Narrow Results

This paper proposes a novel approach to automatic recognition of handprinted Bangla (an Indian script) numerals. A modified Topology Adaptive Self-Organizing Neural Network is proposed to extract a vector skeleton from a binary numeral image. Simple heuristics are considered to prune artifacts, if any, in such a skeletal shape. Certain topological and structural features like loops, junctions, positions of terminal nodes, etc. are used along with a hierarchical tree classifier to classify handwritten numerals into smaller subgroups. Multilayer perceptron (MLP) networks are then employed to uniquely classify the numerals belonging to each subgroup. The system is trained using a sample data set of 1800 numerals and we have obtained 93.26% correct recognition rate and 1.71% rejection on a separate test set of another 7760 samples. In addition, a validation set consisting of 1440 samples has been used to determine the termination of the training algorithm of the MLP networks. The proposed scheme is sufficiently robust with respect to considerable object noise.

A preprocessing stage in every speech/music applications including audio/speech separation, speech/speaker recognition and audio/genre transcription task is inevitable. The importance of such pre-processing stage is originated from the requisite of determining each frame of the given signal is belonged to which classes, namely: speech only, music only or speech/music mixture. Such classification can significantly decrease the computational burden due to exhaustive search commonly introduced as a problem in model-based speech recognition or separation as well as music transcription scenarios. In this paper, we present a new method to separate mixed type audio frames based on support vector machine (SVM) and neural network. We present a feature type selection algorithm which seeks for the most appropriate features to discriminate possible classes (hypotheses) on the mixed signal. We also propose features based on eigen-decomposition on the mixed frame. Experimental results demonstrate that the proposed features together with the selected audio classifiers achieve acceptable classification results. From the experimental results, it is observed that the proposed system outperforms other classification systems including k-nearest neighbor (k-NN) and multi-layer perceptron (MLP).

In this study, the effectiveness of an SPAD-502 portable chlorophyll (Chl) meter was evaluated for estimating the Chl contents in leaves of some medicinal and aromatic plants. To predict the individual chlorophyll concentration indexes of St. John’s wort (Hypericum perforatum L.), mint (Mentha angustifolia L.), melissa (Melissa officinalis L.), thyme (Thymus sp.), and echinacea (Echinacea purpurea L.), models were developed using SPAD value. Multi-layer perceptron (MLP), adaptive neuro fuzzy inference system (ANFIS), and general regression neural network (GRNN) were used for determining the chlorophyll concentration indexes.

Inertial navigation system (INS) is often integrated with satellite navigation systems to achieve the required precision at high-speed applications. In global navigation system (GPS)/INS integration systems, GPS outages are unavoidable and a severe challenge. Moreover, because of the usage of low-cost microelectromechanical sensors (MEMS) with noisy outputs, the INS will get diverged during GPS outages, and that is why navigation precision severely decreases in commercial applications. In this paper, we improve GPS/INS integration system during GPS outages using extended Kalman filter (EKF) and artificial intelligence (AI) together. In this integration algorithm, the AI receives the angular rates and specific forces from the inertial measurement unit (IMU) and velocity from the INS at $t$ and $t-1$. Therefore, the AI has positioning and timing data of the INS. While the GPS signals are available, the output of the AI is compared with the GPS increment; so that the AI is trained. During GPS outages, the AI will practically play the GPS role. Thus, it can prevent the divergence of the GPS/INS integration system in GPS-denied environments. Furthermore, we utilize neural networks (NNs) as an AI module in five different types: multi-layer perceptron (MLP) NN, radial basis function (RBF) NN, wavelet NN, support vector regression (SVR) and adaptive neuro-fuzzy inference system (ANFIS). To evaluate the proposed approach, we utilize a real dataset that has been gathered by a mini-airplane. The results demonstrate that the proposed approach outperforms the INS and GPS/INS integration systems with the EKF during GPS outages. Meanwhile, the ANFIS also reached more than 47.77% precision compared to the traditional method.

Microarray technology has supplied a large volume of data, which changes many problems in biology into the problems of computing. As a result techniques for extracting useful information from the data are developed. In particular, microarray technology has been applied to prediction and diagnosis of cancer, so that it expectedly helps us to exactly predict and diagnose cancer. To precisely classify cancer we have to select genes related to cancer because the genes extracted from microarray have many noises. In this paper, we attempt to explore seven feature selection methods and four classifiers and propose ensemble classifiers in three benchmark datasets to systematically evaluate the performances of the feature selection methods and machine learning classifiers. Three benchmark datasets are leukemia cancer dataset, colon cancer dataset and lymphoma cancer data set. The methods to combine the classifiers are majority voting, weighted voting, and Bayesian approach to improve the performance of classification. Experimental results show that the ensemble with several basis classifiers produces the best recognition rate on the benchmark datasets.

Brain-Computer Interface is an emerging field that focuses on transforming brain data into machine commands. EEG-based BCI is widely used due to the non-invasive nature of Electroencephalogram. Classification of EEG signals is one of the primary components in BCI applications. Steady-State Visually Evoked Potential (SSVEP) paradigms have gained importance because of lesser training time, higher precision, and improved information transfer rate compared to P300 and motor imagery paradigms. In this paper, a novel hybrid Anchoring-based Particle Swarm Optimized Scaled Conjugate Gradient Multi-Layer Perceptron classifier (APS-MLP) is proposed to improve the classification accuracy of SSVEP five classes viz. 6.66, 7.5, 8.57, 10 and 12 Hz, signals. Scaled Conjugate Gradient descent anchors the initial position of Particle Swarm Optimization. The best position, Pbest, of each particle initializes an SCG-MLP, the accuracy of APS-MLP is obtained by averaging the accuracies of each SCG-MLP. The proposed method is compared with standard classifiers namely, k-NN, SVM, LDA and MLP. In which, the proposed algorithm achieves improved training and testing accuracies of 88.69% and 95.4% respectively, which is 12–15% higher than the standard EEG-based BCI classifiers. The proposed algorithm is robust, with a Cohen’s kappa coefficient of 0.96, and will be used in applications such as motion control and improving the quality of life for people with disabilities.

Machine learning (ML) and diffusion magnetic resonance imaging (dMRI) approaches can be employed to identify individual brain aging conditions in both healthy people and patients with brain diseases. This research establishes a new brain age prediction system, which comprises different phases like pre-processing, feature extraction, feature selection, and prediction. The original magnetic resonance imaging (MRI) picture is first carried out in a pre-processing stage, which enhances image quality as well as visual appearances. Following that, the shape, intensity, as well as texture-based characteristics are retrieved. Furthermore, texture features like modified entropy, as well as modified correlation are retrieved along with the traditional features. Then, a modified principle component analysis (PCA) method is utilized for feature selection stage. In the prediction phase, hybrid classifiers such as multi-layer perception (MLP) as well as long short term memory (LSTM) are used. The weight of LSTM and MLP is optimally tuned with the aid of an implemented self-updated red deer algorithm (SURDA) model to make an accurate prediction. Moreover, the suggested work outperforms other traditional works in terms of MSE, MAPE, MSLE, and MAE, correspondingly.

This paper proposes an intelligent classification technique to identify two categories of MRI volume data as normal and abnormal. The manual interpretation of MRI slices based on visual examination by radiologist/physician may lead to incorrect diagnosis when a large number of MRIs are analyzed. In this work, the textural features are extracted from the MR data of patients and these features are used to classify a patient as belonging to normal (healthy brain) or abnormal (tumor brain). The categorization is obtained using various classifiers such as support vector machine (SVM), radial basis function, multilayer perceptron and k-nearest neighbor. The performance of these classifiers are analyzed and a quantitative indication of how better the SVM performance is when compared with other classifiers is presented. In intelligent computer aided health care system, the proposed classification system using SVM classifier can be used to assist the physician for accurate diagnosis.

In IP networks, packets forwarding performance can be improved by adding more nodes and dividing the network into smaller segments. Being able to measure and predict traffic flows to direct to a given segment can be crucial in respecting traffic shaping, scheduling and QoS. This paper proposes to model network packets forwarding performance for optimization and prediction purposes by using multi-layer feed-forward neural network model that uses sigmoid functions to activate the hidden nodes. Gradient descent technique has been considered to optimize and enhance the MLP accuracy. Simulations of MPL neurons training stages pointed out a relative improvement of the forwarding process when network posses a larger density of neurons. Numerical results validated our theoretical analysis and confirmed that to enhance the forwarding process, it is necessary to divide the network into small segments by optimizing resources allocation.

Colonoscopy allows doctors to check the abnormalities in the intestinal tract without any surgical operations. The major problem in the Computer-Aided Diagnosis (CAD) of colonoscopy images is the low illumination condition of the images. This study aims to provide an image enhancement method and feature extraction and classification techniques for detecting polyps in colonoscopy images. We propose a novel image enhancement method with a Pyramid Histogram of Oriented Gradients (PHOG) feature extractor to detect polyps in the colonoscopy images. The approach is evaluated across different classifiers, such as Multi-Layer Perceptron (MLP), Adaboost, Support Vector Machine (SVM), and Random Forest. The proposed method has been trained using the publicly available databases CVC ClinicDB and tested in ETIS Larib and CVC ColonDB. The proposed approach outperformed the existing state-of-the-art methods on both databases. The reliability of the classifiers’ performance was examined by comparing their F1 score, precision, F2 score, recall, and accuracy. PHOG with Random Forest classifier outperformed the existing methods in terms of recall of 97.95%, precision 98.46%, F1 score 98.20%, F2 score of 98.00%, and accuracy of 98.21% in the CVC-ColonDB. In the ETIS-LARIB dataset it attained a recall value of 96.83%, precision 98.65%, F1 score 97.73%, F2 score 98.59%, and accuracy of 97.75%. We observed that the proposed image enhancement method with PHOG feature extraction and the Random Forest classifier will help doctors to evaluate and analyze anomalies from colonoscopy data and make decisions quickly.

The coronavirus or COVID-19 infectious virus is the deadliest and potentially dangerous disease for humans. Radiologists frequently employ medical imaging tools to visualize complex internal structures as well as the functioning of the body. With precise diagnosis, it is possible to identify the infectious COVID-19 virus earlier, especially in an individual having no visible symptoms. For the diagnosis and early detection of the infectious COVID-19 virus, chest X-rays (CXRs) have been utilized which are available at https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database. Applying the gray-level co-occurrence matrix (GLCM) and gray-level run length matrix (GLRLM) feature extraction techniques, the features of the four classes (normal, lung opacity, viral pneumonia, and COVID-19) have been extracted and then classified by utilizing a machine learning (ML) classifier. Six distinct ML classifiers SMO (Sequential Minimal Optimization), Random Tree, MLP (Multi-Layer Perceptron), Linear SVM, Ensemble Classifier (Boosted Tree), and Bayes Net (Bayesian Network) with respective accuracy of 98.85%, 93.19%, 93.35%, 91.5%, 96.4%, and 96.454% are utilized to classify. The classifiers successfully distinguish between normal individuals, viral pneumonia-affected persons, lung opacity individuals, and COVID-19 virus-infected individuals who were considered for the study. These advanced technologies for coronavirus identification may be helpful in areas where access to skilled medical professionals and modern facilities is limited. Hence, as per the analysis, the study may be helpful in disease detection and classification. To classify the virus, radiologists’ second opinion can be quick and accurate in this urgent scenario.

This paper presents a hybrid approach to recognition of handwritten basic characters of Bangla, the official script of Bangladesh and second most popular script of India. This is a 50 class recognition problem and the proposed recognition approach consists of two stages. In the first stage, a shape feature vector computed from two-directional-view-based strokes of an input character image is used by a hidden Markov model (HMM). This HMM defines its states in a data-driven or adaptive approach. The statistical distribution of the shapes of strokes present in the available training database is modelled as a mixture distribution and each component is a state of the present HMM. The confusion matrix of the training set provided by the HMM classifier of the first stage is analyzed and eight smaller groups of Bangla basic characters are identified within which misclassifications are significant. The second stage of the present recognition approach implements a combination of three multilayer perceptron (MLP) classifiers within each of the above groups of characters. Representations of a character image at multiple resolutions based on a wavelet transform are used as inputs to these MLPs. This two stage recognition scheme has been trained and tested on a recently developed large database of representative samples of handwritten Bangla basic characters and obtained 93.19% and 90.42% average recognition accuracies on its training and test sets respectively.