Emmanuel Adetiba

Lung Cancer Prediction Using Neural Network Ensemble with Histogram of Oriented Gradient Genomic Features

This paper reports an experimental comparison of artificial neural network (ANN) and support vector machine (SVM) ensembles and their “nonensemble” variants for lung cancer prediction. These machine learning classifiers were trained to predict lung cancer using samples of patient nucleotides with mutations in the epidermal growth factor receptor, Kirsten rat sarcoma viral oncogene, and tumor suppressor p53 genomes collected as biomarkers from the IGDB.NSCLC corpus. The Voss DNA encoding was used to map the nucleotide sequences of mutated and normal genomes to obtain the equivalent numerical genomic sequences for training the selected classifiers. The histogram of oriented gradient (HOG) and local binary pattern (LBP) state-of-the-art feature extraction schemes were applied to extract representative genomic features from the encoded sequences of nucleotides. The ANN ensemble and HOG best fit the training dataset of this study with an accuracy of 95.90% and mean square error of 0.0159. The result of the ANN ensemble and HOG genomic features is promising for automated screening and early detection of lung cancer. This will hopefully assist pathologists in administering targeted molecular therapy and offering counsel to early stage lung cancer patients and persons in at risk populations.

Improved Classification of Lung Cancer Using Radial Basis Function Neural Network with Affine Transforms of Voss Representation.

Lung cancer is one of the diseases responsible for a large number of cancer related death cases worldwide. The recommended standard for screening and early detection of lung cancer is the low dose computed tomography. However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for screening and early detection of lung cancer. We present computational methods that can be implemented in a functional multi-genomic system for classification, screening and early detection of lung cancer victims. Samples of top ten biomarker genes previously reported to have the highest frequency of lung cancer mutations and sequences of normal biomarker genes were respectively collected from the COSMIC and NCBI databases to validate the computational methods. Experiments were performed based on the combinations of Z-curve and tetrahedron affine transforms, Histogram of Oriented Gradient (HOG), Multilayer perceptron and Gaussian Radial Basis Function (RBF) neural networks to obtain an appropriate combination of computational methods to achieve improved classification of lung cancer biomarker genes. Results show that a combination of affine transforms of Voss representation, HOG genomic features and Gaussian RBF neural network perceptibly improves classification accuracy, specificity and sensitivity of lung cancer biomarker genes as well as achieving low mean square error.

Pixel intensity clustering algorithm for multilevel image segmentation

Image segmentation is an important problem that has received significant attention in the literature. Over the last few decades, a lot of algorithms were developed to solve image segmentation problem; prominent amongst these are the thresholding algorithms. However, the computational time complexity of thresholding exponentially increases with increasing number of desired thresholds. A wealth of alternative algorithms, notably those based on particle swarm optimization and evolutionary metaheuristics, were proposed to tackle the intrinsic challenges of thresholding. In codicil, clustering based algorithms were developed as multidimensional extensions of thresholding. While these algorithms have demonstrated successful results for fewer thresholds, their computational costs for a large number of thresholds are still a limiting factor. We propose a new clustering algorithm based on linear partitioning of the pixel intensity set and between-cluster variance criterion function for multilevel image segmentation. The results of testing the proposed algorithm on real images from Berkeley Segmentation Dataset and Benchmark show that the algorithm is comparable with state-of-the-art multilevel segmentation algorithms and consistently produces high quality results. The attractive properties of the algorithm are its simplicity, generalization to a large number of clusters, and computational cost effectiveness.

Optimal Model for Path Loss Predictions using Feed-Forward Neural Networks

Abstract In this paper, an optimal model is developed for path loss predictions using the Feed-Forward Neural Network (FFNN) algorithm. Drive test measurements were carried out in Canaanland Ota, Nigeria and Ilorin, Nigeria to obtain path loss data at varying distances from 11 different 1,800 MHz base station transmitters. Single-layered FFNNs were trained with normalized terrain profile data (longitude, latitude, elevation, altitude, clutter height) and normalized distances to produce the corresponding path loss values based on the Levenberg–Marquardt algorithm. The number of neurons in the hidden layer was varied (1–50) to determine the Artificial Neural Network (ANN) model with the best prediction accuracy. The performance of the ANN models was evaluated based on different metrics: Mean Absolute error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), standard deviation, and regression coefficient (R). Results of the machine learning processes show that the FNN architecture adopting a tangent activation function and 48 hidden neurons produced the least prediction error, with MAE, MSE, RMSE, standard deviation, and R values of 4.21 dB, 30.99 dB, 5.56 dB, 5.56 dB, and 0.89, respectively. Regarding generalization ability, the predictions of the optimal ANN model yielded MAE, MSE, RMSE, standard deviation, and R values of 4.74 dB, 39.38 dB, 6.27 dB, 6.27 dB, and 0.86, respectively, when tested with new data not previously included in the training process. Compared to the Hata, COST 231, ECC-33, and Egli models, the developed ANN model performed better in terms of prediction accuracy and generalization ability.

Identification of Pathogenic Viruses Using Genomic Cepstral Coefficients with Radial Basis Function Neural Network

Human populations are constantly inundated with viruses, some of which are responsible for various deadly diseases. Molecular biology approaches have been employed extensively to identify pathogenic viruses despite the limitations of the approaches. Nevertheless, recent advances in the next generation sequencing technologies have led to a surge in viral genome sequence databases with potentials for Bioinformatics based virus identification. In this study, we have utilised the Gaussian radial basis function neural network to identify pathogenic viruses. To validate the neural network model, samples of sequences of four different pathogenic viruses were extracted from the ViPR corpus. Electron-ion interaction pseudopotential scheme was used to encode the extracted sample sequences while cepstral analysis technique was applied to the encoded sequences to obtain a new set of genomic features, here called Genomic Cepstral Coefficients (GCCs). Experiments were performed to determine the potency of the GCCs to discriminate between different pathogenic viruses. Results show that GCCs are highly discriminating and gave good results when applied to identify some selected pathogenic viruses.

Automated detection of heart defects in athletes based on electrocardiography and artificial neural network

Abstract Electrocardiography (ECG) has proven to be one of the most efficient ways of tracking heart defects in athletes. However, the interpretation of electrocardiograms often require the expertise of a cardiologist. Meanwhile, an automated heart monitoring system could be used to ensure early heart defect detection in athletes, even in the absence of a cardiologist. In this paper, an automated heart defect detection model is proposed for athletes using ECG and Artificial Neural Network (ANN). We developed an ECG biomedical equipment to acquire 400 ECG data vectors from 40 participants, who comprises of athletes and non-athletes. Four classes of possible heart conditions among athletes, namely: normal, tachyarrhythmia, bradyarrhythmia and hypertrophic cardiomyopathy were considered. The ECG data collected were pre-processed and features were extracted based on first order moment. Different ANNs were trained to correctly classify the ECG data. By and large, the performances of ANNs that were trained based on Levenberg-Marquardt learning algorithm outperformed those trained based on Scale Conjugate Gradient learning algorithm. The network architecture with tansig activation function at both hidden and output layers and ten neurons in the hidden layer (TTLM) produced the best performance that cut across all the key performance indicators. The generalization testing of the developed TTLM model with new input data (that were excluded from the training dataset) produced acceptable results with classification accuracy, sensitivity and specificity of 90.00, 91.96 and 97.06% respectively. In essence, the implementation of the developed model in this study could potentially assist in reducing sudden cardiac death among athletes.

Smart city technology based architecture for refuse disposal management

Many modern cities are currently encumbered with various challenges among which is the need to promote the culture of environmental sanitation for healthy living. However, advances in information communications technology have given birth to the concept of smart city, which is rapidly being applied to address some of the challenges being faced in such cities. This paper presents the development of an architecture based on smart city technology, for refuse disposal management in communities. A proof of concept prototype was implemented for the proposed architecture using Arduino UNO microcontroller board, proximity sensor, breadboard, refuse bin and a personal computer. The proximity sensor was interfaced with the Arduino board to capture dataset that correspond to the five different positions calibrated on a refuse bin. The dataset was shown to be of good quality since the graph of the mean voltages against the distances is similar to the proximity sensor characteristic graph. To determine the appropriate classifier for realizing the pattern classification unit of the prototype, an experiment was performed using the acquired dataset to train five different variants of the K-NN classifier. The 1-NN classifier was nominated for the prototype because it is simple and it gave higher values of accuracy, precision and recall.

Classification of Eukaryotic Organisms Through Cepstral Analysis of Mitochondrial DNA

Accurate classification of organisms into taxonomical hierarchies based on genomic sequences is currently an open challenge, because majority of the traditional techniques have been found wanting. In this study, we employed mitochondrial DNA (mtDNA) genomic sequences and Digital Signal Processing (DSP) for accurate classification of Eukaryotic organisms. The mtDNA sequences of the selected organisms were first encoded using three popular genomic numerical representation methods in the literature, which are Atomic Number (AN), Molecular Mass (MM) and Electron-Ion Interaction Pseudopotential (EIIP). The numerically encoded sequences were further processed with a DSP based cepstral analysis to obtain three sets of Genomic Cepstral Coefficients (GCC), which serve as the genomic descriptors in this study. The three genomic descriptors are named AN-GCC, MM-GCC and EIIP-GCC. The experimental results using the genomic descriptors, backpropagation and radial basis function neural networks gave better classification accuracies than a comparable descriptor in the literature. The results further show that the accuracy of the proposed genomic descriptors in this study are not dependent on the numerical encoding methods.

Medical Image Classification with Hand-Designed or Machine-Designed Texture Descriptors: A Performance Evaluation

Accurate diagnosis and early detection of various disease conditions are key to improving living conditions in any community. The existing framework for medical image classification depends largely on advanced digital image processing and machine (deep) learning techniques for significant improvement. In this paper, the performance of traditional hand-designed texture descriptors within the image-based learning paradigm is evaluated in comparison with machine-designed descriptors (extracted from pre-trained Convolution Neural Networks). Performance is evaluated, with respect to speed, accuracy and storage requirements, based on four popular medical image datasets. The experiments reveal an increased accuracy with machine-designed descriptors in most cases, though at a higher computational cost. It is therefore necessary to consider other parameters for tradeoff depending on the application being considered.

Alignment-Free Z-Curve Genomic Cepstral Coefficients and Machine Learning for Classification of Viruses

Accurate detection of pathogenic viruses has become highly imperative. This is because viral diseases constitute a huge threat to human health and wellbeing on a global scale. However, both traditional and recent techniques for viral detection suffer from various setbacks. In codicil, some of the existing alignment-free methods are also limited with respect to viral detection accuracy. In this paper, we present the development of an alignment-free, digital signal processing based method for pathogenic viral detection named Z-Curve Genomic Cesptral Coefficients (ZCGCC). To evaluate the method, ZCGCC were computed from twenty six pathogenic viral strains extracted from the ViPR corpus. Naïve Bayesian classifier, which is a popular machine learning method was experimentally trained and validated using the extracted ZCGCC and other alignment-free methods in the literature. Comparative results show that the proposed ZCGCC gives good accuracy (93.0385%) and improved performance to existing alignment-free methods.