Search results for: bit-serial neural processor

Authors: Adel Bougamouza, Boualam Remini, Abd El Hadi Ammari, Feteh Sakhraoui

Abstract:

The assessment of sediments being carried by a river is importance for planning and designing of various water resources projects. In this study, Artificial Neural Network Techniques are used to estimate the daily suspended sediment concentration for the corresponding daily discharge flow in the upstream of Foum El Gherza dam, Biskra, Algeria. The FFNN, GRNN, and RBNN models are established for estimating current suspended sediment values. Some statistics involving RMSE and R2 were used to evaluate the performance of applied models. The comparison of three AI models showed that the RBNN model performed better than the FFNN and GRNN models with R2 = 0.967 and RMSE= 5.313 mg/l. Therefore, the ANN model had capability to improve nonlinear relationships between discharge flow and suspended sediment with reasonable precision.

Keywords: artificial neural network, Oued Abiod watershed, feedforward network, generalized regression network, radial basis network, sediment concentration

Procedia PDF Downloads 417

Authors: Riznaldi Akbar

Abstract:

In this study, we compared the performance of the Artificial Neural Network (ANN) model with back-propagation algorithm in correctly predicting in-sample and out-of-sample external debt crisis in Indonesia. We found that exchange rate, foreign reserves, and exports are the major determinants to experiencing external debt crisis. The ANN in-sample performance provides relatively superior results. The ANN model is able to classify correctly crisis of 89.12 per cent with reasonably low false alarms of 7.01 per cent. In out-of-sample, the prediction performance fairly deteriorates compared to their in-sample performances. It could be explained as the ANN model tends to over-fit the data in the in-sample, but it could not fit the out-of-sample very well. The 10-fold cross-validation has been used to improve the out-of-sample prediction accuracy. The results also offer policy implications. The out-of-sample performance could be very sensitive to the size of the samples, as it could yield a higher total misclassification error and lower prediction accuracy. The ANN model could be used to identify past crisis episodes with some accuracy, but predicting crisis outside the estimation sample is much more challenging because of the presence of uncertainty.

Keywords: debt crisis, external debt, artificial neural network, ANN

Procedia PDF Downloads 437

Authors: Sezin Ekşioğlu

Abstract:

Multilabel classification has a huge importance for several applications, it is also a challenging research topic. It is a kind of supervised learning that contains binary targets. The distance between multilabel and binary classification is having more than one class in multilabel classification problems. Features can belong to one class or many classes. There exists a wide range of applications for multi label prediction such as image labeling, text categorization, gene functionality. Even though features are classified in many classes, they may not always be properly classified. There are many ensemble methods for the classification. However, most of the researchers have been concerned about better multilabel methods. Especially little ones focus on both efficiency of classifiers and pairwise relationships at the same time in order to implement better multilabel classification. In this paper, we worked on modified ensemble methods by getting benefit from k-Nearest Neighbors and neural network structure to address issues within a beneficial way and to get better impacts from the multilabel classification. Publicly available datasets (yeast, emotion, scene and birds) are performed to demonstrate the developed algorithm efficiency and the technique is measured by accuracy, F1 score and hamming loss metrics. Our algorithm boosts benchmarks for each datasets with different metrics.

Keywords: multilabel, classification, neural network, KNN

Procedia PDF Downloads 151

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 193

Authors: Yilin Liao, Hewen Li, Paula McConvey

Abstract:

Speed skaters often face a risk of concussion when they fall on the ice floor and impact crash mats during practices and competitive races. Several variables, including those related to the skater, the crash mat, and the impact position (body side/head/feet impact), are believed to influence the severity of the skater's concussion. While computer simulation modeling can be employed to analyze these accidents, the simulation process is time-consuming and does not provide rapid information for coaches and teams to assess the skater's injury risk in competitive events. This research paper promotes the exploration of the feasibility of using AI techniques for evaluating skater’s potential concussion severity, and to develop a fast concussion prediction tool using artificial neural networks to reduce the risk of treatment delays for injured skaters. The primary data is collected through virtual tests and physical experiments designed to simulate skater-mat impact. It is then analyzed to identify patterns and correlations; finally, it is used to train and fine-tune the artificial neural networks for accurate prediction. The development of the prediction tool by employing machine learning strategies contributes to the application of AI methods in sports science and has theoretical involvements for using AI techniques in predicting and preventing sports-related injuries.

Keywords: artificial neural networks, concussion, machine learning, impact, speed skater

Procedia PDF Downloads 108

Authors: F. Massri, M. Shkarneh, B. Almassri

Abstract:

Water scarcity and increasing water demand especially for residential use are major challenges facing Palestine. The need to accurately forecast water consumption is useful for the planning and management of this natural resource. The main objective of this paper is to (i) study the major factors influencing the water consumption in Palestine, (ii) understand the general pattern of Household water consumption, (iii) assess the possible changes in household water consumption and suggest appropriate remedies and (iv) develop prediction model based on the Artificial Neural Network to the water consumption in Palestinian cities. The paper is organized in four parts. The first part includes literature review of household water consumption studies. The second part concerns data collection methodology, conceptual frame work for the household water consumption surveys, survey descriptions and data processing methods. The third part presents descriptive statistics, multiple regression and analysis of the water consumption in the two Palestinian cities. The final part develops the use of Artificial Neural Network for modeling the water consumption in Palestinian cities.

Keywords: water management, demand forecasting, consumption, ANN, Ramallah

Procedia PDF Downloads 217

Authors: Jérémie Ochin

Abstract:

Soccer analytics are built on two data sources: the frame-by-frame position of each player on the terrain and the sequences of events, such as ball drive, pass, cross, shot, throw-in... With more than 2000 ball-events per soccer game, their precise and exhaustive annotation, based on a monocular video stream such as a TV broadcast, remains a tedious and costly manual task. State-of-the-art methods for spatio-temporal action detection from a monocular video stream, often based on 3D convolutional neural networks, are close to reach levels of performances in mean Average Precision (mAP) compatibles with the automation of such task. Nevertheless, to meet their expectation of exhaustiveness in the context of data analytics, such methods must be applied in a regime of high recall – low precision, using low confidence score thresholds. This setting unavoidably leads to the detection of false positives that are the product of the well documented overconfidence behaviour of neural networks and, in this case, their limited access to contextual information and understanding of the game: their predictions are highly unstructured. Based on the assumption that professional soccer players’ behaviour, pose, positions and velocity are highly interrelated and locally driven by the player performing a ball-action, it is hypothesized that the addition of information regarding surrounding player’s appearance, positions and velocity in the prediction methods can improve their metrics. Several methods are compared to build a proper representation of the game surrounding a player, from handcrafted features of the local graph, based on domain knowledge, to the use of Graph Neural Networks trained in an end-to-end fashion with existing state-of-the-art 3D convolutional neural networks. It is shown that the inclusion of information regarding surrounding players helps reaching higher metrics.

Keywords: fine-grained action recognition, human action recognition, convolutional neural networks, graph neural networks, spatio-temporal action recognition

Procedia PDF Downloads 22

Authors: Xiao-Yin Liu, Liang-Xue Zhou

Abstract:

Traumatic brain injury (TBI), as a kind of nerve trauma caused by an external force, affects people all over the world and is a global public health problem. Although there are various clinical treatments for brain injury, including surgery, drug therapy, and rehabilitation therapy, the therapeutic effect is very limited. To improve the therapeutic effect of TBI, scaffolds combined with exosomes are a promising but challenging method for TBI repair. In this study, we examined whether a novel 3D-printed collagen/chitosan scaffold/exosomes derived from neural stem cells (NSCs) pretreated with insulin growth factor-1 (IGF-I) scaffolds (3D-CC-INExos) could be used to improve TBI repair and functional recovery after TBI. Our results showed that composite scaffolds of collagen-, chitosan- and exosomes derived from NSCs pretreated with IGF-I (INExos) could continuously release the exosomes for two weeks. In the rat TBI model, 3D-CC-INExos scaffold transplantation significantly improved motor and cognitive function after TBI, as assessed by the Morris water maze test and modified neurological severity scores. In addition, immunofluorescence staining and transmission electron microscopy showed that the recovery of damaged nerve tissue in the injured area was significantly improved by 3D-CC-INExos implantation. In conclusion, our data suggest that 3D-CC-INExos might provide a potential strategy for the treatment of TBI and lay a solid foundation for clinical translation.

Keywords: traumatic brain injury, exosomes, insulin growth factor-1, neural stem cells, collagen, chitosan, 3D printing, neural regeneration, angiogenesis, functional recovery

Procedia PDF Downloads 79

Authors: Benjamin Bobbia, Matthias Picard

Abstract:

In recent years active learning methodologies based on the representativity of the data seems more promising to limit overfitting. The presented query methodology for regression using the Wasserstein distance measuring the representativity of our labelled dataset compared to the global distribution. In this work a crucial use of GroupSort Neural Networks is made therewith to draw a double advantage. The Wasserstein distance can be exactly expressed in terms of such neural networks. Moreover, one can provide explicit bounds for their size and depth together with rates of convergence. However, heterogeneity of the dataset is also considered by weighting the Wasserstein distance with the error of approximation at the previous step of active learning. Such an approach leads to a reduction of overfitting and high prediction performance after few steps of query. After having detailed the methodology and algorithm, an empirical study is presented in order to investigate the range of our hyperparameters. The performances of this method are compared, in terms of numbers of query needed, with other classical and recent query methods on several UCI datasets.

Keywords: active learning, Lipschitz regularization, neural networks, optimal transport, regression

Procedia PDF Downloads 80

Authors: Ying Li, Yan Li

Abstract:

A new algorithm for single hidden layer feedforward neural networks (SLFN), Orthogonal Basis Extreme Learning (OBEL) algorithm, is proposed and the algorithm derivation is given in the paper. The algorithm can decide both the NNs parameters and the neuron number of hidden layer(s) during training while providing extreme fast learning speed. It will provide a practical way to develop NNs. The simulation results of function approximation showed that the algorithm is effective and feasible with good accuracy and adaptability.

Keywords: neural network, orthogonal basis extreme learning, function approximation

Procedia PDF Downloads 533

Authors: Deba Kumar Sarma, Sanjib Kr. Rajbongshi

Abstract:

Surface finish is an important product quality in machining. At first, experiments were carried out to investigate the effect of the cutting tool nose radius (considering 1mm and 0.65mm) in prediction of surface finish with process parameters of cutting speed, feed and depth of cut. For all possible cutting conditions, full factorial design was considered as two levels four parameters. Commercial Mild Steel bar and High Speed Steel (HSS) material were considered as work-piece and cutting tool material respectively. In order to obtain functional relationship between process parameters and surface roughness, neural network was used which was found to be capable for the prediction of surface roughness within a reasonable degree of accuracy. It was observed that tool nose radius of 1mm provides better surface finish in comparison to 0.65 mm. Also, it was observed that feed rate has a significant influence on surface finish.

Keywords: full factorial design, neural network, nose radius, surface finish

Procedia PDF Downloads 365

Authors: M. Khajezadeh, M. Saied Fallah Niasar, S. Ali Asli, D. Davani Davari, M. Godarzi, Y. Asgari

Abstract:

This study aims to explore the joint application of both Boston and Ansoff matrices in the operational development of the product. We conduct deep analysis, by utilizing the Artificial Neural Network, to predict the position of the product in the market while the company is interested in increasing its share. The data are gathered from two industries, called hygiene and detergent. In doing so, the effort is being made by investigating the behavior of top player companies and, recommend strategic orientations. In conclusion, this combination analysis is appropriate for operational development; as well, it plays an important role in providing the position of the product in the market for both hygiene and detergent industries. More importantly, it will elaborate on the company’s strategies to increase its market share related to a combination of the Boston Consulting Group (BCG) Matrix and Ansoff Matrix.

Keywords: artificial neural network, portfolio analysis, BCG matrix, Ansoff matrix

Procedia PDF Downloads 140

Authors: Sharad Shrivastava, Arun Jalan

Abstract:

In this study tensile testing was performed on randomly oriented short glass fiber/epoxy resin composite specimens which were prepared using hand lay-up method. Samples were tested over a wide range of strain rate/loading rate from 2mm/min to 40mm/min to see the effect on ultimate tensile strength of the composite. A multi layered 'back propagation artificial neural network of supervised learning type' was used to analyze and predict the tensile properties with strain rate and temperature as given input and output as UTS to predict. Various network structures were designed and investigated with varying parameters and network sizes, and an optimized network structure was proposed to predict the UTS of short glass fiber/epoxy resin composite specimens with reasonably good accuracy.

Keywords: glass fiber composite, mechanical properties, strain rate, artificial neural network

Procedia PDF Downloads 436

Authors: Mona Lisa M. Oliveira, Nara A. Policarpo, Ana Luiza B. P. Barros, Carla A. Silva

Abstract:

Selective catalytic reduction systems for nitrogen oxides reduction by ammonia has been the chosen technology by most of diesel vehicle (i.e. bus and truck) manufacturers in Brazil, as also in Europe. Furthermore, at some conditions, over-stoichiometric ammonia availability is also needed that increases the NH₃ slips even more. Ammonia (NH₃) by this vehicle exhaust aftertreatment system provides a maximum efficiency of NOx removal if a significant amount of NH₃ is stored on its catalyst surface. In the other words, the practice shows that slightly less than 100% of the NOx conversion is usually targeted, so that the aqueous urea solution hydrolyzes to NH₃ via other species formation, under relatively low temperatures. This paper presents a model based on neural networks integrated with a road vehicle simulator that allows to estimate NH₃-slip emission factors for different driving conditions and patterns. The proposed model generates high NH₃slips which are not also limited in Brazil, but more efforts needed to be made to elucidate the contribution of vehicle-emitted NH₃ to the urban atmosphere.

Keywords: ammonia slip, neural-network, vehicles emissions, SCR-NOx

Procedia PDF Downloads 212

Authors: Milagros Jaén-Vargas, Javier García Martínez, Karla Miriam Reyes Leiva, María Fernanda Trujillo-Guerrero, Francisco Fernandes, Sérgio Barroso Gonçalves, Miguel Tavares Silva, Daniel Simões Lopes, José Javier Serrano Olmedo

Abstract:

Human Activity Recognition (HAR) is having a growing impact in creating new applications and is responsible for emerging new technologies. Also, the use of wearable sensors is an important key to exploring the human body's behavior when performing activities. Hence, the use of these dispositive is less invasive and the person is more comfortable. In this study, a database that includes three activities is used. The activities were acquired from inertial measurement unit sensors (IMU) and motion capture systems (MOCAP). The main objective is differentiating the performance from four Deep Learning (DL) models: Deep Neural Network (DNN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN) and hybrid model Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM), when considering acceleration, velocity and position and evaluate if integrating the IMU acceleration to obtain velocity and position represent an increment in performance when it works as input to the DL models. Moreover, compared with the same type of data provided by the MOCAP system. Despite the acceleration data is cleaned when integrating, results show a minimal increase in accuracy for the integrated signals.

Keywords: HAR, IMU, MOCAP, acceleration, velocity, position, feature maps

Procedia PDF Downloads 96

Authors: Henni Mansour Abdelwaheb

Abstract:

This study discusses the design of a bounded position/force feedback controller developed to ensure position and force tracking for bilateral teleoperation arms operating with variable delay, and actuator saturation. Also, an adaptive robust Radial Basis Function (RBF) neural network is used to estimate the environment torque. The parameters of the environment torque are then sent from the slave site to the master site as a non-power signal to avoid passivity problems. Moreover, a nonlinear function is applied to each controller term as a smooth saturation function, providing a bounded control signal and preserving the system’s actuators. Lastly, the Lyapunov approach demonstrates the global stability of the controlled system, and numerical experiment results further confirm the validity of the presented strategy.

Keywords: teleoperation manipulators system, time-varying delay, actuator saturation, adaptive robust rbf neural network approximation, uncertainties

Procedia PDF Downloads 73

Authors: Hanbey Hazar, Hakan Gul

Abstract:

In this study; piston, exhaust, and suction valves of a diesel engine were coated in 300 mm thickness with Tungsten Carbide (WC) by using the HVOF coating method. Mathematical modeling of a coated and uncoated (standardized) engine was performed by using ANN (Artificial Neural Networks). The purpose was to decrease the number of repetitions of tests and reduce the test cost through mathematical modeling of engines by using ANN. The results obtained from the tests were entered in ANN and therefore engines' values at all speeds were estimated. Results obtained from the tests were compared with those obtained from ANN and they were observed to be compatible. It was also observed that, with thermal barrier coating, hydrocarbon (HC), carbon monoxide (CO), and smoke density values of the diesel engine decreased; but nitrogen oxides (NOx) increased. Furthermore, it was determined that results obtained through mathematical modeling by means of ANN reduced the number of test repetitions. Therefore, it was understood that time, fuel and labor could be saved in this way.

Keywords: Artificial Neural Network, Diesel Engine, Mathematical Modelling, Thermal Barrier Coating

Procedia PDF Downloads 527

Authors: Jia Xin Low, Keng Wah Choo

Abstract:

This paper presents an automatic normal and abnormal heart sound classification model developed based on deep learning algorithm. MITHSDB heart sounds datasets obtained from the 2016 PhysioNet/Computing in Cardiology Challenge database were used in this research with the assumption that the electrocardiograms (ECG) were recorded simultaneously with the heart sounds (phonocardiogram, PCG). The PCG time series are segmented per heart beat, and each sub-segment is converted to form a square intensity matrix, and classified using convolutional neural network (CNN) models. This approach removes the need to provide classification features for the supervised machine learning algorithm. Instead, the features are determined automatically through training, from the time series provided. The result proves that the prediction model is able to provide reasonable and comparable classification accuracy despite simple implementation. This approach can be used for real-time classification of heart sounds in Internet of Medical Things (IoMT), e.g. remote monitoring applications of PCG signal.

Keywords: convolutional neural network, discrete wavelet transform, deep learning, heart sound classification

Procedia PDF Downloads 346

Authors: Jinan Fiaidhi, Sabah Mohammed

Abstract:

Cross-domain learning in the medical field is a research challenge as many conditions, like in oncology imaging, use different imaging modalities. Moreover, in most of the medical learning applications, the sample training size is relatively small. Although few-shot learning (FSL) through the use of a Siamese neural network was able to be trained on a small sample with remarkable accuracy, FSL fails to be effective for use in multiple domains as their convolution weights are set for task-specific applications. In this paper, we are addressing this problem by enabling FSL to possess the ability to shift across domains by designing a two-layer FSL network that can learn individually from each domain and produce a shared features map with extra modulation to be used at the second layer that can recognize important targets from mix domains. Our initial experimentations based on mixed medical datasets like the Medical-MNIST reveal promising results. We aim to continue this research to perform full-scale analytics for testing our cross-domain FSL learning.

Keywords: Siamese neural network, few-shot learning, meta-learning, metric-based learning, thick data transformation and analytics

Procedia PDF Downloads 55

Authors: Ashish Payal, C. S. Rai, B. V. R. Reddy

Abstract:

With the increasing use and application of Wireless Sensor Networks (WSN), need has arisen to explore them in more effective and efficient manner. An important area which can bring efficiency to WSNs is the localization process, which refers to the estimation of the position of wireless sensor nodes in an ad hoc network setting, in reference to a coordinate system that may be internal or external to the network. In this paper, we have done comparison and analysed Sigmoidal Feedforward Artificial Neural Networks (SFFANNs) and Radial Basis Function (RBF) networks for developing localization framework in WSNs. The presented work utilizes the Received Signal Strength Indicator (RSSI), measured by static node on 100 x 100 m² grid from three anchor nodes. The comprehensive evaluation of these approaches is done using MATLAB software. The simulation results effectively demonstrate that FFANNs based sensor motes will show better localization accuracy as compared to RBF.

Keywords: localization, wireless sensor networks, artificial neural network, radial basis function, multi-layer perceptron, backpropagation, RSSI, GPS

Procedia PDF Downloads 337

Authors: J. Balaraju, M. Govinda Raj, C. S. N. Murthy

Abstract:

Every industry is constantly looking for enhancement of its day to day production and productivity. This can be possible only by maintaining the men and machinery at its adequate level. Prediction of performance characteristics plays an important role in performance evaluation of the equipment. Analytical and statistical approaches will take a bit more time to solve complex problems such as performance estimations as compared with software-based approaches. Keeping this in view the present study deals with an Artificial Neural Network (ANN) modelling of a Load-Haul-Dump (LHD) machine to predict the performance characteristics such as reliability, availability and preventive maintenance (PM). A feed-forward-back-propagation ANN technique has been used to model the Levenberg-Marquardt (LM) training algorithm. The performance characteristics were computed using Isograph Reliability Workbench 13.0 software. These computed values were validated using predicted output responses of ANN models. Further, recommendations are given to the industry based on the performed analysis for improvement of equipment performance.

Keywords: load-haul-dump, LHD, artificial neural network, ANN, performance, reliability, availability, preventive maintenance

Procedia PDF Downloads 147

Authors: Go Woon Kwak, Siyoung Jun, Soyun Maeng, Haeyoung Lee

Abstract:

Entry is an education platform used in South Korea, created to help students learn to program, in which they can learn to code while playing. Using the online version of the entry, teachers can easily assign programming homework to the student and the students can make programs simply by linking programming blocks. However, the programs may be made by others, so that the authors of the programs should be identified. In this paper, as the first step toward author identification of entry programs, we present an artificial neural network based classification approach to identify genders of authors of a program written in an entry. A neural network has been trained from labeled training data that we have collected. Our result in progress, although preliminary, shows that the proposed approach could be feasible to be applied to the online version of entry for gender identification of authors. As future work, we will first use a machine learning technique for age identification of entry programs, which would be the second step toward the author identification.

Keywords: artificial intelligence, author identification, deep neural network, gender identification, machine learning

Procedia PDF Downloads 320

Authors: Yalong Jiang, Zheru Chi

Abstract:

In this paper, we study the factors which determine the capacity of a Convolutional Neural Network (CNN) model and propose the ways to evaluate and adjust the capacity of a CNN model for best matching to a specific pattern recognition task. Firstly, a scheme is proposed to adjust the number of independent functional units within a CNN model to make it be better fitted to a task. Secondly, the number of independent functional units in the capsule network is adjusted to fit it to the training dataset. Thirdly, a method based on Bayesian GAN is proposed to enrich the variances in the current dataset to increase its complexity. Experimental results on the PASCAL VOC 2010 Person Part dataset and the MNIST dataset show that, in both conventional CNN models and capsule networks, the number of independent functional units is an important factor that determines the capacity of a network model. By adjusting the number of functional units, the capacity of a model can better match the complexity of a dataset.

Keywords: CNN, convolutional neural network, capsule network, capacity optimization, character recognition, data augmentation, semantic segmentation

Procedia PDF Downloads 152

Authors: Kemka Ihemelandu, Chukwuemeka Ihemelandu

Abstract:

Melanoma remains a public health crisis, with incidence rates increasing rapidly in the past decades. Improving diagnostic accuracy to decrease misdiagnosis using Artificial intelligence (AI) continues to be documented. Unfortunately, unintended racially biased outcomes, a product of lack of diversity in the dataset used, with a noted class imbalance favoring lighter vs. darker skin tone, have increasingly been recognized as a problem.Resulting in noted limitations of the accuracy of the Convolutional neural network (CNN)models. CNN models are prone to biased output due to biases in the dataset used to train them. Our aim in this study was the optimization of convolutional neural network algorithms to mitigate bias in the automated diagnosis of melanoma. We hypothesized that our proposed training algorithms based on a data augmentation method to optimize the diagnostic accuracy of a CNN classifier by generating new training samples from the original ones will reduce bias in the automated diagnosis of melanoma. We applied geometric transformation, including; rotations, translations, scale change, flipping, and shearing. Resulting in a CNN model that provided a modifiedinput data making for a model that could learn subtle racial features. Optimal selection of the momentum and batch hyperparameter increased our model accuracy. We show that our augmented model reduces bias while maintaining accuracy in the automated diagnosis of melanoma.

Keywords: bias, augmentation, melanoma, convolutional neural network

Procedia PDF Downloads 208

Authors: Min Shi

Abstract:

State of the art research with Artificial Neural Networks for the downscaling of General Circulation Models (GCMs) mainly uses back-propagation algorithm as a training approach. This paper introduces another training approach of ANNs, Evolutionary Algorithm. The combined algorithm names neuroevolutionary (NE) algorithm. We investigate and evaluate the use of the NE algorithms in statistical downscaling by generating temperature estimates at interior points given information from a lattice of surrounding locations. The results of our experiments indicate that NE algorithms can be efficient alternative downscaling methods for daily temperatures.

Keywords: temperature, downscaling, artificial neural networks, evolutionary algorithms

Procedia PDF Downloads 348

Authors: Jun Seung Woo, Shin Dong Ho

Abstract:

The Image Captioning models with Attention technology have developed significantly compared to previous models, but it is still unsatisfactory in recognizing images. We perform an extensive search over seven interesting Convolutional Neural Networks(CNN) architectures to analyze the behavior of different models for image captioning. We compared seven different CNN Architectures, according to batch size, using on public benchmarks: MS-COCO datasets. In our experimental results, DenseNet and InceptionV3 got about 14% loss and about 160sec training time per epoch. It was the most satisfactory result among the seven CNN architectures after training 50 epochs on GPU.

Keywords: deep learning, image captioning, CNN architectures, densenet, inceptionV3

Procedia PDF Downloads 130

Authors: Edward Guillén, Jeisson Sánchez, Carlos Omar Ramos

Abstract:

In recent years, a wide variety of applications are developed with Support Vector Machines -SVM- methods and Artificial Neural Networks -ANN-. In general, these methods depend on intrusion knowledge databases such as KDD99, ISCX, and CAIDA among others. New classes of detectors are generated by machine learning techniques, trained and tested over network databases. Thereafter, detectors are employed to detect anomalies in network communication scenarios according to user’s connections behavior. The first detector based on training dataset is deployed in different real-world networks with mobile and non-mobile devices to analyze the performance and accuracy over static detection. The vulnerabilities are based on previous work in telemedicine apps that were developed on the research group. This paper presents the differences on detections results between some network scenarios by applying traditional detectors deployed with artificial neural networks and support vector machines.

Keywords: anomaly detection, back-propagation neural networks, network intrusion detection systems, support vector machines

Procedia PDF Downloads 356

Authors: Wullapa Wongsinlatam

Abstract:

Back propagation algorithm (BP) is a widely used technique in artificial neural network and has been used as a tool for solving the time series problems, such as decreasing training time, maximizing the ability to fall into local minima, and optimizing sensitivity of the initial weights and bias. This paper proposes an improvement of a BP technique which is called IM-COH algorithm (IM-COH). By combining IM-COH algorithm with cuckoo search algorithm (CS), the result is cuckoo search improved control output hidden layer algorithm (CS-IM-COH). This new algorithm has a better ability in optimizing sensitivity of the initial weights and bias than the original BP algorithm. In this research, the algorithm of CS-IM-COH is compared with the original BP, the IM-COH, and the original BP with CS (CS-BP). Furthermore, the selected benchmarks, four time series samples, are shown in this research for illustration. The research shows that the CS-IM-COH algorithm give the best forecasting results compared with the selected samples.

Keywords: artificial neural networks, back propagation algorithm, time series, local minima problem, metaheuristic optimization

Procedia PDF Downloads 151

Authors: Christopher Latella, Ashlee M. Hendy, Dan Vander Westhuizen, Wei-Peng Teo

Abstract:

Introduction: Neural adaptations following resistance training interventions have been widely investigated, however the evidence regarding the mechanisms of early adaptation are less clear. Understanding neural responses from an acute resistance training session is pivotal in the prescription of frequency, intensity and volume in applied strength and conditioning practice. Therefore the primary aim of this study was to investigate the time course of neurophysiological mechanisms post training against current super compensation theory, and secondly, to examine whether these responses reflect neural adaptations observed with resistance training interventions. Methods: Participants (N=14) completed a randomised, counterbalanced crossover study comparing; control, strength and hypertrophy conditions. The strength condition involved 3 x 5RM leg extensions with 3min recovery, while the hypertrophy condition involved 3 x 12 RM with 60s recovery. Transcranial magnetic stimulation (TMS) and peripheral nerve stimulation were used to measure excitability of the central and peripheral neural pathways, and maximal voluntary contraction (MVC) to quantify strength changes. Measures were taken pre, immediately post, 10, 20 and 30 mins and 1, 2, 6, 24, 48, 72 and 96 hrs following training. Results: Significant decreases were observed at post, 10, 20, 30 min, 1 and 2 hrs for both training groups compared to control group for force, (p <.05), maximal compound wave; (p < .005), silent period; (p < .05). A significant increase in corticospinal excitability; (p < .005) was observed for both groups. Corticospinal excitability between strength and hypertrophy groups was near significance, with a large effect (η2= .202). All measures returned to baseline within 6 hrs post training. Discussion: Neurophysiological mechanisms appear to be significantly altered in the period 2 hrs post training, returning to homeostasis by 6 hrs. The evidence suggests that the time course of neural recovery post resistance training occurs 18-40 hours shorter than previous super compensation models. Strength and hypertrophy protocols showed similar response profiles with current findings suggesting greater post training corticospinal drive from hypertrophy training, despite previous evidence that strength training requires greater neural input. The increase in corticospinal drive and decrease inl inhibition appear to be a compensatory mechanism for decreases in peripheral nerve excitability and maximal voluntary force output. The changes in corticospinal excitability and inhibition are akin to adaptive processes observed with training interventions of 4 wks or longer. It appears that the 2 hr recovery period post training is the most influential for priming further neural adaptations with resistance training. Secondly, the frequency of prescribed resistance sessions can be scheduled closer than previous super compensation theory for optimal strength gains.

Keywords: neural responses, resistance training, super compensation, transcranial magnetic stimulation

Procedia PDF Downloads 283

Authors: Marcio Leal, Marta Villamil

Abstract:

Computacional recognition of sign languages aims to allow a greater social and digital inclusion of deaf people through interpretation of their language by computer. This article presents a model of recognition of two of global parameters from sign languages; hand configurations and hand movements. Hand motion is captured through an infrared technology and its joints are built into a virtual three-dimensional space. A Multilayer Perceptron Neural Network (MLP) was used to classify hand configurations and Dynamic Time Warping (DWT) recognizes hand motion. Beyond of the method of sign recognition, we provide a dataset of hand configurations and motion capture built with help of fluent professionals in sign languages. Despite this technology can be used to translate any sign from any signs dictionary, Brazilian Sign Language (Libras) was used as case study. Finally, the model presented in this paper achieved a recognition rate of 80.4%.

Keywords: artificial neural network, computer vision, dynamic time warping, infrared, sign language recognition

Procedia PDF Downloads 214