Search results for: Neural Networks Model

Authors: Jacqueline Rose T. Alipo-on, Francesca Isabelle F. Escobar, Myles Joshua T. Tan, Hezerul Abdul Karim, Nouar Al Dahoul

Abstract:

Electrocardiogram (ECG) signal analysis and processing are crucial in the diagnosis of cardiovascular diseases, which are considered one of the leading causes of mortality worldwide. However, the traditional rule-based analysis of large volumes of ECG data is time-consuming, labor-intensive, and prone to human errors. With the advancement of the programming paradigm, algorithms such as machine learning have been increasingly used to perform an analysis of ECG signals. In this paper, various deep learning algorithms were adapted to classify five classes of heartbeat types. The dataset used in this work is the synthetic MIT-BIH Arrhythmia dataset produced from generative adversarial networks (GANs). Various deep learning models such as ResNet-50 convolutional neural network (CNN), 1-D CNN, and long short-term memory (LSTM) were evaluated and compared. ResNet-50 was found to outperform other models in terms of recall and F1 score using a five-fold average score of 98.88% and 98.87%, respectively. 1-D CNN, on the other hand, was found to have the highest average precision of 98.93%.

Keywords: heartbeat classification, convolutional neural network, electrocardiogram signals, generative adversarial networks, long short-term memory, ResNet-50

Procedia PDF Downloads 86

Authors: Min Jindong, Wang Mingxia

Abstract:

With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.

Keywords: object detection, knowledge distillation, convolutional network, model compression

Procedia PDF Downloads 248

Authors: John Pomerat, Aviv Segev

Abstract:

Recently, deep learning has had many theoretical breakthroughs. For deep learning to be successful in the industry, however, there need to be practical algorithms capable of handling many real-world hiccups preventing the immediate application of a learning algorithm. Although AI promises to revolutionize the healthcare industry, getting access to patient data in order to train learning algorithms has not been easy. One proposed solution to this is data- sharing. In this paper, we propose an alternative protocol, based on multi-party computation, to train deep learning models while maintaining both the privacy and security of training data. We examine three methods of training neural networks in this way: Transfer learning, average ensemble learning, and series network learning. We compare these methods to the equivalent model obtained through data-sharing across two different experiments. Additionally, we address the security concerns of this protocol. While the motivating example is healthcare, our findings regarding multi-party computation of neural network training are purely theoretical and have use-cases outside the domain of healthcare.

Keywords: neural network aggregation, multi-party computation, transfer learning, average ensemble learning

Procedia PDF Downloads 129

Authors: Grienggrai Rajchakit

Abstract:

As we all know that coronavirus is announced as a pandemic in the world by WHO. It is speeded all over the world with few days of time. To control this spreading, every citizen maintains social distance and self-preventive measures are the best strategies. As of now, many researchers and scientists are continuing their research in finding out the exact vaccine. The machine learning model finds that the coronavirus disease behaves in an exponential manner. To abolish the consequence of this pandemic, an efficient step should be taken to analyze this disease. In this paper, a recurrent neural network model is chosen to predict the number of active cases in a particular state. To make this prediction of active cases, we need a database. The database of COVID-19 is downloaded from the KAGGLE website and is analyzed by applying a recurrent LSTM neural network with univariant features to predict the number of active cases of patients suffering from the corona virus. The downloaded database is divided into training and testing the chosen neural network model. The model is trained with the training data set and tested with a testing dataset to predict the number of active cases in a particular state; here, we have concentrated on Andhra Pradesh state.

Keywords: COVID-19, coronavirus, KAGGLE, LSTM neural network, machine learning

Procedia PDF Downloads 136

Authors: Mohamed Lotfy, Ghada Soliman

Abstract:

Recognizing Arabic dot-matrix digits is a challenging problem due to the unique characteristics of dot-matrix fonts, such as irregular dot spacing and varying dot sizes. This paper presents an approach for recognizing Arabic digits printed in dot matrix format. The proposed model is based on Convolutional Neural Networks (CNN) that take the dot matrix as input and generate embeddings that are rounded to generate binary representations of the digits. The binary embeddings are then used to perform Optical Character Recognition (OCR) on the digit images. To overcome the challenge of the limited availability of dotted Arabic expiration date images, we developed a True Type Font (TTF) for generating synthetic images of Arabic dot-matrix characters. The model was trained on a synthetic dataset of 3287 images and 658 synthetic images for testing, representing realistic expiration dates from 2019 to 2027 in the format of yyyy/mm/dd. Our model achieved an accuracy of 98.94% on the expiry date recognition with Arabic dot matrix format using fewer parameters and less computational resources than traditional CNN-based models. By investigating and presenting our findings comprehensively, we aim to contribute substantially to the field of OCR and pave the way for advancements in Arabic dot-matrix character recognition. Our proposed approach is not limited to Arabic dot matrix digit recognition but can also be extended to text recognition tasks, such as text classification and sentiment analysis.

Keywords: computer vision, pattern recognition, optical character recognition, deep learning

Procedia PDF Downloads 50

Authors: Sun Zhe, Ruggero Micheletto

Abstract:

As discussed extensively in many studies, noise in neural networks have an important role in the functioning and time evolution of the system. The mechanism by which noise induce stochastic resonance enhancing and influencing certain operations is not clarified nor is the mechanism of information storage and coding. With the present research we want to study the role of noise, especially focusing on the frequency peaks in a three variable Hindmarsh−Rose Small−World network. We investigated the behaviour of the network to external noises. We demonstrate that a variation of signal to noise ratio of about 10 dB induces an increase in membrane potential signal of about 15%, averaged over the whole network. We also considered the integral of the whole membrane potential as a paradigm of internal noise, the one generated by the brain network. We showed that this internal noise is attenuated with the size of the network or with the number of random connections. By means of Fourier analysis we found that it has distinct peaks of frequencies, moreover, we showed that increasing the size of the network introducing more neurons, reduced the maximum frequencies generated by the network, whereas the increase in the number of random connections (determined by the small-world probability p) led to a trend toward higher frequencies. This study may give clues on how networks utilize noise to alter the collective behaviour of the system in their operations.

Keywords: neural networks, stochastic processes, small-world networks, discrete Fourier analysis

Procedia PDF Downloads 268

Authors: Gizelle K. Vianna, Gustavo S. Oliveira, Gabriel V. Cunha

Abstract:

The use of decision support systems in agriculture may help monitoring large fields of crops by automatically detecting the symptoms of foliage diseases. In our work, we designed and implemented a decision support system for small tomatoes producers. This work investigates ways to recognize the late blight disease from the analysis of digital images of tomatoes, using a pair of multilayer perceptron neural networks. The networks outputs are used to generate repainted tomato images in which the injuries on the plant are highlighted, and to calculate the damage level of each plant. Those levels are then used to construct a situation map of a farm where a cellular automata simulates the outbreak evolution over the fields. The simulator can test different pesticides actions, helping in the decision on when to start the spraying and in the analysis of losses and gains of each choice of action.

Keywords: artificial neural networks, cellular automata, decision support system, pattern recognition

Procedia PDF Downloads 416

Authors: Kefaya Qaddoum

Abstract:

The aim of this study is to predict breast cancer and to construct a supportive model that will stimulate a more reliable prediction as a factor that is fundamental for public health. In this study, we utilize general regression neural networks (GRNN) to replace the normal predictions with prediction periods to achieve a reasonable percentage of confidence. The mechanism employed here utilises a machine learning system called conformal prediction (CP), in order to assign consistent confidence measures to predictions, which are combined with GRNN. We apply the resulting algorithm to the problem of breast cancer diagnosis. The results show that the prediction constructed by this method is reasonable and could be useful in practice.

Keywords: neural network, conformal prediction, cancer classification, regression

Procedia PDF Downloads 255

Authors: Skiker Kaoutar, Mounir Maouene

Abstract:

Neuroimaging studies have shown that animal and tool concepts rely on distinct networks of brain areas. Animal concepts depend predominantly on temporal areas while tool concepts rely on fronto-temporo-parietal areas. However, the origin of this neurofunctional distinction for processing animal and tool concepts remains still unclear. Here, we address this question from a network perspective suggesting that the neural distinction between animals and tools might reflect the differences in their structural semantic networks. We build semantic networks for animal and tool concepts derived from McRae and colleagues’s behavioral study conducted on a large number of participants. These two networks are thus analyzed through a large number of graph theoretical measures for small-worldness: centrality, clustering coefficient, average shortest path length, as well as resistance to random and targeted attacks. The results indicate that both animal and tool networks have small-world properties. More importantly, the animal network is more vulnerable to targeted attacks compared to the tool network a result that correlates with brain lesions studies.

Keywords: animals, tools, network, semantics, small-worls, resilience to damage

Procedia PDF Downloads 514

Authors: Oyebade K. Oyedotun

Abstract:

The cardiotocogram is a technical recording of the heartbeat rate and uterine contractions of a fetus during pregnancy. During pregnancy, several complications can occur to both the mother and the fetus; hence it is very crucial that medical experts are able to find technical means to check the healthiness of the mother and especially the fetus. It is very important that the fetus develops as expected in stages during the pregnancy period; however, the task of monitoring the health status of the fetus is not that which is easily achieved as the fetus is not wholly physically available to medical experts for inspection. Hence, doctors have to resort to some other tests that can give an indication of the status of the fetus. One of such diagnostic test is to obtain cardiotocograms of the fetus. From the analysis of the cardiotocograms, medical experts can determine the status of the fetus, and therefore necessary medical interventions. Generally, medical experts classify examined cardiotocograms into ‘normal’, ‘suspect’, or ‘pathological’. This work presents an artificial neural network based decision support system which can filter cardiotocograms data, producing the corresponding statuses of the fetuses. The capability of artificial neural network to explore the cardiotocogram data and learn features that distinguish one class from the others has been exploited in this research. In this research, feedforward and radial basis neural networks were trained on a publicly available database to classify the processed cardiotocogram data into one of the three classes: ‘normal’, ‘suspect’, or ‘pathological’. Classification accuracies of 87.8% and 89.2% were achieved during the test phase of the trained network for the feedforward and radial basis neural networks respectively. It is the hope that while the system described in this work may not be a complete replacement for a medical expert in fetus status evaluation, it can significantly reinforce the confidence in medical diagnosis reached by experts.

Keywords: decision support, cardiotocogram, classification, neural networks

Procedia PDF Downloads 298

Authors: Rodrigo S. Fonseca, Antônio C. P. Veiga

Abstract:

Aiming at helping people with some movement limitation that makes typing and communication difficult, there is a need to customize an assistive tool with a learning environment that helps the user in order to optimize text input, identifying the error and providing the correction and possibilities of choice in the Portuguese language. The work presents an Orthographic and Grammatical System that can be incorporated into writing environments, improving and facilitating the use of an alphanumeric keyboard, using a prototype built using a genetic algorithm in addition to carrying out the prediction, which can occur based on the quantity and position of the inserted letters and even placement in the sentence, ensuring the sequence of ideas using a Long Short Term Memory (LSTM) neural network. The prototype optimizes data entry, being a component of assistive technology for the textual formulation, detecting errors, seeking solutions and informing the user of accurate predictions quickly and effectively through machine learning.

Keywords: genetic algorithm, neural networks, word prediction, machine learning

Procedia PDF Downloads 164

Authors: Hritwik Ghosh, Irfan Sadiq Rahat, Sachi Nandan Mohanty, J. V. R. Ravindra

Abstract:

In the rapidly evolving landscape of medical diagnostics, the early detection and accurate classification of skin cancer remain paramount for effective treatment outcomes. This research delves into the transformative potential of Artificial Intelligence (AI), specifically Deep Learning (DL), as a tool for discerning and categorizing various skin conditions. Utilizing a diverse dataset of 3,000 images representing nine distinct skin conditions, we confront the inherent challenge of class imbalance. This imbalance, where conditions like melanomas are over-represented, is addressed by incorporating class weights during the model training phase, ensuring an equitable representation of all conditions in the learning process. Our pioneering approach introduces a hybrid model, amalgamating the strengths of two renowned Convolutional Neural Networks (CNNs), VGG16 and ResNet50. These networks, pre-trained on the ImageNet dataset, are adept at extracting intricate features from images. By synergizing these models, our research aims to capture a holistic set of features, thereby bolstering classification performance. Preliminary findings underscore the hybrid model's superiority over individual models, showcasing its prowess in feature extraction and classification. Moreover, the research emphasizes the significance of rigorous data pre-processing, including image resizing, color normalization, and segmentation, in ensuring data quality and model reliability. In essence, this study illuminates the promising role of AI and DL in revolutionizing skin cancer diagnostics, offering insights into its potential applications in broader medical domains.

Keywords: artificial intelligence, machine learning, deep learning, skin cancer, dermatology, convolutional neural networks, image classification, computer vision, healthcare technology, cancer detection, medical imaging

Procedia PDF Downloads 46

Authors: Balimu Mwiya, Mundia Muya, Chabota Kaliba, Peter Mukalula

Abstract:

Factors affecting construction unit cost vary depending on a country’s political, economic, social and technological inclinations. Factors affecting construction costs have been studied from various perspectives. Analysis of cost factors requires an appreciation of a country’s practices. Identified cost factors provide an indication of a country’s construction economic strata. The purpose of this paper is to identify the essential factors that affect unit cost estimation and their breakdown using artificial neural networks. Twenty-five (25) identified cost factors in road construction were subjected to a questionnaire survey and employing SPSS factor analysis the factors were reduced to eight. The 8 factors were analysed using the neural network (NN) to determine the proportionate breakdown of the cost factors in a given construction unit rate. NN predicted that political environment accounted 44% of the unit rate followed by contractor capacity at 22% and financial delays, project feasibility, overhead and profit each at 11%. Project location, material availability and corruption perception index had minimal impact on the unit cost from the training data provided. Quantified cost factors can be incorporated in unit cost estimation models (UCEM) to produce more accurate estimates. This can create improvements in the cost estimation of infrastructure projects and establish a benchmark standard to assist the process of alignment of work practises and training of new staff, permitting the on-going development of best practises in cost estimation to become more effective.

Keywords: construction cost factors, neural networks, roadworks, Zambian construction industry

Procedia PDF Downloads 332

Authors: Pau Rodriguez, Jordi Gonzalez, Josep M. Gonfaus, Xavier Roca

Abstract:

Image sharing in social networks has increased exponentially in the past years. Officially, there are 600 million Instagrammers uploading around 100 million photos and videos per day. Consequently, there is a need for developing new tools to understand the content expressed in shared images, which will greatly benefit social media communication and will enable broad and promising applications in education, advertisement, entertainment, and also psychology. Following these trends, our work aims to take advantage of the existing relationship between text and personality, already demonstrated by multiple researchers, so that we can prove that there exists a relationship between images and personality as well. To achieve this goal, we consider that images posted on social networks are typically conditioned on specific words, or hashtags, therefore any relationship between text and personality can also be observed with those posted images. Our proposal makes use of the most recent image understanding models based on neural networks to process the vast amount of data generated by social users to determine those images most correlated with personality traits. The final aim is to train a weakly-supervised image-based model for personality assessment that can be used even when textual data is not available, which is an increasing trend. The procedure is described next: we explore the images directly publicly shared by users based on those accompanying texts or hashtags most strongly related to personality traits as described by the OCEAN model. These images will be used for personality prediction since they have the potential to convey more complex ideas, concepts, and emotions. As a result, the use of images in personality questionnaires will provide a deeper understanding of respondents than through words alone. In other words, from the images posted with specific tags, we train a deep learning model based on neural networks, that learns to extract a personality representation from a picture and use it to automatically find the personality that best explains such a picture. Subsequently, a deep neural network model is learned from thousands of images associated with hashtags correlated to OCEAN traits. We then analyze the network activations to identify those pictures that maximally activate the neurons: the most characteristic visual features per personality trait will thus emerge since the filters of the convolutional layers of the neural model are learned to be optimally activated depending on each personality trait. For example, among the pictures that maximally activate the high Openness trait, we can see pictures of books, the moon, and the sky. For high Conscientiousness, most of the images are photographs of food, especially healthy food. The high Extraversion output is mostly activated by pictures of a lot of people. In high Agreeableness images, we mostly see flower pictures. Lastly, in the Neuroticism trait, we observe that the high score is maximally activated by animal pets like cats or dogs. In summary, despite the huge intra-class and inter-class variabilities of the images associated to each OCEAN traits, we found that there are consistencies between visual patterns of those images whose hashtags are most correlated to each trait.

Keywords: emotions and effects of mood, social impact theory in social psychology, social influence, social structure and social networks

Procedia PDF Downloads 164

Authors: Umair Rashid

Abstract:

Normally softmax loss is used as the supervision signal in face recognition (FR) system, and it boosts the separability of features. In the last two years, a number of techniques have been proposed by reformulating the original softmax loss to enhance the discriminating power of Deep Convolutional Neural Networks (DCNNs) for FR system. To learn angularly discriminative features Cosine-Margin based softmax has been adjusted as monotonically decreasing angular function, that is the main challenge for angular based softmax. On that issue, we propose monotonically decreasing element for Cosine-Margin based softmax and also, we discussed the effect of different monotonically decreasing parameters on angular Margin softmax for FR system. We train the model on publicly available dataset CASIA- WebFace via our proposed monotonically decreasing parameters for cosine function and the tests on YouTube Faces (YTF, Labeled Face in the Wild (LFW), VGGFace1 and VGGFace2 attain the state-of-the-art performance.

Keywords: deep convolutional neural networks, cosine margin face recognition, softmax loss, monotonically decreasing parameter

Procedia PDF Downloads 65

Authors: Anoop T. R., Otman Basir, Robert F. Hess, Eileen E. Birch, Brooke A. Koritala, Reed M. Jost, Becky Luu, David Stager, Ben Thompson

Abstract:

Strabismus refers to a misalignment of the eyes. Early detection and treatment of strabismus in childhood can prevent the development of permanent vision loss due to abnormal development of visual brain areas. We developed a two-stage method for strabismus detection and classification based on photographs of the face. The first stage detects the presence or absence of strabismus, and the second stage classifies the type of strabismus. The first stage comprises face detection using Haar cascade, facial landmark estimation, face alignment, aligned face landmark detection, segmentation of the eye region, and detection of strabismus using VGG 16 convolution neural networks. Face alignment transforms the face to a canonical pose to ensure consistency in subsequent analysis. Using facial landmarks, the eye region is segmented from the aligned face and fed into a VGG 16 CNN model, which has been trained to classify strabismus. The CNN determines whether strabismus is present and classifies the type of strabismus (exotropia, esotropia, and vertical deviation). If stage 1 detects strabismus, the eye region image is fed into stage 2, which starts with the estimation of pupil center coordinates using mask R-CNN deep neural networks. Then, the distance between the pupil coordinates and eye landmarks is calculated along with the angle that the pupil coordinates make with the horizontal and vertical axis. The distance and angle information is used to characterize the degree and direction of the strabismic eye misalignment. This model was tested on 100 clinically labeled images of children with (n = 50) and without (n = 50) strabismus. The True Positive Rate (TPR) and False Positive Rate (FPR) of the first stage were 94% and 6% respectively. The classification stage has produced a TPR of 94.73%, 94.44%, and 100% for esotropia, exotropia, and vertical deviations, respectively. This method also had an FPR of 5.26%, 5.55%, and 0% for esotropia, exotropia, and vertical deviation, respectively. The addition of one more feature related to the location of corneal light reflections may reduce the FPR, which was primarily due to children with pseudo-strabismus (the appearance of strabismus due to a wide nasal bridge or skin folds on the nasal side of the eyes).

Keywords: strabismus, deep neural networks, face detection, facial landmarks, face alignment, segmentation, VGG 16, mask R-CNN, pupil coordinates, angle deviation, horizontal and vertical deviation

Procedia PDF Downloads 56

Authors: Girish J. Showkatramani, Arthi M. Krishna, Sashi Nareddi, Naresh Nula, Aaron Pepe, Glen Brown, Greg Gabel, Chris Doninger

Abstract:

Trademark examination and approval is a complex process that involves analysis and review of the design components of the marks such as the visual representation as well as the textual data associated with marks such as marks' description. Currently, the process of identifying marks with similar visual representation is done manually in United States Patent and Trademark Office (USPTO) and takes a considerable amount of time. Moreover, the accuracy of these searches depends heavily on the experts determining the trademark design codes used to catalog the visual design codes in the mark. In this study, we explore several methods to automate trademark design code classification. Based on recent successes of convolutional neural networks in image classification, we have used several different convolutional neural networks such as Google’s Inception v3, Inception-ResNet-v2, and Xception net. The study also looks into other techniques to augment the results from CNNs such as using Open Source Computer Vision Library (OpenCV) to pre-process the images. This paper reports the results of the various models trained on year of annotated trademark images.

Keywords: trademark design code, convolutional neural networks, trademark image classification, trademark image search, Inception-ResNet-v2

Procedia PDF Downloads 198

Authors: Felipe A. Guth, Shane Ward, Kevin McDonnell

Abstract:

The assessment of disease levels in crop fields is an important and time-consuming task that generally relies on expert knowledge of trained individuals. Image classification in agriculture problems historically has been based on classical machine learning strategies that make use of hand-engineered features in the top of a classification algorithm. This approach tends to not produce results with high accuracy and generalization to the classes classified by the system when the nature of the elements has a significant variability. The advent of deep convolutional neural networks has revolutionized the field of machine learning, especially in computer vision tasks. These networks have great resourcefulness of learning and have been applied successfully to image classification and object detection tasks in the last years. The objective of this work was to propose a new method based on deep learning convolutional neural networks towards the task of disease level monitoring. Common RGB images of winter wheat were obtained during a growing season. Five categories of disease levels presence were produced, in collaboration with agronomists, for the algorithm classification. Disease level tasks performed by experts provided ground truth data for the disease score of the same winter wheat plots were RGB images were acquired. The system had an overall accuracy of 84% on the discrimination of the disease level classes.

Keywords: crop disease assessment, deep learning, precision agriculture, residual neural networks

Procedia PDF Downloads 297

Authors: Cheng Zeng, George Michailidis, Hitoshi Iyatomi, Leo L. Duan

Abstract:

The conditional density characterizes the distribution of a response variable y given other predictor x and plays a key role in many statistical tasks, including classification and outlier detection. Although there has been abundant work on the problem of Conditional Density Estimation (CDE) for a low-dimensional response in the presence of a high-dimensional predictor, little work has been done for a high-dimensional response such as images. The promising performance of normalizing flow (NF) neural networks in unconditional density estimation acts as a motivating starting point. In this work, the authors extend NF neural networks when external x is present. Specifically, they use the NF to parameterize a one-to-one transform between a high-dimensional y and a latent z that comprises two components [zₚ, zₙ]. The zₚ component is a low-dimensional subvector obtained from the posterior distribution of an elementary predictive model for x, such as logistic/linear regression. The zₙ component is a high-dimensional independent Gaussian vector, which explains the variations in y not or less related to x. Unlike existing CDE methods, the proposed approach coined Augmented Posterior CDE (AP-CDE) only requires a simple modification of the common normalizing flow framework while significantly improving the interpretation of the latent component since zₚ represents a supervised dimension reduction. In image analytics applications, AP-CDE shows good separation of 𝑥-related variations due to factors such as lighting condition and subject id from the other random variations. Further, the experiments show that an unconditional NF neural network based on an unsupervised model of z, such as a Gaussian mixture, fails to generate interpretable results.

Keywords: conditional density estimation, image generation, normalizing flow, supervised dimension reduction

Procedia PDF Downloads 65

Authors: P. S. Jagadeesh Kumar, Yang Yung, Mingmin Pan, Xianpei Li, Wenli Hu

Abstract:

Glaucoma is impelled by optic nerve mutilation habitually represented as cupping and visual field injury frequently with an arcuate pattern of mid-peripheral loss, subordinate to retinal ganglion cell damage and death. Glaucoma is the second foremost cause of blindness and the chief cause of permanent blindness worldwide. Consequently, all-embracing study into the analysis and empathy of glaucoma is happening to escort deep learning based neural network intrusions to deliberate this substantial optic neuropathy. This paper advances an ophthalmic hashing based supervision of glaucoma and corneal disorders preeminent on deep graphical model. Ophthalmic hashing is a newly proposed method extending the efficacy of visual hash-coding to predict glaucoma corneal disorder matching, which is the faster than the existing methods. Deep graphical model is proficient of learning interior explications of corneal disorders in satisfactory time to solve hard combinatoric incongruities using deep Boltzmann machines.

Keywords: corneal disorders, deep Boltzmann machines, deep graphical model, glaucoma, neural networks, ophthalmic hashing

Procedia PDF Downloads 215

Authors: Laidi Maamar, Hanini Salah

Abstract:

The present work investigates the potential of artificial neural network (ANN) model to predict the horizontal global solar radiation (HGSR). The ANN is developed and optimized using three years meteorological database from 2011 to 2013 available at the meteorological station of Blida (Blida 1 university, Algeria, Latitude 36.5°, Longitude 2.81° and 163 m above mean sea level). Optimal configuration of the ANN model has been determined by minimizing the Root Means Square Error (RMSE) and maximizing the correlation coefficient (R2) between observed and predicted data with the ANN model. To select the best ANN architecture, we have conducted several tests by using different combinations of parameters. A two-layer ANN model with six hidden neurons has been found as an optimal topology with (RMSE=4.036 W/m²) and (R²=0.999). A graphical user interface (GUI), was designed based on the best network structure and training algorithm, to enhance the users’ friendliness application of the model.

Keywords: artificial neural network, global solar radiation, solar energy, prediction, Algeria

Procedia PDF Downloads 472

Authors: Sirilak Areerachakul, Nat Ployong, Supayothin Na Songkla

Abstract:

This research’s objective is to select the model with most accurate value by using Neural Network Technique as a way to filter potential students who enroll in IT course by electronic learning at Suan Suanadha Rajabhat University. It is designed to help students selecting the appropriate courses by themselves. The result showed that the most accurate model was 100 Folds Cross-validation which had 73.58% points of accuracy.

Keywords: artificial neural network, classification, students, e-learning

Procedia PDF Downloads 394

Authors: Biruhi Tesfaye, Avinash M. Potdar

Abstract:

The laboratory test process to determine the California bearing ratio (CBR) of black cotton soils is not only overpriced but also time-consuming as well. Hence advanced prediction of CBR plays a significant role as it is applicable In pavement design. The prediction of CBR of treated soil was executed by Artificial Neural Networks (ANNs) which is a Computational tool based on the properties of the biological neural system. To observe CBR values, combined eggshell and waste glass was added to soil as 4, 8, 12, and 16 % of the weights of the soil samples. Accordingly, the laboratory related tests were conducted to get the required best model. The maximum CBR value found at 5.8 at 8 % of eggshell waste glass powder addition. The model was developed using CBR as an output layer variable. CBR was considered as a function of the joint effect of liquid limit, plastic limit, and plastic index, optimum moisture content and maximum dry density. The best model that has been found was ANN with 5, 6 and 1 neurons in the input, hidden and output layer correspondingly. The performance of selected ANN has been 0.99996, 4.44E-05, 0.00353 and 0.0067 which are correlation coefficient (R), mean square error (MSE), mean absolute error (MAE) and root mean square error (RMSE) respectively. The research presented or summarized above throws light on future scope on stabilization with waste glass combined with different percentages of eggshell that leads to the economical design of CBR acceptable to pavement sub-base or base, as desired.

Keywords: CBR, artificial neural network, liquid limit, plastic limit, maximum dry density, OMC

Procedia PDF Downloads 155

Authors: Jonathan Sohn

Abstract:

Deep neural networks (DNNs) have shown state-of-the-art performance for many applications, including computer vision, natural language processing, and speech recognition. Recently, adversarial attacks have been studied in the context of deep neural networks, which aim to alter the results of deep neural networks by modifying the inputs slightly. For example, an adversarial attack on a DNN used for object detection can cause the DNN to miss certain objects. As a result, the reliability of DNNs is undermined by their lack of robustness against adversarial attacks, raising concerns about their use in safety-critical applications such as autonomous driving. In this paper, we focus on studying the adversarial attacks and defenses on DNNs for image classification. There are two types of adversarial attacks studied which are fast gradient sign method (FGSM) attack and projected gradient descent (PGD) attack. A DNN forms decision boundaries that separate the input images into different categories. The adversarial attack slightly alters the image to move over the decision boundary, causing the DNN to misclassify the image. FGSM attack obtains the gradient with respect to the image and updates the image once based on the gradients to cross the decision boundary. PGD attack, instead of taking one big step, repeatedly modifies the input image with multiple small steps. There is also another type of attack called the target attack. This adversarial attack is designed to make the machine classify an image to a class chosen by the attacker. We can defend against adversarial attacks by incorporating adversarial examples in training. Specifically, instead of training the neural network with clean examples, we can explicitly let the neural network learn from the adversarial examples. In our experiments, the digit recognition accuracy on the MNIST dataset drops from 97.81% to 39.50% and 34.01% when the DNN is attacked by FGSM and PGD attacks, respectively. If we utilize FGSM training as a defense method, the classification accuracy greatly improves from 39.50% to 92.31% for FGSM attacks and from 34.01% to 75.63% for PGD attacks. To further improve the classification accuracy under adversarial attacks, we can also use a stronger PGD training method. PGD training improves the accuracy by 2.7% under FGSM attacks and 18.4% under PGD attacks over FGSM training. It is worth mentioning that both FGSM and PGD training do not affect the accuracy of clean images. In summary, we find that PGD attacks can greatly degrade the performance of DNNs, and PGD training is a very effective way to defend against such attacks. PGD attacks and defence are overall significantly more effective than FGSM methods.

Keywords: deep neural network, adversarial attack, adversarial defense, adversarial machine learning

Procedia PDF Downloads 158

Authors: A. Clementking, C. Jothi Venkateswaran

Abstract:

Mathematical and computational functionalities such as descriptive mining, optimization, and predictions are espoused to resolve natural resource planning. The water quality prediction and its attributes influence determinations are adopted optimization techniques. The water properties are tainted while merging water resource one with another. This work aimed to predict influencing water resource distribution connectivity in accordance to water quality and sediment using an innovative proposed master-slave neural network back-propagation model. The experiment results are arrived through collecting water quality attributes, computation of water quality index, design and development of neural network model to determine water quality and sediment, master–slave back propagation neural network back-propagation model to determine variations on water quality and sediment attributes between the water resources and the recommendation for connectivity. The homogeneous and parallel biochemical reactions are influences water quality and sediment while distributing water from one location to another. Therefore, an innovative master-slave neural network model [M (9:9:2)::S(9:9:2)] designed and developed to predict the attribute variations. The result of training dataset given as an input to master model and its maximum weights are assigned as an input to the slave model to predict the water quality. The developed master-slave model is predicted physicochemical attributes weight variations for 85 % to 90% of water quality as a target values.The sediment level variations also predicated from 0.01 to 0.05% of each water quality percentage. The model produced the significant variations on physiochemical attribute weights. According to the predicated experimental weight variation on training data set, effective recommendations are made to connect different resources.

Keywords: master-slave back propagation neural network model(MSBPNNM), water quality analysis, multivariate analysis, environmental mining

Procedia PDF Downloads 445

Authors: Nkechinyere Joy Olawuyi, Babajide Samuel Afolabi, Bola Ibitoye

Abstract:

This study collected a preprocessed dataset of chest radiographs and formulated a deep neural network model for detecting abnormalities. It also evaluated the performance of the formulated model and implemented a prototype of the formulated model. This was with the view to developing a deep neural network model to automatically classify abnormalities in chest radiographs. In order to achieve the overall purpose of this research, a large set of chest x-ray images were sourced for and collected from the CheXpert dataset, which is an online repository of annotated chest radiographs compiled by the Machine Learning Research Group, Stanford University. The chest radiographs were preprocessed into a format that can be fed into a deep neural network. The preprocessing techniques used were standardization and normalization. The classification problem was formulated as a multi-label binary classification model, which used convolutional neural network architecture to make a decision on whether an abnormality was present or not in the chest radiographs. The classification model was evaluated using specificity, sensitivity, and Area Under Curve (AUC) score as the parameter. A prototype of the classification model was implemented using Keras Open source deep learning framework in Python Programming Language. The AUC ROC curve of the model was able to classify Atelestasis, Support devices, Pleural effusion, Pneumonia, A normal CXR (no finding), Pneumothorax, and Consolidation. However, Lung opacity and Cardiomegaly had a probability of less than 0.5 and thus were classified as absent. Precision, recall, and F1 score values were 0.78; this implies that the number of False Positive and False Negative is the same, revealing some measure of label imbalance in the dataset. The study concluded that the developed model is sufficient to classify abnormalities present in chest radiographs into present or absent.

Keywords: transfer learning, convolutional neural network, radiograph, classification, multi-label

Procedia PDF Downloads 85

Authors: Jamerson Felipe Pereira Lima, Jeane Cecília Bezerra de Melo

Abstract:

The difficulty and cost related to obtaining of protein tertiary structure information through experimental methods, such as X-ray crystallography or NMR spectroscopy, helped raising the development of computational methods to do so. An approach used in these last is prediction of tridimensional structure based in the residue chain, however, this has been proved an NP-hard problem, due to the complexity of this process, explained by the Levinthal paradox. An alternative solution is the prediction of intermediary structures, such as the secondary structure of the protein. Artificial Intelligence methods, such as Bayesian statistics, artificial neural networks (ANN), support vector machines (SVM), among others, were used to predict protein secondary structure. Due to its good results, artificial neural networks have been used as a standard method to predict protein secondary structure. Recent published methods that use this technique, in general, achieved a Q3 accuracy between 75% and 83%, whereas the theoretical accuracy limit for protein prediction is 88%. Alternatively, to achieve better results, support vector machines prediction methods have been developed. The statistical evaluation of methods that use different AI techniques, such as ANNs and SVMs, for example, is not a trivial problem, since different training sets, validation techniques, as well as other variables can influence the behavior of a prediction method. In this study, we propose a prediction method based on artificial neural networks, which is then compared with a selected SVM method. The chosen SVM protein secondary structure prediction method is the one proposed by Huang in his work Extracting Physico chemical Features to Predict Protein Secondary Structure (2013). The developed ANN method has the same training and testing process that was used by Huang to validate his method, which comprises the use of the CB513 protein data set and three-fold cross-validation, so that the comparative analysis of the results can be made comparing directly the statistical results of each method.

Keywords: artificial neural networks, protein secondary structure, protein structure prediction, support vector machines

Procedia PDF Downloads 583

Authors: Salim Ouchtati, Jean Sequeira, Mouldi Bedda

Abstract:

In this work we present an off line system for the recognition of the Arabic handwritten words of the Algerian departments. The study is based mainly on the evaluation of neural network performances, trained with the gradient back propagation algorithm. The used parameters to form the input vector of the neural network are extracted on the binary images of the handwritten word by several methods: the parameters of distribution, the moments centered of the different projections and the Barr features. It should be noted that these methods are applied on segments gotten after the division of the binary image of the word in six segments. The classification is achieved by a multi layers perceptron. Detailed experiments are carried and satisfactory recognition results are reported.

Keywords: handwritten word recognition, neural networks, image processing, pattern recognition, features extraction

Procedia PDF Downloads 483

Authors: Rehab Abdulmajed, Amr Hamada, Ahmed Elsaid, Hisashi Hayakawa, Ayman Mahrous

Abstract:

Solar emissions have a high impact on the Earth’s magnetic field, and the prediction of solar events is of high interest. Various techniques have been used in the prediction of solar wind using mathematical models, MHD models, and neural network (NN) models. This study investigates the coronal hole (CH) derived high-speed streams (HSSs) and their correlation to the CH area and create a neural network model to predict the HSSs. Two different algorithms were used to compare different models to find a model that best simulates the HSSs. A dataset of CH synoptic maps through Carrington rotations 1601 to 2185 along with Omni-data set solar wind speed averaged over the Carrington rotations is used, which covers Solar cycles (sc) 21, 22, 23, and most of 24.

Keywords: artificial neural network, coronal hole area, feed-forward neural network models, solar high speed streams

Procedia PDF Downloads 56

Authors: Motonobu Hattori

Abstract:

In neural networks, when new patters are learned by a network, they radically interfere with previously stored patterns. This drawback is called catastrophic forgetting. We have already proposed a biologically inspired dual-network memory model which can much reduce this forgetting for static patterns. In this model, information is first stored in the hippocampal network, and thereafter, it is transferred to the neocortical network using pseudo patterns. Because, temporal sequence learning is more important than static pattern learning in the real world, in this study, we improve our conventional dual-network memory model so that it can deal with temporal sequences without catastrophic forgetting. The computer simulation results show the effectiveness of the proposed dual-network memory model.

Keywords: catastrophic forgetting, dual-network, temporal sequences, hippocampal

Procedia PDF Downloads 239