We consider qualitatively robust predictive mappings of stochastic environmental models, where protection against outlier data is incorporated. We utilize digital representations of the models and deploy stochastic bi...We consider qualitatively robust predictive mappings of stochastic environmental models, where protection against outlier data is incorporated. We utilize digital representations of the models and deploy stochastic binary neural networks that are pre-trained to produce such mappings. The pre-training is implemented by a back propagating supervised learning algorithm which converges almost surely to the probabilities induced by the environment, under general ergodicity conditions.展开更多
The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has signifi...The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty quantification.Therefore,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the predictions.It prepares convolutional neural network(CNN)and BCNN models.The proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN model.This study then trains them on a dataset of cataract images filtered from the ocular disease fundus images fromKaggle.The deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye conditions.When compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.展开更多
A demodulator based on convolutional neural networks（ CNNs） is proposed to demodulate bipolar extended binary phase shifting keying（ EBPSK） signals transmitted at a faster-thanNyquist（ FTN） rate, solving the pro...A demodulator based on convolutional neural networks（ CNNs） is proposed to demodulate bipolar extended binary phase shifting keying（ EBPSK） signals transmitted at a faster-thanNyquist（ FTN） rate, solving the problem of severe inter symbol interference（ ISI） caused by FTN rate signals. With the characteristics of local connectivity, pooling and weight sharing,a six-layer CNNs structure is used to demodulate and eliminate ISI. The results showthat with the symbol rate of 1. 07 k Bd, the bandwidth of the band-pass filter（ BPF） in a transmitter of 1 k Hz and the changing number of carrier cycles in a symbol K = 5,10,15,28, the overall bit error ratio（ BER） performance of CNNs with single-symbol decision is superior to that with a doublesymbol united-decision. In addition, the BER performance of single-symbol decision is approximately 0. 5 d B better than that of the coherent demodulator while K equals the total number of carrier circles in a symbol, i. e., K = N = 28. With the symbol rate of 1. 07 k Bd, the bandwidth of BPF in a transmitter of 500 Hz and K = 5,10,15,28, the overall BER performance of CNNs with double-symbol united-decision is superior to those with single-symbol decision. Moreover, the double-symbol uniteddecision method is approximately 0. 5 to 1. 5 d B better than that of the coherent demodulator while K = N = 28. The demodulators based on CNNs successfully solve the serious ISI problems generated during the transmission of FTN rate bipolar EBPSK signals, which is beneficial for the improvement of spectrum efficiency.展开更多
<div style="text-align:justify;"> Load identification method is one of the major technical difficulties of non-intrusive composite monitoring. Binary V-I trajectory image can reflect the original V-I t...<div style="text-align:justify;"> Load identification method is one of the major technical difficulties of non-intrusive composite monitoring. Binary V-I trajectory image can reflect the original V-I trajectory characteristics to a large extent, so it is widely used in load identification. However, using single binary V-I trajectory feature for load identification has certain limitations. In order to improve the accuracy of load identification, the power feature is added on the basis of the binary V-I trajectory feature in this paper. We change the initial binary V-I trajectory into a new 3D feature by mapping the power feature to the third dimension. In order to reduce the impact of imbalance samples on load identification, the SVM SMOTE algorithm is used to balance the samples. Based on the deep learning method, the convolutional neural network model is used to extract the newly produced 3D feature to achieve load identification in this paper. The results indicate the new 3D feature has better observability and the proposed model has higher identification performance compared with other classification models on the public data set PLAID. </div>展开更多
Analyzing and predicting the learning behavior data of students in blended teaching can provide reference basis for teaching.Aiming at weak generalization ability of existing algorithm models in performance prediction...Analyzing and predicting the learning behavior data of students in blended teaching can provide reference basis for teaching.Aiming at weak generalization ability of existing algorithm models in performance prediction,a BP neural network is introduced to classify and predict the grades of students in the blended teaching.L2 regularization term is added to construct the BP neural network model in order to reduce the risk of overfitting.Combined with Pearson coefficient,effective feature data are selected as the validation dataset of the model by mining the data of Chao-Xing platform.The performance of common machine learning algorithms and the BP neural network are compared on the dataset.Experiments show that BP neural network model has stronger generalizability than common machine learning models.The BP neural network with L2 regularization has better fitting ability than the original BP neural network model.It achieves better performance with improved accuracy.展开更多
Adolescent Idiopathic Scoliosis(AIS)is a deformity of the spine that affects teenagers.The current method for detecting AIS is based on radiographic images which may increase the risk of cancer growth due to radiation...Adolescent Idiopathic Scoliosis(AIS)is a deformity of the spine that affects teenagers.The current method for detecting AIS is based on radiographic images which may increase the risk of cancer growth due to radiation.Photogrammetry is another alternative used to identify AIS by distinguishing the curves of the spine from the surface of a human’s back.Currently,detecting the curve of the spine is manually performed,making it a time-consuming task.To overcome this issue,it is crucial to develop a better model that automatically detects the curve of the spine and classify the types of AIS.This research proposes a new integration of ESNN and Feature Extraction(FE)methods and explores the architecture of ESNN for the AIS classification model.This research identifies the optimal Feature Extraction(FE)methods to reduce computational complexity.The ability of ESNN to provide a fast result with a simplicity and performance capability makes this model suitable to be implemented in a clinical setting where a quick result is crucial.A comparison between the conventional classifier(Support Vector Machine(SVM),Multi-layer Perceptron(MLP)and Random Forest(RF))with the proposed AIS model also be performed on a dataset collected by an orthopedic expert from Hospital Universiti Kebangsaan Malaysia(HUKM).This dataset consists of various photogrammetry images of the human back with different types ofMalaysian AIS patients to solve the scoliosis problem.The process begins by pre-processing the images which includes resizing and converting the captured pictures to gray-scale images.This is then followed by feature extraction,normalization,and classification.The experimental results indicate that the integration of LBP and ESNN achieves higher accuracy compared to the performance of multiple baseline state-of-the-art Machine Learning for AIS classification.This demonstrates the capability of ESNN in classifying the types of AIS based on photogrammetry images.展开更多
The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographica...The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community.展开更多
Gene regulatory network (GRN) inference from gene expression data remains a big challenge in system biology. In this paper, flexible neural tree (FNT) model is proposed as a binary classifier for inference of gene reg...Gene regulatory network (GRN) inference from gene expression data remains a big challenge in system biology. In this paper, flexible neural tree (FNT) model is proposed as a binary classifier for inference of gene regulatory network. A novel tree-based evolutionary algorithm and firefly algorithm (FA) are used to optimize the structure and parameters of FNT model, respectively.The two E.coli networks are used to test FNT model and the results reveal that FNT model performs better than state-of-the-art unsupervised and supervised learning methods.展开更多
Traditional classification methods for cervical cells heavily rely on manual feature extraction,constraining their versatility due to the intricacies of cytology images.Although deep learning approaches offer remarkab...Traditional classification methods for cervical cells heavily rely on manual feature extraction,constraining their versatility due to the intricacies of cytology images.Although deep learning approaches offer remarkable po-tential,they often sacrifice domain-specific knowledge,particularly the morphological patterns characterizing various cell subtypes during automated feature extraction.To bridge this gap,we introduce a novel hierarchical framework that integrates robust features from color,texture,and morphology with latent representations discovered by an improved attention-based multi-scale local binary convolutional neural networks(MS-LBCNN),designed to facilitate powerful feature extraction mechanism.We enhance the standard 6-class Bethesda system(TBS)classification by incorporating a coarse-to-refine fusion strategy,which optimizes the classification pro-cess.The proposed method is uniquely equipped to manage the complexities present in both individual and clustered cell images.Upon rigorous evaluation across three independent data cohorts,our method consistently surpassed existing state-of-the-art techniques.The experimental results indicated the potential of our method in enhancing the development of automation-aided diagnostic systems,and bolstering both the accuracy and ef-ficiency of cytology screening procedures.展开更多
The identification of cancer tissues in Gastroenterology imaging poses novel challenges to the computer vision community in designing generic decision support systems.This generic nature demands the image descriptors ...The identification of cancer tissues in Gastroenterology imaging poses novel challenges to the computer vision community in designing generic decision support systems.This generic nature demands the image descriptors to be invariant to illumination gradients,scaling,homogeneous illumination,and rotation.In this article,we devise a novel feature extraction methodology,which explores the effectiveness of Gabor filters coupled with Block Local Binary Patterns in designing such descriptors.We effectively exploit the illumination invariance properties of Block Local Binary Patterns and the inherent capability of convolutional neural networks to construct novel rotation,scale and illumination invariant features.The invariance characteristics of the proposed Gabor Block Local Binary Patterns(GBLBP)are demonstrated using a publicly available texture dataset.We use the proposed feature extraction methodology to extract texture features from Chromoendoscopy(CH)images for the classification of cancer lesions.The proposed feature set is later used in conjuncture with convolutional neural networks to classify the CH images.The proposed convolutional neural network is a shallow network comprising of fewer parameters in contrast to other state-of-the-art networks exhibiting millions of parameters required for effective training.The obtained results reveal that the proposed GBLBP performs favorably to several other state-of-the-art methods including both hand crafted and convolutional neural networks-based features.展开更多
The proposed deep learning algorithm will be integrated as a binary classifier under the umbrella of a multi-class classification tool to facilitate the automated detection of non-healthy deformities, anatomical landm...The proposed deep learning algorithm will be integrated as a binary classifier under the umbrella of a multi-class classification tool to facilitate the automated detection of non-healthy deformities, anatomical landmarks, pathological findings, other anomalies and normal cases, by examining medical endoscopic images of GI tract. Each binary classifier is trained to detect one specific non-healthy condition. The algorithm analyzed in the present work expands the ability of detection of this tool by classifying GI tract image snapshots into two classes, depicting haemorrhage and non-haemorrhage state. The proposed algorithm is the result of the collaboration between interdisciplinary specialists on AI and Data Analysis, Computer Vision, Gastroenterologists of four University Gastroenterology Departments of Greek Medical Schools. The data used are 195 videos (177 from non-healthy cases and 18 from healthy cases) videos captured from the PillCam<sup>(R)</sup> Medronics device, originated from 195 patients, all diagnosed with different forms of angioectasia, haemorrhages and other diseases from different sites of the gastrointestinal (GI), mainly including difficult cases of diagnosis. Our AI algorithm is based on convolutional neural network (CNN) trained on annotated images at image level, using a semantic tag indicating whether the image contains angioectasia and haemorrhage traces or not. At least 22 CNN architectures were created and evaluated some of which pre-trained applying transfer learning on ImageNet data. All the CNN variations were introduced, trained to a prevalence dataset of 50%, and evaluated of unseen data. On test data, the best results were obtained from our CNN architectures which do not utilize backbone of transfer learning. Across a balanced dataset from no-healthy images and healthy images from 39 videos from different patients, identified correct diagnosis with sensitivity 90%, specificity 92%, precision 91.8%, FPR 8%, FNR 10%. Besides, we compared the performance of our best CNN algorithm versus our same goal algorithm based on HSV colorimetric lesions features extracted of pixel-level annotations, both algorithms trained and tested on the same data. It is evaluated that the CNN trained on image level annotated images, is 9% less sensitive, achieves 2.6% less precision, 1.2% less FPR, and 7% less FNR, than that based on HSV filters, extracted from on pixel-level annotated training data.展开更多
文摘We consider qualitatively robust predictive mappings of stochastic environmental models, where protection against outlier data is incorporated. We utilize digital representations of the models and deploy stochastic binary neural networks that are pre-trained to produce such mappings. The pre-training is implemented by a back propagating supervised learning algorithm which converges almost surely to the probabilities induced by the environment, under general ergodicity conditions.
基金Saudi Arabia for funding this work through Small Research Group Project under Grant Number RGP.1/316/45.
文摘The effective and timely diagnosis and treatment of ocular diseases are key to the rapid recovery of patients.Today,the mass disease that needs attention in this context is cataracts.Although deep learning has significantly advanced the analysis of ocular disease images,there is a need for a probabilistic model to generate the distributions of potential outcomes and thusmake decisions related to uncertainty quantification.Therefore,this study implements a Bayesian Convolutional Neural Networks(BCNN)model for predicting cataracts by assigning probability values to the predictions.It prepares convolutional neural network(CNN)and BCNN models.The proposed BCNN model is CNN-based in which reparameterization is in the first and last layers of the CNN model.This study then trains them on a dataset of cataract images filtered from the ocular disease fundus images fromKaggle.The deep CNN model has an accuracy of 95%,while the BCNN model has an accuracy of 93.75% along with information on uncertainty estimation of cataracts and normal eye conditions.When compared with other methods,the proposed work reveals that it can be a promising solution for cataract prediction with uncertainty estimation.
基金The National Natural Science Foundation of China(No.6504000089)
文摘A demodulator based on convolutional neural networks（ CNNs） is proposed to demodulate bipolar extended binary phase shifting keying（ EBPSK） signals transmitted at a faster-thanNyquist（ FTN） rate, solving the problem of severe inter symbol interference（ ISI） caused by FTN rate signals. With the characteristics of local connectivity, pooling and weight sharing,a six-layer CNNs structure is used to demodulate and eliminate ISI. The results showthat with the symbol rate of 1. 07 k Bd, the bandwidth of the band-pass filter（ BPF） in a transmitter of 1 k Hz and the changing number of carrier cycles in a symbol K = 5,10,15,28, the overall bit error ratio（ BER） performance of CNNs with single-symbol decision is superior to that with a doublesymbol united-decision. In addition, the BER performance of single-symbol decision is approximately 0. 5 d B better than that of the coherent demodulator while K equals the total number of carrier circles in a symbol, i. e., K = N = 28. With the symbol rate of 1. 07 k Bd, the bandwidth of BPF in a transmitter of 500 Hz and K = 5,10,15,28, the overall BER performance of CNNs with double-symbol united-decision is superior to those with single-symbol decision. Moreover, the double-symbol uniteddecision method is approximately 0. 5 to 1. 5 d B better than that of the coherent demodulator while K = N = 28. The demodulators based on CNNs successfully solve the serious ISI problems generated during the transmission of FTN rate bipolar EBPSK signals, which is beneficial for the improvement of spectrum efficiency.
文摘<div style="text-align:justify;"> Load identification method is one of the major technical difficulties of non-intrusive composite monitoring. Binary V-I trajectory image can reflect the original V-I trajectory characteristics to a large extent, so it is widely used in load identification. However, using single binary V-I trajectory feature for load identification has certain limitations. In order to improve the accuracy of load identification, the power feature is added on the basis of the binary V-I trajectory feature in this paper. We change the initial binary V-I trajectory into a new 3D feature by mapping the power feature to the third dimension. In order to reduce the impact of imbalance samples on load identification, the SVM SMOTE algorithm is used to balance the samples. Based on the deep learning method, the convolutional neural network model is used to extract the newly produced 3D feature to achieve load identification in this paper. The results indicate the new 3D feature has better observability and the proposed model has higher identification performance compared with other classification models on the public data set PLAID. </div>
基金This research was supported by the Natural Science Foundation of the Jiangsu Higher Education Institution of China,(Grant No.19KJB520044)the Innovation and Entrepreneurship Training Program for College Students in Jiangsu Province of China,(Grant No.202113982023Y)+2 种基金the Jiangsu Graduate Practice and Innovation Project of China,(Grant No.SJCX21_0356)Innovation Practice Project of Graduate Students in Wuxi Campus of Nanjing University of Information Science&Technology,(Grant No.WXCX202117)Project on Teaching Reform Research of Wuxi University,(Grant No.JGYB202113).
文摘Analyzing and predicting the learning behavior data of students in blended teaching can provide reference basis for teaching.Aiming at weak generalization ability of existing algorithm models in performance prediction,a BP neural network is introduced to classify and predict the grades of students in the blended teaching.L2 regularization term is added to construct the BP neural network model in order to reduce the risk of overfitting.Combined with Pearson coefficient,effective feature data are selected as the validation dataset of the model by mining the data of Chao-Xing platform.The performance of common machine learning algorithms and the BP neural network are compared on the dataset.Experiments show that BP neural network model has stronger generalizability than common machine learning models.The BP neural network with L2 regularization has better fitting ability than the original BP neural network model.It achieves better performance with improved accuracy.
基金This work is supported by the Ministry of Education Malaysia and Universiti Teknologi Malaysia through Research University Grant Scheme(Q.J130000.2651.16J63).
文摘Adolescent Idiopathic Scoliosis(AIS)is a deformity of the spine that affects teenagers.The current method for detecting AIS is based on radiographic images which may increase the risk of cancer growth due to radiation.Photogrammetry is another alternative used to identify AIS by distinguishing the curves of the spine from the surface of a human’s back.Currently,detecting the curve of the spine is manually performed,making it a time-consuming task.To overcome this issue,it is crucial to develop a better model that automatically detects the curve of the spine and classify the types of AIS.This research proposes a new integration of ESNN and Feature Extraction(FE)methods and explores the architecture of ESNN for the AIS classification model.This research identifies the optimal Feature Extraction(FE)methods to reduce computational complexity.The ability of ESNN to provide a fast result with a simplicity and performance capability makes this model suitable to be implemented in a clinical setting where a quick result is crucial.A comparison between the conventional classifier(Support Vector Machine(SVM),Multi-layer Perceptron(MLP)and Random Forest(RF))with the proposed AIS model also be performed on a dataset collected by an orthopedic expert from Hospital Universiti Kebangsaan Malaysia(HUKM).This dataset consists of various photogrammetry images of the human back with different types ofMalaysian AIS patients to solve the scoliosis problem.The process begins by pre-processing the images which includes resizing and converting the captured pictures to gray-scale images.This is then followed by feature extraction,normalization,and classification.The experimental results indicate that the integration of LBP and ESNN achieves higher accuracy compared to the performance of multiple baseline state-of-the-art Machine Learning for AIS classification.This demonstrates the capability of ESNN in classifying the types of AIS based on photogrammetry images.
文摘The inter-class face classification problem is more reasonable than the intra-class classification problem.To address this issue,we have carried out empirical research on classifying Indian people to their geographical regions.This work aimed to construct a computational classification model for classifying Indian regional face images acquired from south and east regions of India,referring to human vision.We have created an Automated Human Intelligence System(AHIS)to evaluate human visual capabilities.Analysis of AHIS response showed that face shape is a discriminative feature among the other facial features.We have developed a modified convolutional neural network to characterize the human vision response to improve face classification accuracy.The proposed model achieved mean F1 and Matthew Correlation Coefficient(MCC)of 0.92 and 0.84,respectively,on the validation set,outperforming the traditional Convolutional Neural Network(CNN).The CNN-Contoured Face(CNN-FC)model is developed to train contoured face images to investigate the influence of face shape.Finally,to cross-validate the accuracy of these models,the traditional CNN model is trained on the same dataset.With an accuracy of 92.98%,the Modified-CNN(M-CNN)model has demonstrated that the proposed method could facilitate the tangible impact in intra-classification problems.A novel Indian regional face dataset is created for supporting this supervised classification work,and it will be available to the research community.
文摘Gene regulatory network (GRN) inference from gene expression data remains a big challenge in system biology. In this paper, flexible neural tree (FNT) model is proposed as a binary classifier for inference of gene regulatory network. A novel tree-based evolutionary algorithm and firefly algorithm (FA) are used to optimize the structure and parameters of FNT model, respectively.The two E.coli networks are used to test FNT model and the results reveal that FNT model performs better than state-of-the-art unsupervised and supervised learning methods.
基金supported by the Beijing Capital Health Development Research Project[Grant no.2024-2-1031]the Beijing Municipal Natural Science Foundation[Grant no.7192105].
文摘Traditional classification methods for cervical cells heavily rely on manual feature extraction,constraining their versatility due to the intricacies of cytology images.Although deep learning approaches offer remarkable po-tential,they often sacrifice domain-specific knowledge,particularly the morphological patterns characterizing various cell subtypes during automated feature extraction.To bridge this gap,we introduce a novel hierarchical framework that integrates robust features from color,texture,and morphology with latent representations discovered by an improved attention-based multi-scale local binary convolutional neural networks(MS-LBCNN),designed to facilitate powerful feature extraction mechanism.We enhance the standard 6-class Bethesda system(TBS)classification by incorporating a coarse-to-refine fusion strategy,which optimizes the classification pro-cess.The proposed method is uniquely equipped to manage the complexities present in both individual and clustered cell images.Upon rigorous evaluation across three independent data cohorts,our method consistently surpassed existing state-of-the-art techniques.The experimental results indicated the potential of our method in enhancing the development of automation-aided diagnostic systems,and bolstering both the accuracy and ef-ficiency of cytology screening procedures.
基金The authors extend their appreciation to the Deputyship for Research&Innovation,Ministry of Education in Saudi Arabia for funding this research work through the project number 7906。
文摘The identification of cancer tissues in Gastroenterology imaging poses novel challenges to the computer vision community in designing generic decision support systems.This generic nature demands the image descriptors to be invariant to illumination gradients,scaling,homogeneous illumination,and rotation.In this article,we devise a novel feature extraction methodology,which explores the effectiveness of Gabor filters coupled with Block Local Binary Patterns in designing such descriptors.We effectively exploit the illumination invariance properties of Block Local Binary Patterns and the inherent capability of convolutional neural networks to construct novel rotation,scale and illumination invariant features.The invariance characteristics of the proposed Gabor Block Local Binary Patterns(GBLBP)are demonstrated using a publicly available texture dataset.We use the proposed feature extraction methodology to extract texture features from Chromoendoscopy(CH)images for the classification of cancer lesions.The proposed feature set is later used in conjuncture with convolutional neural networks to classify the CH images.The proposed convolutional neural network is a shallow network comprising of fewer parameters in contrast to other state-of-the-art networks exhibiting millions of parameters required for effective training.The obtained results reveal that the proposed GBLBP performs favorably to several other state-of-the-art methods including both hand crafted and convolutional neural networks-based features.
文摘The proposed deep learning algorithm will be integrated as a binary classifier under the umbrella of a multi-class classification tool to facilitate the automated detection of non-healthy deformities, anatomical landmarks, pathological findings, other anomalies and normal cases, by examining medical endoscopic images of GI tract. Each binary classifier is trained to detect one specific non-healthy condition. The algorithm analyzed in the present work expands the ability of detection of this tool by classifying GI tract image snapshots into two classes, depicting haemorrhage and non-haemorrhage state. The proposed algorithm is the result of the collaboration between interdisciplinary specialists on AI and Data Analysis, Computer Vision, Gastroenterologists of four University Gastroenterology Departments of Greek Medical Schools. The data used are 195 videos (177 from non-healthy cases and 18 from healthy cases) videos captured from the PillCam<sup>(R)</sup> Medronics device, originated from 195 patients, all diagnosed with different forms of angioectasia, haemorrhages and other diseases from different sites of the gastrointestinal (GI), mainly including difficult cases of diagnosis. Our AI algorithm is based on convolutional neural network (CNN) trained on annotated images at image level, using a semantic tag indicating whether the image contains angioectasia and haemorrhage traces or not. At least 22 CNN architectures were created and evaluated some of which pre-trained applying transfer learning on ImageNet data. All the CNN variations were introduced, trained to a prevalence dataset of 50%, and evaluated of unseen data. On test data, the best results were obtained from our CNN architectures which do not utilize backbone of transfer learning. Across a balanced dataset from no-healthy images and healthy images from 39 videos from different patients, identified correct diagnosis with sensitivity 90%, specificity 92%, precision 91.8%, FPR 8%, FNR 10%. Besides, we compared the performance of our best CNN algorithm versus our same goal algorithm based on HSV colorimetric lesions features extracted of pixel-level annotations, both algorithms trained and tested on the same data. It is evaluated that the CNN trained on image level annotated images, is 9% less sensitive, achieves 2.6% less precision, 1.2% less FPR, and 7% less FNR, than that based on HSV filters, extracted from on pixel-level annotated training data.
