Optimal Feature Vector Research Articles

An effective no-reference image quality index prediction with a hybrid Artificial Intelligence approach for denoised MRI images

As the quantity and significance of digital pictures in the medical industry continue to increase, Image Quality Assessment (IQA) has recently become a prevalent subject in the research community. Due to the wide range of distortions that Magnetic Resonance Images (MRI) can experience and the wide variety of information they contain, No-Reference Image Quality Assessment (NR-IQA) has always been a challenging study issue. In an attempt to address this issue, a novel hybrid Artificial Intelligence (AI) is proposed to analyze NR-IQ in massive MRI data. First, the features from the denoised MRI images are extracted using the gray level run length matrix (GLRLM) and EfficientNet B7 algorithm. Next, the Multi-Objective Reptile Search Algorithm (MRSA) was proposed for optimal feature vector selection. Then, the Self-evolving Deep Belief Fuzzy Neural network (SDBFN) algorithm was proposed for the effective NR-IQ analysis. The implementation of this research is executed using MATLAB software. The simulation results are compared with the various conventional methods in terms of correlation coefficient (PLCC), Root Mean Square Error (RMSE), Spearman Rank Order Correlation Coefficient (SROCC) and Kendall Rank Order Correlation Coefficient (KROCC), and Mean Absolute Error (MAE). In addition, our proposed approach yielded a quality number approximately we achieved significant 20% improvement than existing methods, with the PLCC parameter showing a notable increase compared to current techniques. Moreover, the RMSE number decreased by 12% when compared to existing methods. Graphical representations indicated mean MAE values of 0.02 for MRI knee dataset, 0.09 for MRI brain dataset, and 0.098 for MRI breast dataset, showcasing significantly lower MAE values compared to the baseline models.

StackedEnC-AOP: prediction of antioxidant proteins using transform evolutionary and sequential features based multi-scale vector with stacked ensemble learning

BackgroundAntioxidant proteins are involved in several biological processes and can protect DNA and cells from the damage of free radicals. These proteins regulate the body's oxidative stress and perform a significant role in many antioxidant-based drugs. The current invitro-based medications are costly, time-consuming, and unable to efficiently screen and identify the targeted motif of antioxidant proteins.MethodsIn this model, we proposed an accurate prediction method to discriminate antioxidant proteins namely StackedEnC-AOP. The training sequences are formulation encoded via incorporating a discrete wavelet transform (DWT) into the evolutionary matrix to decompose the PSSM-based images via two levels of DWT to form a Pseudo position-specific scoring matrix (PsePSSM-DWT) based embedded vector. Additionally, the Evolutionary difference formula and composite physiochemical properties methods are also employed to collect the structural and sequential descriptors. Then the combined vector of sequential features, evolutionary descriptors, and physiochemical properties is produced to cover the flaws of individual encoding schemes. To reduce the computational cost of the combined features vector, the optimal features are chosen using Minimum redundancy and maximum relevance (mRMR). The optimal feature vector is trained using a stacking-based ensemble meta-model.ResultsOur developed StackedEnC-AOP method reported a prediction accuracy of 98.40% and an AUC of 0.99 via training sequences. To evaluate model validation, the StackedEnC-AOP training model using an independent set achieved an accuracy of 96.92% and an AUC of 0.98.ConclusionOur proposed StackedEnC-AOP strategy performed significantly better than current computational models with a ~ 5% and ~ 3% improved accuracy via training and independent sets, respectively. The efficacy and consistency of our proposed StackedEnC-AOP make it a valuable tool for data scientists and can execute a key role in research academia and drug design.

An Effective Algorithm Based on Sequence and Property Information for N4-methylcytosine Identification in Multiple Species

Abstract: N4-methylcytosine (4mC) is one of the most important epigenetic modifications, which plays a significant role in biological progress and helps explain biological functions. Although biological experiments can identify potential 4mC sites, they are limited due to the experimental environment and labor-intensive process. Therefore, it is crucial to construct a computational model to identify the 4mC sites. Some computational methods have been proposed to identify the 4mC sites, but some problems should not be ignored, such as those presented as follows: (1) a more accurate algorithm is required to improve the prediction, especially for Matthew’s correlation coefficient (MCC); (2) easier method is needed for clinical research to design medicine or treat disease. Considering these aspects, an effective algorithm using comprehensible encoding in multiple species was proposed in this study. Since nucleotide arrangement and its property information could reflect the sequence structure and function, several feature vectors have been developed based on nucleotide energy information, trinucleotide energy information, and nucleotide chemical property information. Besides, feature effect has been analyzed to select the optimal feature vectors for multiple species. Finally, the optimal feature vectors were inputted into the CatBoost algorithm to construct the identification model. The evaluation results showed that our study obtained the highest MCC, i.e., 2.5%~11.1%, 1.4%~17.8%, 1.1%~7.6%, and 2.3%~18.0% higher than previous models for the A. thaliana, C. elegans, D. melanogaster, and E. coli datasets, respectively. These satisfactory results reflect that the proposed method is available to identify 4mC sites in multiple species, especially for MCC. It could provide a reasonable supplement for biological research.

A Novel Technique for Facial Recognition Based on the GSO-CNN Deep Learning Algorithm

Face recognition is one of the important elements that can be used for securing the facilities, emotion recognition, sentiment exploration, fraud analysis, and traffic pattern analysis. Intelligent face recognition has yielded excellent accuracy in a controlled environment whereas vice versa in an uncontrolled environment. However, conventional methods can no longer satisfy the demand at present due to their low recognition accuracy and restrictions on many occasions. This study proposed an optimal deep learning-based face recognition system that improves the security of the model developed in the IoT cloud environment. Initially, the dataset of images was gathered from the public repository. The captured images are explored using image processing techniques like image preprocessing employing the Gaussian filter technique for removing the noise and smoothing the image. The histogram of oriented gradients (HOGs) is used for the image segmentation. The processed images are preserved at the cloud service layer. Extract features were linked to facial activities using the spatial-temporal interest point (STIP). On the other hand, the extracted feature vectors are investigated using galactic swarm optimization (GSO) techniques that give optimized feature vectors. The necessary features are selected using the gray level co-occurrence matrix (GLCM), which separates the statistical texture features. The GSO output is fed into the deep convolutional neural network (DCNN) that effectively trains the captured face images. This will allow the effectiveness of the GSO-CNN technique to be assessed in terms of recognition accuracy, recall, precision, and error rate.

UsIL-6: An unbalanced learning strategy for identifying IL-6 inducing peptides by undersampling technique

Background and objectiveInterleukin-6 (IL-6) is the critical factor of early warning, monitoring, and prognosis in the inflammatory storm of COVID-19 cases. IL-6 inducing peptides, which can induce cytokine IL-6 production, are very important for the development of diagnosis and immunotherapy. Although the existing methods have some success in predicting IL-6 inducing peptides, there is still room for improvement in the performance of these models in practical application. MethodsIn this study, we proposed UsIL-6, a high-performance bioinformatics tool for identifying IL-6 inducing peptides. First, we extracted five groups of physicochemical properties and sequence structural information from IL-6 inducing peptide sequences, and obtained a 636-dimensional feature vector, we also employed NearMiss3 undersampling method and normalization method StandardScaler to process the data. Then, a 40-dimensional optimal feature vector was obtained by Boruta feature selection method. Finally, we combined this feature vector with extreme randomization tree classifier to build the final model UsIL-6. ResultsThe AUC value of UsIL-6 on the independent test dataset was 0.87, and the BACC value was 0.808, which indicated that UsIL-6 had better performance than the existing methods in IL-6 inducing peptide recognition. ConclusionsThe performance comparison on independent test dataset confirmed that UsIL-6 could achieve the highest performance, best robustness, and most excellent generalization ability. We hope that UsIL-6 will become a valuable method to identify, annotate and characterize new IL-6 inducing peptides.

A novel stacking-based predictor for accurate prediction of antimicrobial peptides

Antimicrobial peptides (AMPs) are gaining acceptance and support as a chief antibiotic substitute since they boost human immunity. They retain a wide range of actions and have a low risk of developing resistance, which are critical properties to the pharmaceutical industry for drug discovery. Antibiotic sensitivity, however, is an issue that affects people all around the world and has the potential to one day lead to an epidemic. As cutting-edge therapeutic agents, AMPs are also expected to cure microbial infections. In order to produce tolerable drugs, it is crucial to understand the significance of the basic architecture of AMPs. Traditional laboratory methods are expensive and time-consuming for AMPs testing and detection. Currently, bioinformatics techniques are being successfully applied to the detection of AMPs. In this study, we have developed a novel STacking-based ensemble learning framework for AntiMicrobial Peptide (STAMP) prediction. First, we constructed 84 different baseline models by using 12 different feature encoding schemes and 7 popular machine learning algorithms. Second, these baseline models were trained and employed to create a new probabilistic feature vector. Finally, based on the feature selection strategy, we determined the optimal probabilistic feature vector, which was further utilized for the construction of our stacked model. Resultantly, the STAMP predictor achieved excellent performance during cross-validation with an accuracy and Matthew’s correlation coefficient of 0.930 and 0.860, respectively. The corresponding metrics during the independent test were 0.710 and 0.464, respectively. Overall, STAMP achieved a more accurate and stable performance than the baseline models and significantly outperformed the existing predictors, demonstrating the effectiveness of our proposed hybrid framework. Furthermore, STAMP is expected to assist community-wide efforts in identifying AMPs and will contribute to the development of novel therapeutic methods and drug-design for immunity. Communicated by Ramaswamy H. Sarma

Improving Performance of Massive Text Real-Time Classification for Document Confidentiality Management

For classified and sensitive electronic documents within the scope of enterprises and organizations, in order to standardize and strengthen the confidentiality management of enterprises and meet the actual needs of secret text classification, a document automatic classification optimization method based on keyword retrieval and the kNN classification algorithm is proposed. The method supports keyword classification management, provides users with keywords of multiple risk levels, and then combines a matching scanning algorithm to label keywords of different levels. The text with labels is used as the training set of the kNN algorithm to classify the target text and realize the classification protection of text data. Aimed at solving the shortcomings of large feature vector dimension, low classification efficiency, and low accuracy in existing kNN text classification methods, an optimization method is proposed using a feature selection algorithm and a kNN algorithm based on an AVX instruction set to realize real-time classification of massive texts. By constructing a keyword dictionary and an optimized feature vector, parallel calculation of the feature vector weight and distance vector is realized, and the accuracy and efficiency of text classification are improved. The experimental results show that the multi-classification effect of the feature selection algorithm used in this paper, tf-DE, is better than that of the traditional tf-idf algorithm, and the classification effect of kNN is comparable to that of the support vector machine (SVM) algorithm. With the increase in feature vector dimensions, the classification effect of the text classification algorithm is improved and the classification time also increases linearly. The AVX-256 acceleration method takes about 55% of the time of the original version, thus verifying the effect of multi-classification of massive texts for document confidentiality management.

An integrated exploration of heat kernel invariant feature and manifolding technique for 3D object recognition system

Spectral Graph theory has been utilized frequently in the field of Computer Vision and Pattern Recognition to address challenges in the field of Image Segmentation and Image Classification. In the proposed method, for classification techniques, the associated graph's Eigen values and Eigen vectors of the adjacency matrix or Laplacian matrix created from the images are employed. The Laplacian spectrum and a graph's heat kernel are inextricably linked. Exponentiating the Laplacian eigensystem over time yields the heat kernel, which is the solution to the heat equations. In the proposed technique K-Nearest neighborhood and Delaunay triangulation techniques are used to generate a graph from the 3D model. The graph is then represented into Normalized Laplacian (NL) and Laplacian matrix (L). From each Normalized Laplacian and Laplacian matrix, the feature vectors like Heat Content Invariant and Laplacian Eigen values are extracted. Then, using all of the available clustering algorithms on datasets, the optimum feature vector for clustering is determined. For clustering various manifolding techniques are employed. In the suggested method, the graph heat kernel is constructed using industry-standard objects which are taken from the Engineering bench mark Data set.

Developed A Hybrid Optimal Feature Vector Selection with Blockchain Technology for Smart Healthcare 4.0

The health economy has been an innovative technology since time-honored. Preserving and maintaining patient data are essential in a routine life. Patient’s medical information is very important for every individual not only for patients but also for doctors who are examining them. Advances in sensing technology, processing of data, and communication protocols have transformed the healthcare industry. Patients, physicians, hospitals, and other stakeholder may keep vital data and medical records with the use of electronic healthcare records (EHR). The goal of research should be to develop a Hybrid Optimal Feature Vector Selection with Blockchain Technology (HOFVS-BT) for smart healthcare 4.0 to improve the secure transmission of data which is supported intelligent IoT and medical detection platform possible. For Feature vector selection, proposed an Orthogonal Wolf Optimization (OWO) algorithm. Furthermore, safeguarding private patient details is taken into account by establishing an upgraded Blockchain-based IoT data security solution that not only secures the data, but also fosters trust between patients/users and healthcare service providers.

Hand gesture classification framework leveraging the entropy features from sEMG signals and VMD augmented multi-class SVM

To improve the classification accuracy of hand movements from sEMG signals, this paper puts forward a unified hand gesture classification framework which exploits the potentials of variational mode decomposition (VMD) and multi-class support vector machine (SVM). Acquiring the sEMG signals from 25 intact subjects for ten functional activities in real-time, we implement a non-recursive adaptive decomposition technique to sEMG signals and perform power spectral analysis to identify the dominant narrow-band intrinsic mode functions (IMFs) that contain prominent biomarkers. Subsequently, to compute the optimal feature vectors from a set of entropy measures, this work investigates the performance of two techniques namely minimum redundancy and maximum relevance (MRMR) technique and kernel principal component analysis (kPCA). After extracting the optimal set of entropy features, the proposed approach implements a multi-class SVM based on one-vs-one (OVO) strategy to classify the hand gestures. The performance of the multi-class SVM compared with those of the K-nearest neighbor (KNN) and naïve bayes (NB) classifiers highlight that multi-class SVM offers superior performance with an average classification accuracy of 99.98%. Moreover, for statistical analysis of the experimental results, this work performs Friedman test to analyze the significance of the SVM, KNN and NB classifier performances. Finally, the performance comparison of the proposed approach with those of the state-of-the-art techniques highlights the superiority of the proposed framework to improve the hand gesture classification accuracy.

An intelligent deep neural network with Opposition based Laplacian Equilibrium Optimizer to improve feature extraction using ECG signals

ProblemThe leading cause of death in the world is cardiovascular disease (CVD). It is required to detect, prevent and manage cardiovascular diseases to reduce their effect and improve the outcome. Interpretation of ECG signals may vary from one expert to another. That’s why an automatic categorization of ECG recordings is needed. AimThe proposed study attempted to address the above issues by developing an automated method for predicting arrhythmias based on ECG signal categorization. This method would offer more precise and enhanced interpretation of ECGs while reducing small biases brought on by manual interpretation. MethodsIn this paper, a unique deep learning-based algorithm is used to efficiently and swiftly classify cardiac arrhythmias. We have used Discrete Wavelet Transformation (DWT) to appropriately classify ECG data into important arrhythmia categories during the pre-processing stage by removing intrinsic noise from ECG signals. To obtain optimal placement (equilibrium state) for better search space diversification, OB-L-EO uses Laplace distribution followed by opposition-based modelling to modify the intensity of search agents. A powerful type of machine learning technique called deep neural network (DNN) is used to accomplish signal categorization among sixteen categories using the MIT-BIH Arrhythmia ECG dataset. ResultsWith the help of analysing classification technique including optimized feature vector and the OBLEO method with DNN, the heart rate has been detected with a 98.779% accuracy, 98.67% sensitivity, 98.87% specificity and execution time with a value of 1.34 ms across the entire dataset. The application of 10-fold cross validation provides the better accuracy i.e 99.79%. ConclusionThe achieved performance parameters have demonstrated that the suggested ECG signal classification model is capable of categorizing arrhythmia classes appropriately using ECG signals.

TIPred: a novel stacked ensemble approach for the accelerated discovery of tyrosinase inhibitory peptides

BackgroundTyrosinase is an enzyme involved in melanin production in the skin. Several hyperpigmentation disorders involve the overproduction of melanin and instability of tyrosinase activity resulting in darker, discolored patches on the skin. Therefore, discovering tyrosinase inhibitory peptides (TIPs) is of great significance for basic research and clinical treatments. However, the identification of TIPs using experimental methods is generally cost-ineffective and time-consuming.ResultsHerein, a stacked ensemble learning approach, called TIPred, is proposed for the accurate and quick identification of TIPs by using sequence information. TIPred explored a comprehensive set of various baseline models derived from well-known machine learning (ML) algorithms and heterogeneous feature encoding schemes from multiple perspectives, such as chemical structure properties, physicochemical properties, and composition information. Subsequently, 130 baseline models were trained and optimized to create new probabilistic features. Finally, the feature selection approach was utilized to determine the optimal feature vector for developing TIPred. Both tenfold cross-validation and independent test methods were employed to assess the predictive capability of TIPred by using the stacking strategy. Experimental results showed that TIPred significantly outperformed the state-of-the-art method in terms of the independent test, with an accuracy of 0.923, MCC of 0.757 and an AUC of 0.977.ConclusionsThe proposed TIPred approach could be a valuable tool for rapidly discovering novel TIPs and effectively identifying potential TIP candidates for follow-up experimental validation. Moreover, an online webserver of TIPred is publicly available at http://pmlabstack.pythonanywhere.com/TIPred.

WCGAN-GP based synthetic attack data generation with GA based feature selection for IDS

Cyber-attack is one of the alarming issues in today's era. Firewalls, Intrusion Detection Systems (IDSs), and other techniques are popularly applied to prevent those attacks. Intrusion Detection System (IDS) works as the watchdog to monitor the network traffic and identify an alert when an unauthorized action is detected. However, most IDSs are designed on traditional datasets, which do not address the data imbalance problem. As a result, their performance is not good enough against minority class samples. In order to overcome the aforementioned problem and detect cyber-attacks with higher precision, this paper proposes a novel IDS applying Wasserstein Conditional Generative Adversarial Network – Gradient Penalty (WCGAN-GP) and Genetic Algorithm (GA). The objective of the two components- WCGAN-GP and Genetic Algorithm are introduced in the proposed work for synthetic data generation, feature optimization, and attack detection system. The proposed model generates synthetic samples that follow the underlying data distribution of actual data. This paper uses a novel fitness function for the convergence of the Genetic algorithm and produces an optimal feature vector for the classification problem. In this work, an extensive experimental study applying NSL-KDD and UNSW-NB15 datasets in combination with generated samples and reduced feature set from the proposed model is carried out to evaluate the performance of different machine learning models. Observations show that Xgboost gives the best performances among others. To justify using a genetic algorithm for feature optimization, this paper has compared the proposed model with other traditional feature selection approaches such as PCA, Autoencoder, and T-SNE on the proposed model. It is found that the proposed GA-based feature selection outperforms others. The reason behind it is that the GA-based feature selection technique offers certain advantages over PCA and Autoencoder-based dimensionality reduction techniques, such as the ability to handle non-linearity between features in the data, enhanced flexibility in feature selection, interpretability, and human insight, handling high-dimensional data, robustness to noise and outliers. It also offers an advantage over T-SNE, a nonlinear dimensionality reduction technique in terms of computational efficiency. Furthermore, the model is also compared with other state-of-the-art which address data imbalance problems. Our proposed model with Xgboost classifier gives better results than other existing approaches in terms of accuracy (95.54%), precision (92.61%), recall (95.54%), F1-score (93.41%), and false alarm rate (4.30%) on the NSL-KDD dataset and accuracy (89.58%), precision (89.46%), recall (89.58%), F1-score (88.89%) and false alarm rate (1.18%) on the UNSW-NB15 dataset.

StackTTCA: a stacking ensemble learning-based framework for accurate and high-throughput identification of tumor T cell antigens

BackgroundThe identification of tumor T cell antigens (TTCAs) is crucial for providing insights into their functional mechanisms and utilizing their potential in anticancer vaccines development. In this context, TTCAs are highly promising. Meanwhile, experimental technologies for discovering and characterizing new TTCAs are expensive and time-consuming. Although many machine learning (ML)-based models have been proposed for identifying new TTCAs, there is still a need to develop a robust model that can achieve higher rates of accuracy and precision.ResultsIn this study, we propose a new stacking ensemble learning-based framework, termed StackTTCA, for accurate and large-scale identification of TTCAs. Firstly, we constructed 156 different baseline models by using 12 different feature encoding schemes and 13 popular ML algorithms. Secondly, these baseline models were trained and employed to create a new probabilistic feature vector. Finally, the optimal probabilistic feature vector was determined based the feature selection strategy and then used for the construction of our stacked model. Comparative benchmarking experiments indicated that StackTTCA clearly outperformed several ML classifiers and the existing methods in terms of the independent test, with an accuracy of 0.932 and Matthew's correlation coefficient of 0.866.ConclusionsIn summary, the proposed stacking ensemble learning-based framework of StackTTCA could help to precisely and rapidly identify true TTCAs for follow-up experimental verification. In addition, we developed an online web server (http://2pmlab.camt.cmu.ac.th/StackTTCA) to maximize user convenience for high-throughput screening of novel TTCAs.

A fault diagnosis method on GWO-SPA and MAE for fault diagnosis of reciprocating compressors

Given the non-stationary and nonlinear features of the reciprocating compressor vibration signal, as well as the problems of end-point effect and modal aliasing existing in the current adaptive decomposition method, the fault diagnosis method for reciprocating compressors based on gray wolf optimization-smoothness priors approach (GWO-SPA) and multiscale attention entropy (MAE) is proposed in this paper. The selection of the regularization parameter λ in the SPA algorithm is studied, and the GWO is introduced to improve the decomposition effect of the SPA method. Then, the entropy value of the MAE is calculated for the detrended term components decomposed by GWO-SPA to describe the fault characteristics quantitatively, and perform PCA dimensionality reduction processing. Finally, the optimized feature vector is input into the SVM. Through the experiments show it is proved that the method proposed can effectively extract the fault state features of reciprocating compressors, and realize the accurate distinction of the fault types of reciprocating compressors.

Analysis and classification of arrhythmia types using improved firefly optimization algorithm and autoencoder model

In the present scenario, Electrocardiogram (ECG) is an effective non-invasive clinical tool, which reveals the functionality and rhythm of the heart. The non-stationary nature of ECG signal, noise existence, and heartbeat abnormality makes it difficult for clinicians to diagnose arrhythmia. The most of the existing models concentrate only on classification accuracy. In this manuscript, an automated model is introduced that concentrates on arrhythmia type classification using ECG signals, and also focuses on computational complexity and time. After collecting the signals from the MIT-BIH database, the signal transformation and decomposition are performed by Multiscale Local Polynomial Transform (MLPT) and Ensemble Empirical Mode Decomposition (EEMD). The decomposed ECG signals are given to the feature extraction phase for extracting features. The feature extraction phase includes six techniques: standard deviation, zero crossing rate, mean curve length, Hjorth parameters, mean Teager energy, and log energy entropy. Next, the feature dimensionality reduction and arrhythmia classification are performed utilizing the improved Firefly Optimization Algorithm and autoencoder. The selection of optimal feature vectors by the improved Firefly Optimization Algorithm reduces the computational complexity to linear and consumes computational time of 18.23 seconds. The improved Firefly Optimization Algorithm and autoencoder model achieved 98.96% of accuracy in the arrhythmia type classification, which is higher than the comparative models.

Zebra Crossing Detection Using Concatenation of SIFT-Gabor Features

Abstract: Zebra-crossing recognition is a challenging activity for visually impaired navigating safely. This paper proposes a zebra-crossing scene recognition model-based fusion of texture features and geometrical features. The Gabor features for 8 orientations are extracted for different orientations Zebra Crossing lines. The SIFT is employed for keypoint detection and description. The final features vector is obtained by concatenating Gabor and SIFT features. The feature vector is optimized using K-means clustering and Principle Component Analysis (PCA). The optimized feature vectors were classified using five Classifiers, SVM, Random Forest, Decision Tree, Naïve Bayes Classifiers. The proposed model successfully recognizes the crosswalks with 89% accuracy. The different classifier models are evaluated for Precision, Accuracy, F1 Score, Recall, and RoC. This paper specifies the classification of two class positive which is zebra-crossing and negative which is no zebra-crossing. The designed system will classify either the crosswalk is detected or not on the basis of percentage specified for each class. This can be done by matching the features of the trained dataset. Those features are matched with the real videos or images to recognize the motion and classify into specific class. More specific crosswalk detection in real time can be executed to get more specific type of positive and negative class and classification.

A Hybrid Technique for Diabetic Retinopathy Detection Based on Ensemble-Optimized CNN and Texture Features.

One of the most prevalent chronic conditions that can result in permanent vision loss is diabetic retinopathy (DR). Diabetic retinopathy occurs in five stages: no DR, and mild, moderate, severe, and proliferative DR. The early detection of DR is essential for preventing vision loss in diabetic patients. In this paper, we propose a method for the detection and classification of DR stages to determine whether patients are in any of the non-proliferative stages or in the proliferative stage. The hybrid approach based on image preprocessing and ensemble features is the foundation of the proposed classification method. We created a convolutional neural network (CNN) model from scratch for this study. Combining Local Binary Patterns (LBP) and deep learning features resulted in the creation of the ensemble features vector, which was then optimized using the Binary Dragonfly Algorithm (BDA) and the Sine Cosine Algorithm (SCA). Moreover, this optimized feature vector was fed to the machine learning classifiers. The SVM classifier achieved the highest classification accuracy of 98.85% on a publicly available dataset, i.e., Kaggle EyePACS. Rigorous testing and comparisons with state-of-the-art approaches in the literature indicate the effectiveness of the proposed methodology.

A new iterative initialization of EM algorithm for Gaussian mixture models.

The expectation maximization (EM) algorithm is a common tool for estimating the parameters of Gaussian mixture models (GMM). However, it is highly sensitive to initial value and easily gets trapped in a local optimum. To address these problems, a new iterative method of EM initialization (MRIPEM) is proposed in this paper. It incorporates the ideas of multiple restarts, iterations and clustering. In particular, the mean vector and covariance matrix of sample are calculated as the initial values of the iteration. Then, the optimal feature vector is selected from the candidate feature vectors by the maximum Mahalanobis distance as a new partition vector for clustering. The parameter values are renewed continuously according to the clustering results. To verify the applicability of the MRIPEM, we compared it with other two popular initialization methods on simulated and real datasets, respectively. The comparison results of the three stochastic algorithms indicate that MRIPEM algorithm is comparable in relatively high dimensions and high overlaps and significantly better in low dimensions and low overlaps.

The amalgamation of wavelet packet information gain entropy tuned source and system parameters for improved speech emotion recognition

This paper proposes a three-stage feature selection algorithm by exploring the wavelet packet (WP) decomposition, statistical, and Information Gain (IG) feature ranking algorithm based on high IG entropy for the automatic classification of speech emotions (SE). Effective frame-level vocal tract systems and the excitation source parameters are initially extracted from a few significant WP sub-bands containing emotionally relevant information based on Eigenvalue decomposition. Further, Several intelligent amalgamations of the derived optimal feature vectors are formed for improved performance in a low-dimensional feature space. The fundamental argument is that in case the identification errors of any system subjected to individual feature streams transpire at separate points, there exists a probability that the inclusion of complementary information can nullify a few of these inaccuracies by increasing the available information. The models of the Cost-Sensitive-Decision Tree (CS-DT), Support Vector Machine (SVM), and Decision Tree (DT) have been validated and tested with the proposed setup for their efficacy. Results indicate the superiority of the proposed algorithms compared to other published articles cited in the literature with the CS-DT outperforming others. The proposed low-dimensional amalgamation vectors have witnessed more than 20% improvement in recognition performance with greater speed of response, savings in cost, and lower F- rank hence is a significant achievement in this direction.The link to compute the Hurst parameter for the feature amalgamation is available at (https://www.mathworks.com/matlabcentral/fileexchange/9842-hurst-exponent).