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

Adetiba, Emmanuel; Olugbara, Oludayo O.

doi:10.1155/2015/786013

Cited by 64 publications

(35 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two state-of-the-art pattern classifiers investigated for the classification of the features in this work are the Multilayer Perceptron Artificial Neural Network (MLP-ANN) and Support Vector Machine (SVM). They are extensively engaged in the literature to solve pattern classification problems [42]. Nevertheless, each of the classifiers have inherent merits and demerits.…”

Section: Pattern Classificationmentioning

confidence: 99%

“…The MLP-ANN and SVM were tuned in this study through established parameters in the literature as well as via experimentations to determine the configuration that gives the most optimal performance [33,42].…”

Section: Configuration Of the Pattern Classifiersmentioning

confidence: 99%

“…The accuracy is the degree of closeness of the measurements of a quantity to its true value. Whereas MSE is the mean of the square of the difference between the expected output and the actual output [42,51].…”

Section: Performance Evaluationmentioning

confidence: 99%

See 2 more Smart Citations

Development of a Prototype Smart City System for Refuse Disposal Management

Adeyemo¹,

Olugbara²,

Adetiba³

2019

MCS

Self Cite

View full text Add to dashboard Cite

The future of modern cities largely depends on how well they can tackle problems that confront them by embracing the next era of digital revolution. A vital element of such revolution is the creation of smart cities. Smart city is an evolving paradigm that involves the deployment of information communication technology wares into public or private infrastructure to provide intelligent data gathering and analysis. To align concretely with the smart city revolution in the area of environmental cleanliness, this paper involves the development of a smart city system for refuse disposal management. The architecture of the proposed system is an adaptation of the Jalali reference smart city architecture. It features four essential layers, which are signal sensing and processing, network, intelligent user application and Internet of Things (IoT) web application layers. A proof of concept prototype was implemented based on the designed architecture of the proposed system. The signal sensing and processing layer was implemented to produce a smart refuse bin that contains the Arduino microcontroller board, Wi-Fi/GSM transceiver, proximity sensor, gas sensor, temperature sensor and other relevant electronic components. The network layer provides interconnectivity among the layers via the internet. The intelligent user application layer was realized with non-browser client application, statistical feature extraction method and pattern classifiers. Whereas the IoT web application layer was realised with ThingSpeak, which is an online web application for IoT based projects. The sensors in the smart refuse bin generate multivariate dataset that corresponds to the status of refuse in the bin. Training and testing features were extracted from the dataset using first order statistical feature extraction method. Afterward, multilayer perceptron artificial neural network and support vector machine were trained and compared experimentally. The multilayer perceptron artificial neural network model gave the overall best accuracy of 98.0% and the least mean square error of 0.0036.

show abstract

Section: Pattern Classificationmentioning

confidence: 99%

Section: Configuration Of the Pattern Classifiersmentioning

confidence: 99%

See 1 more Smart Citation

Development of a Prototype Smart City System for Refuse Disposal Management

Adeyemo¹,

Olugbara²,

Adetiba³

2019

MCS

Self Cite

View full text Add to dashboard Cite

show abstract

“…Adetiba et al [13] complete an exploratory correlation of manufactured neural system (ANN) and bolster vector machine (SVM) troupes and their "nonensemble" variations for lung growth forecast. The histogram of situated angle (HOG) and neighborhood paired example (LBP) cutting edge highlight extraction plans were connected to concentrate delegate genomic elements from the encoded arrangements of nucleotides.…”

Section: Existing Literaturesmentioning

confidence: 99%

Reviewing the Techniques of Disease Detection and Classification from the Challenging Medical Data

S¹,

Seetharam²

2015

IJCA

View full text Add to dashboard Cite

The area of healthcare sector is now meeting a new challenge of data management. Owing to adoption of advance technology for patient-related services as well as diagnosis, a high-dimensional data is being generated. The biggest problems of such data are manifold e.g. i) they are much bigger in size that is difficult to be stored in physical servers, ii) they are massively growing in size with respect to increase of time, iii) they are of various forms and formats owing to be generated from multiple devices, and iv) there is larger dimensionality of uncertainty too. Owing to all these problems, it is almost impossible to apply the conventional data analysis algorithm for extracting teh knowledge. This paper discusses about the some of the recently adopted technique for analysis such medical data for an effective disease detection and classification with a contribution of exploring the research gap for the existing literatures.

show abstract

“…Most traditional methods for automated classification of nodules do not work in an end‐to‐end way: first, they extract features with predefined filters, such as descriptors of histogram of oriented gradients (Adetiba and Olugbara, ), local binary patterns (Shan, ) and wavelet feature descriptor (Orozco et al, ), or extract hand‐crafted features, such as geometry (Lee et al, ; Tartar et al, ), appearance (Li et al, ) or texture (Han et al, ). An alternative to setting predefined features is using feature learning methods to learn a high‐level representation directly from the training data.…”

Section: Introductionmentioning

confidence: 99%

Multiview convolutional neural networks for lung nodule classification

Liu

Kang

2017

Int J Imaging Syst Tech

View full text Add to dashboard Cite

To find a better way to screen early lung cancer, motivated by the great success of deep learning, we empirically investigate the challenge of classifying lung nodules in computed tomography (CT) in an end-to-end manner. Multi-view convolutional neural networks (MV-CNN) are proposed in this article for lung nodule classification. Unlike the traditional CNNs, a MV-CNN takes multiple views of each entered nodule. We carry out a binary classification (benign and malignant) and a ternary classification (benign, primary malignant, and metastatic malignant) using the Lung Image Database Consortium and Image Database Resource Initiative database. The results show that, for binary or ternary classifications, the multiview strategy produces higher accuracy than the single view method, even for cases that are over-fitted. Our model achieves an error rate of 5.41 and 13.91% for binary and ternary classifications, respectively. Finally, the receiver operating characteristic curve and t-distributed stochastic neighbor embedding algorithm are used to analyze the models. The results reveal that the deep features learned by the model proposed in this article have a higher separability than features from the image space and the multiview strategies; therefore, researchers can get better representation.

show abstract

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

Cited by 64 publications

References 57 publications

Development of a Prototype Smart City System for Refuse Disposal Management

Development of a Prototype Smart City System for Refuse Disposal Management

Reviewing the Techniques of Disease Detection and Classification from the Challenging Medical Data

Multiview convolutional neural networks for lung nodule classification

Contact Info

Product

Resources

About