial tracking is performed and the Taylor Poor Rich Optimization (TPRO) algorithm assigns the weight and bias of the Deep LSTM. The TPRO is obtained by the unification of the Taylor series along with the Poor and Rich Optimization algorithm. By combining visual and spatial tracking, the final tracked output is generated. The devised method achieves a performance with the highest value of 88.9% for Multiple Object Tracking Precision (MOTP), smallest tracking distance (TD) of 4.185, average MOTP of 0.889, average TD of 4.201, and highest tracking number (TN) of 14.

LSTM-QDCNN: long short-term memory and quantum dilated convolutional neural network enabled occlusion percentage prediction

ABSTRACT Occlusion detection is vital in longer video sequences of real-time scenarios, as deformable objects generally occlude themselves or be occluded by exterior objects eventually. Occlusion can affect accuracy of the entire model significantly, because optical flow may reveal random attributes in occluded as well as neighbourhood areas. Occlusion is a challenging issue in real-world visual object tracking. Several techniques learn imprecise appearance of target while it becomes occluded by another object in the scene. Occlusion is a complicated issue that causes target loss in tracking procedure. Here, long short-term memory fused quantum dilated convolutional neural network (LSTM-QDCNN) is presented for occlusion percentage prediction. Initially, video frames are extracted from considered input video. The extracted frame is pre-processed by adaptive fuzzy filtering, and object localisation is accomplished by employing sparse fuzzy c-means with local optimal oriented pattern feature. Thereafter, occlusion category detection is conducted by deep Q-network. Lastly, occlusion percentage prediction is done by utilising LSTM-QDCNN. Additionally, LSTM-QDCNN is designed by merging deep LSTM (DLSTM) with quantum dilated convolutional neural network (QDCNN). Furthermore LSTM-QDCNN achieved maximum multiple-object tracking precision of 0.892 and minimum tracking distance of 3.714. In addition, LSTM-QDCNN achieved tracking number about 18.

MCSO: MANTA CROW SEARCH OPTIMIZATION-ENABLED ACTOR CRITIC NEURAL NETWORK FOR ALZHEIMER CLASSIFICATION USING 3D MRI IMAGES

A form of dementia is Alzheimer’s syndrome, also known as a neurodegenerative syndrome, damages the neuron cells in a selective mode. The count of patients that is increased gradually here by the disease is considered a worldwide concern, which may cause death in more cases. The rapid and accurate detection and categorization of Alzheimer’s disease have obtained enormous awareness from researchers due to the studies of a deep model. However, the productive detection and categorization of Alzheimer’s disease with reliable biomarkers are more challenging tasks. In this paper, Manta crow search optimization (MCSO)-based Actor Critic Neural Network (ACNN) is devised for the Alzheimer classification process. The Region of Interest (ROI) is extracted based on the thresholding process, and the preprocessing is done using the Type 2 Fuzzy and Cuckoo Search (T2FCS) filter. Moreover, the Sparse Fuzzy C-means (Sparse FCM) model has been in employment to segment preprocessed images. The feature extraction is a productive process for classifying Alzheimer’s disease. The ACNN classifier is utilized for performing Alzheimer’s disease classification process. Furthermore, the ACNN classifier is skilled by a devised optimization algorithm named the MCSO model. The projected MCSO-based ACNN outperformed other existing techniques with a testing accuracy of 0.9295, sensitivity of 0.9378, and specificity of 0.9354.

Sparse FCM-Based Map-Reduce Framework for Distributed Parallel Data Clustering in E-Khool Learning Platform

Parallel clustering serves as a platform for handling big data. The literature displays a number of clustering algorithms using a map-reduce framework, but they did not assure the effective clusters such that knowledge extraction becomes tough. With the aim to render a better and effective data clustering method to analyze the big data arriving from distributed systems, this paper uses a new clustering method. The proposed method named as BatDolphin-based Sparse Fuzzy C-Means (BatDol-Sparse FCM) clustering algorithm is proposed that paves way for the optimal selection of the cluster centroids. The distributed big data is managed using the Map-Reduce framework that is inbuilt with the BatDolphin-based Sparse Fuzzy C-Means algorithm such that the local and global clustering is executed. The implementation of the proposed BatDol-Sparse FCM algorithm is done by using data from the E-khool Learning Management System (LMS) and three medical datasets from the UCI repository. The analysis is performed using the metrics, such as clustering accuracy (CA) and dice coefficient (DC). From the simulation results, it is evident that the proposed parallel clustering scheme provided better results than the existing algorithms with the values of 0.96 and 0.9667 for CA and DC respectively.

An effective weather forecasting method using a deep long–short-term memory network based on time-series data with sparse fuzzy c-means clustering

Weather forecasting is the scientific procedure of determining the state of the atmosphere considering both time frames and locations. This article devises a novel magnetic feedback artificial tree algorithm-based deep long–short-term memory (MFATA-based deep LSTM) classifier with time-series data. MFATA is the combination of the magnetic optimization algorithm MOA with the feedback artificial tree FAT algorithm for weather forecasting. Here, the feature selection is processed using a Moth Flame Optimization based Bat (MFO-Bat). Then, based on the clustered result, the forecasting process is accomplished using a deep LSTM classifier. Finally, the Taylor series model is used to generate the final forecast result. The proposed method achieved mean square error, root mean square error, mean absolute scaled error and symmetric mean absolute percentage error values of 4.12, 2.03, 0.602 and 56.376, respectively. The approach developed in this study has the potential to be used as an efficient and reliable weather forecasting method.

TaylorCSROA-based Deep Residual Network: An Optimization driven Deep Network for the multilevel spinal cord disease classification

ABSTRACT Spinal cord is a cylindrical shape located in Central Nervous System (CNS) and extended between the medulla oblongata and lumbar vertebrae. The main task in the classification of multilevel spinal cord disease in Computed Tomography (CT) is the accuracy. In this research, a Taylor Crow Search-Rider Optimization Algorithm (TaylorCSROA) is developed for accurate classification of spinal cord disease. The segmentation is done through the adaptive thresholding method. The Sparse Fuzzy C-Means clustering (Sparse FCM) algorithm is implemented for the localization of disc. The features, like connectivity, Local Optimal-Oriented Pattern (LOOP), statistical, image-level, Grid-based shape features, and tetrolet features are extracted. The spinal cord disease is classified into intervertebral disc (IVD) bulges, the cal sac compressing, bone marrow disease, central or foraminal stenosis, annular tears, scoliosis, end plate degeneration, endplate defects (modic type), facet connection, and ligamentum flavum hypertrophy, and spondylolisthes is by training the Deep Residual Network using the developed TaylorCSROA. The developed TaylorCSROA algorithm derived from the integration of Taylor Series, Crow Search Algorithm (CSA), and the Rider Optimization Algorithm (ROA). When compared with the existing spinal cord disease classification methods, the developed method obtained a maximum accuracy of 0.9102, sensitivity of 0.8945, and specificity of 0.9245.

Performance Analysis and Critical Review on Segmentation Techniques for Brain Tumor Classification

An irregular growth in brain cells causes brain tumors. In recent years, a considerable rate of increment in medical cases regarding brain tumors has been observed, affecting adults and children. However, it is highly curable in recent times only if detected in the early time of tumor growth. Moreover, there are many sophisticated approaches devised by researchers for predicting the tumor regions and their stages. In addition, Magnetic Resonance Imaging (MRI) is utilized commonly by radiologists to evaluate tumors. In this paper, the input image is from a database, and brain tumor segmentation is performed using various segmentation techniques. Here, the comparative analysis is performed by comparing the performance of segmentation approaches, like Hybrid Active Contour (HAC) model, Bayesian Fuzzy Clustering (BFC), Active Contour (AC), Fuzzy C-Means (FCM) clustering technique, Sparse (Sparse FCM), and Black Hole Entropy Fuzzy Clustering (BHEFC) model. Moreover, segmentation technique performance is evaluated with the Dice coefficient, Jaccard coefficient, and segmentation accuracy. The proposed method shows high Dice and Jaccard coefficients of 0.7809 and 0.6456 by varying iteration with the REMBRANDT dataset and a better segmentation accuracy of 0.9789 by changing image size in the Brats-2015 database.

On efficient model selection for sparse hard and fuzzy center-based clustering algorithms

The class of center-based clustering algorithms offers methods to efficiently identify clusters in data sets, making them applicable to larger data sets. While a data set may contain several features, not all of them may be equally informative or helpful towards cluster detection. Therefore, sparse center-based clustering methods offer a way to select only those features that may be useful in identifying the clusters present in a data set. However, to automatically determine the degree to which features should be selected, these methods use the Permutation Method which involves generating and clustering multiple randomly permuted data sets, leading to much higher computation costs. In this paper, we propose an improved approach towards model selection for sparse clustering by using expressions of Bayesian Information Criterion (BIC) derived for the center-based clustering methods of k-Means and Fuzzy c-Means. The derived expressions of BIC require significantly lower computation costs, yet allow us to compare and select a suitable sparse clustering among several possible sparse partitions that may have selected different subsets of features. Experiments on synthetic and real-world data sets show that using BIC for model selection leads to remarkable improvements in the identification of sparse clusterings for both Sparse k-Means and Sparse Fuzzy c-Means.

Object Detection and Localization Using Sparse-FCM and Optimization-driven Deep Convolutional Neural Network

Abstract Object detection and localization attract the researchers to address the challenges associated with the computer vision. The literature presents numerous unsupervised methods to detect and localize the objects, but with inaccuracies and inconsistencies. The problem is tackled through proposing a novel model based on the optimization algorithm. The object in the image is detected using the Sparse Fuzzy C-Means (Sparse FCM) that is the enhanced Fuzzy C-Means algorithm used to manage the high-dimensional data. The detected objects are subjected to the object localization, which is performed using the proposed Cat Crow Optimization (CCO)-based Deep Convolutional Neural Network. The proposed CCO is the integration of Cat Swarm Optimization Algorithm and Crow Search Algorithm and inherits the advantages of both the optimization algorithms. The experimentation of the proposed method is performed using images obtained from the Visual Object Classes Challenge 2012 dataset. The analysis revealed that the proposed method acquired an average accuracy, precision, and recall of 0.8278, 0.8549, and 0.7911, respectively.

Time-shifted Pilot-based Scheduling with Adaptive Optimization for Pilot Contamination Reduction in Massive MIMO

Massive multiple-input multiple-output (MIMO) is considered to be an emerging technique in wireless communication systems, as it offers the ability to boost channel capacity and spectral efficiency. However, a massive MIMO system requires huge base station (BS) antennas to handle users and suffers from inter-cell interference that leads to pilot contamination. To cope with this, time-shifted pilots are devised for avoiding interference between cells, by rearranging the order of transmitting pilots in different cells. In this paper, an adaptive-elephant-based spider monkey optimization (adaptive ESMO) mechanism is employed for time-shifted optimal pilot scheduling in a massive MIMO system. Here, user grouping is performed with the sparse fuzzy c-means (Sparse FCM) algorithm, grouping users based on such parameters as large-scale fading factor, SINR, and user distance. Here, the user grouping approach prevents inappropriate grouping of users, thus enabling effective grouping, even under the worst conditions in which the channel operates. Finally, optimal time-shifted scheduling of the pilot is performed using the proposed adaptive ESMO concept designed by incorporating adaptive tuning parameters. The efficiency of the adaptive ESMO approach is evaluated and reveals superior performance with the highest achievable uplink rate of 43.084 bps/Hz, the highest SINR of 132.9 dB, and maximum throughput of 2.633 Mbps

Injury classification and level detection of the spinal cord based on the optimized recurrent neural network

Abstract Objectives Spinal cord damage is one of the traumatic situations in persons that may cause the loss of sensation and proper functioning of the muscles either temporarily or permanently. Hence, steps to assure the recovery through the early functioning and precaution could safe-guard a proper interceptive. To ensure the recovery of spinal cord damage through optimized recurrent neural network. Methods The research on the spinal cord injury classification and level detection is done using the CT images, which is initially given to the segmentation that is done using the adaptive thresholding methodology. Once the segments are formed, the disc is localized using the sparse fuzzy C-means clustering approach. In the next step, the features are extracted from the localized disc and the features include the connectivity features, statistical features, image-level features, grid-level features, Histogram of Oriented Gradients (HOG), and Linear Gradient Pattern (LGP). Then, the injury detection is done based on the Crow search Rider Optimization algorithm-based Deep Convolutional Neural Network (CS-ROA-based DCNN). Once the result regarding the presence of the injury is obtained, the injury-level classification is done based on the proposed Deep Recurrent Neural Network (Deep RNN), and in case of the absence of injury, the process is terminated. Therefore, the injury detection classifier derives the level of the injury, such as normal, wedge, biconcavity, and crush. Results The experimentation is carried out using an Osteoporotic vertebral fractures database. The performance of the injury level detection based on the proposed model is evaluated based on accuracy, sensitivity, and specificity. The proposed model achieves the maximal accuracy of 0.895, maximal sensitivity of 0.871, and the maximal specificity of 0.933 with respect to K-Fold. Conclusions The experimental results show that the proposed model is better than the existing models in terms of accuracy, sensitivity, and specificity.

User grouping and optimization-based pilot scheduling for mitigating the pilot contamination in massive multi cell MIMO systems

Massive multiple-input multiple-output (massive MIMO) is a promising approach in wireless communication systems for providing improved link reliability and spectral efficiency and it helps several users. The main aim is to solve pilot contamination issue in massive MIMO systems; this research paper utilizes two approaches for reducing the contamination. This paper presents the user grouping approach based on sparse fuzzy C-means clustering (sparse FCM), which groups user parameters based on parameters such as large-scale fading factor, SINR, and user distance. Here, same pilot sequences are assigned to center users in which the impact of pilot contamination is limited, while the algorithm assigns orthogonal pilot sequences to the edge users that suffer severely from pilot contamination. Therefore, the proposed user grouping keeps away from the inappropriate grouping of users, enabling effective grouping even under the worst situations of the channel. Secondly, pilot scheduling is done based on elephant spider monkey optimization (ESMO), which is designed by integrating elephant herding optimization (EHO) into spider monkey optimization (SMO). The performance of pilot scheduling based on grouping-based ESMO is evaluated based on achievable rate and SINR. The proposed method achieves maximal achievable rate of 41.29[Formula: see text]bps/Hz and maximal SINR of 124.31[Formula: see text]dB.

MapReduce framework based big data clustering using fractional integrated sparse fuzzy C means algorithm

Big data analytics gain significant interest over the traditional data-processing methodologies that engage in extracting the hidden patterns and correlations from the massive data, termed as big data. With the aim of relieving the computational complexity the clustering method plays a significant role. With the knowledge of the clustering algorithms, the big data arriving from the distributed sources is processed using the MapReduce framework (MRF). The MRF possesses two functions, namely, map function and reduce function, such that the map function is based on the proposed Fractional Sparse Fuzzy C-Means (FrSparse FCM) algorithm and reduce function is based on particle swarm optimisation-based whale optimisation algorithm (P-Whale). Initially, the optimal centroids are computed using the proposed algorithm in the mapper phase that is optimally tuned in the reducer phase, and it is clear that the proposed FrSparse FCM-based MRF ensures the parallel processing of the big data. Experimentation is performed using the Skin data set and the localisation data set taken from the UCI machine learning repository, and the analysis is progressed using the metrics, such as accuracy and DB Index. The analysis proves that the proposed method acquired a maximum accuracy of 90.6012% and a minimum DB Index of 5.33.

Taylor Bird Swarm Algorithm Based on Deep Belief Network for Heart Disease Diagnosis

Contemporary medicine depends on a huge amount of information contained in medical databases. Thus, the extraction of valuable knowledge, and making scientific decisions for the treatment of disease, has progressively become necessary to attain effective diagnosis. The obtainability of a large amount of medical data leads to the requirement of effective data analysis tools for extracting constructive knowledge. This paper proposes a novel method for heart disease diagnosis. Here, the pre-processing of medical data is done using log-transformation that converts the data to its uniform value range. Then, the feature selection process is performed using sparse fuzzy-c-means (FCM) for selecting significant features to classify medical data. Incorporating sparse FCM for the feature selection process provides more benefits for interpreting the models, as this sparse technique provides important features for detection, and can be utilized for handling high dimensional data. Then, the selected features are given to the deep belief network (DBN), which is trained using the proposed Taylor-based bird swarm algorithm (Taylor-BSA) for detection. Here, the proposed Taylor-BSA is designed by combining the Taylor series and bird swarm algorithm (BSA). The proposed Taylor-BSA–DBN outperformed other methods, with maximal accuracy of 93.4%, maximal sensitivity of 95%, and maximal specificity of 90.3%, respectively.

Sparse-FCM and Deep Convolutional Neural Network for the segmentation and classification of acute lymphoblastic leukaemia.

Leukaemia detection and diagnosis in advance is the trending topic in the medical applications for reducing the death toll of patients with acute lymphoblastic leukaemia (ALL). For the detection of ALL, it is essential to analyse the white blood cells (WBCs) for which the blood smear images are employed. This paper proposes a new technique for the segmentation and classification of the acute lymphoblastic leukaemia. The proposed method of automatic leukaemia detection is based on the Deep Convolutional Neural Network (Deep CNN) that is trained using an optimization algorithm, named Grey wolf-based Jaya Optimization Algorithm (GreyJOA), which is developed using the Grey Wolf Optimizer (GWO) and Jaya Optimization Algorithm (JOA) that improves the global convergence. Initially, the input image is applied to pre-processing and the segmentation is performed using the Sparse Fuzzy C-Means (Sparse FCM) clustering algorithm. Then, the features, such as Local Directional Patterns (LDP) and colour histogram-based features, are extracted from the segments of the pre-processed input image. Finally, the extracted features are applied to the Deep CNN for the classification. The experimentation evaluation of the method using the images of the ALL IDB2 database reveals that the proposed method acquired a maximal accuracy, sensitivity, and specificity of 0.9350, 0.9528, and 0.9389, respectively.

Gaussian hybrid fuzzy clustering and radial basis neural network for automatic brain tumor classification in MRI images

Magnetic Resonance Imaging (MRI) is an emerging research area, employed extensively in radiology for the diagnosis of various neurological diseases. Here, as the classification of MRI gains significant importance for the tumor diagnosis, various techniques are developed in the literature for the automatic classification of MRI images. In this paper, a clustering scheme, namely gaussian hybrid fuzzy clustering (GHFC) is developed by hybridizing the fuzzy c-means (FCM) clustering and sparse FCM along with the Gaussian function for the segmentation purpose. After segmenting the image, the suitable features are extracted from the image and given to the Exponential cuckoo based Radial Basis Neural Network (Exponential cuckoo based RBNN) classifier. The features serve as the training information for the Exponential cuckoo based RBNN classifier, and it finally detects the training class. Simulation of the proposed work is done using BRATS and SIMBRATS databases, and the results are compared with several state-of-art techniques. Simulation results depict that the proposed GHFC along with the RBNN classifier achieved improved accuracy and mean squared error results with the values of 0.8952, and 0.0074, respectively, for the BRATS dataset and 0.8719 and 0.0036, for the SIMBRATS dataset.

Moth-Flame Optimization-Bat Optimization: Map-Reduce Framework for Big Data Clustering Using the Moth-Flame Bat Optimization and Sparse Fuzzy C-Means.

The technical advancements in big data have become popular and most desirable among users for storing, processing, and handling huge data sets. However, clustering using these big data sets has become a major challenge in big data analysis. The conventional clustering algorithms used scalable solutions for managing huge data sets. Thus, this study proposes a technique for big data clustering using the spark architecture. The proposed technique undergoes two steps for clustering the big data, involving feature selection and clustering, performed in the initial cluster nodes of spark architecture. At first, the initial cluster nodes read the big data from various distributed systems, and the optimal features are selected and placed in the feature vector based on the proposed moth-flame optimization-based bat (MFO-Bat) algorithm, which is designed by integrating MFO and Bat algorithms. Then, the selected features are fed to the final cluster nodes of spark, which uses the sparse-fuzzy C-means method for performing optimal clustering. The performance of proposed MFO-Bat outperformed other existing methods with a maximal classification accuracy of 95.806%, Dice coefficient of 99.181%, and Jaccard coefficient of 98.376%, respectively.

Sparse-FCM and deep learning for effective classification of land area in multi-spectral satellite images

Remote sensing plays a major role in crop classification, land use classification, and land cover classification such that the information for the classification is assured with the help of the satellite images. This paper concentrates on the land use classification and proposes an optimization algorithm, called Firefly Harmony Search (FHS) for training the Deep Belief Neural Network (DBN). The FHS algorithm is the integration of the Firefly Algorithm and Harmony Search Algorithm (HSA), which tunes the weights of DBN to perform the multi-class classification. For the effective classification, the multispectral image is subjected to the sparse Fuzzy C-Means to form segments such that the feature extraction is effective, free from dimensionality issues and computational complexities. The features extracted from the segments of the multi-spectral images include vegetation indices and statistical features. Then, these features are fed to the DBN, which is tuned using the FHS algorithm for performing the land use classification. Experimentation using four datasets proves the effectiveness of the proposed multi-class classification approach. The accuracy, sensitivity, and specificity of the method are found to be 0.9317, 0.9568, and 0.0379, respectively, that is effective over the existing land use classification methods.

Stock Market Prediction Using Optimized Deep-ConvLSTM Model.

Stock market prediction acts as a challenging area for the investors for obtaining the profits in the financial markets. A greater number of models used in stock market forecasting is not capable of providing an accurate prediction. This article proposes a stock market prediction system that effectively predicts the state of the stock market. The deep convolutional long short-term memory (Deep-ConvLSTM) model acts as the prediction module, which is trained by using the proposed Rider-based monarch butterfly optimization (Rider-MBO) algorithm. The proposed Rider-MBO algorithm is the integration of rider optimization algorithm (ROA) and MBO. Initially, the data from the live stock market are subjected to the computation of the technical indicators, representing the features from which the necessary features are obtained through clustering by using the Sparse-Fuzzy C-Means (Sparse-FCM) followed with feature selection. The robust features are given to the Deep-ConvLSTM model to perform an accurate prediction. The evaluation is based on the evaluation metrics, such as mean squared error (MSE) and root mean squared error (RMSE), by using six forms of live stock market data. The proposed stock market prediction model acquired a minimal MSE and RMSE of 7.2487 and 2.6923 that shows the effectiveness of the proposed method in stock market prediction.

Unsupervised Learning of Multi-Sense Embedding with Matrix Factorization and Sparse Soft Clustering

In the natural language environment, accurately inferring the meaning of a token according to its context is crucial to understanding a sophisticated expression. However, this is not easy for a machine. The traditional language models used to train distributed word vectors are often restricted by single-sense embedding. In this paper, we develop a model called MSCvec (Multi-sense Soft Clustering Vector) for word sense disambiguation of polysemy in context. We extract the features of individual words by the co-occurrence PPMI (Positive Pointwise Mutual Information) matrix, and decompose the matrix by NMF (Nonnegative Matrix Factorization) into low-rank representations of target words, which are used as the input of an unsupervised sparse soft clustering method called Sparse Fuzzy C-means (SFCM). We use SFCM to determine the global semantic space of words, and partition the subspaces of multiple senses of a polysemous word. We relabel candidate words by the negative average log likelihood, and train multi-sense embedding with extensional vocabulary by the fastText model. Compared with the traditional static embeddings, the result shows that NMF and SFCM design can improve the performance in word similarity and relatedness tasks as well as in text classification tasks of different types of text. Accurate semantic representation of MSCvec would be necessary to produce outstanding results.